From b5e99701b1e1a103085933a44fb7d2a21189d6ec Mon Sep 17 00:00:00 2001
From: Andrea Mannocci <andremann@libero.it>
Date: Tue, 23 Mar 2021 19:03:37 +0100
Subject: [PATCH] adding preprocessing with make

---
 notebooks/01-Exploration.ipynb | 8973 ++++++++++++++++----------------
 src/data/make_dataset.py       |   41 +-
 2 files changed, 4549 insertions(+), 4465 deletions(-)

diff --git a/notebooks/01-Exploration.ipynb b/notebooks/01-Exploration.ipynb
index 0f8d755..4efffc5 100644
--- a/notebooks/01-Exploration.ipynb
+++ b/notebooks/01-Exploration.ipynb
@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -89,12 +89,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Anomalies ORCiD profile"
+    "Notable anomalies:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -108,7 +108,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Notable fake ORCID iDs for explorative purposes:"
+    "Notable fake ORCID iDs:"
    ]
   },
   {
@@ -133,25 +133,10 @@
     "Load the dataset"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 163,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df = pd.read_csv('../data/raw/initial_info_whole.tsv', sep='\\t', header=0,\n",
-    "                         names=['orcid', 'claimed','verified_email', 'verified_primary_email', \n",
-    "                                  'given_names', 'family_name', 'biography', 'other_names', 'urls', \n",
-    "                                  'primary_email', 'other_emails', 'keywords', 'external_ids', 'education', \n",
-    "                                  'employment', 'n_works', 'works_source'])"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "scrolled": true
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -184,360 +169,175 @@
        "      <th>other_names</th>\n",
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
+       "      <th>...</th>\n",
        "      <th>employment</th>\n",
        "      <th>n_works</th>\n",
        "      <th>works_source</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>7552</th>\n",
-       "      <td>0000-0001-7831-7567</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Vahab</td>\n",
-       "      <td>Vahdat</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[\"Scopus Author ID\", \"57193490305\"], [\"Scopus...</td>\n",
-       "      <td>[[\"Industrial Engineering\", \"PhD\", \"Northeaste...</td>\n",
-       "      <td>[[\"Post-doctorate fellow\", \"Harvard Medical Sc...</td>\n",
-       "      <td>25</td>\n",
-       "      <td>[\"Vahab Vahdat\", \"Scopus - Elsevier\", \"Multidi...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8416</th>\n",
-       "      <td>0000-0001-8161-1345</td>\n",
+       "      <th>0</th>\n",
+       "      <td>0000-0001-5009-2052</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>AYFER</td>\n",
-       "      <td>TEKIN ATACAN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2019-06-05t20:25:43.066z</td>\n",
+       "      <td>2019-12-11t03:57:41.741z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>16498</th>\n",
-       "      <td>0000-0002-1133-1505</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Xianrong</td>\n",
-       "      <td>Lai</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[\"Scopus Author ID\", \"15769435500\"]]</td>\n",
-       "      <td>[[\"Department of pharmacy\", \"Bachelor of Tradi...</td>\n",
-       "      <td>[[\"Associate Research, Professor\", \"Chengdu Un...</td>\n",
-       "      <td>115</td>\n",
-       "      <td>[\"Xianrong Lai\", \"Scopus - Elsevier\", \"Crossref\"]</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>16830</th>\n",
-       "      <td>0000-0002-1257-5536</td>\n",
+       "      <th>1</th>\n",
+       "      <td>0000-0001-5943-0732</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Alexandra</td>\n",
-       "      <td>Zimmer</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[\"Research assistent\", \"Fraunhofer-Institut f...</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2015-08-18t13:10:42.871z</td>\n",
+       "      <td>2016-06-15t01:05:19.986z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>18835</th>\n",
-       "      <td>0000-0002-2026-4156</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Fatma</td>\n",
-       "      <td>Sri Wahyuni</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[\"Ayu\"]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[\"ResearcherID\", \"C-5194-2015\"], [\"Scopus Aut...</td>\n",
-       "      <td>[[\"Biosains\", \"PHD\", \"Universiti Putra Malaysi...</td>\n",
-       "      <td>[[\"Lecturer\", \"Universitas Andalas\", \"Padang\",...</td>\n",
-       "      <td>27</td>\n",
-       "      <td>[\"Publons\", \"Crossref Metadata Search\", \"Scopu...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10733293</th>\n",
-       "      <td>0000-0002-9887-7788</td>\n",
+       "      <th>2</th>\n",
+       "      <td>0000-0001-6083-622x</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Markéta</td>\n",
-       "      <td>Laštůvková</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[\"\", \"VSB - Technical University of Ostrava\",...</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2019-01-21t10:55:27.997z</td>\n",
+       "      <td>2019-01-28t16:24:02.199z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10737258</th>\n",
-       "      <td>0000-0003-1367-8104</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>LORENA</td>\n",
-       "      <td>GUTIÉRREZ GARCÍA</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[\"LinkedIn\", \"https://www.linkedin.com/in/lor...</td>\n",
-       "      <td>lorenagg@unex.es</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[\"Agroecolog\\u00eda, Bot\\u00e1nica, Did\\u00e1c...</td>\n",
-       "      <td>[[\"ResearcherID\", \"AAE-6316-2021\"]]</td>\n",
-       "      <td>[[\"\", \"M\\u00e1ster en Formaci\\u00f3n del profe...</td>\n",
-       "      <td>[[\"PCI\", \"Universidad de Extremadura - Campus ...</td>\n",
-       "      <td>14</td>\n",
-       "      <td>[\"Multidisciplinary Digital Publishing Institu...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10738308</th>\n",
-       "      <td>0000-0003-1741-3437</td>\n",
+       "      <th>3</th>\n",
+       "      <td>0000-0001-6262-5709</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Xing</td>\n",
-       "      <td>Liu</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[\"ResearcherID\", \"S-3053-2017\"]]</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2015-08-18t14:29:39.440z</td>\n",
+       "      <td>2017-06-21t07:18:20.787z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10741460</th>\n",
-       "      <td>0000-0003-2909-8585</td>\n",
+       "      <th>4</th>\n",
+       "      <td>0000-0001-6616-4890</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Yusuf</td>\n",
-       "      <td>Özcan</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[\"\\u0130lahiyat Fak\\u00fcltesi\", \"Doktora\", \"...</td>\n",
-       "      <td>[[\"Research Assistant\", \"\\u00c7ukurova Univers...</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10745078</th>\n",
-       "      <td>0000-0003-4259-5324</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>P Rama Mohan</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[\"Scopus Author ID\", \"24776757000\"]]</td>\n",
-       "      <td>[[\"EEE Department\", \"Ph.D. (Power Electronics ...</td>\n",
-       "      <td>[[\"Associate Professor\", \"RGM College of Engin...</td>\n",
-       "      <td>21</td>\n",
-       "      <td>[\"Scopus - Elsevier\", \"P Rama Mohan\"]</td>\n",
+       "      <td>2015-08-13t01:59:51.802z</td>\n",
+       "      <td>2016-06-15t01:05:21.373z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>2418 rows × 17 columns</p>\n",
+       "<p>5 rows × 24 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                        orcid  claimed  verified_email  \\\n",
-       "7552      0000-0001-7831-7567        1               1   \n",
-       "8416      0000-0001-8161-1345        1               1   \n",
-       "16498     0000-0002-1133-1505        1               1   \n",
-       "16830     0000-0002-1257-5536        1               1   \n",
-       "18835     0000-0002-2026-4156        1               1   \n",
-       "...                       ...      ...             ...   \n",
-       "10733293  0000-0002-9887-7788        1               1   \n",
-       "10737258  0000-0003-1367-8104        1               1   \n",
-       "10738308  0000-0003-1741-3437        1               1   \n",
-       "10741460  0000-0003-2909-8585        1               1   \n",
-       "10745078  0000-0003-4259-5324        1               1   \n",
-       "\n",
-       "          verified_primary_email   given_names       family_name biography  \\\n",
-       "7552                           1         Vahab            Vahdat       NaN   \n",
-       "8416                           1         AYFER      TEKIN ATACAN       NaN   \n",
-       "16498                          1      Xianrong               Lai       NaN   \n",
-       "16830                          1     Alexandra            Zimmer       NaN   \n",
-       "18835                          1         Fatma       Sri Wahyuni       NaN   \n",
-       "...                          ...           ...               ...       ...   \n",
-       "10733293                       1       Markéta        Laštůvková       NaN   \n",
-       "10737258                       1        LORENA  GUTIÉRREZ GARCÍA       NaN   \n",
-       "10738308                       1          Xing               Liu       NaN   \n",
-       "10741460                       1         Yusuf             Özcan       NaN   \n",
-       "10745078                       1  P Rama Mohan               NaN       NaN   \n",
-       "\n",
-       "         other_names                                               urls  \\\n",
-       "7552             NaN                                                NaN   \n",
-       "8416             NaN                                                NaN   \n",
-       "16498            NaN                                                NaN   \n",
-       "16830            NaN                                                NaN   \n",
-       "18835        [\"Ayu\"]                                                NaN   \n",
-       "...              ...                                                ...   \n",
-       "10733293         NaN                                                NaN   \n",
-       "10737258         NaN  [[\"LinkedIn\", \"https://www.linkedin.com/in/lor...   \n",
-       "10738308         NaN                                                NaN   \n",
-       "10741460         NaN                                                NaN   \n",
-       "10745078         NaN                                                NaN   \n",
-       "\n",
-       "             primary_email other_emails  \\\n",
-       "7552                   NaN          NaN   \n",
-       "8416                   NaN          NaN   \n",
-       "16498                  NaN          NaN   \n",
-       "16830                  NaN          NaN   \n",
-       "18835                  NaN          NaN   \n",
-       "...                    ...          ...   \n",
-       "10733293               NaN          NaN   \n",
-       "10737258  lorenagg@unex.es          NaN   \n",
-       "10738308               NaN          NaN   \n",
-       "10741460               NaN          NaN   \n",
-       "10745078               NaN          NaN   \n",
-       "\n",
-       "                                                   keywords  \\\n",
-       "7552                                                    NaN   \n",
-       "8416                                                    NaN   \n",
-       "16498                                                   NaN   \n",
-       "16830                                                   NaN   \n",
-       "18835                                                   NaN   \n",
-       "...                                                     ...   \n",
-       "10733293                                                NaN   \n",
-       "10737258  [\"Agroecolog\\u00eda, Bot\\u00e1nica, Did\\u00e1c...   \n",
-       "10738308                                                NaN   \n",
-       "10741460                                                NaN   \n",
-       "10745078                                                NaN   \n",
-       "\n",
-       "                                               external_ids  \\\n",
-       "7552      [[\"Scopus Author ID\", \"57193490305\"], [\"Scopus...   \n",
-       "8416                                                    NaN   \n",
-       "16498                 [[\"Scopus Author ID\", \"15769435500\"]]   \n",
-       "16830                                                   NaN   \n",
-       "18835     [[\"ResearcherID\", \"C-5194-2015\"], [\"Scopus Aut...   \n",
-       "...                                                     ...   \n",
-       "10733293                                                NaN   \n",
-       "10737258                [[\"ResearcherID\", \"AAE-6316-2021\"]]   \n",
-       "10738308                  [[\"ResearcherID\", \"S-3053-2017\"]]   \n",
-       "10741460                                                NaN   \n",
-       "10745078              [[\"Scopus Author ID\", \"24776757000\"]]   \n",
-       "\n",
-       "                                                  education  \\\n",
-       "7552      [[\"Industrial Engineering\", \"PhD\", \"Northeaste...   \n",
-       "8416                                                    NaN   \n",
-       "16498     [[\"Department of pharmacy\", \"Bachelor of Tradi...   \n",
-       "16830                                                   NaN   \n",
-       "18835     [[\"Biosains\", \"PHD\", \"Universiti Putra Malaysi...   \n",
-       "...                                                     ...   \n",
-       "10733293                                                NaN   \n",
-       "10737258  [[\"\", \"M\\u00e1ster en Formaci\\u00f3n del profe...   \n",
-       "10738308                                                NaN   \n",
-       "10741460  [[\"\\u0130lahiyat Fak\\u00fcltesi\", \"Doktora\", \"...   \n",
-       "10745078  [[\"EEE Department\", \"Ph.D. (Power Electronics ...   \n",
-       "\n",
-       "                                                 employment  n_works  \\\n",
-       "7552      [[\"Post-doctorate fellow\", \"Harvard Medical Sc...       25   \n",
-       "8416                                                    NaN        0   \n",
-       "16498     [[\"Associate Research, Professor\", \"Chengdu Un...      115   \n",
-       "16830     [[\"Research assistent\", \"Fraunhofer-Institut f...        0   \n",
-       "18835     [[\"Lecturer\", \"Universitas Andalas\", \"Padang\",...       27   \n",
-       "...                                                     ...      ...   \n",
-       "10733293  [[\"\", \"VSB - Technical University of Ostrava\",...        0   \n",
-       "10737258  [[\"PCI\", \"Universidad de Extremadura - Campus ...       14   \n",
-       "10738308                                                NaN        0   \n",
-       "10741460  [[\"Research Assistant\", \"\\u00c7ukurova Univers...        0   \n",
-       "10745078  [[\"Associate Professor\", \"RGM College of Engin...       21   \n",
-       "\n",
-       "                                               works_source  \n",
-       "7552      [\"Vahab Vahdat\", \"Scopus - Elsevier\", \"Multidi...  \n",
-       "8416                                                    NaN  \n",
-       "16498     [\"Xianrong Lai\", \"Scopus - Elsevier\", \"Crossref\"]  \n",
-       "16830                                                   NaN  \n",
-       "18835     [\"Publons\", \"Crossref Metadata Search\", \"Scopu...  \n",
-       "...                                                     ...  \n",
-       "10733293                                                NaN  \n",
-       "10737258  [\"Multidisciplinary Digital Publishing Institu...  \n",
-       "10738308                                                NaN  \n",
-       "10741460                                                NaN  \n",
-       "10745078              [\"Scopus - Elsevier\", \"P Rama Mohan\"]  \n",
-       "\n",
-       "[2418 rows x 17 columns]"
+       "                 orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "0  0000-0001-5009-2052        1               1                       1   \n",
+       "1  0000-0001-5943-0732        1               1                       1   \n",
+       "2  0000-0001-6083-622x        1               1                       1   \n",
+       "3  0000-0001-6262-5709        1               1                       1   \n",
+       "4  0000-0001-6616-4890        1               1                       1   \n",
+       "\n",
+       "  given_names family_name biography other_names urls primary_email  ...  \\\n",
+       "0         NaN         NaN       NaN         NaN  NaN           NaN  ...   \n",
+       "1         NaN         NaN       NaN         NaN  NaN           NaN  ...   \n",
+       "2         NaN         NaN       NaN         NaN  NaN           NaN  ...   \n",
+       "3         NaN         NaN       NaN         NaN  NaN           NaN  ...   \n",
+       "4         NaN         NaN       NaN         NaN  NaN           NaN  ...   \n",
+       "\n",
+       "  employment n_works works_source           activation_date  \\\n",
+       "0        NaN       0          NaN  2019-06-05t20:25:43.066z   \n",
+       "1        NaN       0          NaN  2015-08-18t13:10:42.871z   \n",
+       "2        NaN       0          NaN  2019-01-21t10:55:27.997z   \n",
+       "3        NaN       0          NaN  2015-08-18t14:29:39.440z   \n",
+       "4        NaN       0          NaN  2015-08-13t01:59:51.802z   \n",
+       "\n",
+       "           last_update_date  n_doi n_arxiv n_pmc n_other_pids  label  \n",
+       "0  2019-12-11t03:57:41.741z      0       0     0            0      0  \n",
+       "1  2016-06-15t01:05:19.986z      0       0     0            0      0  \n",
+       "2  2019-01-28t16:24:02.199z      0       0     0            0      0  \n",
+       "3  2017-06-21t07:18:20.787z      0       0     0            0      0  \n",
+       "4  2016-06-15t01:05:21.373z      0       0     0            0      0  \n",
+       "\n",
+       "[5 rows x 24 columns]"
       ]
      },
      "execution_count": 6,
@@ -546,107 +346,20 @@
     }
    ],
    "source": [
-    "df[df.duplicated()]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df.drop_duplicates(inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Basic column manipulation (interpret columns as lists when necessary)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['other_names'] = df[df.other_names.notna()]['other_names'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 164,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['keywords'] = df[df.keywords.notna()]['keywords'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['urls'] = df[df.urls.notna()]['urls'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['other_emails'] = df[df.other_emails.notna()]['other_emails'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['education'] = df[df.education.notna()]['education'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['employment'] = df[df.employment.notna()]['employment'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['external_ids'] = df[df.external_ids.notna()]['external_ids'].apply(lambda x: ast.literal_eval(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['works_source'] = df[df.works_source.notna()]['works_source'].apply(lambda x: ast.literal_eval(x))"
+    "df = pd.read_pickle('../data/processed/dataset.pkl')\n",
+    "df.head(5)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "That's how it looks like"
+    "Notable profiles inspection"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -680,169 +393,92 @@
        "      <th>other_names</th>\n",
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
+       "      <th>...</th>\n",
        "      <th>employment</th>\n",
        "      <th>n_works</th>\n",
        "      <th>works_source</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0000-0001-5000-2053</td>\n",
+       "      <th>1575869</th>\n",
+       "      <td>0000-0002-5193-7851</td>\n",
        "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Jorge</td>\n",
-       "      <td>Jaramillo Sanchez</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0000-0001-5000-6548</td>\n",
        "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Wiseman</td>\n",
-       "      <td>Bekelesi</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>andrea</td>\n",
+       "      <td>mannocci</td>\n",
+       "      <td>data scientist &amp; researcher; scholarly knowled...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[personal website, https://andremann.github.i...</td>\n",
+       "      <td>andrea.mannocci@isti.cnr.it</td>\n",
+       "      <td>...</td>\n",
+       "      <td>[[research associate, istituto di scienza e te...</td>\n",
+       "      <td>37</td>\n",
+       "      <td>[scopus - elsevier, crossref metadata search, ...</td>\n",
+       "      <td>2017-09-12t14:28:33.467z</td>\n",
+       "      <td>2021-03-09t08:32:47.840z</td>\n",
+       "      <td>34</td>\n",
        "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0000-0001-5000-7962</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>60</td>\n",
        "      <td>1</td>\n",
-       "      <td>ALICE</td>\n",
-       "      <td>INDIMULI</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0000-0001-5000-8586</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>shim</td>\n",
-       "      <td>ji yun</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0000-0001-5001-0256</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Sandro</td>\n",
-       "      <td>Caramaschi</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>1 rows × 24 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                 orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "0  0000-0001-5000-2053        1               0                       0   \n",
-       "1  0000-0001-5000-6548        1               0                       0   \n",
-       "2  0000-0001-5000-7962        1               1                       1   \n",
-       "3  0000-0001-5000-8586        1               0                       0   \n",
-       "4  0000-0001-5001-0256        1               0                       0   \n",
-       "\n",
-       "  given_names         family_name biography other_names urls primary_email  \\\n",
-       "0      Jorge   Jaramillo Sanchez        NaN         NaN  NaN           NaN   \n",
-       "1     Wiseman            Bekelesi       NaN         NaN  NaN           NaN   \n",
-       "2       ALICE            INDIMULI       NaN         NaN  NaN           NaN   \n",
-       "3        shim              ji yun       NaN         NaN  NaN           NaN   \n",
-       "4      Sandro          Caramaschi       NaN         NaN  NaN           NaN   \n",
-       "\n",
-       "  other_emails keywords external_ids education employment  n_works  \\\n",
-       "0          NaN      NaN          NaN       NaN        NaN        0   \n",
-       "1          NaN      NaN          NaN       NaN        NaN        0   \n",
-       "2          NaN      NaN          NaN       NaN        NaN        0   \n",
-       "3          NaN      NaN          NaN       NaN        NaN        0   \n",
-       "4          NaN      NaN          NaN       NaN        NaN        0   \n",
-       "\n",
-       "  works_source  \n",
-       "0          NaN  \n",
-       "1          NaN  \n",
-       "2          NaN  \n",
-       "3          NaN  \n",
-       "4          NaN  "
+       "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "1575869  0000-0002-5193-7851        1               1                       1   \n",
+       "\n",
+       "        given_names family_name  \\\n",
+       "1575869      andrea    mannocci   \n",
+       "\n",
+       "                                                 biography other_names  \\\n",
+       "1575869  data scientist & researcher; scholarly knowled...         NaN   \n",
+       "\n",
+       "                                                      urls  \\\n",
+       "1575869  [[personal website, https://andremann.github.i...   \n",
+       "\n",
+       "                       primary_email  ...  \\\n",
+       "1575869  andrea.mannocci@isti.cnr.it  ...   \n",
+       "\n",
+       "                                                employment n_works  \\\n",
+       "1575869  [[research associate, istituto di scienza e te...      37   \n",
+       "\n",
+       "                                              works_source  \\\n",
+       "1575869  [scopus - elsevier, crossref metadata search, ...   \n",
+       "\n",
+       "                  activation_date          last_update_date  n_doi n_arxiv  \\\n",
+       "1575869  2017-09-12t14:28:33.467z  2021-03-09t08:32:47.840z     34       0   \n",
+       "\n",
+       "        n_pmc n_other_pids  label  \n",
+       "1575869     0           60      1  \n",
+       "\n",
+       "[1 rows x 24 columns]"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df.head(5)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Add labels to the dataframe based on their presence in OpenAIRE"
+    "df[df['orcid'] == AM]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 97,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -867,105 +503,218 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>orcid</th>\n",
+       "      <th>claimed</th>\n",
+       "      <th>verified_email</th>\n",
+       "      <th>verified_primary_email</th>\n",
+       "      <th>given_names</th>\n",
+       "      <th>family_name</th>\n",
+       "      <th>biography</th>\n",
+       "      <th>other_names</th>\n",
+       "      <th>urls</th>\n",
+       "      <th>primary_email</th>\n",
+       "      <th>...</th>\n",
+       "      <th>employment</th>\n",
+       "      <th>n_works</th>\n",
+       "      <th>works_source</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0000-0002-4292-8072</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0000-0003-3026-718x</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0000-0002-4568-8748</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0000-0002-1380-859x</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0000-0001-7526-5095</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
+       "      <th>6819986</th>\n",
+       "      <td>0000-0001-6997-9470</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>other</td>\n",
+       "      <td>whatsapp</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[[otherwhatsapp, https://otherwhatsapp.com/], ...</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2934111</th>\n",
-       "      <td>0000-0002-2394-5387</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2934112</th>\n",
-       "      <td>0000-0002-6125-3170</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2934113</th>\n",
-       "      <td>0000-0002-7062-5845</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2934114</th>\n",
-       "      <td>0000-0001-8677-5162</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2934115</th>\n",
-       "      <td>0000-0002-0240-8021</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-10-07t10:37:12.237z</td>\n",
+       "      <td>2020-10-08t02:32:03.935z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>2934116 rows × 1 columns</p>\n",
+       "<p>1 rows × 24 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                       orcid\n",
-       "0        0000-0002-4292-8072\n",
-       "1        0000-0003-3026-718x\n",
-       "2        0000-0002-4568-8748\n",
-       "3        0000-0002-1380-859x\n",
-       "4        0000-0001-7526-5095\n",
-       "...                      ...\n",
-       "2934111  0000-0002-2394-5387\n",
-       "2934112  0000-0002-6125-3170\n",
-       "2934113  0000-0002-7062-5845\n",
-       "2934114  0000-0001-8677-5162\n",
-       "2934115  0000-0002-0240-8021\n",
-       "\n",
-       "[2934116 rows x 1 columns]"
+       "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "6819986  0000-0001-6997-9470        1               1                       1   \n",
+       "\n",
+       "        given_names family_name biography other_names  \\\n",
+       "6819986       other    whatsapp       NaN         NaN   \n",
+       "\n",
+       "                                                      urls primary_email  ...  \\\n",
+       "6819986  [[otherwhatsapp, https://otherwhatsapp.com/], ...           NaN  ...   \n",
+       "\n",
+       "        employment n_works works_source           activation_date  \\\n",
+       "6819986        NaN       0          NaN  2020-10-07t10:37:12.237z   \n",
+       "\n",
+       "                 last_update_date  n_doi n_arxiv n_pmc n_other_pids  label  \n",
+       "6819986  2020-10-08t02:32:03.935z      0       0     0            0      0  \n",
+       "\n",
+       "[1 rows x 24 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[df['orcid'] == WHATSAPP]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "orcid                     10916574\n",
+       "claimed                   10916574\n",
+       "verified_email            10916574\n",
+       "verified_primary_email    10916574\n",
+       "given_names               10886150\n",
+       "family_name               10601571\n",
+       "biography                   348649\n",
+       "other_names                 551482\n",
+       "urls                        707687\n",
+       "primary_email               123851\n",
+       "other_emails                 48306\n",
+       "keywords                    646400\n",
+       "external_ids               1301959\n",
+       "education                  2430233\n",
+       "employment                 2665092\n",
+       "n_works                   10916574\n",
+       "works_source               2721431\n",
+       "activation_date           10916574\n",
+       "last_update_date          10916574\n",
+       "n_doi                     10916574\n",
+       "n_arxiv                   10916574\n",
+       "n_pmc                     10916574\n",
+       "n_other_pids              10916574\n",
+       "label                     10916574\n",
+       "dtype: int64"
       ]
      },
-     "execution_count": 97,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "openaire_orcid = pd.read_csv('../data/raw/orcid_openaire.txt', header=None, names=['orcid'])\n",
-    "openaire_orcid"
+    "df.count()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 110,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count                10916574\n",
+       "unique               10916574\n",
+       "top       0000-0002-5454-7613\n",
+       "freq                        1\n",
+       "Name: orcid, dtype: object"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "df['label'] = df.orcid.isin(openaire_orcid['orcid'])\n",
-    "df[\"label\"] = df[\"label\"].astype(int)"
+    "df['orcid'].describe()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Notable profiles inspection"
+    "## Primary email"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count                       123851\n",
+       "unique                      123848\n",
+       "top       patrick.davey@monash.edu\n",
+       "freq                             2\n",
+       "Name: primary_email, dtype: object"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['primary_email'].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Dupe emails"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "6347224            maykin@owasp.org\n",
+       "7027865    patrick.davey@monash.edu\n",
+       "9529005      opercin@erbakan.edu.tr\n",
+       "Name: primary_email, dtype: object"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['primary_email'].dropna().loc[df['primary_email'].duplicated()]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 111,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -1002,83 +751,106 @@
        "      <th>...</th>\n",
        "      <th>n_works</th>\n",
        "      <th>works_source</th>\n",
-       "      <th>primary_email_domain</th>\n",
-       "      <th>other_email_domains</th>\n",
-       "      <th>n_emails</th>\n",
-       "      <th>url_domains</th>\n",
-       "      <th>n_urls</th>\n",
-       "      <th>n_ids</th>\n",
-       "      <th>n_keywords</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
        "      <th>label</th>\n",
+       "      <th>primary_email_domain</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>8840413</th>\n",
-       "      <td>0000-0002-5193-7851</td>\n",
+       "      <th>4450046</th>\n",
+       "      <td>0000-0001-9855-1676</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Andrea</td>\n",
-       "      <td>Mannocci</td>\n",
+       "      <td>maykin</td>\n",
+       "      <td>warasart</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Personal website, https://andremann.github.i...</td>\n",
-       "      <td>andrea.mannocci@isti.cnr.it</td>\n",
-       "      <td>...</td>\n",
-       "      <td>37</td>\n",
-       "      <td>[Scopus - Elsevier, Crossref Metadata Search, ...</td>\n",
-       "      <td>isti.cnr.it</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>maykin@owasp.org</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[github.io, twitter.com, linkedin.com]</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
+       "      <td>2020-10-23t17:51:51.925z</td>\n",
+       "      <td>2021-01-01t15:00:52.053z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>owasp.org</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6347224</th>\n",
+       "      <td>0000-0002-0836-2271</td>\n",
        "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>maykin</td>\n",
+       "      <td>warasart</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>maykin@owasp.org</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-09-15t04:43:55.709z</td>\n",
+       "      <td>2020-09-15t05:17:28.509z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>owasp.org</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1 rows × 25 columns</p>\n",
+       "<p>2 rows × 25 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "8840413  0000-0002-5193-7851        1               1                       1   \n",
+       "4450046  0000-0001-9855-1676        1               1                       1   \n",
+       "6347224  0000-0002-0836-2271        1               1                       1   \n",
        "\n",
-       "        given_names family_name biography other_names  \\\n",
-       "8840413      Andrea    Mannocci       NaN         NaN   \n",
+       "        given_names family_name biography other_names urls     primary_email  \\\n",
+       "4450046      maykin    warasart       NaN         NaN  NaN  maykin@owasp.org   \n",
+       "6347224      maykin    warasart       NaN         NaN  NaN  maykin@owasp.org   \n",
        "\n",
-       "                                                      urls  \\\n",
-       "8840413  [[Personal website, https://andremann.github.i...   \n",
-       "\n",
-       "                       primary_email  ... n_works  \\\n",
-       "8840413  andrea.mannocci@isti.cnr.it  ...      37   \n",
-       "\n",
-       "                                              works_source  \\\n",
-       "8840413  [Scopus - Elsevier, Crossref Metadata Search, ...   \n",
+       "         ... n_works works_source           activation_date  \\\n",
+       "4450046  ...       0          NaN  2020-10-23t17:51:51.925z   \n",
+       "6347224  ...       0          NaN  2020-09-15t04:43:55.709z   \n",
        "\n",
-       "        primary_email_domain other_email_domains n_emails  \\\n",
-       "8840413          isti.cnr.it                 NaN      NaN   \n",
+       "                 last_update_date n_doi  n_arxiv n_pmc n_other_pids label  \\\n",
+       "4450046  2021-01-01t15:00:52.053z     0        0     0            0     0   \n",
+       "6347224  2020-09-15t05:17:28.509z     0        0     0            0     0   \n",
        "\n",
-       "                                    url_domains n_urls n_ids n_keywords  label  \n",
-       "8840413  [github.io, twitter.com, linkedin.com]    3.0   1.0        5.0      1  \n",
+       "         primary_email_domain  \n",
+       "4450046             owasp.org  \n",
+       "6347224             owasp.org  \n",
        "\n",
-       "[1 rows x 25 columns]"
+       "[2 rows x 25 columns]"
       ]
      },
-     "execution_count": 111,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[df['orcid'] == AM]"
+    "df[df['primary_email'] == 'maykin@owasp.org']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 112,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -1115,125 +887,106 @@
        "      <th>...</th>\n",
        "      <th>n_works</th>\n",
        "      <th>works_source</th>\n",
-       "      <th>primary_email_domain</th>\n",
-       "      <th>other_email_domains</th>\n",
-       "      <th>n_emails</th>\n",
-       "      <th>url_domains</th>\n",
-       "      <th>n_urls</th>\n",
-       "      <th>n_ids</th>\n",
-       "      <th>n_keywords</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
        "      <th>label</th>\n",
+       "      <th>primary_email_domain</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>9517099</th>\n",
-       "      <td>0000-0001-6997-9470</td>\n",
+       "      <th>6840791</th>\n",
+       "      <td>0000-0002-2232-9638</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>other</td>\n",
-       "      <td>whatsapp</td>\n",
+       "      <td>osman</td>\n",
+       "      <td>perçin</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Otherwhatsapp, https://otherwhatsapp.com/], ...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>opercin@erbakan.edu.tr</td>\n",
        "      <td>...</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2015-01-12t13:47:55.549z</td>\n",
+       "      <td>2020-01-27t07:38:24.269z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>erbakan.edu.tr</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9529005</th>\n",
+       "      <td>0000-0003-0033-0918</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>osman</td>\n",
+       "      <td>perçin</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[otherwhatsapp.com, im-creator.com, facebook.c...</td>\n",
-       "      <td>27.0</td>\n",
+       "      <td>opercin@erbakan.edu.tr</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>4.0</td>\n",
+       "      <td>2015-10-13t05:47:12.014z</td>\n",
+       "      <td>2020-12-25t13:52:03.976z</td>\n",
+       "      <td>0</td>\n",
        "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>erbakan.edu.tr</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1 rows × 25 columns</p>\n",
+       "<p>2 rows × 25 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "9517099  0000-0001-6997-9470        1               1                       1   \n",
-       "\n",
-       "        given_names family_name biography other_names  \\\n",
-       "9517099       other    whatsapp       NaN         NaN   \n",
+       "6840791  0000-0002-2232-9638        1               1                       1   \n",
+       "9529005  0000-0003-0033-0918        1               1                       1   \n",
        "\n",
-       "                                                      urls primary_email  ...  \\\n",
-       "9517099  [[Otherwhatsapp, https://otherwhatsapp.com/], ...           NaN  ...   \n",
+       "        given_names family_name biography other_names urls  \\\n",
+       "6840791       osman      perçin       NaN         NaN  NaN   \n",
+       "9529005       osman      perçin       NaN         NaN  NaN   \n",
        "\n",
-       "        n_works works_source primary_email_domain other_email_domains  \\\n",
-       "9517099       0          NaN                  NaN                 NaN   \n",
+       "                  primary_email  ... n_works works_source  \\\n",
+       "6840791  opercin@erbakan.edu.tr  ...       0          NaN   \n",
+       "9529005  opercin@erbakan.edu.tr  ...       0          NaN   \n",
        "\n",
-       "        n_emails                                        url_domains n_urls  \\\n",
-       "9517099      NaN  [otherwhatsapp.com, im-creator.com, facebook.c...   27.0   \n",
+       "                  activation_date          last_update_date n_doi  n_arxiv  \\\n",
+       "6840791  2015-01-12t13:47:55.549z  2020-01-27t07:38:24.269z     0        0   \n",
+       "9529005  2015-10-13t05:47:12.014z  2020-12-25t13:52:03.976z     0        0   \n",
        "\n",
-       "        n_ids n_keywords  label  \n",
-       "9517099   NaN        4.0      0  \n",
+       "        n_pmc n_other_pids label  primary_email_domain  \n",
+       "6840791     0            0     0        erbakan.edu.tr  \n",
+       "9529005     0            0     0        erbakan.edu.tr  \n",
        "\n",
-       "[1 rows x 25 columns]"
-      ]
-     },
-     "execution_count": 112,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df[df['orcid'] == WHATSAPP]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 103,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "orcid                     10744621\n",
-       "claimed                   10744621\n",
-       "verified_email            10744621\n",
-       "verified_primary_email    10744621\n",
-       "given_names               10716788\n",
-       "family_name               10437093\n",
-       "biography                   333885\n",
-       "other_names                 544550\n",
-       "urls                        688262\n",
-       "primary_email               121476\n",
-       "other_emails                 47470\n",
-       "keywords                    638634\n",
-       "external_ids               1285292\n",
-       "education                  2402439\n",
-       "employment                 2626669\n",
-       "n_works                   10744621\n",
-       "works_source               2671905\n",
-       "primary_email_domain        121476\n",
-       "other_email_domains          47470\n",
-       "n_emails                     47470\n",
-       "url_domains                 688262\n",
-       "n_urls                      688262\n",
-       "n_ids                      1285292\n",
-       "n_keywords                  638634\n",
-       "label                     10744621\n",
-       "dtype: int64"
+       "[2 rows x 25 columns]"
       ]
      },
-     "execution_count": 103,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df.count()"
+    "df[df['primary_email'] == 'opercin@erbakan.edu.tr']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
@@ -1270,171 +1023,139 @@
        "      <th>...</th>\n",
        "      <th>n_works</th>\n",
        "      <th>works_source</th>\n",
-       "      <th>primary_email_domain</th>\n",
-       "      <th>other_email_domains</th>\n",
-       "      <th>n_emails</th>\n",
-       "      <th>url_domains</th>\n",
-       "      <th>n_urls</th>\n",
-       "      <th>n_ids</th>\n",
-       "      <th>n_keywords</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
        "      <th>label</th>\n",
+       "      <th>primary_email_domain</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>4595263</th>\n",
-       "      <td>0000-0002-5154-6404</td>\n",
+       "      <th>944993</th>\n",
+       "      <td>0000-0002-9158-1757</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Olusola</td>\n",
-       "      <td>Bamisile</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>patrick</td>\n",
+       "      <td>davey</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>patrick.davey@monash.edu</td>\n",
        "      <td>...</td>\n",
-       "      <td>3</td>\n",
-       "      <td>[Multidisciplinary Digital Publishing Institut...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2019-05-09t23:01:02.170z</td>\n",
+       "      <td>2019-08-20t03:00:17.844z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>monash.edu</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7027865</th>\n",
+       "      <td>0000-0002-8774-0030</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>patrick</td>\n",
+       "      <td>davey</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>False</td>\n",
+       "      <td>patrick.davey@monash.edu</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>[crossref]</td>\n",
+       "      <td>2018-09-11t10:47:10.997z</td>\n",
+       "      <td>2021-02-09t06:21:44.138z</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>monash.edu</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1 rows × 25 columns</p>\n",
+       "<p>2 rows × 25 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "4595263  0000-0002-5154-6404        1               1                       1   \n",
+       "944993   0000-0002-9158-1757        1               1                       1   \n",
+       "7027865  0000-0002-8774-0030        1               1                       1   \n",
        "\n",
-       "        given_names family_name biography other_names urls primary_email  ...  \\\n",
-       "4595263     Olusola    Bamisile       NaN         NaN  NaN           NaN  ...   \n",
+       "        given_names family_name biography other_names urls  \\\n",
+       "944993      patrick       davey       NaN         NaN  NaN   \n",
+       "7027865     patrick       davey       NaN         NaN  NaN   \n",
        "\n",
-       "        n_works                                       works_source  \\\n",
-       "4595263       3  [Multidisciplinary Digital Publishing Institut...   \n",
+       "                    primary_email  ... n_works works_source  \\\n",
+       "944993   patrick.davey@monash.edu  ...       0          NaN   \n",
+       "7027865  patrick.davey@monash.edu  ...       1   [crossref]   \n",
        "\n",
-       "        primary_email_domain other_email_domains n_emails  url_domains n_urls  \\\n",
-       "4595263                  NaN                 NaN      NaN          NaN    NaN   \n",
+       "                  activation_date          last_update_date n_doi  n_arxiv  \\\n",
+       "944993   2019-05-09t23:01:02.170z  2019-08-20t03:00:17.844z     0        0   \n",
+       "7027865  2018-09-11t10:47:10.997z  2021-02-09t06:21:44.138z     1        0   \n",
        "\n",
-       "        n_ids n_keywords  label  \n",
-       "4595263   NaN        NaN  False  \n",
+       "        n_pmc n_other_pids label  primary_email_domain  \n",
+       "944993      0            0     0            monash.edu  \n",
+       "7027865     0            0     1            monash.edu  \n",
        "\n",
-       "[1 rows x 25 columns]"
+       "[2 rows x 25 columns]"
       ]
      },
-     "execution_count": 104,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[df['orcid'] == '0000-0002-5154-6404']"
+    "df[df['primary_email'] == 'patrick.davey@monash.edu']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
-    "df.drop(index=4595264, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "count                10744621\n",
-       "unique               10744621\n",
-       "top       0000-0001-8644-5622\n",
-       "freq                        1\n",
-       "Name: orcid, dtype: object"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df['orcid'].describe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Primary email"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "count                       121476\n",
-       "unique                      121473\n",
-       "top       patrick.davey@monash.edu\n",
-       "freq                             2\n",
-       "Name: primary_email, dtype: object"
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df['primary_email'].describe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Dupe emails"
+    "df['primary_email_domain'] = df['primary_email'].apply(lambda x: x.split('@')[1] if pd.notna(x) else x)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "7483666             maykin@owasp.org\n",
-       "9068234       opercin@erbakan.edu.tr\n",
-       "10246485    patrick.davey@monash.edu\n",
-       "Name: primary_email, dtype: object"
+       "count        123851\n",
+       "unique        17089\n",
+       "top       gmail.com\n",
+       "freq          26540\n",
+       "Name: primary_email_domain, dtype: object"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df['primary_email'].dropna().loc[df['primary_email'].duplicated()]"
+    "df['primary_email_domain'].describe()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
     {
@@ -1459,489 +1180,93 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>orcid</th>\n",
-       "      <th>claimed</th>\n",
-       "      <th>verified_email</th>\n",
-       "      <th>verified_primary_email</th>\n",
-       "      <th>given_names</th>\n",
-       "      <th>family_name</th>\n",
-       "      <th>biography</th>\n",
-       "      <th>other_names</th>\n",
-       "      <th>urls</th>\n",
-       "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>primary_email_domain</th>\n",
+       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>3776350</th>\n",
-       "      <td>0000-0002-0836-2271</td>\n",
-       "      <td>1</td>\n",
+       "      <th>gmail.com</th>\n",
+       "      <td>26540</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>hotmail.com</th>\n",
+       "      <td>3769</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yahoo.com</th>\n",
+       "      <td>2614</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>163.com</th>\n",
+       "      <td>2109</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yuhs.ac</th>\n",
+       "      <td>1132</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>imean-biotech.com</th>\n",
        "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>imec.msu.ru</th>\n",
        "      <td>1</td>\n",
-       "      <td>Maykin</td>\n",
-       "      <td>Warasart</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>maykin@owasp.org</td>\n",
-       "      <td>[maykin@dga.or.th]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>7483666</th>\n",
-       "      <td>0000-0001-9855-1676</td>\n",
+       "      <th>imedea.uib-csic.es</th>\n",
        "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>imes.uni-hannover.de</th>\n",
        "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>zzuli.edu.cn</th>\n",
        "      <td>1</td>\n",
-       "      <td>Maykin</td>\n",
-       "      <td>Warasart</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>maykin@owasp.org</td>\n",
-       "      <td>[maykin@dga.or.th, maykin@ieee.org]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>17089 rows × 1 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "3776350  0000-0002-0836-2271        1               1                       1   \n",
-       "7483666  0000-0001-9855-1676        1               1                       1   \n",
-       "\n",
-       "        given_names family_name biography other_names urls     primary_email  \\\n",
-       "3776350      Maykin    Warasart       NaN         NaN  NaN  maykin@owasp.org   \n",
-       "7483666      Maykin    Warasart       NaN         NaN  NaN  maykin@owasp.org   \n",
-       "\n",
-       "                                other_emails keywords external_ids education  \\\n",
-       "3776350                   [maykin@dga.or.th]      NaN          NaN       NaN   \n",
-       "7483666  [maykin@dga.or.th, maykin@ieee.org]      NaN          NaN       NaN   \n",
+       "                      orcid\n",
+       "primary_email_domain       \n",
+       "gmail.com             26540\n",
+       "hotmail.com            3769\n",
+       "yahoo.com              2614\n",
+       "163.com                2109\n",
+       "yuhs.ac                1132\n",
+       "...                     ...\n",
+       "imean-biotech.com         1\n",
+       "imec.msu.ru               1\n",
+       "imedea.uib-csic.es        1\n",
+       "imes.uni-hannover.de      1\n",
+       "zzuli.edu.cn              1\n",
        "\n",
-       "        employment  n_works works_source  \n",
-       "3776350        NaN        0          NaN  \n",
-       "7483666        NaN        0          NaN  "
+       "[17089 rows x 1 columns]"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[df['primary_email'] == 'maykin@owasp.org']"
+    "primary_emails = df[['primary_email_domain', 'orcid']].groupby('primary_email_domain').count().sort_values('orcid', ascending=False)\n",
+    "primary_emails"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>orcid</th>\n",
-       "      <th>claimed</th>\n",
-       "      <th>verified_email</th>\n",
-       "      <th>verified_primary_email</th>\n",
-       "      <th>given_names</th>\n",
-       "      <th>family_name</th>\n",
-       "      <th>biography</th>\n",
-       "      <th>other_names</th>\n",
-       "      <th>urls</th>\n",
-       "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>3995032</th>\n",
-       "      <td>0000-0002-2232-9638</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Osman</td>\n",
-       "      <td>Perçin</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>opercin@erbakan.edu.tr</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9068234</th>\n",
-       "      <td>0000-0003-0033-0918</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Osman</td>\n",
-       "      <td>PERÇİN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>opercin@erbakan.edu.tr</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, Necmettin Erbakan University, Konya, , TR,...</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "3995032  0000-0002-2232-9638        1               1                       1   \n",
-       "9068234  0000-0003-0033-0918        1               1                       1   \n",
-       "\n",
-       "        given_names family_name biography other_names urls  \\\n",
-       "3995032       Osman      Perçin       NaN         NaN  NaN   \n",
-       "9068234       Osman      PERÇİN       NaN         NaN  NaN   \n",
-       "\n",
-       "                  primary_email other_emails keywords external_ids education  \\\n",
-       "3995032  opercin@erbakan.edu.tr          NaN      NaN          NaN       NaN   \n",
-       "9068234  opercin@erbakan.edu.tr          NaN      NaN          NaN       NaN   \n",
-       "\n",
-       "                                                employment  n_works  \\\n",
-       "3995032                                                NaN        0   \n",
-       "9068234  [[, Necmettin Erbakan University, Konya, , TR,...        0   \n",
-       "\n",
-       "        works_source  \n",
-       "3995032          NaN  \n",
-       "9068234          NaN  "
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df[df['primary_email'] == 'opercin@erbakan.edu.tr']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>orcid</th>\n",
-       "      <th>claimed</th>\n",
-       "      <th>verified_email</th>\n",
-       "      <th>verified_primary_email</th>\n",
-       "      <th>given_names</th>\n",
-       "      <th>family_name</th>\n",
-       "      <th>biography</th>\n",
-       "      <th>other_names</th>\n",
-       "      <th>urls</th>\n",
-       "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5087745</th>\n",
-       "      <td>0000-0002-8774-0030</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Patrick</td>\n",
-       "      <td>Davey</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>patrick.davey@monash.edu</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[PhD Student, Monash University, Melbourne, V...</td>\n",
-       "      <td>1</td>\n",
-       "      <td>[Crossref]</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10246485</th>\n",
-       "      <td>0000-0002-9158-1757</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Patrick</td>\n",
-       "      <td>Davey</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>patrick.davey@monash.edu</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Radiopharmaceuticals, Inorganic Chemistry, Bi...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[PhD Student, Monash University, Melbourne, ,...</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                        orcid  claimed  verified_email  \\\n",
-       "5087745   0000-0002-8774-0030        1               1   \n",
-       "10246485  0000-0002-9158-1757        1               1   \n",
-       "\n",
-       "          verified_primary_email given_names family_name biography  \\\n",
-       "5087745                        1     Patrick       Davey       NaN   \n",
-       "10246485                       1     Patrick       Davey       NaN   \n",
-       "\n",
-       "         other_names urls             primary_email other_emails  \\\n",
-       "5087745          NaN  NaN  patrick.davey@monash.edu          NaN   \n",
-       "10246485         NaN  NaN  patrick.davey@monash.edu          NaN   \n",
-       "\n",
-       "                                                   keywords external_ids  \\\n",
-       "5087745                                                 NaN          NaN   \n",
-       "10246485  [Radiopharmaceuticals, Inorganic Chemistry, Bi...          NaN   \n",
-       "\n",
-       "         education                                         employment  \\\n",
-       "5087745        NaN  [[PhD Student, Monash University, Melbourne, V...   \n",
-       "10246485       NaN  [[PhD Student, Monash University, Melbourne, ,...   \n",
-       "\n",
-       "          n_works works_source  \n",
-       "5087745         1   [Crossref]  \n",
-       "10246485        0          NaN  "
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df[df['primary_email'] == 'patrick.davey@monash.edu']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['primary_email_domain'] = df['primary_email'].apply(lambda x: x.split('@')[1] if pd.notna(x) else x)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "count        121476\n",
-       "unique        17047\n",
-       "top       gmail.com\n",
-       "freq          25892\n",
-       "Name: primary_email_domain, dtype: object"
-      ]
-     },
-     "execution_count": 29,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df['primary_email_domain'].describe()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>orcid</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>primary_email_domain</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>gmail.com</th>\n",
-       "      <td>25892</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>hotmail.com</th>\n",
-       "      <td>3674</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>yahoo.com</th>\n",
-       "      <td>2578</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>163.com</th>\n",
-       "      <td>2067</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>yuhs.ac</th>\n",
-       "      <td>1124</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>iiap.gob.pe</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>iiap.org.pe</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>iibb.csic.es</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>iic.hokudai.ac.jp</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>zzuli.edu.cn</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>17047 rows × 1 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                      orcid\n",
-       "primary_email_domain       \n",
-       "gmail.com             25892\n",
-       "hotmail.com            3674\n",
-       "yahoo.com              2578\n",
-       "163.com                2067\n",
-       "yuhs.ac                1124\n",
-       "...                     ...\n",
-       "iiap.gob.pe               1\n",
-       "iiap.org.pe               1\n",
-       "iibb.csic.es              1\n",
-       "iic.hokudai.ac.jp         1\n",
-       "zzuli.edu.cn              1\n",
-       "\n",
-       "[17047 rows x 1 columns]"
-      ]
-     },
-     "execution_count": 30,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "primary_emails = df[['primary_email_domain', 'orcid']].groupby('primary_email_domain').count().sort_values('orcid', ascending=False)\n",
-    "primary_emails"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
@@ -1967,8 +1292,8 @@
           "bu.edu",
           "usgs.gov",
           "mail.ru",
-          "usp.br",
           "yahoo.com.br",
+          "usp.br",
           "ua.pt",
           "umich.edu",
           "ust.hk",
@@ -1980,44 +1305,44 @@
           "unesp.br",
           "ucl.ac.uk",
           "ieee.org",
-          "stcatz.ox.ac.uk",
-          "st-annes.ox.ac.uk",
           "naver.com",
+          "st-annes.ox.ac.uk",
+          "stcatz.ox.ac.uk",
           "yahoo.fr",
           "ucm.es",
           "live.com"
          ],
          "y": [
-          25892,
-          3674,
-          2578,
-          2067,
-          1124,
-          1035,
-          914,
-          755,
-          626,
+          26540,
+          3769,
+          2614,
+          2109,
+          1132,
+          1056,
+          940,
+          762,
+          630,
           584,
-          564,
-          455,
-          454,
-          291,
+          575,
+          458,
+          457,
+          300,
           290,
-          278,
-          249,
+          277,
+          258,
+          247,
           242,
-          237,
-          234,
-          220,
-          214,
+          235,
+          225,
+          218,
+          207,
           204,
-          203,
-          185,
+          187,
+          184,
           184,
-          182,
           172,
-          166,
-          159
+          171,
+          163
          ]
         }
        ],
@@ -2844,9 +2169,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"1cbe8512-63ad-46aa-a8f8-33bcaa30971a\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"1cbe8512-63ad-46aa-a8f8-33bcaa30971a\")) {                    Plotly.newPlot(                        \"1cbe8512-63ad-46aa-a8f8-33bcaa30971a\",                        [{\"type\": \"bar\", \"x\": [\"gmail.com\", \"hotmail.com\", \"yahoo.com\", \"163.com\", \"yuhs.ac\", \"qq.com\", \"outlook.com\", \"126.com\", \"bu.edu\", \"usgs.gov\", \"mail.ru\", \"usp.br\", \"yahoo.com.br\", \"ua.pt\", \"umich.edu\", \"ust.hk\", \"foxmail.com\", \"uomustansiriyah.edu.iq\", \"yandex.ru\", \"uq.edu.au\", \"ukr.net\", \"unesp.br\", \"ucl.ac.uk\", \"ieee.org\", \"stcatz.ox.ac.uk\", \"st-annes.ox.ac.uk\", \"naver.com\", \"yahoo.fr\", \"ucm.es\", \"live.com\"], \"y\": [25892, 3674, 2578, 2067, 1124, 1035, 914, 755, 626, 584, 564, 455, 454, 291, 290, 278, 249, 242, 237, 234, 220, 214, 204, 203, 185, 184, 182, 172, 166, 159]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 email domains\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"15d3677b-72ef-4927-9ec5-b34a376fc263\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"15d3677b-72ef-4927-9ec5-b34a376fc263\")) {                    Plotly.newPlot(                        \"15d3677b-72ef-4927-9ec5-b34a376fc263\",                        [{\"type\": \"bar\", \"x\": [\"gmail.com\", \"hotmail.com\", \"yahoo.com\", \"163.com\", \"yuhs.ac\", \"qq.com\", \"outlook.com\", \"126.com\", \"bu.edu\", \"usgs.gov\", \"mail.ru\", \"yahoo.com.br\", \"usp.br\", \"ua.pt\", \"umich.edu\", \"ust.hk\", \"foxmail.com\", \"uomustansiriyah.edu.iq\", \"yandex.ru\", \"uq.edu.au\", \"ukr.net\", \"unesp.br\", \"ucl.ac.uk\", \"ieee.org\", \"naver.com\", \"st-annes.ox.ac.uk\", \"stcatz.ox.ac.uk\", \"yahoo.fr\", \"ucm.es\", \"live.com\"], \"y\": [26540, 3769, 2614, 2109, 1132, 1056, 940, 762, 630, 584, 575, 458, 457, 300, 290, 277, 258, 247, 242, 235, 225, 218, 207, 204, 187, 184, 184, 172, 171, 163]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 email domains\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('1cbe8512-63ad-46aa-a8f8-33bcaa30971a');\n",
+       "var gd = document.getElementById('15d3677b-72ef-4927-9ec5-b34a376fc263');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -2901,7 +2226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2914,7 +2239,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2923,7 +2248,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 31,
    "metadata": {
     "scrolled": true
    },
@@ -2959,13 +2284,15 @@
        "      <th>other_names</th>\n",
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
+       "      <th>...</th>\n",
        "      <th>works_source</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "    </tr>\n",
@@ -2973,177 +2300,176 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>34</th>\n",
-       "      <td>0000-0001-5011-9833</td>\n",
+       "      <td>0000-0002-5774-8947</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Mark</td>\n",
-       "      <td>Kilbane</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>mark.kilbane@seh.ox.ac.uk</td>\n",
-       "      <td>[mark.kilbane@bsg.ox.ac.uk]</td>\n",
+       "      <td>[omah m. williams - duncan]</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Blavatnik School of Government; St Edmund Ha...</td>\n",
+       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>2014-03-07t04:34:39.598z</td>\n",
+       "      <td>2019-05-21t17:08:12.202z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>seh.ox.ac.uk</td>\n",
-       "      <td>[bsg.ox.ac.uk]</td>\n",
+       "      <td>[gmail.com]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>47</th>\n",
-       "      <td>0000-0001-5017-1295</td>\n",
+       "      <th>1199</th>\n",
+       "      <td>0000-0003-2877-5492</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Xinfeng</td>\n",
-       "      <td>Tang</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[tang.xinfeng@foxmail.com]</td>\n",
+       "      <td>0</td>\n",
+       "      <td>aliasghar</td>\n",
+       "      <td>khosroabadi</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Scopus Author ID, 56927186900]]</td>\n",
-       "      <td>[[, , University of Hong Kong, Hong Kong, , HK...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>11</td>\n",
-       "      <td>[Scopus - Elsevier, Xinfeng Tang]</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[foxmail.com]</td>\n",
+       "      <td>khosroedc@yahoo.com</td>\n",
+       "      <td>...</td>\n",
+       "      <td>[scopus - elsevier]</td>\n",
+       "      <td>2018-01-19t13:40:29.874z</td>\n",
+       "      <td>2019-12-11t02:19:08.160z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>yahoo.com</td>\n",
+       "      <td>[medsab.ac.ir, gmail.com]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>299</th>\n",
-       "      <td>0000-0001-5109-3989</td>\n",
+       "      <th>1995</th>\n",
+       "      <td>0000-0001-8004-5054</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>colin</td>\n",
-       "      <td>tysall</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[colin.tysall@nhs.net]</td>\n",
+       "      <td>angiola</td>\n",
+       "      <td>orlando</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Associate Mental Health Act Manager, Coventr...</td>\n",
+       "      <td>angiola.orlando@mib.infn.it</td>\n",
+       "      <td>...</td>\n",
+       "      <td>[angiola orlando, crossref]</td>\n",
+       "      <td>2015-08-31t09:12:02.349z</td>\n",
+       "      <td>2020-06-22t14:22:31.786z</td>\n",
+       "      <td>59</td>\n",
+       "      <td>2</td>\n",
        "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[nhs.net]</td>\n",
+       "      <td>53</td>\n",
+       "      <td>1</td>\n",
+       "      <td>mib.infn.it</td>\n",
+       "      <td>[ge.infn.it]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>868</th>\n",
-       "      <td>0000-0001-5320-1277</td>\n",
+       "      <th>2323</th>\n",
+       "      <td>0000-0003-3048-4504</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Gökhan</td>\n",
-       "      <td>KESKİN</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>apichat</td>\n",
+       "      <td>saejio</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>2012001598@stu.adu.edu.tr</td>\n",
-       "      <td>[gokhankkeskin@gmail.com]</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, Adnan Menderes University, Aydin, , TR, gr...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>[scopus - elsevier]</td>\n",
+       "      <td>2016-03-06t08:54:15.121z</td>\n",
+       "      <td>2020-08-28t08:31:15.790z</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>stu.adu.edu.tr</td>\n",
-       "      <td>[gmail.com]</td>\n",
+       "      <td>[eat.kmutnb.ac.th]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1176</th>\n",
-       "      <td>0000-0001-5434-9994</td>\n",
+       "      <th>4461</th>\n",
+       "      <td>0000-0001-9961-9732</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Elena</td>\n",
-       "      <td>Borucu</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>lenapasali@gmail.com</td>\n",
-       "      <td>[epasali@yildiz.edu.tr]</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>chunfeng</td>\n",
+       "      <td>yun</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>sallyycf@163.com</td>\n",
+       "      <td>...</td>\n",
+       "      <td>[multidisciplinary digital publishing institut...</td>\n",
+       "      <td>2016-11-22t07:55:23.863z</td>\n",
+       "      <td>2019-11-26t02:29:35.104z</td>\n",
+       "      <td>5</td>\n",
        "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>gmail.com</td>\n",
-       "      <td>[yildiz.edu.tr]</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>163.com</td>\n",
+       "      <td>[pku.edu.cn]</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>5 rows × 26 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                    orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "34    0000-0001-5011-9833        1               1                       1   \n",
-       "47    0000-0001-5017-1295        1               1                       1   \n",
-       "299   0000-0001-5109-3989        1               1                       1   \n",
-       "868   0000-0001-5320-1277        1               1                       1   \n",
-       "1176  0000-0001-5434-9994        1               1                       1   \n",
-       "\n",
-       "     given_names family_name biography other_names urls  \\\n",
-       "34          Mark     Kilbane       NaN         NaN  NaN   \n",
-       "47       Xinfeng        Tang       NaN         NaN  NaN   \n",
-       "299        colin      tysall       NaN         NaN  NaN   \n",
-       "868       Gökhan      KESKİN       NaN         NaN  NaN   \n",
-       "1176       Elena      Borucu       NaN         NaN  NaN   \n",
-       "\n",
-       "                  primary_email                 other_emails keywords  \\\n",
-       "34    mark.kilbane@seh.ox.ac.uk  [mark.kilbane@bsg.ox.ac.uk]      NaN   \n",
-       "47                          NaN   [tang.xinfeng@foxmail.com]      NaN   \n",
-       "299                         NaN       [colin.tysall@nhs.net]      NaN   \n",
-       "868   2012001598@stu.adu.edu.tr    [gokhankkeskin@gmail.com]      NaN   \n",
-       "1176       lenapasali@gmail.com      [epasali@yildiz.edu.tr]      NaN   \n",
-       "\n",
-       "                           external_ids  \\\n",
-       "34                                  NaN   \n",
-       "47    [[Scopus Author ID, 56927186900]]   \n",
-       "299                                 NaN   \n",
-       "868                                 NaN   \n",
-       "1176                                NaN   \n",
-       "\n",
-       "                                              education  \\\n",
-       "34    [[Blavatnik School of Government; St Edmund Ha...   \n",
-       "47    [[, , University of Hong Kong, Hong Kong, , HK...   \n",
-       "299                                                 NaN   \n",
-       "868                                                 NaN   \n",
-       "1176                                                NaN   \n",
-       "\n",
-       "                                             employment  n_works  \\\n",
-       "34                                                  NaN        0   \n",
-       "47                                                  NaN       11   \n",
-       "299   [[Associate Mental Health Act Manager, Coventr...        0   \n",
-       "868   [[, Adnan Menderes University, Aydin, , TR, gr...        0   \n",
-       "1176                                                NaN        0   \n",
-       "\n",
-       "                           works_source primary_email_domain  \\\n",
-       "34                                  NaN         seh.ox.ac.uk   \n",
-       "47    [Scopus - Elsevier, Xinfeng Tang]                  NaN   \n",
-       "299                                 NaN                  NaN   \n",
-       "868                                 NaN       stu.adu.edu.tr   \n",
-       "1176                                NaN            gmail.com   \n",
-       "\n",
-       "     other_email_domains  \n",
-       "34        [bsg.ox.ac.uk]  \n",
-       "47         [foxmail.com]  \n",
-       "299            [nhs.net]  \n",
-       "868          [gmail.com]  \n",
-       "1176     [yildiz.edu.tr]  "
+       "34    0000-0002-5774-8947        1               1                       1   \n",
+       "1199  0000-0003-2877-5492        1               1                       0   \n",
+       "1995  0000-0001-8004-5054        1               1                       1   \n",
+       "2323  0000-0003-3048-4504        1               1                       1   \n",
+       "4461  0000-0001-9961-9732        1               1                       1   \n",
+       "\n",
+       "     given_names  family_name biography                  other_names urls  \\\n",
+       "34           NaN          NaN       NaN  [omah m. williams - duncan]  NaN   \n",
+       "1199   aliasghar  khosroabadi       NaN                          NaN  NaN   \n",
+       "1995     angiola      orlando       NaN                          NaN  NaN   \n",
+       "2323     apichat       saejio       NaN                          NaN  NaN   \n",
+       "4461    chunfeng          yun       NaN                          NaN  NaN   \n",
+       "\n",
+       "                    primary_email  ...  \\\n",
+       "34                            NaN  ...   \n",
+       "1199          khosroedc@yahoo.com  ...   \n",
+       "1995  angiola.orlando@mib.infn.it  ...   \n",
+       "2323                          NaN  ...   \n",
+       "4461             sallyycf@163.com  ...   \n",
+       "\n",
+       "                                           works_source  \\\n",
+       "34                                                  NaN   \n",
+       "1199                                [scopus - elsevier]   \n",
+       "1995                        [angiola orlando, crossref]   \n",
+       "2323                                [scopus - elsevier]   \n",
+       "4461  [multidisciplinary digital publishing institut...   \n",
+       "\n",
+       "               activation_date          last_update_date n_doi n_arxiv  n_pmc  \\\n",
+       "34    2014-03-07t04:34:39.598z  2019-05-21t17:08:12.202z     0       0      0   \n",
+       "1199  2018-01-19t13:40:29.874z  2019-12-11t02:19:08.160z     0       0      0   \n",
+       "1995  2015-08-31t09:12:02.349z  2020-06-22t14:22:31.786z    59       2      0   \n",
+       "2323  2016-03-06t08:54:15.121z  2020-08-28t08:31:15.790z     2       0      0   \n",
+       "4461  2016-11-22t07:55:23.863z  2019-11-26t02:29:35.104z     5       0      9   \n",
+       "\n",
+       "     n_other_pids label primary_email_domain        other_email_domains  \n",
+       "34              0     0                  NaN                [gmail.com]  \n",
+       "1199            1     1            yahoo.com  [medsab.ac.ir, gmail.com]  \n",
+       "1995           53     1          mib.infn.it               [ge.infn.it]  \n",
+       "2323            4     0                  NaN         [eat.kmutnb.ac.th]  \n",
+       "4461            0     1              163.com               [pku.edu.cn]  \n",
+       "\n",
+       "[5 rows x 26 columns]"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 31,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3154,7 +2480,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3163,7 +2489,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
@@ -3180,34 +2506,34 @@
          "x": [
           "0000-0003-4171-3835",
           "0000-0001-6239-2968",
-          "0000-0003-2290-2817",
           "0000-0003-2151-4089",
+          "0000-0003-2290-2817",
           "0000-0001-9084-3156",
-          "0000-0003-4147-212X",
           "0000-0001-6349-1044",
           "0000-0002-2085-1908",
-          "0000-0002-8390-8238",
+          "0000-0003-4147-212x",
+          "0000-0002-8565-194x",
+          "0000-0002-7396-1561",
+          "0000-0002-9821-8424",
           "0000-0003-4327-6827",
+          "0000-0001-9311-0687",
           "0000-0003-0391-3430",
-          "0000-0001-5548-8259",
-          "0000-0002-8565-194X",
+          "0000-0002-0776-9547",
           "0000-0003-2657-8225",
+          "0000-0001-5548-8259",
+          "0000-0003-0671-1543",
           "0000-0003-1502-3910",
-          "0000-0001-9311-0687",
+          "0000-0003-4685-5621",
+          "0000-0002-3165-132x",
+          "0000-0001-8420-9204",
+          "0000-0002-1929-6054",
+          "0000-0002-8390-8238",
           "0000-0002-9599-6909",
-          "0000-0002-7396-1561",
-          "0000-0003-0671-1543",
           "0000-0002-5341-6531",
-          "0000-0002-9821-8424",
           "0000-0003-4499-7300",
-          "0000-0002-3165-132X",
           "0000-0002-1615-8633",
-          "0000-0002-0776-9547",
-          "0000-0002-1929-6054",
-          "0000-0001-7093-4085",
-          "0000-0002-0841-5177",
-          "0000-0002-3909-8805",
-          "0000-0002-8160-1320"
+          "0000-0002-6206-4638",
+          "0000-0003-3405-355x"
          ],
          "y": [
           12,
@@ -3236,8 +2562,8 @@
           5,
           5,
           5,
-          4,
-          4,
+          5,
+          5,
           4,
           4
          ]
@@ -4066,9 +3392,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"01356982-52ec-4a7d-af6b-906714d33830\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"01356982-52ec-4a7d-af6b-906714d33830\")) {                    Plotly.newPlot(                        \"01356982-52ec-4a7d-af6b-906714d33830\",                        [{\"type\": \"bar\", \"x\": [\"0000-0003-4171-3835\", \"0000-0001-6239-2968\", \"0000-0003-2290-2817\", \"0000-0003-2151-4089\", \"0000-0001-9084-3156\", \"0000-0003-4147-212X\", \"0000-0001-6349-1044\", \"0000-0002-2085-1908\", \"0000-0002-8390-8238\", \"0000-0003-4327-6827\", \"0000-0003-0391-3430\", \"0000-0001-5548-8259\", \"0000-0002-8565-194X\", \"0000-0003-2657-8225\", \"0000-0003-1502-3910\", \"0000-0001-9311-0687\", \"0000-0002-9599-6909\", \"0000-0002-7396-1561\", \"0000-0003-0671-1543\", \"0000-0002-5341-6531\", \"0000-0002-9821-8424\", \"0000-0003-4499-7300\", \"0000-0002-3165-132X\", \"0000-0002-1615-8633\", \"0000-0002-0776-9547\", \"0000-0002-1929-6054\", \"0000-0001-7093-4085\", \"0000-0002-0841-5177\", \"0000-0002-3909-8805\", \"0000-0002-8160-1320\"], \"y\": [12.0, 9.0, 7.0, 7.0, 6.0, 6.0, 6.0, 6.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 4.0, 4.0, 4.0, 4.0]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 ORCiD by email\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"af09fc26-d772-4201-a866-00d6c313371e\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"af09fc26-d772-4201-a866-00d6c313371e\")) {                    Plotly.newPlot(                        \"af09fc26-d772-4201-a866-00d6c313371e\",                        [{\"type\": \"bar\", \"x\": [\"0000-0003-4171-3835\", \"0000-0001-6239-2968\", \"0000-0003-2151-4089\", \"0000-0003-2290-2817\", \"0000-0001-9084-3156\", \"0000-0001-6349-1044\", \"0000-0002-2085-1908\", \"0000-0003-4147-212x\", \"0000-0002-8565-194x\", \"0000-0002-7396-1561\", \"0000-0002-9821-8424\", \"0000-0003-4327-6827\", \"0000-0001-9311-0687\", \"0000-0003-0391-3430\", \"0000-0002-0776-9547\", \"0000-0003-2657-8225\", \"0000-0001-5548-8259\", \"0000-0003-0671-1543\", \"0000-0003-1502-3910\", \"0000-0003-4685-5621\", \"0000-0002-3165-132x\", \"0000-0001-8420-9204\", \"0000-0002-1929-6054\", \"0000-0002-8390-8238\", \"0000-0002-9599-6909\", \"0000-0002-5341-6531\", \"0000-0003-4499-7300\", \"0000-0002-1615-8633\", \"0000-0002-6206-4638\", \"0000-0003-3405-355x\"], \"y\": [12.0, 9.0, 7.0, 7.0, 6.0, 6.0, 6.0, 6.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 4.0, 4.0]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 ORCiD by email\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('01356982-52ec-4a7d-af6b-906714d33830');\n",
+       "var gd = document.getElementById('af09fc26-d772-4201-a866-00d6c313371e');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -4116,7 +3442,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4130,7 +3456,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 90,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [
     {
@@ -4148,8 +3474,8 @@
           "gmail.com",
           "hotmail.com",
           "yahoo.com",
-          "163.com",
           "qq.com",
+          "163.com",
           "outlook.com",
           "126.com",
           "usp.br",
@@ -4161,51 +3487,51 @@
           "yuhs.ac",
           "naver.com",
           "icloud.com",
-          "ua.pt",
-          "uq.edu.au",
           "foxmail.com",
+          "uq.edu.au",
+          "ua.pt",
           "cam.ac.uk",
+          "imperial.ac.uk",
           "ukr.net",
           "law.ox.ac.uk",
-          "imperial.ac.uk",
           "mit.edu",
+          "stanford.edu",
           "monash.edu",
           "ucl.ac.uk",
           "education.ox.ac.uk",
-          "stanford.edu",
           "ucm.es",
           "conted.ox.ac.uk"
          ],
          "y": [
-          10856,
-          1521,
-          1263,
-          763,
-          755,
-          422,
-          256,
-          235,
-          223,
+          11116,
+          1541,
+          1295,
+          779,
+          774,
+          425,
+          260,
+          236,
+          224,
+          149,
           147,
-          146,
-          138,
+          141,
           136,
+          133,
           130,
-          128,
-          113,
-          92,
-          90,
-          90,
-          81,
+          118,
+          96,
+          94,
+          89,
+          84,
+          77,
           76,
           75,
-          75,
           74,
-          69,
-          67,
+          71,
+          70,
+          68,
           67,
           66,
-          65,
           64
          ]
         }
@@ -5033,9 +4359,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"5e7e5a2b-e6c0-4d40-86d0-df66a2fa2a4d\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"5e7e5a2b-e6c0-4d40-86d0-df66a2fa2a4d\")) {                    Plotly.newPlot(                        \"5e7e5a2b-e6c0-4d40-86d0-df66a2fa2a4d\",                        [{\"type\": \"bar\", \"x\": [\"gmail.com\", \"hotmail.com\", \"yahoo.com\", \"163.com\", \"qq.com\", \"outlook.com\", \"126.com\", \"usp.br\", \"ieee.org\", \"mail.ru\", \"yahoo.com.br\", \"unesp.br\", \"sbs.ox.ac.uk\", \"yuhs.ac\", \"naver.com\", \"icloud.com\", \"ua.pt\", \"uq.edu.au\", \"foxmail.com\", \"cam.ac.uk\", \"ukr.net\", \"law.ox.ac.uk\", \"imperial.ac.uk\", \"mit.edu\", \"monash.edu\", \"ucl.ac.uk\", \"education.ox.ac.uk\", \"stanford.edu\", \"ucm.es\", \"conted.ox.ac.uk\"], \"y\": [10856, 1521, 1263, 763, 755, 422, 256, 235, 223, 147, 146, 138, 136, 130, 128, 113, 92, 90, 90, 81, 76, 75, 75, 74, 69, 67, 67, 66, 65, 64]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 other email domains\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"f62e82ae-82a4-402b-9759-c47003e4a6bc\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"f62e82ae-82a4-402b-9759-c47003e4a6bc\")) {                    Plotly.newPlot(                        \"f62e82ae-82a4-402b-9759-c47003e4a6bc\",                        [{\"type\": \"bar\", \"x\": [\"gmail.com\", \"hotmail.com\", \"yahoo.com\", \"qq.com\", \"163.com\", \"outlook.com\", \"126.com\", \"usp.br\", \"ieee.org\", \"mail.ru\", \"yahoo.com.br\", \"unesp.br\", \"sbs.ox.ac.uk\", \"yuhs.ac\", \"naver.com\", \"icloud.com\", \"foxmail.com\", \"uq.edu.au\", \"ua.pt\", \"cam.ac.uk\", \"imperial.ac.uk\", \"ukr.net\", \"law.ox.ac.uk\", \"mit.edu\", \"stanford.edu\", \"monash.edu\", \"ucl.ac.uk\", \"education.ox.ac.uk\", \"ucm.es\", \"conted.ox.ac.uk\"], \"y\": [11116, 1541, 1295, 779, 774, 425, 260, 236, 224, 149, 147, 141, 136, 133, 130, 118, 96, 94, 89, 84, 77, 76, 75, 74, 71, 70, 68, 67, 66, 64]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 other email domains\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('5e7e5a2b-e6c0-4d40-86d0-df66a2fa2a4d');\n",
+       "var gd = document.getElementById('f62e82ae-82a4-402b-9759-c47003e4a6bc');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -5090,7 +4416,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 36,
    "metadata": {
     "scrolled": true
    },
@@ -5126,13 +4452,14 @@
        "      <th>other_names</th>\n",
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
-       "      <th>other_emails</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "      <th>...</th>\n",
+       "      <th>activation_date</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "      <th>n_emails</th>\n",
@@ -5140,118 +4467,123 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>47</th>\n",
-       "      <td>0000-0001-5017-1295</td>\n",
+       "      <th>34</th>\n",
+       "      <td>0000-0002-5774-8947</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Xinfeng</td>\n",
-       "      <td>Tang</td>\n",
-       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[tang.xinfeng@foxmail.com]</td>\n",
+       "      <td>[omah m. williams - duncan]</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Scopus Author ID, 56927186900]]</td>\n",
-       "      <td>[[, , University of Hong Kong, Hong Kong, , HK...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>11</td>\n",
-       "      <td>[Scopus - Elsevier, Xinfeng Tang]</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2014-03-07t04:34:39.598z</td>\n",
+       "      <td>2019-05-21t17:08:12.202z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[foxmail.com]</td>\n",
+       "      <td>[gmail.com]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>299</th>\n",
-       "      <td>0000-0001-5109-3989</td>\n",
+       "      <th>2323</th>\n",
+       "      <td>0000-0003-3048-4504</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>colin</td>\n",
-       "      <td>tysall</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>apichat</td>\n",
+       "      <td>saejio</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[colin.tysall@nhs.net]</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Associate Mental Health Act Manager, Coventr...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2016-03-06t08:54:15.121z</td>\n",
+       "      <td>2020-08-28t08:31:15.790z</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[nhs.net]</td>\n",
+       "      <td>[eat.kmutnb.ac.th]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1296</th>\n",
-       "      <td>0000-0001-5476-0126</td>\n",
+       "      <th>7622</th>\n",
+       "      <td>0000-0002-5612-7444</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Aura Windy</td>\n",
-       "      <td>Hernández Cetina</td>\n",
+       "      <td>friederike m.</td>\n",
+       "      <td>hesse</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[midwifery care - milla hebammenpraxis, http:...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2017-06-10t07:45:11.387z</td>\n",
+       "      <td>2017-06-10t07:55:03.455z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[u0902038@unimilitar.edu.co]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, Profesional en Relaciones Internacionales ...</td>\n",
-       "      <td>[[Asistente de Investigación, Pontificia Unive...</td>\n",
-       "      <td>1</td>\n",
-       "      <td>[Aura Windy  Hernández Cetina]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[unimilitar.edu.co]</td>\n",
-       "      <td>1.0</td>\n",
+       "      <td>[gmail.com, dghwi.de]</td>\n",
+       "      <td>2.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1429</th>\n",
-       "      <td>0000-0001-5522-427X</td>\n",
+       "      <th>7956</th>\n",
+       "      <td>0000-0002-8943-0538</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Süleyman</td>\n",
-       "      <td>Özen</td>\n",
+       "      <td>geo</td>\n",
+       "      <td>sunny</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Academic CV, https://akademik.yok.gov.tr/Aka...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[suleyman.ozen@btu.edu.tr]</td>\n",
-       "      <td>[construction materials, superplasticizers, co...</td>\n",
-       "      <td>[[Scopus Author ID, 57188750603]]</td>\n",
-       "      <td>[[Civil Engineering, MSc and PhD, Uludağ Unive...</td>\n",
-       "      <td>[[Dr., Bursa Technical University, Bursa, , TR...</td>\n",
-       "      <td>7</td>\n",
-       "      <td>[Scopus - Elsevier, Crossref]</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[btu.edu.tr]</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2019-11-30t14:08:11.221z</td>\n",
+       "      <td>2020-05-15t09:06:25.637z</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[students.cutn.ac.in]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1628</th>\n",
-       "      <td>0000-0001-5597-3115</td>\n",
+       "      <th>10508</th>\n",
+       "      <td>0000-0002-4022-0580</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Wade</td>\n",
-       "      <td>Harrison</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>jean carlos</td>\n",
+       "      <td>da silva gomes</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[currículo lattes, http://lattes.cnpq.br/0026...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[wade_harrison@unc.edu]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, MD, Dartmouth College Geisel School of Med...</td>\n",
-       "      <td>[[Clinical Instructor / Research Fellow, Unive...</td>\n",
-       "      <td>7</td>\n",
-       "      <td>[Wade Harrison]</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2017-05-26t19:09:33.432z</td>\n",
+       "      <td>2020-06-02t00:23:14.020z</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[unc.edu]</td>\n",
+       "      <td>[letras.ufrj.br]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
@@ -5276,288 +4608,229 @@
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
+       "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10743658</th>\n",
-       "      <td>0000-0003-3740-8352</td>\n",
+       "      <th>10915002</th>\n",
+       "      <td>0000-0002-3715-3866</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Rui</td>\n",
-       "      <td>Zhang</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>joanna</td>\n",
+       "      <td>korybut-orlowska</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[joanna gołębiewska]</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[zhang-r15@mails.tsinghua.edu.cn]</td>\n",
-       "      <td>[Lithium metal batteries, Graphene]</td>\n",
-       "      <td>[[ResearcherID, B-3843-2015]]</td>\n",
-       "      <td>[[Department of Chemical Engineering, Ph.D. st...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>15</td>\n",
-       "      <td>[ResearcherID, Crossref]</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2017-04-27t10:08:48.102z</td>\n",
+       "      <td>2020-12-08t09:44:59.088z</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[mails.tsinghua.edu.cn]</td>\n",
+       "      <td>[gmail.com]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10744876</th>\n",
-       "      <td>0000-0003-4192-6451</td>\n",
+       "      <th>10915305</th>\n",
+       "      <td>0000-0003-1925-0141</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Sanjib Raj</td>\n",
-       "      <td>Pandey</td>\n",
+       "      <td>marco</td>\n",
+       "      <td>ferretti</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Personal, https://www.sanjibpandey.wix.com/p...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[srpandey@gmail.com]</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2015-02-23t10:29:00.543z</td>\n",
+       "      <td>2020-11-30t21:58:07.439z</td>\n",
+       "      <td>7</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Computing and Information System, PhD, Unive...</td>\n",
-       "      <td>[[Software Developer &amp; Research Associate, Oxl...</td>\n",
-       "      <td>11</td>\n",
-       "      <td>[BASE - Bielefeld Academic Search Engine, Dr. ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[gmail.com]</td>\n",
+       "      <td>[itabc.cnr.it]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10745274</th>\n",
-       "      <td>0000-0003-4333-9728</td>\n",
+       "      <th>10915495</th>\n",
+       "      <td>0000-0001-5526-3017</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Mario</td>\n",
-       "      <td>De la Fuente Lloreda</td>\n",
-       "      <td>Person in charge to coordinate the scientific ...</td>\n",
-       "      <td>[M.de la Fuente, De la Fuente, M.]</td>\n",
-       "      <td>[[researchgate profile, https://www.researchga...</td>\n",
+       "      <td>nadia</td>\n",
+       "      <td>yacoubi</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[mariofuente@gmail.com]</td>\n",
-       "      <td>[vineyard management, grapevine, viticulture, ...</td>\n",
-       "      <td>[[Scopus Author ID, 47960975000]]</td>\n",
-       "      <td>[[Producción Vegetal, Doctor en Viticultura, U...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2015-03-10t16:45:31.974z</td>\n",
+       "      <td>2020-12-11t00:00:01.060z</td>\n",
        "      <td>3</td>\n",
-       "      <td>[Scopus - Elsevier]</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[gmail.com]</td>\n",
+       "      <td>[evonik.com]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10745417</th>\n",
-       "      <td>0000-0003-4383-4745</td>\n",
+       "      <th>10915820</th>\n",
+       "      <td>0000-0002-9902-7953</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Jie</td>\n",
-       "      <td>Yang</td>\n",
+       "      <td>s m mahmudul</td>\n",
+       "      <td>hasan</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[jyang@esat.kuleuven.be]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[faculty of engineering science, Dr., KU Leuv...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2018-01-26t02:18:25.551z</td>\n",
+       "      <td>2020-11-24t05:37:24.167z</td>\n",
+       "      <td>7</td>\n",
        "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[esat.kuleuven.be]</td>\n",
+       "      <td>[gmail.com]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10746702</th>\n",
-       "      <td>0000-0003-4878-2737</td>\n",
+       "      <th>10916306</th>\n",
+       "      <td>0000-0002-5126-5127</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Aleksey</td>\n",
-       "      <td>Adamtsevich</td>\n",
+       "      <td>andonis</td>\n",
+       "      <td>neophytou</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Moscow State University of Civil Engineering...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[AdamtsevichAO@mgsu.ru]</td>\n",
-       "      <td>[concrete, calorimetry, cement, construction, ...</td>\n",
-       "      <td>[[Scopus Author ID, 56301531000], [ResearcherI...</td>\n",
-       "      <td>[[, Engineer (Industrial and Civil Engineering...</td>\n",
-       "      <td>[[Senior Researcher, Moscow State University o...</td>\n",
-       "      <td>25</td>\n",
-       "      <td>[Scopus - Elsevier, ResearcherID]</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[mgsu.ru]</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2017-03-30t17:08:15.383z</td>\n",
+       "      <td>2020-12-09t16:16:50.762z</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[ucy.ac.cy]</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>19409 rows × 20 columns</p>\n",
+       "<p>19692 rows × 27 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                        orcid  claimed  verified_email  \\\n",
-       "47        0000-0001-5017-1295        1               1   \n",
-       "299       0000-0001-5109-3989        1               1   \n",
-       "1296      0000-0001-5476-0126        1               1   \n",
-       "1429      0000-0001-5522-427X        1               1   \n",
-       "1628      0000-0001-5597-3115        1               1   \n",
+       "34        0000-0002-5774-8947        1               1   \n",
+       "2323      0000-0003-3048-4504        1               1   \n",
+       "7622      0000-0002-5612-7444        1               1   \n",
+       "7956      0000-0002-8943-0538        1               1   \n",
+       "10508     0000-0002-4022-0580        1               1   \n",
        "...                       ...      ...             ...   \n",
-       "10743658  0000-0003-3740-8352        1               1   \n",
-       "10744876  0000-0003-4192-6451        1               1   \n",
-       "10745274  0000-0003-4333-9728        1               1   \n",
-       "10745417  0000-0003-4383-4745        1               1   \n",
-       "10746702  0000-0003-4878-2737        1               1   \n",
-       "\n",
-       "          verified_primary_email  given_names           family_name  \\\n",
-       "47                             1      Xinfeng                  Tang   \n",
-       "299                            1        colin                tysall   \n",
-       "1296                           1  Aura Windy       Hernández Cetina   \n",
-       "1429                           1     Süleyman                  Özen   \n",
-       "1628                           1         Wade              Harrison   \n",
-       "...                          ...          ...                   ...   \n",
-       "10743658                       1          Rui                 Zhang   \n",
-       "10744876                       1   Sanjib Raj                Pandey   \n",
-       "10745274                       1        Mario  De la Fuente Lloreda   \n",
-       "10745417                       1          Jie                  Yang   \n",
-       "10746702                       1      Aleksey           Adamtsevich   \n",
-       "\n",
-       "                                                  biography  \\\n",
-       "47                                                      NaN   \n",
-       "299                                                     NaN   \n",
-       "1296                                                    NaN   \n",
-       "1429                                                    NaN   \n",
-       "1628                                                    NaN   \n",
-       "...                                                     ...   \n",
-       "10743658                                                NaN   \n",
-       "10744876                                                NaN   \n",
-       "10745274  Person in charge to coordinate the scientific ...   \n",
-       "10745417                                                NaN   \n",
-       "10746702                                                NaN   \n",
-       "\n",
-       "                                 other_names  \\\n",
-       "47                                       NaN   \n",
-       "299                                      NaN   \n",
-       "1296                                     NaN   \n",
-       "1429                                     NaN   \n",
-       "1628                                     NaN   \n",
-       "...                                      ...   \n",
-       "10743658                                 NaN   \n",
-       "10744876                                 NaN   \n",
-       "10745274  [M.de la Fuente, De la Fuente, M.]   \n",
-       "10745417                                 NaN   \n",
-       "10746702                                 NaN   \n",
+       "10915002  0000-0002-3715-3866        1               1   \n",
+       "10915305  0000-0003-1925-0141        1               1   \n",
+       "10915495  0000-0001-5526-3017        1               1   \n",
+       "10915820  0000-0002-9902-7953        1               1   \n",
+       "10916306  0000-0002-5126-5127        1               1   \n",
+       "\n",
+       "          verified_primary_email    given_names       family_name biography  \\\n",
+       "34                             1            NaN               NaN       NaN   \n",
+       "2323                           1        apichat            saejio       NaN   \n",
+       "7622                           1  friederike m.             hesse       NaN   \n",
+       "7956                           1            geo             sunny       NaN   \n",
+       "10508                          1    jean carlos    da silva gomes       NaN   \n",
+       "...                          ...            ...               ...       ...   \n",
+       "10915002                       1         joanna  korybut-orlowska       NaN   \n",
+       "10915305                       1          marco          ferretti       NaN   \n",
+       "10915495                       1          nadia           yacoubi       NaN   \n",
+       "10915820                       1   s m mahmudul             hasan       NaN   \n",
+       "10916306                       1        andonis         neophytou       NaN   \n",
+       "\n",
+       "                          other_names  \\\n",
+       "34        [omah m. williams - duncan]   \n",
+       "2323                              NaN   \n",
+       "7622                              NaN   \n",
+       "7956                              NaN   \n",
+       "10508                             NaN   \n",
+       "...                               ...   \n",
+       "10915002         [joanna gołębiewska]   \n",
+       "10915305                          NaN   \n",
+       "10915495                          NaN   \n",
+       "10915820                          NaN   \n",
+       "10916306                          NaN   \n",
        "\n",
        "                                                       urls primary_email  \\\n",
-       "47                                                      NaN           NaN   \n",
-       "299                                                     NaN           NaN   \n",
-       "1296                                                    NaN           NaN   \n",
-       "1429      [[Academic CV, https://akademik.yok.gov.tr/Aka...           NaN   \n",
-       "1628                                                    NaN           NaN   \n",
+       "34                                                      NaN           NaN   \n",
+       "2323                                                    NaN           NaN   \n",
+       "7622      [[midwifery care - milla hebammenpraxis, http:...           NaN   \n",
+       "7956                                                    NaN           NaN   \n",
+       "10508     [[currículo lattes, http://lattes.cnpq.br/0026...           NaN   \n",
        "...                                                     ...           ...   \n",
-       "10743658                                                NaN           NaN   \n",
-       "10744876  [[Personal, https://www.sanjibpandey.wix.com/p...           NaN   \n",
-       "10745274  [[researchgate profile, https://www.researchga...           NaN   \n",
-       "10745417                                                NaN           NaN   \n",
-       "10746702  [[Moscow State University of Civil Engineering...           NaN   \n",
-       "\n",
-       "                               other_emails  \\\n",
-       "47               [tang.xinfeng@foxmail.com]   \n",
-       "299                  [colin.tysall@nhs.net]   \n",
-       "1296           [u0902038@unimilitar.edu.co]   \n",
-       "1429             [suleyman.ozen@btu.edu.tr]   \n",
-       "1628                [wade_harrison@unc.edu]   \n",
-       "...                                     ...   \n",
-       "10743658  [zhang-r15@mails.tsinghua.edu.cn]   \n",
-       "10744876               [srpandey@gmail.com]   \n",
-       "10745274            [mariofuente@gmail.com]   \n",
-       "10745417           [jyang@esat.kuleuven.be]   \n",
-       "10746702            [AdamtsevichAO@mgsu.ru]   \n",
-       "\n",
-       "                                                   keywords  \\\n",
-       "47                                                      NaN   \n",
-       "299                                                     NaN   \n",
-       "1296                                                    NaN   \n",
-       "1429      [construction materials, superplasticizers, co...   \n",
-       "1628                                                    NaN   \n",
-       "...                                                     ...   \n",
-       "10743658                [Lithium metal batteries, Graphene]   \n",
-       "10744876                                                NaN   \n",
-       "10745274  [vineyard management, grapevine, viticulture, ...   \n",
-       "10745417                                                NaN   \n",
-       "10746702  [concrete, calorimetry, cement, construction, ...   \n",
-       "\n",
-       "                                               external_ids  \\\n",
-       "47                        [[Scopus Author ID, 56927186900]]   \n",
-       "299                                                     NaN   \n",
-       "1296                                                    NaN   \n",
-       "1429                      [[Scopus Author ID, 57188750603]]   \n",
-       "1628                                                    NaN   \n",
-       "...                                                     ...   \n",
-       "10743658                      [[ResearcherID, B-3843-2015]]   \n",
-       "10744876                                                NaN   \n",
-       "10745274                  [[Scopus Author ID, 47960975000]]   \n",
-       "10745417                                                NaN   \n",
-       "10746702  [[Scopus Author ID, 56301531000], [ResearcherI...   \n",
-       "\n",
-       "                                                  education  \\\n",
-       "47        [[, , University of Hong Kong, Hong Kong, , HK...   \n",
-       "299                                                     NaN   \n",
-       "1296      [[, Profesional en Relaciones Internacionales ...   \n",
-       "1429      [[Civil Engineering, MSc and PhD, Uludağ Unive...   \n",
-       "1628      [[, MD, Dartmouth College Geisel School of Med...   \n",
-       "...                                                     ...   \n",
-       "10743658  [[Department of Chemical Engineering, Ph.D. st...   \n",
-       "10744876  [[Computing and Information System, PhD, Unive...   \n",
-       "10745274  [[Producción Vegetal, Doctor en Viticultura, U...   \n",
-       "10745417  [[faculty of engineering science, Dr., KU Leuv...   \n",
-       "10746702  [[, Engineer (Industrial and Civil Engineering...   \n",
-       "\n",
-       "                                                 employment  n_works  \\\n",
-       "47                                                      NaN       11   \n",
-       "299       [[Associate Mental Health Act Manager, Coventr...        0   \n",
-       "1296      [[Asistente de Investigación, Pontificia Unive...        1   \n",
-       "1429      [[Dr., Bursa Technical University, Bursa, , TR...        7   \n",
-       "1628      [[Clinical Instructor / Research Fellow, Unive...        7   \n",
-       "...                                                     ...      ...   \n",
-       "10743658                                                NaN       15   \n",
-       "10744876  [[Software Developer & Research Associate, Oxl...       11   \n",
-       "10745274                                                NaN        3   \n",
-       "10745417                                                NaN        0   \n",
-       "10746702  [[Senior Researcher, Moscow State University o...       25   \n",
-       "\n",
-       "                                               works_source  \\\n",
-       "47                        [Scopus - Elsevier, Xinfeng Tang]   \n",
-       "299                                                     NaN   \n",
-       "1296                         [Aura Windy  Hernández Cetina]   \n",
-       "1429                          [Scopus - Elsevier, Crossref]   \n",
-       "1628                                        [Wade Harrison]   \n",
-       "...                                                     ...   \n",
-       "10743658                           [ResearcherID, Crossref]   \n",
-       "10744876  [BASE - Bielefeld Academic Search Engine, Dr. ...   \n",
-       "10745274                                [Scopus - Elsevier]   \n",
-       "10745417                                                NaN   \n",
-       "10746702                  [Scopus - Elsevier, ResearcherID]   \n",
-       "\n",
-       "         primary_email_domain      other_email_domains  n_emails  \n",
-       "47                        NaN            [foxmail.com]       1.0  \n",
-       "299                       NaN                [nhs.net]       1.0  \n",
-       "1296                      NaN      [unimilitar.edu.co]       1.0  \n",
-       "1429                      NaN             [btu.edu.tr]       1.0  \n",
-       "1628                      NaN                [unc.edu]       1.0  \n",
-       "...                       ...                      ...       ...  \n",
-       "10743658                  NaN  [mails.tsinghua.edu.cn]       1.0  \n",
-       "10744876                  NaN              [gmail.com]       1.0  \n",
-       "10745274                  NaN              [gmail.com]       1.0  \n",
-       "10745417                  NaN       [esat.kuleuven.be]       1.0  \n",
-       "10746702                  NaN                [mgsu.ru]       1.0  \n",
-       "\n",
-       "[19409 rows x 20 columns]"
+       "10915002                                                NaN           NaN   \n",
+       "10915305                                                NaN           NaN   \n",
+       "10915495                                                NaN           NaN   \n",
+       "10915820                                                NaN           NaN   \n",
+       "10916306                                                NaN           NaN   \n",
+       "\n",
+       "          ...           activation_date          last_update_date n_doi  \\\n",
+       "34        ...  2014-03-07t04:34:39.598z  2019-05-21t17:08:12.202z     0   \n",
+       "2323      ...  2016-03-06t08:54:15.121z  2020-08-28t08:31:15.790z     2   \n",
+       "7622      ...  2017-06-10t07:45:11.387z  2017-06-10t07:55:03.455z     0   \n",
+       "7956      ...  2019-11-30t14:08:11.221z  2020-05-15t09:06:25.637z     1   \n",
+       "10508     ...  2017-05-26t19:09:33.432z  2020-06-02t00:23:14.020z     2   \n",
+       "...       ...                       ...                       ...   ...   \n",
+       "10915002  ...  2017-04-27t10:08:48.102z  2020-12-08t09:44:59.088z     6   \n",
+       "10915305  ...  2015-02-23t10:29:00.543z  2020-11-30t21:58:07.439z     7   \n",
+       "10915495  ...  2015-03-10t16:45:31.974z  2020-12-11t00:00:01.060z     3   \n",
+       "10915820  ...  2018-01-26t02:18:25.551z  2020-11-24t05:37:24.167z     7   \n",
+       "10916306  ...  2017-03-30t17:08:15.383z  2020-12-09t16:16:50.762z     2   \n",
+       "\n",
+       "         n_arxiv n_pmc  n_other_pids label primary_email_domain  \\\n",
+       "34             0     0             0     0                  NaN   \n",
+       "2323           0     0             4     0                  NaN   \n",
+       "7622           0     0             0     0                  NaN   \n",
+       "7956           0     0             0     1                  NaN   \n",
+       "10508          0     0             2     1                  NaN   \n",
+       "...          ...   ...           ...   ...                  ...   \n",
+       "10915002       0     0             0     0                  NaN   \n",
+       "10915305       0     0             9     1                  NaN   \n",
+       "10915495       0     0             0     1                  NaN   \n",
+       "10915820       0     2             7     1                  NaN   \n",
+       "10916306       0     0             3     0                  NaN   \n",
+       "\n",
+       "            other_email_domains  n_emails  \n",
+       "34                  [gmail.com]       1.0  \n",
+       "2323         [eat.kmutnb.ac.th]       1.0  \n",
+       "7622      [gmail.com, dghwi.de]       2.0  \n",
+       "7956      [students.cutn.ac.in]       1.0  \n",
+       "10508          [letras.ufrj.br]       1.0  \n",
+       "...                         ...       ...  \n",
+       "10915002            [gmail.com]       1.0  \n",
+       "10915305         [itabc.cnr.it]       1.0  \n",
+       "10915495           [evonik.com]       1.0  \n",
+       "10915820            [gmail.com]       1.0  \n",
+       "10916306            [ucy.ac.cy]       1.0  \n",
+       "\n",
+       "[19692 rows x 27 columns]"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 36,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5589,7 +4862,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5605,7 +4878,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5614,7 +4887,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
@@ -5649,12 +4922,12 @@
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
        "      <th>...</th>\n",
-       "      <th>keywords</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "      <th>last_update_date</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "      <th>n_emails</th>\n",
@@ -5663,205 +4936,184 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0000-0001-5001-4994</td>\n",
+       "      <th>9</th>\n",
+       "      <td>0000-0001-8718-0056</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Siren</td>\n",
-       "      <td>Rühs</td>\n",
-       "      <td>I am an oceanographer studying the interannual...</td>\n",
-       "      <td>[Siren Ruehs]</td>\n",
-       "      <td>[[ResearchGate, https://www.researchgate.net/p...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>11</td>\n",
-       "      <td>[Siren Rühs]</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>[飛資得]</td>\n",
+       "      <td>[[link1, http://orcid.flysheetmed.info], [ntu ...</td>\n",
+       "      <td>ericlin.flysheet@gmail.com</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2019-10-11t17:51:12.473z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>gmail.com</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[researchgate.net]</td>\n",
+       "      <td>[flysheetmed.info, ntu.edu.tw]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>0000-0001-5004-7761</td>\n",
+       "      <th>41</th>\n",
+       "      <td>0000-0002-7845-4016</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>scaffolding</td>\n",
-       "      <td>hire</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[The first feature that you have to check in t...</td>\n",
-       "      <td>[[scaffolding hire Wellington, https://www.tig...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>[scaffolding hire Wellington]</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[publication profile, http://publications.lib...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2016-06-06t15:29:36.952z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[tigerscaffolds.co.nz]</td>\n",
+       "      <td>[chalmers.se]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>15</th>\n",
-       "      <td>0000-0001-5005-0557</td>\n",
+       "      <th>59</th>\n",
+       "      <td>0000-0003-0967-6157</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Sen</td>\n",
-       "      <td>RT</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Research on Psychology, psychiatry, Genetics...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[徐興慶]</td>\n",
+       "      <td>[[ntu researcher profile, http://ah.ntu.edu.tw...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2017-03-10t07:30:04.778z</td>\n",
+       "      <td>12</td>\n",
        "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[corticalbrain.com]</td>\n",
+       "      <td>[ntu.edu.tw, ntu.edu.tw]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>29</th>\n",
-       "      <td>0000-0001-5009-8091</td>\n",
+       "      <th>149</th>\n",
+       "      <td>0000-0002-8015-3781</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Gabriela</td>\n",
-       "      <td>Madruga</td>\n",
-       "      <td>Possui graduação em Medicina Veterinaria pela ...</td>\n",
-       "      <td>[Gabriela Morais Madruga]</td>\n",
-       "      <td>[[Curriculo lattes, http://buscatextual.cnpq.b...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>[veterinary ophthalmology]</td>\n",
+       "      <td>alejandro</td>\n",
+       "      <td>ossorio</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Surgery in small animal, PhD, Universidade E...</td>\n",
-       "      <td>[[PhD , University of Minnesota, Minneapolis, ...</td>\n",
-       "      <td>14</td>\n",
-       "      <td>[Gabriela Madruga]</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[web de la universidad carlos iii de madrid, ...</td>\n",
+       "      <td>aossorio@di.uc3m.es</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2019-07-04t08:47:12.005z</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>di.uc3m.es</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[cnpq.br]</td>\n",
+       "      <td>[uc3m.es]</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>30</th>\n",
-       "      <td>0000-0001-5010-9539</td>\n",
+       "      <th>155</th>\n",
+       "      <td>0000-0003-3444-936x</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Sangram Keshari</td>\n",
-       "      <td>Sahu</td>\n",
+       "      <td>alessandra</td>\n",
+       "      <td>caravale</td>\n",
+       "      <td>archeologa, con laurea in metodologia e tecnic...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[sk-sahu]</td>\n",
-       "      <td>[[Academic webpage, https://sksahu.net]]</td>\n",
+       "      <td>[[isma- cnr, http://www.isma.cnr.it/?page_id=1...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[Computational Genomics and Bioinformatics]</td>\n",
-       "      <td>[[Loop profile, 1098977]]</td>\n",
-       "      <td>[[Centre for Bioinformatics, M.Sc. Bioinformat...</td>\n",
-       "      <td>[[Bioinformatics Junior Research Fellow, India...</td>\n",
-       "      <td>3</td>\n",
-       "      <td>[Crossref Metadata Search, Sangram Keshari Sahu]</td>\n",
+       "      <td>2020-05-14t15:54:38.235z</td>\n",
+       "      <td>7</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>14</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[sksahu.net]</td>\n",
+       "      <td>[cnr.it]</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>5 rows × 21 columns</p>\n",
+       "<p>5 rows × 28 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                  orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "5   0000-0001-5001-4994        1               1                       1   \n",
-       "14  0000-0001-5004-7761        1               1                       1   \n",
-       "15  0000-0001-5005-0557        1               1                       1   \n",
-       "29  0000-0001-5009-8091        1               1                       1   \n",
-       "30  0000-0001-5010-9539        1               1                       1   \n",
-       "\n",
-       "        given_names family_name  \\\n",
-       "5             Siren        Rühs   \n",
-       "14      scaffolding        hire   \n",
-       "15              Sen          RT   \n",
-       "29         Gabriela     Madruga   \n",
-       "30  Sangram Keshari        Sahu   \n",
-       "\n",
-       "                                            biography  \\\n",
-       "5   I am an oceanographer studying the interannual...   \n",
-       "14                                                NaN   \n",
-       "15                                                NaN   \n",
-       "29  Possui graduação em Medicina Veterinaria pela ...   \n",
-       "30                                                NaN   \n",
-       "\n",
-       "                                          other_names  \\\n",
-       "5                                       [Siren Ruehs]   \n",
-       "14  [The first feature that you have to check in t...   \n",
-       "15                                                NaN   \n",
-       "29                          [Gabriela Morais Madruga]   \n",
-       "30                                          [sk-sahu]   \n",
-       "\n",
-       "                                                 urls primary_email  ...  \\\n",
-       "5   [[ResearchGate, https://www.researchgate.net/p...           NaN  ...   \n",
-       "14  [[scaffolding hire Wellington, https://www.tig...           NaN  ...   \n",
-       "15  [[Research on Psychology, psychiatry, Genetics...           NaN  ...   \n",
-       "29  [[Curriculo lattes, http://buscatextual.cnpq.b...           NaN  ...   \n",
-       "30           [[Academic webpage, https://sksahu.net]]           NaN  ...   \n",
-       "\n",
-       "                                       keywords               external_ids  \\\n",
-       "5                                           NaN                        NaN   \n",
-       "14                [scaffolding hire Wellington]                        NaN   \n",
-       "15                                          NaN                        NaN   \n",
-       "29                   [veterinary ophthalmology]                        NaN   \n",
-       "30  [Computational Genomics and Bioinformatics]  [[Loop profile, 1098977]]   \n",
-       "\n",
-       "                                            education  \\\n",
-       "5                                                 NaN   \n",
-       "14                                                NaN   \n",
-       "15                                                NaN   \n",
-       "29  [[Surgery in small animal, PhD, Universidade E...   \n",
-       "30  [[Centre for Bioinformatics, M.Sc. Bioinformat...   \n",
-       "\n",
-       "                                           employment n_works  \\\n",
-       "5                                                 NaN      11   \n",
-       "14                                                NaN       0   \n",
-       "15                                                NaN       0   \n",
-       "29  [[PhD , University of Minnesota, Minneapolis, ...      14   \n",
-       "30  [[Bioinformatics Junior Research Fellow, India...       3   \n",
-       "\n",
-       "                                        works_source primary_email_domain  \\\n",
-       "5                                       [Siren Rühs]                  NaN   \n",
-       "14                                               NaN                  NaN   \n",
-       "15                                               NaN                  NaN   \n",
-       "29                                [Gabriela Madruga]                  NaN   \n",
-       "30  [Crossref Metadata Search, Sangram Keshari Sahu]                  NaN   \n",
-       "\n",
-       "   other_email_domains n_emails             url_domains  \n",
-       "5                  NaN      NaN      [researchgate.net]  \n",
-       "14                 NaN      NaN  [tigerscaffolds.co.nz]  \n",
-       "15                 NaN      NaN     [corticalbrain.com]  \n",
-       "29                 NaN      NaN               [cnpq.br]  \n",
-       "30                 NaN      NaN            [sksahu.net]  \n",
-       "\n",
-       "[5 rows x 21 columns]"
+       "                   orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "9    0000-0001-8718-0056        1               1                       1   \n",
+       "41   0000-0002-7845-4016        1               1                       1   \n",
+       "59   0000-0003-0967-6157        1               1                       1   \n",
+       "149  0000-0002-8015-3781        1               1                       1   \n",
+       "155  0000-0003-3444-936x        1               1                       1   \n",
+       "\n",
+       "    given_names family_name  \\\n",
+       "9           NaN         NaN   \n",
+       "41          NaN         NaN   \n",
+       "59          NaN         NaN   \n",
+       "149   alejandro     ossorio   \n",
+       "155  alessandra    caravale   \n",
+       "\n",
+       "                                             biography other_names  \\\n",
+       "9                                                  NaN       [飛資得]   \n",
+       "41                                                 NaN         NaN   \n",
+       "59                                                 NaN       [徐興慶]   \n",
+       "149                                                NaN         NaN   \n",
+       "155  archeologa, con laurea in metodologia e tecnic...         NaN   \n",
+       "\n",
+       "                                                  urls  \\\n",
+       "9    [[link1, http://orcid.flysheetmed.info], [ntu ...   \n",
+       "41   [[publication profile, http://publications.lib...   \n",
+       "59   [[ntu researcher profile, http://ah.ntu.edu.tw...   \n",
+       "149  [[web de la universidad carlos iii de madrid, ...   \n",
+       "155  [[isma- cnr, http://www.isma.cnr.it/?page_id=1...   \n",
+       "\n",
+       "                  primary_email  ...          last_update_date n_doi n_arxiv  \\\n",
+       "9    ericlin.flysheet@gmail.com  ...  2019-10-11t17:51:12.473z     0       0   \n",
+       "41                          NaN  ...  2016-06-06t15:29:36.952z     0       0   \n",
+       "59                          NaN  ...  2017-03-10t07:30:04.778z    12       0   \n",
+       "149         aossorio@di.uc3m.es  ...  2019-07-04t08:47:12.005z     0       0   \n",
+       "155                         NaN  ...  2020-05-14t15:54:38.235z     7       0   \n",
+       "\n",
+       "    n_pmc n_other_pids  label primary_email_domain other_email_domains  \\\n",
+       "9       0            6      1            gmail.com                 NaN   \n",
+       "41      0            0      0                  NaN                 NaN   \n",
+       "59      0            4      1                  NaN                 NaN   \n",
+       "149     0            0      0           di.uc3m.es                 NaN   \n",
+       "155     0           14      1                  NaN                 NaN   \n",
+       "\n",
+       "    n_emails                     url_domains  \n",
+       "9        NaN  [flysheetmed.info, ntu.edu.tw]  \n",
+       "41       NaN                   [chalmers.se]  \n",
+       "59       NaN        [ntu.edu.tw, ntu.edu.tw]  \n",
+       "149      NaN                       [uc3m.es]  \n",
+       "155      NaN                        [cnr.it]  \n",
+       "\n",
+       "[5 rows x 28 columns]"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5872,7 +5124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5881,7 +5133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
@@ -5911,27 +5163,27 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>70577</th>\n",
-       "      <td>0000-0002-1234-835X</td>\n",
+       "      <th>257375</th>\n",
+       "      <td>0000-0002-1234-835x</td>\n",
        "      <td>219.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>5164541</th>\n",
+       "      <th>3630067</th>\n",
        "      <td>0000-0001-7478-4539</td>\n",
        "      <td>174.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1215225</th>\n",
+       "      <th>5196089</th>\n",
        "      <td>0000-0002-7392-3792</td>\n",
        "      <td>169.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10240510</th>\n",
+       "      <th>10696059</th>\n",
        "      <td>0000-0002-6938-9638</td>\n",
        "      <td>152.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4004281</th>\n",
+       "      <th>6868932</th>\n",
        "      <td>0000-0002-5710-4041</td>\n",
        "      <td>114.0</td>\n",
        "    </tr>\n",
@@ -5941,53 +5193,53 @@
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10747035</th>\n",
-       "      <td>0000-0003-4998-1551</td>\n",
+       "      <th>10916569</th>\n",
+       "      <td>0000-0001-5692-7639</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10747036</th>\n",
-       "      <td>0000-0003-4998-4111</td>\n",
+       "      <th>10916570</th>\n",
+       "      <td>0000-0003-1539-0999</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10747037</th>\n",
-       "      <td>0000-0003-4998-6045</td>\n",
+       "      <th>10916571</th>\n",
+       "      <td>0000-0003-2858-5509</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10747038</th>\n",
-       "      <td>0000-0003-4998-8868</td>\n",
+       "      <th>10916572</th>\n",
+       "      <td>0000-0003-2438-9500</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10747039</th>\n",
-       "      <td>0000-0003-4999-7916</td>\n",
+       "      <th>10916573</th>\n",
+       "      <td>0000-0003-4119-4772</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>10744621 rows × 2 columns</p>\n",
+       "<p>10916574 rows × 2 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                        orcid  n_urls\n",
-       "70577     0000-0002-1234-835X   219.0\n",
-       "5164541   0000-0001-7478-4539   174.0\n",
-       "1215225   0000-0002-7392-3792   169.0\n",
-       "10240510  0000-0002-6938-9638   152.0\n",
-       "4004281   0000-0002-5710-4041   114.0\n",
+       "257375    0000-0002-1234-835x   219.0\n",
+       "3630067   0000-0001-7478-4539   174.0\n",
+       "5196089   0000-0002-7392-3792   169.0\n",
+       "10696059  0000-0002-6938-9638   152.0\n",
+       "6868932   0000-0002-5710-4041   114.0\n",
        "...                       ...     ...\n",
-       "10747035  0000-0003-4998-1551     NaN\n",
-       "10747036  0000-0003-4998-4111     NaN\n",
-       "10747037  0000-0003-4998-6045     NaN\n",
-       "10747038  0000-0003-4998-8868     NaN\n",
-       "10747039  0000-0003-4999-7916     NaN\n",
+       "10916569  0000-0001-5692-7639     NaN\n",
+       "10916570  0000-0003-1539-0999     NaN\n",
+       "10916571  0000-0003-2858-5509     NaN\n",
+       "10916572  0000-0003-2438-9500     NaN\n",
+       "10916573  0000-0003-4119-4772     NaN\n",
        "\n",
-       "[10744621 rows x 2 columns]"
+       "[10916574 rows x 2 columns]"
       ]
      },
-     "execution_count": 44,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5998,7 +5250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [
     {
@@ -6013,17 +5265,18 @@
         {
          "type": "bar",
          "x": [
-          "0000-0002-1234-835X",
+          "0000-0002-1234-835x",
           "0000-0001-7478-4539",
           "0000-0002-7392-3792",
           "0000-0002-6938-9638",
           "0000-0002-5710-4041",
-          "0000-0003-2450-090X",
+          "0000-0003-2450-090x",
           "0000-0002-3920-7389",
+          "0000-0001-5384-0001",
           "0000-0002-6689-4129",
           "0000-0002-4621-5571",
-          "0000-0001-9131-1266",
           "0000-0002-7754-8889",
+          "0000-0001-9131-1266",
           "0000-0002-5250-1144",
           "0000-0002-9025-8632",
           "0000-0002-7456-3848",
@@ -6034,85 +5287,84 @@
           "0000-0001-8873-6677",
           "0000-0002-3997-5070",
           "0000-0002-1856-6905",
-          "0000-0002-4062-3603",
           "0000-0002-4316-1467",
-          "0000-0002-0752-7513",
+          "0000-0002-4062-3603",
           "0000-0001-5880-7091",
-          "0000-0003-1524-6268",
           "0000-0003-0594-2462",
+          "0000-0003-1524-6268",
+          "0000-0002-0752-7513",
           "0000-0003-2593-7134",
           "0000-0002-1298-5252",
-          "0000-0003-1761-3842",
           "0000-0003-2383-8386",
+          "0000-0003-1761-3842",
           "0000-0003-3546-2312",
           "0000-0002-2886-9248",
-          "0000-0002-1929-6054",
+          "0000-0003-4948-9268",
           "0000-0003-2183-8112",
+          "0000-0002-1929-6054",
           "0000-0003-2407-3557",
-          "0000-0002-4305-4215",
-          "0000-0003-0796-0234",
           "0000-0001-7133-6896",
           "0000-0002-9276-6921",
-          "0000-0002-7568-3403",
+          "0000-0002-4305-4215",
           "0000-0003-1484-6958",
+          "0000-0002-7568-3403",
           "0000-0002-4004-6666",
+          "0000-0003-0796-0234",
           "0000-0002-8208-0897",
-          "0000-0002-9071-5450",
-          "0000-0002-8116-9611",
           "0000-0003-4993-5555",
+          "0000-0002-8116-9611",
           "0000-0003-0930-6121",
-          "0000-0003-4948-9268",
-          "0000-0002-8122-879X",
-          "0000-0001-9559-1103",
+          "0000-0002-9071-5450",
+          "0000-0002-8122-879x",
           "0000-0002-3277-9659",
+          "0000-0001-9559-1103",
           "0000-0003-2862-6315",
           "0000-0002-2000-8339",
           "0000-0001-5300-4601",
           "0000-0002-6547-0172",
           "0000-0003-4808-6619",
+          "0000-0002-5139-2660",
           "0000-0002-6254-8683",
           "0000-0002-0971-9375",
           "0000-0003-3933-0229",
-          "0000-0002-4659-5391",
+          "0000-0003-1585-1134",
           "0000-0003-0694-1154",
-          "0000-0002-2916-2893",
-          "0000-0003-4501-3756",
-          "0000-0001-6783-2037",
+          "0000-0002-4659-5391",
           "0000-0001-6461-2573",
+          "0000-0001-6783-2037",
+          "0000-0003-4501-3756",
+          "0000-0002-2916-2893",
           "0000-0001-5549-6822",
-          "0000-0001-8978-4830",
           "0000-0003-4326-9336",
-          "0000-0001-8096-4333",
+          "0000-0001-8978-4830",
           "0000-0002-8940-3177",
+          "0000-0001-8096-4333",
           "0000-0002-6680-1703",
           "0000-0002-5946-1595",
           "0000-0002-8593-9257",
-          "0000-0002-7653-4899",
           "0000-0002-5196-4905",
-          "0000-0001-8808-4867",
-          "0000-0002-5139-2660",
+          "0000-0002-7653-4899",
+          "0000-0003-1904-4188",
           "0000-0001-6921-0426",
+          "0000-0001-8808-4867",
           "0000-0003-1815-1993",
-          "0000-0002-7843-8497",
-          "0000-0003-1675-2840",
           "0000-0001-8644-2114",
-          "0000-0003-0907-9870",
+          "0000-0003-1675-2840",
+          "0000-0002-7843-8497",
+          "0000-0001-7784-0583",
           "0000-0001-8986-2528",
           "0000-0002-5265-6074",
-          "0000-0001-7784-0583",
           "0000-0001-7550-5802",
-          "0000-0001-6979-4273",
-          "0000-0001-9102-8639",
-          "0000-0002-3334-9386",
+          "0000-0003-0907-9870",
           "0000-0002-0696-8560",
+          "0000-0002-3334-9386",
           "0000-0002-7179-6953",
-          "0000-0002-9771-600X",
+          "0000-0001-6979-4273",
+          "0000-0001-9102-8639",
           "0000-0002-8797-6502",
-          "0000-0002-5241-1026",
-          "0000-0001-7193-5039",
           "0000-0001-9119-5955",
-          "0000-0003-2133-2648",
-          "0000-0001-9026-4795"
+          "0000-0001-7608-9433",
+          "0000-0002-5985-9114"
          ],
          "y": [
           219,
@@ -6123,6 +5375,7 @@
           114,
           111,
           104,
+          104,
           90,
           83,
           83,
@@ -6150,6 +5403,7 @@
           64,
           61,
           61,
+          61,
           59,
           57,
           57,
@@ -6163,7 +5417,6 @@
           55,
           55,
           55,
-          51,
           50,
           50,
           50,
@@ -6173,10 +5426,12 @@
           48,
           48,
           48,
+          48,
           47,
           47,
           46,
           46,
+          46,
           45,
           45,
           45,
@@ -6191,7 +5446,7 @@
           42,
           41,
           41,
-          40,
+          41,
           40,
           40,
           39,
@@ -6211,9 +5466,6 @@
           36,
           36,
           36,
-          36,
-          36,
-          36,
           36
          ]
         }
@@ -7041,9 +6293,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"ba6096ce-e63e-49f9-906f-3cfa91f0e7b9\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"ba6096ce-e63e-49f9-906f-3cfa91f0e7b9\")) {                    Plotly.newPlot(                        \"ba6096ce-e63e-49f9-906f-3cfa91f0e7b9\",                        [{\"type\": \"bar\", \"x\": [\"0000-0002-1234-835X\", \"0000-0001-7478-4539\", \"0000-0002-7392-3792\", \"0000-0002-6938-9638\", \"0000-0002-5710-4041\", \"0000-0003-2450-090X\", \"0000-0002-3920-7389\", \"0000-0002-6689-4129\", \"0000-0002-4621-5571\", \"0000-0001-9131-1266\", \"0000-0002-7754-8889\", \"0000-0002-5250-1144\", \"0000-0002-9025-8632\", \"0000-0002-7456-3848\", \"0000-0003-0176-1293\", \"0000-0003-0321-7339\", \"0000-0002-8493-0402\", \"0000-0002-9965-2425\", \"0000-0001-8873-6677\", \"0000-0002-3997-5070\", \"0000-0002-1856-6905\", \"0000-0002-4062-3603\", \"0000-0002-4316-1467\", \"0000-0002-0752-7513\", \"0000-0001-5880-7091\", \"0000-0003-1524-6268\", \"0000-0003-0594-2462\", \"0000-0003-2593-7134\", \"0000-0002-1298-5252\", \"0000-0003-1761-3842\", \"0000-0003-2383-8386\", \"0000-0003-3546-2312\", \"0000-0002-2886-9248\", \"0000-0002-1929-6054\", \"0000-0003-2183-8112\", \"0000-0003-2407-3557\", \"0000-0002-4305-4215\", \"0000-0003-0796-0234\", \"0000-0001-7133-6896\", \"0000-0002-9276-6921\", \"0000-0002-7568-3403\", \"0000-0003-1484-6958\", \"0000-0002-4004-6666\", \"0000-0002-8208-0897\", \"0000-0002-9071-5450\", \"0000-0002-8116-9611\", \"0000-0003-4993-5555\", \"0000-0003-0930-6121\", \"0000-0003-4948-9268\", \"0000-0002-8122-879X\", \"0000-0001-9559-1103\", \"0000-0002-3277-9659\", \"0000-0003-2862-6315\", \"0000-0002-2000-8339\", \"0000-0001-5300-4601\", \"0000-0002-6547-0172\", \"0000-0003-4808-6619\", \"0000-0002-6254-8683\", \"0000-0002-0971-9375\", \"0000-0003-3933-0229\", \"0000-0002-4659-5391\", \"0000-0003-0694-1154\", \"0000-0002-2916-2893\", \"0000-0003-4501-3756\", \"0000-0001-6783-2037\", \"0000-0001-6461-2573\", \"0000-0001-5549-6822\", \"0000-0001-8978-4830\", \"0000-0003-4326-9336\", \"0000-0001-8096-4333\", \"0000-0002-8940-3177\", \"0000-0002-6680-1703\", \"0000-0002-5946-1595\", \"0000-0002-8593-9257\", \"0000-0002-7653-4899\", \"0000-0002-5196-4905\", \"0000-0001-8808-4867\", \"0000-0002-5139-2660\", \"0000-0001-6921-0426\", \"0000-0003-1815-1993\", \"0000-0002-7843-8497\", \"0000-0003-1675-2840\", \"0000-0001-8644-2114\", \"0000-0003-0907-9870\", \"0000-0001-8986-2528\", \"0000-0002-5265-6074\", \"0000-0001-7784-0583\", \"0000-0001-7550-5802\", \"0000-0001-6979-4273\", \"0000-0001-9102-8639\", \"0000-0002-3334-9386\", \"0000-0002-0696-8560\", \"0000-0002-7179-6953\", \"0000-0002-9771-600X\", \"0000-0002-8797-6502\", \"0000-0002-5241-1026\", \"0000-0001-7193-5039\", \"0000-0001-9119-5955\", \"0000-0003-2133-2648\", \"0000-0001-9026-4795\"], \"y\": [219.0, 174.0, 169.0, 152.0, 114.0, 114.0, 111.0, 104.0, 90.0, 83.0, 83.0, 81.0, 81.0, 80.0, 80.0, 80.0, 76.0, 73.0, 72.0, 71.0, 70.0, 69.0, 69.0, 68.0, 68.0, 68.0, 68.0, 67.0, 67.0, 66.0, 66.0, 65.0, 64.0, 61.0, 61.0, 59.0, 57.0, 57.0, 57.0, 57.0, 57.0, 57.0, 57.0, 56.0, 55.0, 55.0, 55.0, 55.0, 51.0, 50.0, 50.0, 50.0, 49.0, 49.0, 48.0, 48.0, 48.0, 48.0, 47.0, 47.0, 46.0, 46.0, 45.0, 45.0, 45.0, 45.0, 44.0, 43.0, 43.0, 43.0, 43.0, 42.0, 42.0, 42.0, 41.0, 41.0, 40.0, 40.0, 40.0, 39.0, 39.0, 39.0, 39.0, 38.0, 38.0, 38.0, 38.0, 38.0, 37.0, 37.0, 37.0, 37.0, 37.0, 36.0, 36.0, 36.0, 36.0, 36.0, 36.0, 36.0]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 100 ORCID with URLs\"}, \"xaxis\": {\"range\": [-0.5, 99.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"bedc1d58-293d-4a5b-99a0-6e6d8bda10c0\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"bedc1d58-293d-4a5b-99a0-6e6d8bda10c0\")) {                    Plotly.newPlot(                        \"bedc1d58-293d-4a5b-99a0-6e6d8bda10c0\",                        [{\"type\": \"bar\", \"x\": [\"0000-0002-1234-835x\", \"0000-0001-7478-4539\", \"0000-0002-7392-3792\", \"0000-0002-6938-9638\", \"0000-0002-5710-4041\", \"0000-0003-2450-090x\", \"0000-0002-3920-7389\", \"0000-0001-5384-0001\", \"0000-0002-6689-4129\", \"0000-0002-4621-5571\", \"0000-0002-7754-8889\", \"0000-0001-9131-1266\", \"0000-0002-5250-1144\", \"0000-0002-9025-8632\", \"0000-0002-7456-3848\", \"0000-0003-0176-1293\", \"0000-0003-0321-7339\", \"0000-0002-8493-0402\", \"0000-0002-9965-2425\", \"0000-0001-8873-6677\", \"0000-0002-3997-5070\", \"0000-0002-1856-6905\", \"0000-0002-4316-1467\", \"0000-0002-4062-3603\", \"0000-0001-5880-7091\", \"0000-0003-0594-2462\", \"0000-0003-1524-6268\", \"0000-0002-0752-7513\", \"0000-0003-2593-7134\", \"0000-0002-1298-5252\", \"0000-0003-2383-8386\", \"0000-0003-1761-3842\", \"0000-0003-3546-2312\", \"0000-0002-2886-9248\", \"0000-0003-4948-9268\", \"0000-0003-2183-8112\", \"0000-0002-1929-6054\", \"0000-0003-2407-3557\", \"0000-0001-7133-6896\", \"0000-0002-9276-6921\", \"0000-0002-4305-4215\", \"0000-0003-1484-6958\", \"0000-0002-7568-3403\", \"0000-0002-4004-6666\", \"0000-0003-0796-0234\", \"0000-0002-8208-0897\", \"0000-0003-4993-5555\", \"0000-0002-8116-9611\", \"0000-0003-0930-6121\", \"0000-0002-9071-5450\", \"0000-0002-8122-879x\", \"0000-0002-3277-9659\", \"0000-0001-9559-1103\", \"0000-0003-2862-6315\", \"0000-0002-2000-8339\", \"0000-0001-5300-4601\", \"0000-0002-6547-0172\", \"0000-0003-4808-6619\", \"0000-0002-5139-2660\", \"0000-0002-6254-8683\", \"0000-0002-0971-9375\", \"0000-0003-3933-0229\", \"0000-0003-1585-1134\", \"0000-0003-0694-1154\", \"0000-0002-4659-5391\", \"0000-0001-6461-2573\", \"0000-0001-6783-2037\", \"0000-0003-4501-3756\", \"0000-0002-2916-2893\", \"0000-0001-5549-6822\", \"0000-0003-4326-9336\", \"0000-0001-8978-4830\", \"0000-0002-8940-3177\", \"0000-0001-8096-4333\", \"0000-0002-6680-1703\", \"0000-0002-5946-1595\", \"0000-0002-8593-9257\", \"0000-0002-5196-4905\", \"0000-0002-7653-4899\", \"0000-0003-1904-4188\", \"0000-0001-6921-0426\", \"0000-0001-8808-4867\", \"0000-0003-1815-1993\", \"0000-0001-8644-2114\", \"0000-0003-1675-2840\", \"0000-0002-7843-8497\", \"0000-0001-7784-0583\", \"0000-0001-8986-2528\", \"0000-0002-5265-6074\", \"0000-0001-7550-5802\", \"0000-0003-0907-9870\", \"0000-0002-0696-8560\", \"0000-0002-3334-9386\", \"0000-0002-7179-6953\", \"0000-0001-6979-4273\", \"0000-0001-9102-8639\", \"0000-0002-8797-6502\", \"0000-0001-9119-5955\", \"0000-0001-7608-9433\", \"0000-0002-5985-9114\"], \"y\": [219.0, 174.0, 169.0, 152.0, 114.0, 114.0, 111.0, 104.0, 104.0, 90.0, 83.0, 83.0, 81.0, 81.0, 80.0, 80.0, 80.0, 76.0, 73.0, 72.0, 71.0, 70.0, 69.0, 69.0, 68.0, 68.0, 68.0, 68.0, 67.0, 67.0, 66.0, 66.0, 65.0, 64.0, 61.0, 61.0, 61.0, 59.0, 57.0, 57.0, 57.0, 57.0, 57.0, 57.0, 57.0, 56.0, 55.0, 55.0, 55.0, 55.0, 50.0, 50.0, 50.0, 49.0, 49.0, 48.0, 48.0, 48.0, 48.0, 48.0, 47.0, 47.0, 46.0, 46.0, 46.0, 45.0, 45.0, 45.0, 45.0, 44.0, 43.0, 43.0, 43.0, 43.0, 42.0, 42.0, 42.0, 41.0, 41.0, 41.0, 40.0, 40.0, 39.0, 39.0, 39.0, 39.0, 38.0, 38.0, 38.0, 38.0, 38.0, 37.0, 37.0, 37.0, 37.0, 37.0, 36.0, 36.0, 36.0, 36.0]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 100 ORCID with URLs\"}, \"xaxis\": {\"range\": [-0.5, 99.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('ba6096ce-e63e-49f9-906f-3cfa91f0e7b9');\n",
+       "var gd = document.getElementById('bedc1d58-293d-4a5b-99a0-6e6d8bda10c0');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -7091,7 +6343,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -7105,7 +6357,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [
     {
@@ -7134,8 +6386,8 @@
           "github.io",
           "google.com.ua",
           "blogspot.com",
-          "google.es",
           "github.com",
+          "google.es",
           "helsinki.fi",
           "unirioja.es",
           "youtube.com",
@@ -7149,39 +6401,39 @@
           "cityu.edu.hk",
           "kcl.ac.uk",
           "au.dk",
-          "ucl.ac.uk"
+          "man.ac.uk"
          ],
          "y": [
-          75344,
-          66267,
-          43468,
-          23936,
-          20786,
-          18017,
-          14552,
-          10339,
-          8883,
-          7003,
-          5532,
-          5371,
-          5273,
-          5158,
-          5070,
-          5053,
-          4682,
-          4549,
-          4196,
-          4053,
-          3730,
-          3481,
-          3332,
-          3083,
-          3029,
-          2944,
-          2719,
-          2711,
-          2640,
-          2581
+          77558,
+          67357,
+          44397,
+          24439,
+          21054,
+          18771,
+          15121,
+          10622,
+          8996,
+          6978,
+          5881,
+          5479,
+          5335,
+          5240,
+          5199,
+          5134,
+          4711,
+          4572,
+          4396,
+          4120,
+          3756,
+          3558,
+          3494,
+          3115,
+          3034,
+          2952,
+          2793,
+          2720,
+          2717,
+          2693
          ]
         }
        ],
@@ -8008,9 +7260,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"e096d545-a5f3-4065-8ff6-3550df5ec9ad\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"e096d545-a5f3-4065-8ff6-3550df5ec9ad\")) {                    Plotly.newPlot(                        \"e096d545-a5f3-4065-8ff6-3550df5ec9ad\",                        [{\"type\": \"bar\", \"x\": [\"linkedin.com\", \"researchgate.net\", \"google.com\", \"cnpq.br\", \"academia.edu\", \"twitter.com\", \"facebook.com\", \"publons.com\", \"wordpress.com\", \"mendeley.com\", \"instagram.com\", \"github.io\", \"google.com.ua\", \"blogspot.com\", \"google.es\", \"github.com\", \"helsinki.fi\", \"unirioja.es\", \"youtube.com\", \"wixsite.com\", \"ku.dk\", \"scopus.com\", \"\", \"weebly.com\", \"us.es\", \"kth.se\", \"cityu.edu.hk\", \"kcl.ac.uk\", \"au.dk\", \"ucl.ac.uk\"], \"y\": [75344, 66267, 43468, 23936, 20786, 18017, 14552, 10339, 8883, 7003, 5532, 5371, 5273, 5158, 5070, 5053, 4682, 4549, 4196, 4053, 3730, 3481, 3332, 3083, 3029, 2944, 2719, 2711, 2640, 2581]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 URL domains\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"eb52759a-1585-4b28-996e-061364c1b3c7\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"eb52759a-1585-4b28-996e-061364c1b3c7\")) {                    Plotly.newPlot(                        \"eb52759a-1585-4b28-996e-061364c1b3c7\",                        [{\"type\": \"bar\", \"x\": [\"linkedin.com\", \"researchgate.net\", \"google.com\", \"cnpq.br\", \"academia.edu\", \"twitter.com\", \"facebook.com\", \"publons.com\", \"wordpress.com\", \"mendeley.com\", \"instagram.com\", \"github.io\", \"google.com.ua\", \"blogspot.com\", \"github.com\", \"google.es\", \"helsinki.fi\", \"unirioja.es\", \"youtube.com\", \"wixsite.com\", \"ku.dk\", \"scopus.com\", \"\", \"weebly.com\", \"us.es\", \"kth.se\", \"cityu.edu.hk\", \"kcl.ac.uk\", \"au.dk\", \"man.ac.uk\"], \"y\": [77558, 67357, 44397, 24439, 21054, 18771, 15121, 10622, 8996, 6978, 5881, 5479, 5335, 5240, 5199, 5134, 4711, 4572, 4396, 4120, 3756, 3558, 3494, 3115, 3034, 2952, 2793, 2720, 2717, 2693]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top 30 URL domains\"}, \"xaxis\": {\"range\": [-0.5, 29.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('e096d545-a5f3-4065-8ff6-3550df5ec9ad');\n",
+       "var gd = document.getElementById('eb52759a-1585-4b28-996e-061364c1b3c7');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -8020,45 +7272,562 @@
        "        }}\n",
        "}});\n",
        "\n",
-       "// Listen for the removal of the full notebook cells\n",
-       "var notebookContainer = gd.closest('#notebook-container');\n",
-       "if (notebookContainer) {{\n",
-       "    x.observe(notebookContainer, {childList: true});\n",
-       "}}\n",
+       "// Listen for the removal of the full notebook cells\n",
+       "var notebookContainer = gd.closest('#notebook-container');\n",
+       "if (notebookContainer) {{\n",
+       "    x.observe(notebookContainer, {childList: true});\n",
+       "}}\n",
+       "\n",
+       "// Listen for the clearing of the current output cell\n",
+       "var outputEl = gd.closest('.output');\n",
+       "if (outputEl) {{\n",
+       "    x.observe(outputEl, {childList: true});\n",
+       "}}\n",
+       "\n",
+       "                        })                };                });            </script>        </div>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "set_top_n(30)\n",
+    "data = [\n",
+    "    go.Bar(\n",
+    "        x=grouped_urls.sort_values(by=['orcid'], ascending=False).index[:TOP_N],\n",
+    "        y=grouped_urls.sort_values(by=['orcid'], ascending=False)['orcid'][:TOP_N]\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "layout = go.Layout(\n",
+    "    title='Top %s URL domains' % TOP_N,\n",
+    "    xaxis=dict(tickangle=45, tickfont=dict(size=12), range=TOP_RANGE)\n",
+    ")\n",
+    "fig = go.Figure(data=data, layout=layout)\n",
+    "plotly.offline.iplot(fig)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>orcid</th>\n",
+       "      <th>claimed</th>\n",
+       "      <th>verified_email</th>\n",
+       "      <th>verified_primary_email</th>\n",
+       "      <th>given_names</th>\n",
+       "      <th>family_name</th>\n",
+       "      <th>biography</th>\n",
+       "      <th>other_names</th>\n",
+       "      <th>urls</th>\n",
+       "      <th>primary_email</th>\n",
+       "      <th>...</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
+       "      <th>primary_email_domain</th>\n",
+       "      <th>other_email_domains</th>\n",
+       "      <th>n_emails</th>\n",
+       "      <th>url_domains</th>\n",
+       "      <th>n_urls</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>382497</th>\n",
+       "      <td>0000-0002-9025-8632</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>buycannabis</td>\n",
+       "      <td>dispensary</td>\n",
+       "      <td>we procure and deliver premium cannabis strain...</td>\n",
+       "      <td>[we procure and deliver premium cannabis strai...</td>\n",
+       "      <td>[[find your cannabis &amp; marijuana dispensary , ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[goowonderland.com, goowonderland.com, goowond...</td>\n",
+       "      <td>81.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>911811</th>\n",
+       "      <td>0000-0002-4062-3603</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>juan de dios</td>\n",
+       "      <td>beltrán mancilla</td>\n",
+       "      <td>juan de dios beltrán mancilla (*) filósofo aut...</td>\n",
+       "      <td>[juan de dios beltrán mancilla, filósofo autod...</td>\n",
+       "      <td>[[01.- juan de dios beltrán mancilla. teoría o...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[yumpu.com, ijopm.org, google.com, blogspot.co...</td>\n",
+       "      <td>69.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1136129</th>\n",
+       "      <td>0000-0002-1929-6054</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>franklin américo</td>\n",
+       "      <td>canaza choque</td>\n",
+       "      <td>docente-investigador social. maestrando en der...</td>\n",
+       "      <td>[franklin américo canaza-choque , franklin a. ...</td>\n",
+       "      <td>[[consejo nacional de ciencia, tecnología e in...</td>\n",
+       "      <td>leo_123fa@hotmail.com</td>\n",
+       "      <td>...</td>\n",
+       "      <td>29</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>33</td>\n",
+       "      <td>1</td>\n",
+       "      <td>hotmail.com</td>\n",
+       "      <td>[gmail.com, gmail.com, hotmail.com, baldwin.ed...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>[concytec.gob.pe, redalyc.org, redalyc.org, un...</td>\n",
+       "      <td>61.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3102686</th>\n",
+       "      <td>0000-0003-2593-7134</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>aan</td>\n",
+       "      <td>jaelani</td>\n",
+       "      <td>all my papers can be downloaded from portal:re...</td>\n",
+       "      <td>[jaelani, a., jaelani, aan]</td>\n",
+       "      <td>[[microsoft academic research, https://academi...</td>\n",
+       "      <td>aan_jaelani@syekhnurjati.ac.id</td>\n",
+       "      <td>...</td>\n",
+       "      <td>88</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>193</td>\n",
+       "      <td>1</td>\n",
+       "      <td>syekhnurjati.ac.id</td>\n",
+       "      <td>[gmail.com]</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>[microsoft.com, twitter.com, academia.edu, aca...</td>\n",
+       "      <td>67.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6868932</th>\n",
+       "      <td>0000-0002-5710-4041</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ryszard</td>\n",
+       "      <td>romaniuk</td>\n",
+       "      <td>professor of electronics and communications en...</td>\n",
+       "      <td>[r.romaniuk, r.s.romaniuk, ryszard romaniuk, r...</td>\n",
+       "      <td>[[scholar google, http://scholar.google.pl/cit...</td>\n",
+       "      <td>rrom@ise.pw.edu.pl</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1221</td>\n",
+       "      <td>25</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1742</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ise.pw.edu.pl</td>\n",
+       "      <td>[ise.pw.edu.pl, elka.pw.edu.pl, cern.ch]</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>[google.pl, publons.com, scopus.com, mendeley....</td>\n",
+       "      <td>114.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8088987</th>\n",
+       "      <td>0000-0002-9965-2425</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>jaroslaw</td>\n",
+       "      <td>spychala</td>\n",
+       "      <td>jaroslaw spychala has received a doctoral degr...</td>\n",
+       "      <td>[jaroslaw jozef spychala]</td>\n",
+       "      <td>[[resume, http://www.biowebspin.com/wp-content...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>15</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>29</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[biowebspin.com, biowebspin.com, google.com, l...</td>\n",
+       "      <td>73.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8658355</th>\n",
+       "      <td>0000-0002-3920-7389</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>а.</td>\n",
+       "      <td>гусев</td>\n",
+       "      <td>surname, name gusev  alexander leonidovichdate...</td>\n",
+       "      <td>[alexander l. gusev , alexander leonidovich gu...</td>\n",
+       "      <td>[[a.l. gusev  alternative energy and ecology, ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>37</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[youtube.com, isjaee.com, researchgate.net, re...</td>\n",
+       "      <td>111.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8778864</th>\n",
+       "      <td>0000-0002-3997-5070</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>dr. parameshachari</td>\n",
+       "      <td>b d</td>\n",
+       "      <td>dr. parameshachari b dacm distinguished speake...</td>\n",
+       "      <td>[dr. parameshachari b d]</td>\n",
+       "      <td>[[gsssietw,mysuru, http://geethashishu.in/], [...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>47</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>48</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[geethashishu.in, geethashishu.in, acm.org, go...</td>\n",
+       "      <td>71.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9980164</th>\n",
+       "      <td>0000-0003-4948-9268</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>gustavo</td>\n",
+       "      <td>duperré</td>\n",
+       "      <td>gustavo norberto duperré graduated in arts and...</td>\n",
+       "      <td>[gustavo norberto duperré, duperré, g. n., gus...</td>\n",
+       "      <td>[[gis in cultural heritage - icomos românia, h...</td>\n",
+       "      <td>gustavo.duperre@usal.edu.ar</td>\n",
+       "      <td>...</td>\n",
+       "      <td>13</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>34</td>\n",
+       "      <td>0</td>\n",
+       "      <td>usal.edu.ar</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[icomos.ro, unirioja.es, unirioja.es, unc.edu....</td>\n",
+       "      <td>61.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10024501</th>\n",
+       "      <td>0000-0003-2407-3557</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>abdul</td>\n",
+       "      <td>aziz</td>\n",
+       "      <td>abdul aziz was born on may 25, 1973, in brebes...</td>\n",
+       "      <td>[abdul aziz, aziz, abdul, aziz, a., aziz, abd,...</td>\n",
+       "      <td>[[google scholar, https://scholar.google.com/c...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[google.com, syekhnurjati.ac.id, orcid.org, bl...</td>\n",
+       "      <td>59.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10091165</th>\n",
+       "      <td>0000-0003-2183-8112</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>pelayo munhoz</td>\n",
+       "      <td>olea</td>\n",
+       "      <td>pós-doutorado em gestão ambiental pela univers...</td>\n",
+       "      <td>[ munhoz, pelayo olea,  olea, pelayo,  olea, p...</td>\n",
+       "      <td>[[currículo lattes, http://lattes.cnpq.br/6209...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>797</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>582</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c...</td>\n",
+       "      <td>61.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10523205</th>\n",
+       "      <td>0000-0003-2450-090x</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>eduard</td>\n",
+       "      <td>babulak</td>\n",
+       "      <td>professor eduard babulak is accomplished inter...</td>\n",
+       "      <td>[professor eduard babulak]</td>\n",
+       "      <td>[[honorary chair, chief mentor &amp; senior adviso...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>199</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>174</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[worldassessmentcouncil.org, spseke.sk, bcs.or...</td>\n",
+       "      <td>114.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10696059</th>\n",
+       "      <td>0000-0002-6938-9638</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>adolfo</td>\n",
+       "      <td>catral sanabria</td>\n",
+       "      <td>my education is in computer science, mathemati...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[[researchgate adolfo catral , https://www.res...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2022</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>16</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[researchgate.net, youtube.com, linkedin.com, ...</td>\n",
+       "      <td>152.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>13 rows × 29 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                        orcid  claimed  verified_email  \\\n",
+       "382497    0000-0002-9025-8632        1               1   \n",
+       "911811    0000-0002-4062-3603        1               1   \n",
+       "1136129   0000-0002-1929-6054        1               1   \n",
+       "3102686   0000-0003-2593-7134        1               1   \n",
+       "6868932   0000-0002-5710-4041        1               1   \n",
+       "8088987   0000-0002-9965-2425        1               1   \n",
+       "8658355   0000-0002-3920-7389        1               1   \n",
+       "8778864   0000-0002-3997-5070        1               1   \n",
+       "9980164   0000-0003-4948-9268        1               1   \n",
+       "10024501  0000-0003-2407-3557        1               1   \n",
+       "10091165  0000-0003-2183-8112        1               1   \n",
+       "10523205  0000-0003-2450-090x        1               1   \n",
+       "10696059  0000-0002-6938-9638        1               1   \n",
+       "\n",
+       "          verified_primary_email         given_names        family_name  \\\n",
+       "382497                         1         buycannabis         dispensary   \n",
+       "911811                         1       juan de dios   beltrán mancilla    \n",
+       "1136129                        1    franklin américo      canaza choque   \n",
+       "3102686                        1                 aan            jaelani   \n",
+       "6868932                        1             ryszard           romaniuk   \n",
+       "8088987                        1            jaroslaw           spychala   \n",
+       "8658355                        1                  а.              гусев   \n",
+       "8778864                        1  dr. parameshachari                b d   \n",
+       "9980164                        1            gustavo             duperré   \n",
+       "10024501                       1               abdul               aziz   \n",
+       "10091165                       1       pelayo munhoz               olea   \n",
+       "10523205                       1              eduard            babulak   \n",
+       "10696059                       1              adolfo    catral sanabria   \n",
        "\n",
-       "// Listen for the clearing of the current output cell\n",
-       "var outputEl = gd.closest('.output');\n",
-       "if (outputEl) {{\n",
-       "    x.observe(outputEl, {childList: true});\n",
-       "}}\n",
+       "                                                  biography  \\\n",
+       "382497    we procure and deliver premium cannabis strain...   \n",
+       "911811    juan de dios beltrán mancilla (*) filósofo aut...   \n",
+       "1136129   docente-investigador social. maestrando en der...   \n",
+       "3102686   all my papers can be downloaded from portal:re...   \n",
+       "6868932   professor of electronics and communications en...   \n",
+       "8088987   jaroslaw spychala has received a doctoral degr...   \n",
+       "8658355   surname, name gusev  alexander leonidovichdate...   \n",
+       "8778864   dr. parameshachari b dacm distinguished speake...   \n",
+       "9980164   gustavo norberto duperré graduated in arts and...   \n",
+       "10024501  abdul aziz was born on may 25, 1973, in brebes...   \n",
+       "10091165  pós-doutorado em gestão ambiental pela univers...   \n",
+       "10523205  professor eduard babulak is accomplished inter...   \n",
+       "10696059  my education is in computer science, mathemati...   \n",
        "\n",
-       "                        })                };                });            </script>        </div>"
+       "                                                other_names  \\\n",
+       "382497    [we procure and deliver premium cannabis strai...   \n",
+       "911811    [juan de dios beltrán mancilla, filósofo autod...   \n",
+       "1136129   [franklin américo canaza-choque , franklin a. ...   \n",
+       "3102686                         [jaelani, a., jaelani, aan]   \n",
+       "6868932   [r.romaniuk, r.s.romaniuk, ryszard romaniuk, r...   \n",
+       "8088987                           [jaroslaw jozef spychala]   \n",
+       "8658355   [alexander l. gusev , alexander leonidovich gu...   \n",
+       "8778864                            [dr. parameshachari b d]   \n",
+       "9980164   [gustavo norberto duperré, duperré, g. n., gus...   \n",
+       "10024501  [abdul aziz, aziz, abdul, aziz, a., aziz, abd,...   \n",
+       "10091165  [ munhoz, pelayo olea,  olea, pelayo,  olea, p...   \n",
+       "10523205                         [professor eduard babulak]   \n",
+       "10696059                                                NaN   \n",
+       "\n",
+       "                                                       urls  \\\n",
+       "382497    [[find your cannabis & marijuana dispensary , ...   \n",
+       "911811    [[01.- juan de dios beltrán mancilla. teoría o...   \n",
+       "1136129   [[consejo nacional de ciencia, tecnología e in...   \n",
+       "3102686   [[microsoft academic research, https://academi...   \n",
+       "6868932   [[scholar google, http://scholar.google.pl/cit...   \n",
+       "8088987   [[resume, http://www.biowebspin.com/wp-content...   \n",
+       "8658355   [[a.l. gusev  alternative energy and ecology, ...   \n",
+       "8778864   [[gsssietw,mysuru, http://geethashishu.in/], [...   \n",
+       "9980164   [[gis in cultural heritage - icomos românia, h...   \n",
+       "10024501  [[google scholar, https://scholar.google.com/c...   \n",
+       "10091165  [[currículo lattes, http://lattes.cnpq.br/6209...   \n",
+       "10523205  [[honorary chair, chief mentor & senior adviso...   \n",
+       "10696059  [[researchgate adolfo catral , https://www.res...   \n",
+       "\n",
+       "                           primary_email  ... n_doi n_arxiv n_pmc  \\\n",
+       "382497                               NaN  ...     0       0     0   \n",
+       "911811                               NaN  ...     0       0     0   \n",
+       "1136129            leo_123fa@hotmail.com  ...    29       0     0   \n",
+       "3102686   aan_jaelani@syekhnurjati.ac.id  ...    88       0     0   \n",
+       "6868932               rrom@ise.pw.edu.pl  ...  1221      25     0   \n",
+       "8088987                              NaN  ...    15       0     0   \n",
+       "8658355                              NaN  ...    37       0     0   \n",
+       "8778864                              NaN  ...    47       0     0   \n",
+       "9980164      gustavo.duperre@usal.edu.ar  ...    13       0     0   \n",
+       "10024501                             NaN  ...    19       0     0   \n",
+       "10091165                             NaN  ...   797       0     1   \n",
+       "10523205                             NaN  ...   199       0     1   \n",
+       "10696059                             NaN  ...  2022       0     0   \n",
+       "\n",
+       "         n_other_pids label  primary_email_domain  \\\n",
+       "382497              0     0                   NaN   \n",
+       "911811              7     0                   NaN   \n",
+       "1136129            33     1           hotmail.com   \n",
+       "3102686           193     1    syekhnurjati.ac.id   \n",
+       "6868932          1742     1         ise.pw.edu.pl   \n",
+       "8088987            29     1                   NaN   \n",
+       "8658355            21     1                   NaN   \n",
+       "8778864            48     1                   NaN   \n",
+       "9980164            34     0           usal.edu.ar   \n",
+       "10024501           77     1                   NaN   \n",
+       "10091165          582     1                   NaN   \n",
+       "10523205          174     1                   NaN   \n",
+       "10696059           16     1                   NaN   \n",
+       "\n",
+       "                                        other_email_domains n_emails  \\\n",
+       "382497                                                  NaN      NaN   \n",
+       "911811                                                  NaN      NaN   \n",
+       "1136129   [gmail.com, gmail.com, hotmail.com, baldwin.ed...      5.0   \n",
+       "3102686                                         [gmail.com]      1.0   \n",
+       "6868932            [ise.pw.edu.pl, elka.pw.edu.pl, cern.ch]      3.0   \n",
+       "8088987                                                 NaN      NaN   \n",
+       "8658355                                                 NaN      NaN   \n",
+       "8778864                                                 NaN      NaN   \n",
+       "9980164                                                 NaN      NaN   \n",
+       "10024501                                                NaN      NaN   \n",
+       "10091165                                                NaN      NaN   \n",
+       "10523205                                                NaN      NaN   \n",
+       "10696059                                                NaN      NaN   \n",
+       "\n",
+       "                                                url_domains  n_urls  \n",
+       "382497    [goowonderland.com, goowonderland.com, goowond...    81.0  \n",
+       "911811    [yumpu.com, ijopm.org, google.com, blogspot.co...    69.0  \n",
+       "1136129   [concytec.gob.pe, redalyc.org, redalyc.org, un...    61.0  \n",
+       "3102686   [microsoft.com, twitter.com, academia.edu, aca...    67.0  \n",
+       "6868932   [google.pl, publons.com, scopus.com, mendeley....   114.0  \n",
+       "8088987   [biowebspin.com, biowebspin.com, google.com, l...    73.0  \n",
+       "8658355   [youtube.com, isjaee.com, researchgate.net, re...   111.0  \n",
+       "8778864   [geethashishu.in, geethashishu.in, acm.org, go...    71.0  \n",
+       "9980164   [icomos.ro, unirioja.es, unirioja.es, unc.edu....    61.0  \n",
+       "10024501  [google.com, syekhnurjati.ac.id, orcid.org, bl...    59.0  \n",
+       "10091165  [cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c...    61.0  \n",
+       "10523205  [worldassessmentcouncil.org, spseke.sk, bcs.or...   114.0  \n",
+       "10696059  [researchgate.net, youtube.com, linkedin.com, ...   152.0  \n",
+       "\n",
+       "[13 rows x 29 columns]"
       ]
      },
+     "execution_count": 45,
      "metadata": {},
-     "output_type": "display_data"
+     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "set_top_n(30)\n",
-    "data = [\n",
-    "    go.Bar(\n",
-    "        x=grouped_urls.sort_values(by=['orcid'], ascending=False).index[:TOP_N],\n",
-    "        y=grouped_urls.sort_values(by=['orcid'], ascending=False)['orcid'][:TOP_N]\n",
-    "    )\n",
-    "]\n",
-    "\n",
-    "layout = go.Layout(\n",
-    "    title='Top %s URL domains' % TOP_N,\n",
-    "    xaxis=dict(tickangle=45, tickfont=dict(size=12), range=TOP_RANGE)\n",
-    ")\n",
-    "fig = go.Figure(data=data, layout=layout)\n",
-    "plotly.offline.iplot(fig)"
+   ],
+   "source": [
+    "df[(df['url_domains'].str.len() > 50) & (df['n_works'] > 0)]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 46,
    "metadata": {
     "scrolled": true
    },
@@ -8095,11 +7864,11 @@
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
        "      <th>...</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "      <th>n_emails</th>\n",
@@ -8109,533 +7878,407 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>482862</th>\n",
-       "      <td>0000-0003-4948-9268</td>\n",
+       "      <th>97666</th>\n",
+       "      <td>0000-0002-7843-8497</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Gustavo</td>\n",
-       "      <td>Duperré</td>\n",
-       "      <td>Gustavo Norberto Duperré graduated in Arts and...</td>\n",
-       "      <td>[Gustavo Norberto Duperré, Duperré, G. N.]</td>\n",
-       "      <td>[[Gis in Cultural Heritage - ICOMOS România, h...</td>\n",
-       "      <td>gustavo.duperre@usal.edu.ar</td>\n",
+       "      <td>davi</td>\n",
+       "      <td>barbosa</td>\n",
+       "      <td>pesquisador na área sociojurídica, professor, ...</td>\n",
+       "      <td>[professor davi barbosa delmont]</td>\n",
+       "      <td>[[plataforma de cursos ideia criativa, https:/...</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 57195936346], [ResearcherI...</td>\n",
-       "      <td>[[Programme in History, History of Art and Ter...</td>\n",
-       "      <td>[[Titular Professor, Dirección General de Cult...</td>\n",
-       "      <td>13</td>\n",
-       "      <td>[Gustavo Duperré, Scopus - Elsevier, Publons, ...</td>\n",
-       "      <td>usal.edu.ar</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[icomos.ro, unirioja.es, unirioja.es, unc.edu....</td>\n",
-       "      <td>51.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[eadplataforma.com, facebook.com, youtube.com,...</td>\n",
+       "      <td>39.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>554859</th>\n",
-       "      <td>0000-0002-1929-6054</td>\n",
+       "      <th>200670</th>\n",
+       "      <td>0000-0003-1554-1531</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Franklin Américo</td>\n",
-       "      <td>Canaza Choque</td>\n",
-       "      <td>Docente-Investigador Social. Maestrando en Der...</td>\n",
-       "      <td>[Franklin Américo Canaza-Choque , Franklin A. ...</td>\n",
-       "      <td>[[Consejo Nacional de Ciencia, Tecnología e In...</td>\n",
-       "      <td>Leo_123fa@hotmail.com</td>\n",
+       "      <td>katarzyna</td>\n",
+       "      <td>ochman</td>\n",
+       "      <td>katarzyna ochman [kataˈʐɨna ˈɔxman] is assista...</td>\n",
+       "      <td>[[kataˈʐɨna ˈɔxman], catharina ochman, cathari...</td>\n",
+       "      <td>[[researchgate, https://www.researchgate.net/p...</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[ResearcherID, P-8613-2018], [Loop profile, 8...</td>\n",
-       "      <td>[[Facultad de Ciencias de la Educación , Maest...</td>\n",
-       "      <td>[[Investigador Social, Universidad Católica de...</td>\n",
-       "      <td>38</td>\n",
-       "      <td>[ResearcherID, BASE - Bielefeld Academic Searc...</td>\n",
-       "      <td>hotmail.com</td>\n",
-       "      <td>[gmail.com, gmail.com, hotmail.com, baldwin.ed...</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>[concytec.gob.pe, redalyc.org, redalyc.org, un...</td>\n",
-       "      <td>61.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1381092</th>\n",
-       "      <td>0000-0002-9025-8632</td>\n",
-       "      <td>1</td>\n",
        "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>1</td>\n",
-       "      <td>buycannabis</td>\n",
-       "      <td>dispensary</td>\n",
-       "      <td>We procure and deliver premium cannabis strain...</td>\n",
-       "      <td>[We procure and deliver premium cannabis strai...</td>\n",
-       "      <td>[[find your cannabis &amp; marijuana dispensary , ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>10</td>\n",
-       "      <td>[goowonderland dispensary]</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[goowonderland.com, goowonderland.com, goowond...</td>\n",
-       "      <td>81.0</td>\n",
+       "      <td>[researchgate.net, academia.edu, facebook.com,...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2679353</th>\n",
-       "      <td>0000-0003-2407-3557</td>\n",
+       "      <th>210325</th>\n",
+       "      <td>0000-0003-3080-4643</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Abdul</td>\n",
-       "      <td>Aziz</td>\n",
-       "      <td>Abdul Aziz was born on May 25, 1973, in Brebes...</td>\n",
-       "      <td>[Abdul Aziz, Aziz, Abdul, Aziz, A., Aziz, Abd,...</td>\n",
-       "      <td>[[Google Scholar, https://scholar.google.com/c...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>graham</td>\n",
+       "      <td>dawson</td>\n",
+       "      <td>science and engineering faculty (sef) libraria...</td>\n",
+       "      <td>[ graham colin dawson, g.c. dawson]</td>\n",
+       "      <td>[[qut home page, https://www.library.qut.edu.a...</td>\n",
+       "      <td>g.dawson@qut.edu.au</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Ilmu Ekonomi, Dr, Universitas Borobudur, Jak...</td>\n",
-       "      <td>[[Assisten Professor/Dr, Institut Agama Islam ...</td>\n",
-       "      <td>72</td>\n",
-       "      <td>[BASE - Bielefeld Academic Search Engine, Abdu...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>qut.edu.au</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[google.com, syekhnurjati.ac.id, orcid.org, bl...</td>\n",
-       "      <td>59.0</td>\n",
+       "      <td>[qut.edu.au, qut.edu.au, google.com.au, resear...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>3354430</th>\n",
-       "      <td>0000-0002-3920-7389</td>\n",
+       "      <th>218947</th>\n",
+       "      <td>0000-0003-3193-030x</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>А.</td>\n",
-       "      <td>Гусев</td>\n",
-       "      <td>Surname, Name Gusev  Alexander LeonidovichDate...</td>\n",
-       "      <td>[Alexander L. Gusev , Alexander Leonidovich Gu...</td>\n",
-       "      <td>[[A.L. Gusev  Alternative Energy and Ecology, ...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>juan pablo</td>\n",
+       "      <td>wolff mejia</td>\n",
+       "      <td>aspirante a maestría en derecho y negocios int...</td>\n",
+       "      <td>[juan pablo wolff, pablo wolff mejia, juan p. ...</td>\n",
+       "      <td>[[twitter, https://twitter.com/pablomejiam], [...</td>\n",
+       "      <td>juanpmejia@ulasallista.edu.co</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[ResearcherID, F-8048-2014], [Scopus Author I...</td>\n",
-       "      <td>[[Chemical technology and cryogenic-vacuum tec...</td>\n",
-       "      <td>[[General Director, Scientific Technical Centr...</td>\n",
-       "      <td>472</td>\n",
-       "      <td>[Publons, DataCite, Scopus - Elsevier, A.L. Gu...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ulasallista.edu.co</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[youtube.com, isjaee.com, researchgate.net, re...</td>\n",
-       "      <td>111.0</td>\n",
+       "      <td>[twitter.com, youtube.com, google.com, linkedi...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4004281</th>\n",
-       "      <td>0000-0002-5710-4041</td>\n",
+       "      <th>261974</th>\n",
+       "      <td>0000-0002-5341-6531</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Ryszard</td>\n",
-       "      <td>Romaniuk</td>\n",
-       "      <td>Professor of Electronics and Communications En...</td>\n",
-       "      <td>[R.Romaniuk, R.S.Romaniuk, Ryszard Romaniuk, R...</td>\n",
-       "      <td>[[Scholar Google, http://scholar.google.pl/cit...</td>\n",
-       "      <td>rrom@ise.pw.edu.pl</td>\n",
+       "      <td>trent</td>\n",
+       "      <td>hammond</td>\n",
+       "      <td>mr trent hammond is an honorary research fello...</td>\n",
+       "      <td>[trent ernest hammond (t.e.hammond)]</td>\n",
+       "      <td>[[academic support masters, http://trenthammon...</td>\n",
+       "      <td>trent.hammond@academicsupportmasters.com.au</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[ISNI, 0000000071432485], [ResearcherID, B-91...</td>\n",
-       "      <td>[[Faculty of Electronics and Information Techn...</td>\n",
-       "      <td>[[Professor, Institute Director, Politechnika ...</td>\n",
-       "      <td>5008</td>\n",
-       "      <td>[INSPIRE-HEP, ResearcherID, ISNI2ORCID search ...</td>\n",
-       "      <td>ise.pw.edu.pl</td>\n",
-       "      <td>[ise.pw.edu.pl, elka.pw.edu.pl, cern.ch]</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>[google.pl, publons.com, scopus.com, mendeley....</td>\n",
-       "      <td>114.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4022480</th>\n",
-       "      <td>0000-0003-2450-090X</td>\n",
        "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Eduard</td>\n",
-       "      <td>Babulak</td>\n",
-       "      <td>Professor Eduard Babulak is accomplished inter...</td>\n",
-       "      <td>[Professor Eduard Babulak]</td>\n",
-       "      <td>[[Honorary Chair, Chief Mentor &amp; Senior Adviso...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 6506867432], [ResearcherID...</td>\n",
-       "      <td>[[Information Technology, Doctor Habilitated (...</td>\n",
-       "      <td>[[Consultant, Horizon 2020 Framework Programme...</td>\n",
-       "      <td>274</td>\n",
-       "      <td>[The Lens, BASE - Bielefeld Academic Search En...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[worldassessmentcouncil.org, spseke.sk, bcs.or...</td>\n",
-       "      <td>114.0</td>\n",
+       "      <td>academicsupportmasters.com.au</td>\n",
+       "      <td>[health.nsw.gov.au, csu.edu.au, sociologist.co...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>[wix.com, academia.edu, researchgate.net, rese...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>6335357</th>\n",
-       "      <td>0000-0003-2593-7134</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Aan</td>\n",
-       "      <td>Jaelani</td>\n",
-       "      <td>All my papers can be downloaded from portal:Re...</td>\n",
-       "      <td>[Jaelani, A., Jaelani, Aan]</td>\n",
-       "      <td>[[Microsoft Academic Research, https://academi...</td>\n",
-       "      <td>aan_jaelani@syekhnurjati.ac.id</td>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 57195963463], [Loop profil...</td>\n",
-       "      <td>[[Post Graduate, S3/Dr, Universitas Islam Nege...</td>\n",
-       "      <td>[[Dr, Institut Agama Islam Negeri Syekh Nurjat...</td>\n",
-       "      <td>79</td>\n",
-       "      <td>[Publons, Aan Jaelani, Scopus - Elsevier, Dime...</td>\n",
-       "      <td>syekhnurjati.ac.id</td>\n",
-       "      <td>[gmail.com]</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[microsoft.com, twitter.com, academia.edu, aca...</td>\n",
-       "      <td>67.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>6489838</th>\n",
-       "      <td>0000-0002-9965-2425</td>\n",
+       "      <th>10405738</th>\n",
+       "      <td>0000-0002-3374-5709</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Jaroslaw</td>\n",
-       "      <td>Spychala</td>\n",
-       "      <td>Jaroslaw Spychala has received a doctoral degr...</td>\n",
-       "      <td>[Jaroslaw Jozef Spychala]</td>\n",
-       "      <td>[[RESUME, http://www.biowebspin.com/wp-content...</td>\n",
+       "      <td>guillermo</td>\n",
+       "      <td>ortiz</td>\n",
+       "      <td>médico, internista, neumólogo, intensivista, e...</td>\n",
+       "      <td>[guillermo ortiz-ruiz]</td>\n",
+       "      <td>[[elsevier, https://www.elsevier.com/], [asoci...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 7006745874]]</td>\n",
-       "      <td>[[Department of Chemistry, Postdoctoral Associ...</td>\n",
-       "      <td>[[Assistant Professor, Adam Mickiewicz Univers...</td>\n",
-       "      <td>29</td>\n",
-       "      <td>[Scopus - Elsevier]</td>\n",
+       "      <td>62</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>88</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[biowebspin.com, biowebspin.com, google.com, l...</td>\n",
-       "      <td>73.0</td>\n",
+       "      <td>[elsevier.com, amci.org.co, springer.com, revi...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>7570584</th>\n",
-       "      <td>0000-0003-2183-8112</td>\n",
+       "      <th>10472264</th>\n",
+       "      <td>0000-0001-7228-5680</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Pelayo Munhoz</td>\n",
-       "      <td>Olea</td>\n",
-       "      <td>Pós-Doutorado em Gestão Ambiental pela Univers...</td>\n",
-       "      <td>[ Munhoz, Pelayo Olea,  Olea, Pelayo,  Olea, P...</td>\n",
-       "      <td>[[Currículo Lattes, http://lattes.cnpq.br/6209...</td>\n",
+       "      <td>text</td>\n",
+       "      <td>protocol</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>[[about, https://about.me/textprotocol], [gith...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 55175503300], [ResearcherI...</td>\n",
-       "      <td>[[, Postdoctoral in Environmental Sustainabili...</td>\n",
-       "      <td>[[Professor, Universidade Federal do Rio Grand...</td>\n",
-       "      <td>1105</td>\n",
-       "      <td>[The Lens, Pelayo Munhoz Olea, Dimensions, BAS...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c...</td>\n",
-       "      <td>61.0</td>\n",
+       "      <td>[about.me, github.com, gitlab.com, gravatar.co...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10240510</th>\n",
-       "      <td>0000-0002-6938-9638</td>\n",
+       "      <th>10785961</th>\n",
+       "      <td>0000-0002-3064-0194</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Adolfo</td>\n",
-       "      <td>Catral Sanabria</td>\n",
-       "      <td>My education is in computer science, mathemati...</td>\n",
+       "      <td>leonardo fernando</td>\n",
+       "      <td>cruz basso</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[ResearchGate Adolfo Catral , https://www.res...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[papers-1, https://www.researchgate.net/profi...</td>\n",
+       "      <td>leonardofernando.basso@mackenzie.br</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Loop profile, 747193]]</td>\n",
-       "      <td>[[Education, Capacitación para la enseñanza en...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2023</td>\n",
-       "      <td>[BASE - Bielefeld Academic Search Engine, Data...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[researchgate.net, youtube.com, linkedin.com, ...</td>\n",
-       "      <td>152.0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>mackenzie.br</td>\n",
+       "      <td>[mackenzie.br]</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>[researchgate.net, ssrn.com, cnpq.br, google.c...</td>\n",
+       "      <td>17.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10448304</th>\n",
-       "      <td>0000-0002-4062-3603</td>\n",
+       "      <th>10845645</th>\n",
+       "      <td>0000-0003-1047-4229</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>JUAN DE DIOS</td>\n",
-       "      <td>BELTRÁN MANCILLA</td>\n",
-       "      <td>JUAN DE DIOS BELTRÁN MANCILLA (*) Filósofo aut...</td>\n",
-       "      <td>[Juan de Dios Beltrán Mancilla, FILÓSOFO AUTOD...</td>\n",
-       "      <td>[[01.- Juan de Dios Beltrán Mancilla. Teoría O...</td>\n",
+       "      <td>bayu</td>\n",
+       "      <td>sakti</td>\n",
+       "      <td>bayu purbha saktisaya adalah bayu purbha sakti...</td>\n",
+       "      <td>[bayu purbha sakti]</td>\n",
+       "      <td>[[osf, http://osf.io/qe2ug], [inarxiv, https:/...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, DIPLOMADO EN PRACTICAS DIRECTIVAS  PARA OR...</td>\n",
-       "      <td>[[INSPECTOR GENERAL JORNADA VESPERTINA // De 2...</td>\n",
-       "      <td>11</td>\n",
-       "      <td>[JUAN DE DIOS BELTR´´ÁN MANCILLA]</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[yumpu.com, ijopm.org, google.com, blogspot.co...</td>\n",
-       "      <td>69.0</td>\n",
+       "      <td>[osf.io, osf.io, academia.edu, mendeley.com, f...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10663894</th>\n",
-       "      <td>0000-0002-3997-5070</td>\n",
+       "      <th>10896059</th>\n",
+       "      <td>0000-0003-4836-7074</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Dr. Parameshachari</td>\n",
-       "      <td>B D</td>\n",
-       "      <td>Dr. Parameshachari B DACM Distinguished Speake...</td>\n",
-       "      <td>[Dr. PARAMESHACHARI B D]</td>\n",
-       "      <td>[[GSSSIETW,MYSURU, http://geethashishu.in/], [...</td>\n",
+       "      <td>karla haydee</td>\n",
+       "      <td>ortiz palafox</td>\n",
+       "      <td>karla haydee ortíz palafoxmiembro del sistema ...</td>\n",
+       "      <td>[karla palafox]</td>\n",
+       "      <td>[[opinión día del maestro, http://www.cronicaj...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[ResearcherID, F-7045-2018], [Scopus Author I...</td>\n",
-       "      <td>[[Electronics and Communication Engineering, P...</td>\n",
-       "      <td>[[ACM Distinguished Speaker (Volunteer), Assoc...</td>\n",
-       "      <td>93</td>\n",
-       "      <td>[Publons, Multidisciplinary Digital Publishing...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[geethashishu.in, geethashishu.in, acm.org, go...</td>\n",
-       "      <td>71.0</td>\n",
+       "      <td>[cronicajalisco.com, youtube.com, tlaquepaque....</td>\n",
+       "      <td>22.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>13 rows × 22 columns</p>\n",
+       "<p>141 rows × 29 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "                        orcid  claimed  verified_email  \\\n",
-       "482862    0000-0003-4948-9268        1               1   \n",
-       "554859    0000-0002-1929-6054        1               1   \n",
-       "1381092   0000-0002-9025-8632        1               1   \n",
-       "2679353   0000-0003-2407-3557        1               1   \n",
-       "3354430   0000-0002-3920-7389        1               1   \n",
-       "4004281   0000-0002-5710-4041        1               1   \n",
-       "4022480   0000-0003-2450-090X        1               1   \n",
-       "6335357   0000-0003-2593-7134        1               1   \n",
-       "6489838   0000-0002-9965-2425        1               1   \n",
-       "7570584   0000-0003-2183-8112        1               1   \n",
-       "10240510  0000-0002-6938-9638        1               1   \n",
-       "10448304  0000-0002-4062-3603        1               1   \n",
-       "10663894  0000-0002-3997-5070        1               1   \n",
-       "\n",
-       "          verified_primary_email         given_names        family_name  \\\n",
-       "482862                         1            Gustavo             Duperré   \n",
-       "554859                         1    Franklin Américo      Canaza Choque   \n",
-       "1381092                        1         buycannabis         dispensary   \n",
-       "2679353                        1               Abdul               Aziz   \n",
-       "3354430                        1                  А.              Гусев   \n",
-       "4004281                        1             Ryszard           Romaniuk   \n",
-       "4022480                        1              Eduard            Babulak   \n",
-       "6335357                        1                 Aan            Jaelani   \n",
-       "6489838                        1            Jaroslaw           Spychala   \n",
-       "7570584                        1       Pelayo Munhoz               Olea   \n",
-       "10240510                       1              Adolfo    Catral Sanabria   \n",
-       "10448304                       1       JUAN DE DIOS   BELTRÁN MANCILLA    \n",
-       "10663894                       1  Dr. Parameshachari                B D   \n",
+       "97666     0000-0002-7843-8497        1               1   \n",
+       "200670    0000-0003-1554-1531        1               1   \n",
+       "210325    0000-0003-3080-4643        1               1   \n",
+       "218947    0000-0003-3193-030x        1               1   \n",
+       "261974    0000-0002-5341-6531        1               1   \n",
+       "...                       ...      ...             ...   \n",
+       "10405738  0000-0002-3374-5709        1               1   \n",
+       "10472264  0000-0001-7228-5680        1               1   \n",
+       "10785961  0000-0002-3064-0194        1               1   \n",
+       "10845645  0000-0003-1047-4229        1               1   \n",
+       "10896059  0000-0003-4836-7074        1               1   \n",
+       "\n",
+       "          verified_primary_email        given_names    family_name  \\\n",
+       "97666                          1               davi        barbosa   \n",
+       "200670                         1          katarzyna         ochman   \n",
+       "210325                         1             graham         dawson   \n",
+       "218947                         1         juan pablo    wolff mejia   \n",
+       "261974                         1              trent        hammond   \n",
+       "...                          ...                ...            ...   \n",
+       "10405738                       1          guillermo          ortiz   \n",
+       "10472264                       1               text       protocol   \n",
+       "10785961                       1  leonardo fernando     cruz basso   \n",
+       "10845645                       1               bayu          sakti   \n",
+       "10896059                       1       karla haydee  ortiz palafox   \n",
        "\n",
        "                                                  biography  \\\n",
-       "482862    Gustavo Norberto Duperré graduated in Arts and...   \n",
-       "554859    Docente-Investigador Social. Maestrando en Der...   \n",
-       "1381092   We procure and deliver premium cannabis strain...   \n",
-       "2679353   Abdul Aziz was born on May 25, 1973, in Brebes...   \n",
-       "3354430   Surname, Name Gusev  Alexander LeonidovichDate...   \n",
-       "4004281   Professor of Electronics and Communications En...   \n",
-       "4022480   Professor Eduard Babulak is accomplished inter...   \n",
-       "6335357   All my papers can be downloaded from portal:Re...   \n",
-       "6489838   Jaroslaw Spychala has received a doctoral degr...   \n",
-       "7570584   Pós-Doutorado em Gestão Ambiental pela Univers...   \n",
-       "10240510  My education is in computer science, mathemati...   \n",
-       "10448304  JUAN DE DIOS BELTRÁN MANCILLA (*) Filósofo aut...   \n",
-       "10663894  Dr. Parameshachari B DACM Distinguished Speake...   \n",
+       "97666     pesquisador na área sociojurídica, professor, ...   \n",
+       "200670    katarzyna ochman [kataˈʐɨna ˈɔxman] is assista...   \n",
+       "210325    science and engineering faculty (sef) libraria...   \n",
+       "218947    aspirante a maestría en derecho y negocios int...   \n",
+       "261974    mr trent hammond is an honorary research fello...   \n",
+       "...                                                     ...   \n",
+       "10405738  médico, internista, neumólogo, intensivista, e...   \n",
+       "10472264                                                NaN   \n",
+       "10785961                                                NaN   \n",
+       "10845645  bayu purbha saktisaya adalah bayu purbha sakti...   \n",
+       "10896059  karla haydee ortíz palafoxmiembro del sistema ...   \n",
        "\n",
        "                                                other_names  \\\n",
-       "482862           [Gustavo Norberto Duperré, Duperré, G. N.]   \n",
-       "554859    [Franklin Américo Canaza-Choque , Franklin A. ...   \n",
-       "1381092   [We procure and deliver premium cannabis strai...   \n",
-       "2679353   [Abdul Aziz, Aziz, Abdul, Aziz, A., Aziz, Abd,...   \n",
-       "3354430   [Alexander L. Gusev , Alexander Leonidovich Gu...   \n",
-       "4004281   [R.Romaniuk, R.S.Romaniuk, Ryszard Romaniuk, R...   \n",
-       "4022480                          [Professor Eduard Babulak]   \n",
-       "6335357                         [Jaelani, A., Jaelani, Aan]   \n",
-       "6489838                           [Jaroslaw Jozef Spychala]   \n",
-       "7570584   [ Munhoz, Pelayo Olea,  Olea, Pelayo,  Olea, P...   \n",
-       "10240510                                                NaN   \n",
-       "10448304  [Juan de Dios Beltrán Mancilla, FILÓSOFO AUTOD...   \n",
-       "10663894                           [Dr. PARAMESHACHARI B D]   \n",
+       "97666                      [professor davi barbosa delmont]   \n",
+       "200670    [[kataˈʐɨna ˈɔxman], catharina ochman, cathari...   \n",
+       "210325                  [ graham colin dawson, g.c. dawson]   \n",
+       "218947    [juan pablo wolff, pablo wolff mejia, juan p. ...   \n",
+       "261974                 [trent ernest hammond (t.e.hammond)]   \n",
+       "...                                                     ...   \n",
+       "10405738                             [guillermo ortiz-ruiz]   \n",
+       "10472264                                                NaN   \n",
+       "10785961                                                NaN   \n",
+       "10845645                                [bayu purbha sakti]   \n",
+       "10896059                                    [karla palafox]   \n",
        "\n",
        "                                                       urls  \\\n",
-       "482862    [[Gis in Cultural Heritage - ICOMOS România, h...   \n",
-       "554859    [[Consejo Nacional de Ciencia, Tecnología e In...   \n",
-       "1381092   [[find your cannabis & marijuana dispensary , ...   \n",
-       "2679353   [[Google Scholar, https://scholar.google.com/c...   \n",
-       "3354430   [[A.L. Gusev  Alternative Energy and Ecology, ...   \n",
-       "4004281   [[Scholar Google, http://scholar.google.pl/cit...   \n",
-       "4022480   [[Honorary Chair, Chief Mentor & Senior Adviso...   \n",
-       "6335357   [[Microsoft Academic Research, https://academi...   \n",
-       "6489838   [[RESUME, http://www.biowebspin.com/wp-content...   \n",
-       "7570584   [[Currículo Lattes, http://lattes.cnpq.br/6209...   \n",
-       "10240510  [[ResearchGate Adolfo Catral , https://www.res...   \n",
-       "10448304  [[01.- Juan de Dios Beltrán Mancilla. Teoría O...   \n",
-       "10663894  [[GSSSIETW,MYSURU, http://geethashishu.in/], [...   \n",
-       "\n",
-       "                           primary_email  ...  \\\n",
-       "482862       gustavo.duperre@usal.edu.ar  ...   \n",
-       "554859             Leo_123fa@hotmail.com  ...   \n",
-       "1381092                              NaN  ...   \n",
-       "2679353                              NaN  ...   \n",
-       "3354430                              NaN  ...   \n",
-       "4004281               rrom@ise.pw.edu.pl  ...   \n",
-       "4022480                              NaN  ...   \n",
-       "6335357   aan_jaelani@syekhnurjati.ac.id  ...   \n",
-       "6489838                              NaN  ...   \n",
-       "7570584                              NaN  ...   \n",
-       "10240510                             NaN  ...   \n",
-       "10448304                             NaN  ...   \n",
-       "10663894                             NaN  ...   \n",
-       "\n",
-       "                                               external_ids  \\\n",
-       "482862    [[Scopus Author ID, 57195936346], [ResearcherI...   \n",
-       "554859    [[ResearcherID, P-8613-2018], [Loop profile, 8...   \n",
-       "1381092                                                 NaN   \n",
-       "2679353                                                 NaN   \n",
-       "3354430   [[ResearcherID, F-8048-2014], [Scopus Author I...   \n",
-       "4004281   [[ISNI, 0000000071432485], [ResearcherID, B-91...   \n",
-       "4022480   [[Scopus Author ID, 6506867432], [ResearcherID...   \n",
-       "6335357   [[Scopus Author ID, 57195963463], [Loop profil...   \n",
-       "6489838                    [[Scopus Author ID, 7006745874]]   \n",
-       "7570584   [[Scopus Author ID, 55175503300], [ResearcherI...   \n",
-       "10240510                           [[Loop profile, 747193]]   \n",
-       "10448304                                                NaN   \n",
-       "10663894  [[ResearcherID, F-7045-2018], [Scopus Author I...   \n",
-       "\n",
-       "                                                  education  \\\n",
-       "482862    [[Programme in History, History of Art and Ter...   \n",
-       "554859    [[Facultad de Ciencias de la Educación , Maest...   \n",
-       "1381092                                                 NaN   \n",
-       "2679353   [[Ilmu Ekonomi, Dr, Universitas Borobudur, Jak...   \n",
-       "3354430   [[Chemical technology and cryogenic-vacuum tec...   \n",
-       "4004281   [[Faculty of Electronics and Information Techn...   \n",
-       "4022480   [[Information Technology, Doctor Habilitated (...   \n",
-       "6335357   [[Post Graduate, S3/Dr, Universitas Islam Nege...   \n",
-       "6489838   [[Department of Chemistry, Postdoctoral Associ...   \n",
-       "7570584   [[, Postdoctoral in Environmental Sustainabili...   \n",
-       "10240510  [[Education, Capacitación para la enseñanza en...   \n",
-       "10448304  [[, DIPLOMADO EN PRACTICAS DIRECTIVAS  PARA OR...   \n",
-       "10663894  [[Electronics and Communication Engineering, P...   \n",
-       "\n",
-       "                                                 employment n_works  \\\n",
-       "482862    [[Titular Professor, Dirección General de Cult...      13   \n",
-       "554859    [[Investigador Social, Universidad Católica de...      38   \n",
-       "1381092                                                 NaN      10   \n",
-       "2679353   [[Assisten Professor/Dr, Institut Agama Islam ...      72   \n",
-       "3354430   [[General Director, Scientific Technical Centr...     472   \n",
-       "4004281   [[Professor, Institute Director, Politechnika ...    5008   \n",
-       "4022480   [[Consultant, Horizon 2020 Framework Programme...     274   \n",
-       "6335357   [[Dr, Institut Agama Islam Negeri Syekh Nurjat...      79   \n",
-       "6489838   [[Assistant Professor, Adam Mickiewicz Univers...      29   \n",
-       "7570584   [[Professor, Universidade Federal do Rio Grand...    1105   \n",
-       "10240510                                                NaN    2023   \n",
-       "10448304  [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2...      11   \n",
-       "10663894  [[ACM Distinguished Speaker (Volunteer), Assoc...      93   \n",
-       "\n",
-       "                                               works_source  \\\n",
-       "482862    [Gustavo Duperré, Scopus - Elsevier, Publons, ...   \n",
-       "554859    [ResearcherID, BASE - Bielefeld Academic Searc...   \n",
-       "1381092                          [goowonderland dispensary]   \n",
-       "2679353   [BASE - Bielefeld Academic Search Engine, Abdu...   \n",
-       "3354430   [Publons, DataCite, Scopus - Elsevier, A.L. Gu...   \n",
-       "4004281   [INSPIRE-HEP, ResearcherID, ISNI2ORCID search ...   \n",
-       "4022480   [The Lens, BASE - Bielefeld Academic Search En...   \n",
-       "6335357   [Publons, Aan Jaelani, Scopus - Elsevier, Dime...   \n",
-       "6489838                                 [Scopus - Elsevier]   \n",
-       "7570584   [The Lens, Pelayo Munhoz Olea, Dimensions, BAS...   \n",
-       "10240510  [BASE - Bielefeld Academic Search Engine, Data...   \n",
-       "10448304                  [JUAN DE DIOS BELTR´´ÁN MANCILLA]   \n",
-       "10663894  [Publons, Multidisciplinary Digital Publishing...   \n",
-       "\n",
-       "          primary_email_domain  \\\n",
-       "482862             usal.edu.ar   \n",
-       "554859             hotmail.com   \n",
-       "1381092                    NaN   \n",
-       "2679353                    NaN   \n",
-       "3354430                    NaN   \n",
-       "4004281          ise.pw.edu.pl   \n",
-       "4022480                    NaN   \n",
-       "6335357     syekhnurjati.ac.id   \n",
-       "6489838                    NaN   \n",
-       "7570584                    NaN   \n",
-       "10240510                   NaN   \n",
-       "10448304                   NaN   \n",
-       "10663894                   NaN   \n",
+       "97666     [[plataforma de cursos ideia criativa, https:/...   \n",
+       "200670    [[researchgate, https://www.researchgate.net/p...   \n",
+       "210325    [[qut home page, https://www.library.qut.edu.a...   \n",
+       "218947    [[twitter, https://twitter.com/pablomejiam], [...   \n",
+       "261974    [[academic support masters, http://trenthammon...   \n",
+       "...                                                     ...   \n",
+       "10405738  [[elsevier, https://www.elsevier.com/], [asoci...   \n",
+       "10472264  [[about, https://about.me/textprotocol], [gith...   \n",
+       "10785961  [[papers-1, https://www.researchgate.net/profi...   \n",
+       "10845645  [[osf, http://osf.io/qe2ug], [inarxiv, https:/...   \n",
+       "10896059  [[opinión día del maestro, http://www.cronicaj...   \n",
+       "\n",
+       "                                        primary_email  ... n_doi n_arxiv  \\\n",
+       "97666                                             NaN  ...     0       0   \n",
+       "200670                                            NaN  ...     1       0   \n",
+       "210325                            g.dawson@qut.edu.au  ...     0       0   \n",
+       "218947                  juanpmejia@ulasallista.edu.co  ...     0       0   \n",
+       "261974    trent.hammond@academicsupportmasters.com.au  ...     1       0   \n",
+       "...                                               ...  ...   ...     ...   \n",
+       "10405738                                          NaN  ...    62       0   \n",
+       "10472264                                          NaN  ...     0       0   \n",
+       "10785961          leonardofernando.basso@mackenzie.br  ...     5       0   \n",
+       "10845645                                          NaN  ...     0       0   \n",
+       "10896059                                          NaN  ...     0       0   \n",
+       "\n",
+       "         n_pmc n_other_pids label           primary_email_domain  \\\n",
+       "97666        0            0     0                            NaN   \n",
+       "200670       0            0     1                            NaN   \n",
+       "210325       0            6     1                     qut.edu.au   \n",
+       "218947       0            0     1             ulasallista.edu.co   \n",
+       "261974       0            1     1  academicsupportmasters.com.au   \n",
+       "...        ...          ...   ...                            ...   \n",
+       "10405738     0           88     0                            NaN   \n",
+       "10472264     0            0     0                            NaN   \n",
+       "10785961     0            0     1                   mackenzie.br   \n",
+       "10845645     0            0     1                            NaN   \n",
+       "10896059     0            2     1                            NaN   \n",
        "\n",
        "                                        other_email_domains n_emails  \\\n",
-       "482862                                                  NaN      NaN   \n",
-       "554859    [gmail.com, gmail.com, hotmail.com, baldwin.ed...      5.0   \n",
-       "1381092                                                 NaN      NaN   \n",
-       "2679353                                                 NaN      NaN   \n",
-       "3354430                                                 NaN      NaN   \n",
-       "4004281            [ise.pw.edu.pl, elka.pw.edu.pl, cern.ch]      3.0   \n",
-       "4022480                                                 NaN      NaN   \n",
-       "6335357                                         [gmail.com]      1.0   \n",
-       "6489838                                                 NaN      NaN   \n",
-       "7570584                                                 NaN      NaN   \n",
-       "10240510                                                NaN      NaN   \n",
-       "10448304                                                NaN      NaN   \n",
-       "10663894                                                NaN      NaN   \n",
+       "97666                                                   NaN      NaN   \n",
+       "200670                                                  NaN      NaN   \n",
+       "210325                                                  NaN      NaN   \n",
+       "218947                                                  NaN      NaN   \n",
+       "261974    [health.nsw.gov.au, csu.edu.au, sociologist.co...      5.0   \n",
+       "...                                                     ...      ...   \n",
+       "10405738                                                NaN      NaN   \n",
+       "10472264                                                NaN      NaN   \n",
+       "10785961                                     [mackenzie.br]      1.0   \n",
+       "10845645                                                NaN      NaN   \n",
+       "10896059                                                NaN      NaN   \n",
        "\n",
        "                                                url_domains  n_urls  \n",
-       "482862    [icomos.ro, unirioja.es, unirioja.es, unc.edu....    51.0  \n",
-       "554859    [concytec.gob.pe, redalyc.org, redalyc.org, un...    61.0  \n",
-       "1381092   [goowonderland.com, goowonderland.com, goowond...    81.0  \n",
-       "2679353   [google.com, syekhnurjati.ac.id, orcid.org, bl...    59.0  \n",
-       "3354430   [youtube.com, isjaee.com, researchgate.net, re...   111.0  \n",
-       "4004281   [google.pl, publons.com, scopus.com, mendeley....   114.0  \n",
-       "4022480   [worldassessmentcouncil.org, spseke.sk, bcs.or...   114.0  \n",
-       "6335357   [microsoft.com, twitter.com, academia.edu, aca...    67.0  \n",
-       "6489838   [biowebspin.com, biowebspin.com, google.com, l...    73.0  \n",
-       "7570584   [cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c...    61.0  \n",
-       "10240510  [researchgate.net, youtube.com, linkedin.com, ...   152.0  \n",
-       "10448304  [yumpu.com, ijopm.org, google.com, blogspot.co...    69.0  \n",
-       "10663894  [geethashishu.in, geethashishu.in, acm.org, go...    71.0  \n",
-       "\n",
-       "[13 rows x 22 columns]"
+       "97666     [eadplataforma.com, facebook.com, youtube.com,...    39.0  \n",
+       "200670    [researchgate.net, academia.edu, facebook.com,...    11.0  \n",
+       "210325    [qut.edu.au, qut.edu.au, google.com.au, resear...    11.0  \n",
+       "218947    [twitter.com, youtube.com, google.com, linkedi...    11.0  \n",
+       "261974    [wix.com, academia.edu, researchgate.net, rese...    12.0  \n",
+       "...                                                     ...     ...  \n",
+       "10405738  [elsevier.com, amci.org.co, springer.com, revi...    12.0  \n",
+       "10472264  [about.me, github.com, gitlab.com, gravatar.co...    12.0  \n",
+       "10785961  [researchgate.net, ssrn.com, cnpq.br, google.c...    17.0  \n",
+       "10845645  [osf.io, osf.io, academia.edu, mendeley.com, f...    12.0  \n",
+       "10896059  [cronicajalisco.com, youtube.com, tlaquepaque....    22.0  \n",
+       "\n",
+       "[141 rows x 29 columns]"
       ]
      },
-     "execution_count": 48,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[(df['url_domains'].str.len() > 50) & (df['n_works'] > 0)]"
+    "df[(df['url_domains'].str.len() > 10) & (df['n_works'] > 0) & (df['works_source'].str.len() == 1)]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 47,
    "metadata": {
     "scrolled": true
    },
@@ -8672,11 +8315,11 @@
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
        "      <th>...</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "      <th>n_emails</th>\n",
@@ -8686,124 +8329,124 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>45566</th>\n",
-       "      <td>0000-0003-1948-3180</td>\n",
+       "      <th>0</th>\n",
+       "      <td>0000-0002-7843-8497</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Mark</td>\n",
-       "      <td>Katz</td>\n",
-       "      <td>Mark N. Katz is a professor of government and ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Adjusting to Change: American Foreign Policy...</td>\n",
+       "      <td>davi</td>\n",
+       "      <td>barbosa</td>\n",
+       "      <td>pesquisador na área sociojurídica, professor, ...</td>\n",
+       "      <td>[professor davi barbosa delmont]</td>\n",
+       "      <td>[[plataforma de cursos ideia criativa, https:/...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 25649901800]]</td>\n",
-       "      <td>[[Political Science, Ph.D., Massachusetts Inst...</td>\n",
-       "      <td>[[Professor of Government and Politics, George...</td>\n",
-       "      <td>58</td>\n",
-       "      <td>[Scopus - Elsevier]</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[wordpress.com, marknkatz.com, gmu.edu, atlant...</td>\n",
-       "      <td>16.0</td>\n",
+       "      <td>[eadplataforma.com, facebook.com, youtube.com,...</td>\n",
+       "      <td>39.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>72674</th>\n",
-       "      <td>0000-0002-2000-8339</td>\n",
+       "      <th>1</th>\n",
+       "      <td>0000-0003-1554-1531</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Phòng khám tư nhân Hà Nội</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Sức khỏe, https://onhealth.vn/], [Khám phụ k...</td>\n",
+       "      <td>katarzyna</td>\n",
+       "      <td>ochman</td>\n",
+       "      <td>katarzyna ochman [kataˈʐɨna ˈɔxman] is assista...</td>\n",
+       "      <td>[[kataˈʐɨna ˈɔxman], catharina ochman, cathari...</td>\n",
+       "      <td>[[researchgate, https://www.researchgate.net/p...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>4</td>\n",
-       "      <td>[Phòng khám tư nhân Hà Nội]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[onhealth.vn, onhealth.vn, onhealth.vn, onheal...</td>\n",
-       "      <td>49.0</td>\n",
+       "      <td>[researchgate.net, academia.edu, facebook.com,...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>172820</th>\n",
-       "      <td>0000-0001-9293-2224</td>\n",
+       "      <th>2</th>\n",
+       "      <td>0000-0003-3080-4643</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Juan Carlos</td>\n",
-       "      <td>Garcia Hoyos</td>\n",
-       "      <td>My name is Juan Carlos García Hoyos. I was bor...</td>\n",
-       "      <td>[Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...</td>\n",
-       "      <td>[[Air Force Office of Scientific Research (WRI...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>graham</td>\n",
+       "      <td>dawson</td>\n",
+       "      <td>science and engineering faculty (sef) libraria...</td>\n",
+       "      <td>[ graham colin dawson, g.c. dawson]</td>\n",
+       "      <td>[[qut home page, https://www.library.qut.edu.a...</td>\n",
+       "      <td>g.dawson@qut.edu.au</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Faculty of Philosophy, History - Ph.D., Char...</td>\n",
-       "      <td>[[responsible for the Project Service Level Ag...</td>\n",
-       "      <td>20</td>\n",
-       "      <td>[Juan Carlos Garcia Hoyos]</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>qut.edu.au</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[af.mil, gst.com, govtribe.com, sbir.gov, open...</td>\n",
-       "      <td>28.0</td>\n",
+       "      <td>[qut.edu.au, qut.edu.au, google.com.au, resear...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>209505</th>\n",
-       "      <td>0000-0003-3045-0056</td>\n",
+       "      <th>3</th>\n",
+       "      <td>0000-0003-3193-030x</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Ananda</td>\n",
-       "      <td>Majumdar</td>\n",
-       "      <td>I am Ananda Majumdar, Child Care Educator at B...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Migration Scholar and Ananda , https://grfdt...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>juan pablo</td>\n",
+       "      <td>wolff mejia</td>\n",
+       "      <td>aspirante a maestría en derecho y negocios int...</td>\n",
+       "      <td>[juan pablo wolff, pablo wolff mejia, juan p. ...</td>\n",
+       "      <td>[[twitter, https://twitter.com/pablomejiam], [...</td>\n",
+       "      <td>juanpmejia@ulasallista.edu.co</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Education , B.Ed. After Degree , University ...</td>\n",
-       "      <td>[[General Coordinator- University of Alberta C...</td>\n",
-       "      <td>43</td>\n",
-       "      <td>[Ananda Majumdar]</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ulasallista.edu.co</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[grfdt.com, linkedin.com, academia.edu, resear...</td>\n",
-       "      <td>24.0</td>\n",
+       "      <td>[twitter.com, youtube.com, google.com, linkedi...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>259877</th>\n",
-       "      <td>0000-0003-1815-5732</td>\n",
+       "      <th>4</th>\n",
+       "      <td>0000-0002-5341-6531</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>JAS</td>\n",
-       "      <td>(Jurnal Akuntansi Syariah)</td>\n",
-       "      <td>JAS (Jurnal Akuntansi Syariah) published in pr...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Website, https://ejournal.stiesyariahbengkal...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>trent</td>\n",
+       "      <td>hammond</td>\n",
+       "      <td>mr trent hammond is an honorary research fello...</td>\n",
+       "      <td>[trent ernest hammond (t.e.hammond)]</td>\n",
+       "      <td>[[academic support masters, http://trenthammon...</td>\n",
+       "      <td>trent.hammond@academicsupportmasters.com.au</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>67</td>\n",
-       "      <td>[JAS (Jurnal Akuntansi Syariah)]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[stiesyariahbengkalis.ac.id, lipi.go.id, cross...</td>\n",
-       "      <td>17.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>academicsupportmasters.com.au</td>\n",
+       "      <td>[health.nsw.gov.au, csu.edu.au, sociologist.co...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>[wix.com, academia.edu, researchgate.net, rese...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -8830,302 +8473,264 @@
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10494820</th>\n",
-       "      <td>0000-0002-1324-7171</td>\n",
+       "      <th>136</th>\n",
+       "      <td>0000-0002-3374-5709</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Vanesa Natalia</td>\n",
-       "      <td>Rodriguez</td>\n",
-       "      <td>Nombre y Apellido: Vanesa Natalia Rodriguez.  ...</td>\n",
-       "      <td>[Vanesa Rodriguez, Vanesa N. Rodriguez]</td>\n",
-       "      <td>[[De rufianes y franchutas Representaciones y ...</td>\n",
+       "      <td>guillermo</td>\n",
+       "      <td>ortiz</td>\n",
+       "      <td>médico, internista, neumólogo, intensivista, e...</td>\n",
+       "      <td>[guillermo ortiz-ruiz]</td>\n",
+       "      <td>[[elsevier, https://www.elsevier.com/], [asoci...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, Maestría en Ciencias Sociales con Mención ...</td>\n",
-       "      <td>[[Profesora, Universidad Nacional de La Matanz...</td>\n",
-       "      <td>7</td>\n",
-       "      <td>[Vanesa Natalia Rodriguez]</td>\n",
+       "      <td>62</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>88</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[unlam.edu.ar, unirioja.es, amazon.fr, abebook...</td>\n",
-       "      <td>19.0</td>\n",
+       "      <td>[elsevier.com, amci.org.co, springer.com, revi...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10495806</th>\n",
-       "      <td>0000-0002-1700-8311</td>\n",
+       "      <th>137</th>\n",
+       "      <td>0000-0001-7228-5680</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Fix-IT</td>\n",
-       "      <td>Rite</td>\n",
+       "      <td>text</td>\n",
+       "      <td>protocol</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[Best Heating &amp; Plumbing Company]</td>\n",
-       "      <td>[[Website, https://fix-itrite.com], [Muckrack,...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[about, https://about.me/textprotocol], [gith...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>1</td>\n",
-       "      <td>[Fix-It Rite]</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[fix-itrite.com, muckrack.com, tumblr.com, dri...</td>\n",
-       "      <td>11.0</td>\n",
+       "      <td>[about.me, github.com, gitlab.com, gravatar.co...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10633545</th>\n",
-       "      <td>0000-0003-2676-4431</td>\n",
+       "      <th>138</th>\n",
+       "      <td>0000-0002-3064-0194</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Benny</td>\n",
-       "      <td>Soewandi</td>\n",
+       "      <td>leonardo fernando</td>\n",
+       "      <td>cruz basso</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[Benny Soewandi]</td>\n",
-       "      <td>[[Conservation Efforts as a Result of Theoreti...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[papers-1, https://www.researchgate.net/profi...</td>\n",
+       "      <td>leonardofernando.basso@mackenzie.br</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Membership, Paguyuban Pelestarian Budaya Ban...</td>\n",
-       "      <td>2</td>\n",
-       "      <td>[Benny Soewandi]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[wordpress.com, wordpress.com, linkedin.com, f...</td>\n",
-       "      <td>11.0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>mackenzie.br</td>\n",
+       "      <td>[mackenzie.br]</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>[researchgate.net, ssrn.com, cnpq.br, google.c...</td>\n",
+       "      <td>17.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10648241</th>\n",
-       "      <td>0000-0001-8157-0600</td>\n",
+       "      <th>139</th>\n",
+       "      <td>0000-0003-1047-4229</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Bijan</td>\n",
-       "      <td>Yavar</td>\n",
-       "      <td>Senior Research Assistant and Phd Student in O...</td>\n",
-       "      <td>[B. Yavar, Yavar Bijan]</td>\n",
-       "      <td>[[Web of Science (Pub) Researcher ID: A-3544-2...</td>\n",
+       "      <td>bayu</td>\n",
+       "      <td>sakti</td>\n",
+       "      <td>bayu purbha saktisaya adalah bayu purbha sakti...</td>\n",
+       "      <td>[bayu purbha sakti]</td>\n",
+       "      <td>[[osf, http://osf.io/qe2ug], [inarxiv, https:/...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 56556873600]]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>6</td>\n",
-       "      <td>[Scopus - Elsevier]</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[publons.com, articulate.com, zenodo.org, orci...</td>\n",
-       "      <td>15.0</td>\n",
+       "      <td>[osf.io, osf.io, academia.edu, mendeley.com, f...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>10679699</th>\n",
-       "      <td>0000-0002-9874-1450</td>\n",
+       "      <th>140</th>\n",
+       "      <td>0000-0003-4836-7074</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>FENGZHI</td>\n",
-       "      <td>WU</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[A Systematic Study on the Dynamic Softening ...</td>\n",
+       "      <td>karla haydee</td>\n",
+       "      <td>ortiz palafox</td>\n",
+       "      <td>karla haydee ortíz palafoxmiembro del sistema ...</td>\n",
+       "      <td>[karla palafox]</td>\n",
+       "      <td>[[opinión día del maestro, http://www.cronicaj...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>3</td>\n",
-       "      <td>[FENGZHI WU]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[springer.com, sciencedirect.com, sciencedirec...</td>\n",
-       "      <td>23.0</td>\n",
+       "      <td>[cronicajalisco.com, youtube.com, tlaquepaque....</td>\n",
+       "      <td>22.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>139 rows × 22 columns</p>\n",
+       "<p>141 rows × 29 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                        orcid  claimed  verified_email  \\\n",
-       "45566     0000-0003-1948-3180        1               1   \n",
-       "72674     0000-0002-2000-8339        1               1   \n",
-       "172820    0000-0001-9293-2224        1               1   \n",
-       "209505    0000-0003-3045-0056        1               1   \n",
-       "259877    0000-0003-1815-5732        1               1   \n",
-       "...                       ...      ...             ...   \n",
-       "10494820  0000-0002-1324-7171        1               1   \n",
-       "10495806  0000-0002-1700-8311        1               1   \n",
-       "10633545  0000-0003-2676-4431        1               1   \n",
-       "10648241  0000-0001-8157-0600        1               1   \n",
-       "10679699  0000-0002-9874-1450        1               1   \n",
-       "\n",
-       "          verified_primary_email                given_names  \\\n",
-       "45566                          1                       Mark   \n",
-       "72674                          1  Phòng khám tư nhân Hà Nội   \n",
-       "172820                         1                Juan Carlos   \n",
-       "209505                         1                     Ananda   \n",
-       "259877                         1                        JAS   \n",
-       "...                          ...                        ...   \n",
-       "10494820                       1             Vanesa Natalia   \n",
-       "10495806                       1                     Fix-IT   \n",
-       "10633545                       1                      Benny   \n",
-       "10648241                       1                      Bijan   \n",
-       "10679699                       1                    FENGZHI   \n",
-       "\n",
-       "                         family_name  \\\n",
-       "45566                           Katz   \n",
-       "72674                            NaN   \n",
-       "172820                  Garcia Hoyos   \n",
-       "209505                      Majumdar   \n",
-       "259877    (Jurnal Akuntansi Syariah)   \n",
-       "...                              ...   \n",
-       "10494820                   Rodriguez   \n",
-       "10495806                        Rite   \n",
-       "10633545                    Soewandi   \n",
-       "10648241                       Yavar   \n",
-       "10679699                          WU   \n",
-       "\n",
-       "                                                  biography  \\\n",
-       "45566     Mark N. Katz is a professor of government and ...   \n",
-       "72674                                                   NaN   \n",
-       "172820    My name is Juan Carlos García Hoyos. I was bor...   \n",
-       "209505    I am Ananda Majumdar, Child Care Educator at B...   \n",
-       "259877    JAS (Jurnal Akuntansi Syariah) published in pr...   \n",
-       "...                                                     ...   \n",
-       "10494820  Nombre y Apellido: Vanesa Natalia Rodriguez.  ...   \n",
-       "10495806                                                NaN   \n",
-       "10633545                                                NaN   \n",
-       "10648241  Senior Research Assistant and Phd Student in O...   \n",
-       "10679699                                                NaN   \n",
+       "                   orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "0    0000-0002-7843-8497        1               1                       1   \n",
+       "1    0000-0003-1554-1531        1               1                       1   \n",
+       "2    0000-0003-3080-4643        1               1                       1   \n",
+       "3    0000-0003-3193-030x        1               1                       1   \n",
+       "4    0000-0002-5341-6531        1               1                       1   \n",
+       "..                   ...      ...             ...                     ...   \n",
+       "136  0000-0002-3374-5709        1               1                       1   \n",
+       "137  0000-0001-7228-5680        1               1                       1   \n",
+       "138  0000-0002-3064-0194        1               1                       1   \n",
+       "139  0000-0003-1047-4229        1               1                       1   \n",
+       "140  0000-0003-4836-7074        1               1                       1   \n",
+       "\n",
+       "           given_names    family_name  \\\n",
+       "0                 davi        barbosa   \n",
+       "1            katarzyna         ochman   \n",
+       "2               graham         dawson   \n",
+       "3           juan pablo    wolff mejia   \n",
+       "4                trent        hammond   \n",
+       "..                 ...            ...   \n",
+       "136          guillermo          ortiz   \n",
+       "137               text       protocol   \n",
+       "138  leonardo fernando     cruz basso   \n",
+       "139               bayu          sakti   \n",
+       "140       karla haydee  ortiz palafox   \n",
        "\n",
-       "                                                other_names  \\\n",
-       "45566                                                   NaN   \n",
-       "72674                                                   NaN   \n",
-       "172820    [Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...   \n",
-       "209505                                                  NaN   \n",
-       "259877                                                  NaN   \n",
-       "...                                                     ...   \n",
-       "10494820            [Vanesa Rodriguez, Vanesa N. Rodriguez]   \n",
-       "10495806                  [Best Heating & Plumbing Company]   \n",
-       "10633545                                   [Benny Soewandi]   \n",
-       "10648241                            [B. Yavar, Yavar Bijan]   \n",
-       "10679699                                                NaN   \n",
+       "                                             biography  \\\n",
+       "0    pesquisador na área sociojurídica, professor, ...   \n",
+       "1    katarzyna ochman [kataˈʐɨna ˈɔxman] is assista...   \n",
+       "2    science and engineering faculty (sef) libraria...   \n",
+       "3    aspirante a maestría en derecho y negocios int...   \n",
+       "4    mr trent hammond is an honorary research fello...   \n",
+       "..                                                 ...   \n",
+       "136  médico, internista, neumólogo, intensivista, e...   \n",
+       "137                                                NaN   \n",
+       "138                                                NaN   \n",
+       "139  bayu purbha saktisaya adalah bayu purbha sakti...   \n",
+       "140  karla haydee ortíz palafoxmiembro del sistema ...   \n",
        "\n",
-       "                                                       urls primary_email  \\\n",
-       "45566     [[Adjusting to Change: American Foreign Policy...           NaN   \n",
-       "72674     [[Sức khỏe, https://onhealth.vn/], [Khám phụ k...           NaN   \n",
-       "172820    [[Air Force Office of Scientific Research (WRI...           NaN   \n",
-       "209505    [[Migration Scholar and Ananda , https://grfdt...           NaN   \n",
-       "259877    [[Website, https://ejournal.stiesyariahbengkal...           NaN   \n",
-       "...                                                     ...           ...   \n",
-       "10494820  [[De rufianes y franchutas Representaciones y ...           NaN   \n",
-       "10495806  [[Website, https://fix-itrite.com], [Muckrack,...           NaN   \n",
-       "10633545  [[Conservation Efforts as a Result of Theoreti...           NaN   \n",
-       "10648241  [[Web of Science (Pub) Researcher ID: A-3544-2...           NaN   \n",
-       "10679699  [[A Systematic Study on the Dynamic Softening ...           NaN   \n",
-       "\n",
-       "          ...                       external_ids  \\\n",
-       "45566     ...  [[Scopus Author ID, 25649901800]]   \n",
-       "72674     ...                                NaN   \n",
-       "172820    ...                                NaN   \n",
-       "209505    ...                                NaN   \n",
-       "259877    ...                                NaN   \n",
-       "...       ...                                ...   \n",
-       "10494820  ...                                NaN   \n",
-       "10495806  ...                                NaN   \n",
-       "10633545  ...                                NaN   \n",
-       "10648241  ...  [[Scopus Author ID, 56556873600]]   \n",
-       "10679699  ...                                NaN   \n",
-       "\n",
-       "                                                  education  \\\n",
-       "45566     [[Political Science, Ph.D., Massachusetts Inst...   \n",
-       "72674                                                   NaN   \n",
-       "172820    [[Faculty of Philosophy, History - Ph.D., Char...   \n",
-       "209505    [[Education , B.Ed. After Degree , University ...   \n",
-       "259877                                                  NaN   \n",
-       "...                                                     ...   \n",
-       "10494820  [[, Maestría en Ciencias Sociales con Mención ...   \n",
-       "10495806                                                NaN   \n",
-       "10633545                                                NaN   \n",
-       "10648241                                                NaN   \n",
-       "10679699                                                NaN   \n",
-       "\n",
-       "                                                 employment n_works  \\\n",
-       "45566     [[Professor of Government and Politics, George...      58   \n",
-       "72674                                                   NaN       4   \n",
-       "172820    [[responsible for the Project Service Level Ag...      20   \n",
-       "209505    [[General Coordinator- University of Alberta C...      43   \n",
-       "259877                                                  NaN      67   \n",
-       "...                                                     ...     ...   \n",
-       "10494820  [[Profesora, Universidad Nacional de La Matanz...       7   \n",
-       "10495806                                                NaN       1   \n",
-       "10633545  [[Membership, Paguyuban Pelestarian Budaya Ban...       2   \n",
-       "10648241                                                NaN       6   \n",
-       "10679699                                                NaN       3   \n",
-       "\n",
-       "                              works_source  primary_email_domain  \\\n",
-       "45566                  [Scopus - Elsevier]                   NaN   \n",
-       "72674          [Phòng khám tư nhân Hà Nội]                   NaN   \n",
-       "172820          [Juan Carlos Garcia Hoyos]                   NaN   \n",
-       "209505                   [Ananda Majumdar]                   NaN   \n",
-       "259877    [JAS (Jurnal Akuntansi Syariah)]                   NaN   \n",
-       "...                                    ...                   ...   \n",
-       "10494820        [Vanesa Natalia Rodriguez]                   NaN   \n",
-       "10495806                     [Fix-It Rite]                   NaN   \n",
-       "10633545                  [Benny Soewandi]                   NaN   \n",
-       "10648241               [Scopus - Elsevier]                   NaN   \n",
-       "10679699                      [FENGZHI WU]                   NaN   \n",
-       "\n",
-       "         other_email_domains n_emails  \\\n",
-       "45566                    NaN      NaN   \n",
-       "72674                    NaN      NaN   \n",
-       "172820                   NaN      NaN   \n",
-       "209505                   NaN      NaN   \n",
-       "259877                   NaN      NaN   \n",
-       "...                      ...      ...   \n",
-       "10494820                 NaN      NaN   \n",
-       "10495806                 NaN      NaN   \n",
-       "10633545                 NaN      NaN   \n",
-       "10648241                 NaN      NaN   \n",
-       "10679699                 NaN      NaN   \n",
+       "                                           other_names  \\\n",
+       "0                     [professor davi barbosa delmont]   \n",
+       "1    [[kataˈʐɨna ˈɔxman], catharina ochman, cathari...   \n",
+       "2                  [ graham colin dawson, g.c. dawson]   \n",
+       "3    [juan pablo wolff, pablo wolff mejia, juan p. ...   \n",
+       "4                 [trent ernest hammond (t.e.hammond)]   \n",
+       "..                                                 ...   \n",
+       "136                             [guillermo ortiz-ruiz]   \n",
+       "137                                                NaN   \n",
+       "138                                                NaN   \n",
+       "139                                [bayu purbha sakti]   \n",
+       "140                                    [karla palafox]   \n",
+       "\n",
+       "                                                  urls  \\\n",
+       "0    [[plataforma de cursos ideia criativa, https:/...   \n",
+       "1    [[researchgate, https://www.researchgate.net/p...   \n",
+       "2    [[qut home page, https://www.library.qut.edu.a...   \n",
+       "3    [[twitter, https://twitter.com/pablomejiam], [...   \n",
+       "4    [[academic support masters, http://trenthammon...   \n",
+       "..                                                 ...   \n",
+       "136  [[elsevier, https://www.elsevier.com/], [asoci...   \n",
+       "137  [[about, https://about.me/textprotocol], [gith...   \n",
+       "138  [[papers-1, https://www.researchgate.net/profi...   \n",
+       "139  [[osf, http://osf.io/qe2ug], [inarxiv, https:/...   \n",
+       "140  [[opinión día del maestro, http://www.cronicaj...   \n",
+       "\n",
+       "                                   primary_email  ... n_doi n_arxiv n_pmc  \\\n",
+       "0                                            NaN  ...     0       0     0   \n",
+       "1                                            NaN  ...     1       0     0   \n",
+       "2                            g.dawson@qut.edu.au  ...     0       0     0   \n",
+       "3                  juanpmejia@ulasallista.edu.co  ...     0       0     0   \n",
+       "4    trent.hammond@academicsupportmasters.com.au  ...     1       0     0   \n",
+       "..                                           ...  ...   ...     ...   ...   \n",
+       "136                                          NaN  ...    62       0     0   \n",
+       "137                                          NaN  ...     0       0     0   \n",
+       "138          leonardofernando.basso@mackenzie.br  ...     5       0     0   \n",
+       "139                                          NaN  ...     0       0     0   \n",
+       "140                                          NaN  ...     0       0     0   \n",
+       "\n",
+       "    n_other_pids label           primary_email_domain  \\\n",
+       "0              0     0                            NaN   \n",
+       "1              0     1                            NaN   \n",
+       "2              6     1                     qut.edu.au   \n",
+       "3              0     1             ulasallista.edu.co   \n",
+       "4              1     1  academicsupportmasters.com.au   \n",
+       "..           ...   ...                            ...   \n",
+       "136           88     0                            NaN   \n",
+       "137            0     0                            NaN   \n",
+       "138            0     1                   mackenzie.br   \n",
+       "139            0     1                            NaN   \n",
+       "140            2     1                            NaN   \n",
+       "\n",
+       "                                   other_email_domains n_emails  \\\n",
+       "0                                                  NaN      NaN   \n",
+       "1                                                  NaN      NaN   \n",
+       "2                                                  NaN      NaN   \n",
+       "3                                                  NaN      NaN   \n",
+       "4    [health.nsw.gov.au, csu.edu.au, sociologist.co...      5.0   \n",
+       "..                                                 ...      ...   \n",
+       "136                                                NaN      NaN   \n",
+       "137                                                NaN      NaN   \n",
+       "138                                     [mackenzie.br]      1.0   \n",
+       "139                                                NaN      NaN   \n",
+       "140                                                NaN      NaN   \n",
        "\n",
-       "                                                url_domains  n_urls  \n",
-       "45566     [wordpress.com, marknkatz.com, gmu.edu, atlant...    16.0  \n",
-       "72674     [onhealth.vn, onhealth.vn, onhealth.vn, onheal...    49.0  \n",
-       "172820    [af.mil, gst.com, govtribe.com, sbir.gov, open...    28.0  \n",
-       "209505    [grfdt.com, linkedin.com, academia.edu, resear...    24.0  \n",
-       "259877    [stiesyariahbengkalis.ac.id, lipi.go.id, cross...    17.0  \n",
-       "...                                                     ...     ...  \n",
-       "10494820  [unlam.edu.ar, unirioja.es, amazon.fr, abebook...    19.0  \n",
-       "10495806  [fix-itrite.com, muckrack.com, tumblr.com, dri...    11.0  \n",
-       "10633545  [wordpress.com, wordpress.com, linkedin.com, f...    11.0  \n",
-       "10648241  [publons.com, articulate.com, zenodo.org, orci...    15.0  \n",
-       "10679699  [springer.com, sciencedirect.com, sciencedirec...    23.0  \n",
+       "                                           url_domains  n_urls  \n",
+       "0    [eadplataforma.com, facebook.com, youtube.com,...    39.0  \n",
+       "1    [researchgate.net, academia.edu, facebook.com,...    11.0  \n",
+       "2    [qut.edu.au, qut.edu.au, google.com.au, resear...    11.0  \n",
+       "3    [twitter.com, youtube.com, google.com, linkedi...    11.0  \n",
+       "4    [wix.com, academia.edu, researchgate.net, rese...    12.0  \n",
+       "..                                                 ...     ...  \n",
+       "136  [elsevier.com, amci.org.co, springer.com, revi...    12.0  \n",
+       "137  [about.me, github.com, gitlab.com, gravatar.co...    12.0  \n",
+       "138  [researchgate.net, ssrn.com, cnpq.br, google.c...    17.0  \n",
+       "139  [osf.io, osf.io, academia.edu, mendeley.com, f...    12.0  \n",
+       "140  [cronicajalisco.com, youtube.com, tlaquepaque....    22.0  \n",
        "\n",
-       "[139 rows x 22 columns]"
+       "[141 rows x 29 columns]"
       ]
      },
-     "execution_count": 49,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[(df['url_domains'].str.len() > 10) & (df['n_works'] > 0) & (df['works_source'].str.len() == 1)]"
+    "exploded_sources = df[(df['url_domains'].str.len() > 10) & (df['n_works'] > 0) & (df['works_source'].str.len() == 1)].explode('works_source').reset_index(drop=True)\n",
+    "exploded_sources"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 48,
    "metadata": {
     "scrolled": true
    },
@@ -9162,11 +8767,11 @@
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
        "      <th>...</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "      <th>n_doi</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "      <th>n_emails</th>\n",
@@ -9177,123 +8782,123 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>0000-0003-1948-3180</td>\n",
+       "      <td>0000-0002-7843-8497</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Mark</td>\n",
-       "      <td>Katz</td>\n",
-       "      <td>Mark N. Katz is a professor of government and ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Adjusting to Change: American Foreign Policy...</td>\n",
+       "      <td>davi</td>\n",
+       "      <td>barbosa</td>\n",
+       "      <td>pesquisador na área sociojurídica, professor, ...</td>\n",
+       "      <td>[professor davi barbosa delmont]</td>\n",
+       "      <td>[[plataforma de cursos ideia criativa, https:/...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 25649901800]]</td>\n",
-       "      <td>[[Political Science, Ph.D., Massachusetts Inst...</td>\n",
-       "      <td>[[Professor of Government and Politics, George...</td>\n",
-       "      <td>58</td>\n",
-       "      <td>Scopus - Elsevier</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[wordpress.com, marknkatz.com, gmu.edu, atlant...</td>\n",
-       "      <td>16.0</td>\n",
+       "      <td>[eadplataforma.com, facebook.com, youtube.com,...</td>\n",
+       "      <td>39.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>0000-0002-2000-8339</td>\n",
+       "      <td>0000-0003-1554-1531</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Phòng khám tư nhân Hà Nội</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Sức khỏe, https://onhealth.vn/], [Khám phụ k...</td>\n",
+       "      <td>katarzyna</td>\n",
+       "      <td>ochman</td>\n",
+       "      <td>katarzyna ochman [kataˈʐɨna ˈɔxman] is assista...</td>\n",
+       "      <td>[[kataˈʐɨna ˈɔxman], catharina ochman, cathari...</td>\n",
+       "      <td>[[researchgate, https://www.researchgate.net/p...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>4</td>\n",
-       "      <td>Phòng khám tư nhân Hà Nội</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[onhealth.vn, onhealth.vn, onhealth.vn, onheal...</td>\n",
-       "      <td>49.0</td>\n",
+       "      <td>[researchgate.net, academia.edu, facebook.com,...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0000-0001-9293-2224</td>\n",
+       "      <th>3</th>\n",
+       "      <td>0000-0003-3193-030x</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Juan Carlos</td>\n",
-       "      <td>Garcia Hoyos</td>\n",
-       "      <td>My name is Juan Carlos García Hoyos. I was bor...</td>\n",
-       "      <td>[Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...</td>\n",
-       "      <td>[[Air Force Office of Scientific Research (WRI...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>juan pablo</td>\n",
+       "      <td>wolff mejia</td>\n",
+       "      <td>aspirante a maestría en derecho y negocios int...</td>\n",
+       "      <td>[juan pablo wolff, pablo wolff mejia, juan p. ...</td>\n",
+       "      <td>[[twitter, https://twitter.com/pablomejiam], [...</td>\n",
+       "      <td>juanpmejia@ulasallista.edu.co</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Faculty of Philosophy, History - Ph.D., Char...</td>\n",
-       "      <td>[[responsible for the Project Service Level Ag...</td>\n",
-       "      <td>20</td>\n",
-       "      <td>Juan Carlos Garcia Hoyos</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ulasallista.edu.co</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[af.mil, gst.com, govtribe.com, sbir.gov, open...</td>\n",
-       "      <td>28.0</td>\n",
+       "      <td>[twitter.com, youtube.com, google.com, linkedi...</td>\n",
+       "      <td>11.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0000-0003-3045-0056</td>\n",
+       "      <th>4</th>\n",
+       "      <td>0000-0002-5341-6531</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Ananda</td>\n",
-       "      <td>Majumdar</td>\n",
-       "      <td>I am Ananda Majumdar, Child Care Educator at B...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Migration Scholar and Ananda , https://grfdt...</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>trent</td>\n",
+       "      <td>hammond</td>\n",
+       "      <td>mr trent hammond is an honorary research fello...</td>\n",
+       "      <td>[trent ernest hammond (t.e.hammond)]</td>\n",
+       "      <td>[[academic support masters, http://trenthammon...</td>\n",
+       "      <td>trent.hammond@academicsupportmasters.com.au</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Education , B.Ed. After Degree , University ...</td>\n",
-       "      <td>[[General Coordinator- University of Alberta C...</td>\n",
-       "      <td>43</td>\n",
-       "      <td>Ananda Majumdar</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[grfdt.com, linkedin.com, academia.edu, resear...</td>\n",
-       "      <td>24.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>academicsupportmasters.com.au</td>\n",
+       "      <td>[health.nsw.gov.au, csu.edu.au, sociologist.co...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>[wix.com, academia.edu, researchgate.net, rese...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0000-0003-1815-5732</td>\n",
+       "      <th>5</th>\n",
+       "      <td>0000-0001-5295-2271</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>JAS</td>\n",
-       "      <td>(Jurnal Akuntansi Syariah)</td>\n",
-       "      <td>JAS (Jurnal Akuntansi Syariah) published in pr...</td>\n",
+       "      <td>antoniy</td>\n",
+       "      <td>moysey</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Website, https://ejournal.stiesyariahbengkal...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[academic journals database, http://journalda...</td>\n",
+       "      <td>antoniimoisei@bsmu.edu.ua</td>\n",
        "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>bsmu.edu.ua</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>67</td>\n",
-       "      <td>JAS (Jurnal Akuntansi Syariah)</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[stiesyariahbengkalis.ac.id, lipi.go.id, cross...</td>\n",
-       "      <td>17.0</td>\n",
+       "      <td>[journaldatabase.info, nplu.org, acls.org, ind...</td>\n",
+       "      <td>21.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -9320,262 +8925,314 @@
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>134</th>\n",
-       "      <td>0000-0002-1324-7171</td>\n",
+       "      <th>135</th>\n",
+       "      <td>0000-0002-8125-0081</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Vanesa Natalia</td>\n",
-       "      <td>Rodriguez</td>\n",
-       "      <td>Nombre y Apellido: Vanesa Natalia Rodriguez.  ...</td>\n",
-       "      <td>[Vanesa Rodriguez, Vanesa N. Rodriguez]</td>\n",
-       "      <td>[[De rufianes y franchutas Representaciones y ...</td>\n",
+       "      <td>issam</td>\n",
+       "      <td>bencheikh</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
+       "      <td>[issame1982, دكتور عصام بن الشيخ]</td>\n",
+       "      <td>[[my blog web site, http://issame1982.blogspot...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[, Maestría en Ciencias Sociales con Mención ...</td>\n",
-       "      <td>[[Profesora, Universidad Nacional de La Matanz...</td>\n",
-       "      <td>7</td>\n",
-       "      <td>Vanesa Natalia Rodriguez</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[unlam.edu.ar, unirioja.es, amazon.fr, abebook...</td>\n",
-       "      <td>19.0</td>\n",
+       "      <td>[blogspot.com, researchgate.net, google.com, l...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>135</th>\n",
-       "      <td>0000-0002-1700-8311</td>\n",
+       "      <th>136</th>\n",
+       "      <td>0000-0002-3374-5709</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Fix-IT</td>\n",
-       "      <td>Rite</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Best Heating &amp; Plumbing Company]</td>\n",
-       "      <td>[[Website, https://fix-itrite.com], [Muckrack,...</td>\n",
+       "      <td>guillermo</td>\n",
+       "      <td>ortiz</td>\n",
+       "      <td>médico, internista, neumólogo, intensivista, e...</td>\n",
+       "      <td>[guillermo ortiz-ruiz]</td>\n",
+       "      <td>[[elsevier, https://www.elsevier.com/], [asoci...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
+       "      <td>62</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>88</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Fix-It Rite</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[fix-itrite.com, muckrack.com, tumblr.com, dri...</td>\n",
-       "      <td>11.0</td>\n",
+       "      <td>[elsevier.com, amci.org.co, springer.com, revi...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>136</th>\n",
-       "      <td>0000-0003-2676-4431</td>\n",
+       "      <th>137</th>\n",
+       "      <td>0000-0001-7228-5680</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Benny</td>\n",
-       "      <td>Soewandi</td>\n",
+       "      <td>text</td>\n",
+       "      <td>protocol</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[Benny Soewandi]</td>\n",
-       "      <td>[[Conservation Efforts as a Result of Theoreti...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
        "      <td>NaN</td>\n",
+       "      <td>[[about, https://about.me/textprotocol], [gith...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Membership, Paguyuban Pelestarian Budaya Ban...</td>\n",
-       "      <td>2</td>\n",
-       "      <td>Benny Soewandi</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[wordpress.com, wordpress.com, linkedin.com, f...</td>\n",
-       "      <td>11.0</td>\n",
+       "      <td>[about.me, github.com, gitlab.com, gravatar.co...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>137</th>\n",
-       "      <td>0000-0001-8157-0600</td>\n",
+       "      <th>139</th>\n",
+       "      <td>0000-0003-1047-4229</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Bijan</td>\n",
-       "      <td>Yavar</td>\n",
-       "      <td>Senior Research Assistant and Phd Student in O...</td>\n",
-       "      <td>[B. Yavar, Yavar Bijan]</td>\n",
-       "      <td>[[Web of Science (Pub) Researcher ID: A-3544-2...</td>\n",
+       "      <td>bayu</td>\n",
+       "      <td>sakti</td>\n",
+       "      <td>bayu purbha saktisaya adalah bayu purbha sakti...</td>\n",
+       "      <td>[bayu purbha sakti]</td>\n",
+       "      <td>[[osf, http://osf.io/qe2ug], [inarxiv, https:/...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>[[Scopus Author ID, 56556873600]]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>6</td>\n",
-       "      <td>Scopus - Elsevier</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[publons.com, articulate.com, zenodo.org, orci...</td>\n",
-       "      <td>15.0</td>\n",
+       "      <td>[osf.io, osf.io, academia.edu, mendeley.com, f...</td>\n",
+       "      <td>12.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>138</th>\n",
-       "      <td>0000-0002-9874-1450</td>\n",
+       "      <th>140</th>\n",
+       "      <td>0000-0003-4836-7074</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>FENGZHI</td>\n",
-       "      <td>WU</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[A Systematic Study on the Dynamic Softening ...</td>\n",
+       "      <td>karla haydee</td>\n",
+       "      <td>ortiz palafox</td>\n",
+       "      <td>karla haydee ortíz palafoxmiembro del sistema ...</td>\n",
+       "      <td>[karla palafox]</td>\n",
+       "      <td>[[opinión día del maestro, http://www.cronicaj...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>3</td>\n",
-       "      <td>FENGZHI WU</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[springer.com, sciencedirect.com, sciencedirec...</td>\n",
-       "      <td>23.0</td>\n",
+       "      <td>[cronicajalisco.com, youtube.com, tlaquepaque....</td>\n",
+       "      <td>22.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>139 rows × 22 columns</p>\n",
+       "<p>115 rows × 29 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                   orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "0    0000-0003-1948-3180        1               1                       1   \n",
-       "1    0000-0002-2000-8339        1               1                       1   \n",
-       "2    0000-0001-9293-2224        1               1                       1   \n",
-       "3    0000-0003-3045-0056        1               1                       1   \n",
-       "4    0000-0003-1815-5732        1               1                       1   \n",
-       "..                   ...      ...             ...                     ...   \n",
-       "134  0000-0002-1324-7171        1               1                       1   \n",
-       "135  0000-0002-1700-8311        1               1                       1   \n",
-       "136  0000-0003-2676-4431        1               1                       1   \n",
-       "137  0000-0001-8157-0600        1               1                       1   \n",
-       "138  0000-0002-9874-1450        1               1                       1   \n",
-       "\n",
-       "                   given_names                 family_name  \\\n",
-       "0                         Mark                        Katz   \n",
-       "1    Phòng khám tư nhân Hà Nội                         NaN   \n",
-       "2                  Juan Carlos                Garcia Hoyos   \n",
-       "3                       Ananda                    Majumdar   \n",
-       "4                          JAS  (Jurnal Akuntansi Syariah)   \n",
-       "..                         ...                         ...   \n",
-       "134             Vanesa Natalia                   Rodriguez   \n",
-       "135                     Fix-IT                        Rite   \n",
-       "136                      Benny                    Soewandi   \n",
-       "137                      Bijan                       Yavar   \n",
-       "138                    FENGZHI                          WU   \n",
-       "\n",
-       "                                             biography  \\\n",
-       "0    Mark N. Katz is a professor of government and ...   \n",
-       "1                                                  NaN   \n",
-       "2    My name is Juan Carlos García Hoyos. I was bor...   \n",
-       "3    I am Ananda Majumdar, Child Care Educator at B...   \n",
-       "4    JAS (Jurnal Akuntansi Syariah) published in pr...   \n",
-       "..                                                 ...   \n",
-       "134  Nombre y Apellido: Vanesa Natalia Rodriguez.  ...   \n",
-       "135                                                NaN   \n",
-       "136                                                NaN   \n",
-       "137  Senior Research Assistant and Phd Student in O...   \n",
-       "138                                                NaN   \n",
-       "\n",
-       "                                           other_names  \\\n",
-       "0                                                  NaN   \n",
-       "1                                                  NaN   \n",
-       "2    [Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...   \n",
-       "3                                                  NaN   \n",
-       "4                                                  NaN   \n",
-       "..                                                 ...   \n",
-       "134            [Vanesa Rodriguez, Vanesa N. Rodriguez]   \n",
-       "135                  [Best Heating & Plumbing Company]   \n",
-       "136                                   [Benny Soewandi]   \n",
-       "137                            [B. Yavar, Yavar Bijan]   \n",
-       "138                                                NaN   \n",
-       "\n",
-       "                                                  urls primary_email  ...  \\\n",
-       "0    [[Adjusting to Change: American Foreign Policy...           NaN  ...   \n",
-       "1    [[Sức khỏe, https://onhealth.vn/], [Khám phụ k...           NaN  ...   \n",
-       "2    [[Air Force Office of Scientific Research (WRI...           NaN  ...   \n",
-       "3    [[Migration Scholar and Ananda , https://grfdt...           NaN  ...   \n",
-       "4    [[Website, https://ejournal.stiesyariahbengkal...           NaN  ...   \n",
-       "..                                                 ...           ...  ...   \n",
-       "134  [[De rufianes y franchutas Representaciones y ...           NaN  ...   \n",
-       "135  [[Website, https://fix-itrite.com], [Muckrack,...           NaN  ...   \n",
-       "136  [[Conservation Efforts as a Result of Theoreti...           NaN  ...   \n",
-       "137  [[Web of Science (Pub) Researcher ID: A-3544-2...           NaN  ...   \n",
-       "138  [[A Systematic Study on the Dynamic Softening ...           NaN  ...   \n",
-       "\n",
-       "                          external_ids  \\\n",
-       "0    [[Scopus Author ID, 25649901800]]   \n",
-       "1                                  NaN   \n",
-       "2                                  NaN   \n",
-       "3                                  NaN   \n",
-       "4                                  NaN   \n",
-       "..                                 ...   \n",
-       "134                                NaN   \n",
-       "135                                NaN   \n",
-       "136                                NaN   \n",
-       "137  [[Scopus Author ID, 56556873600]]   \n",
-       "138                                NaN   \n",
-       "\n",
-       "                                             education  \\\n",
-       "0    [[Political Science, Ph.D., Massachusetts Inst...   \n",
-       "1                                                  NaN   \n",
-       "2    [[Faculty of Philosophy, History - Ph.D., Char...   \n",
-       "3    [[Education , B.Ed. After Degree , University ...   \n",
-       "4                                                  NaN   \n",
-       "..                                                 ...   \n",
-       "134  [[, Maestría en Ciencias Sociales con Mención ...   \n",
-       "135                                                NaN   \n",
-       "136                                                NaN   \n",
-       "137                                                NaN   \n",
-       "138                                                NaN   \n",
-       "\n",
-       "                                            employment n_works  \\\n",
-       "0    [[Professor of Government and Politics, George...      58   \n",
-       "1                                                  NaN       4   \n",
-       "2    [[responsible for the Project Service Level Ag...      20   \n",
-       "3    [[General Coordinator- University of Alberta C...      43   \n",
-       "4                                                  NaN      67   \n",
-       "..                                                 ...     ...   \n",
-       "134  [[Profesora, Universidad Nacional de La Matanz...       7   \n",
-       "135                                                NaN       1   \n",
-       "136  [[Membership, Paguyuban Pelestarian Budaya Ban...       2   \n",
-       "137                                                NaN       6   \n",
-       "138                                                NaN       3   \n",
-       "\n",
-       "                       works_source  primary_email_domain other_email_domains  \\\n",
-       "0                 Scopus - Elsevier                   NaN                 NaN   \n",
-       "1         Phòng khám tư nhân Hà Nội                   NaN                 NaN   \n",
-       "2          Juan Carlos Garcia Hoyos                   NaN                 NaN   \n",
-       "3                   Ananda Majumdar                   NaN                 NaN   \n",
-       "4    JAS (Jurnal Akuntansi Syariah)                   NaN                 NaN   \n",
-       "..                              ...                   ...                 ...   \n",
-       "134        Vanesa Natalia Rodriguez                   NaN                 NaN   \n",
-       "135                     Fix-It Rite                   NaN                 NaN   \n",
-       "136                  Benny Soewandi                   NaN                 NaN   \n",
-       "137               Scopus - Elsevier                   NaN                 NaN   \n",
-       "138                      FENGZHI WU                   NaN                 NaN   \n",
-       "\n",
-       "    n_emails                                        url_domains  n_urls  \n",
-       "0        NaN  [wordpress.com, marknkatz.com, gmu.edu, atlant...    16.0  \n",
-       "1        NaN  [onhealth.vn, onhealth.vn, onhealth.vn, onheal...    49.0  \n",
-       "2        NaN  [af.mil, gst.com, govtribe.com, sbir.gov, open...    28.0  \n",
-       "3        NaN  [grfdt.com, linkedin.com, academia.edu, resear...    24.0  \n",
-       "4        NaN  [stiesyariahbengkalis.ac.id, lipi.go.id, cross...    17.0  \n",
-       "..       ...                                                ...     ...  \n",
-       "134      NaN  [unlam.edu.ar, unirioja.es, amazon.fr, abebook...    19.0  \n",
-       "135      NaN  [fix-itrite.com, muckrack.com, tumblr.com, dri...    11.0  \n",
-       "136      NaN  [wordpress.com, wordpress.com, linkedin.com, f...    11.0  \n",
-       "137      NaN  [publons.com, articulate.com, zenodo.org, orci...    15.0  \n",
-       "138      NaN  [springer.com, sciencedirect.com, sciencedirec...    23.0  \n",
-       "\n",
-       "[139 rows x 22 columns]"
+       "                   orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "0    0000-0002-7843-8497        1               1                       1   \n",
+       "1    0000-0003-1554-1531        1               1                       1   \n",
+       "3    0000-0003-3193-030x        1               1                       1   \n",
+       "4    0000-0002-5341-6531        1               1                       1   \n",
+       "5    0000-0001-5295-2271        1               1                       1   \n",
+       "..                   ...      ...             ...                     ...   \n",
+       "135  0000-0002-8125-0081        1               1                       1   \n",
+       "136  0000-0002-3374-5709        1               1                       1   \n",
+       "137  0000-0001-7228-5680        1               1                       1   \n",
+       "139  0000-0003-1047-4229        1               1                       1   \n",
+       "140  0000-0003-4836-7074        1               1                       1   \n",
+       "\n",
+       "      given_names    family_name  \\\n",
+       "0            davi        barbosa   \n",
+       "1       katarzyna         ochman   \n",
+       "3      juan pablo    wolff mejia   \n",
+       "4           trent        hammond   \n",
+       "5         antoniy         moysey   \n",
+       "..            ...            ...   \n",
+       "135         issam      bencheikh   \n",
+       "136     guillermo          ortiz   \n",
+       "137          text       protocol   \n",
+       "139          bayu          sakti   \n",
+       "140  karla haydee  ortiz palafox   \n",
+       "\n",
+       "                                             biography  \\\n",
+       "0    pesquisador na área sociojurídica, professor, ...   \n",
+       "1    katarzyna ochman [kataˈʐɨna ˈɔxman] is assista...   \n",
+       "3    aspirante a maestría en derecho y negocios int...   \n",
+       "4    mr trent hammond is an honorary research fello...   \n",
+       "5                                                  NaN   \n",
+       "..                                                 ...   \n",
+       "135                                                NaN   \n",
+       "136  médico, internista, neumólogo, intensivista, e...   \n",
+       "137                                                NaN   \n",
+       "139  bayu purbha saktisaya adalah bayu purbha sakti...   \n",
+       "140  karla haydee ortíz palafoxmiembro del sistema ...   \n",
+       "\n",
+       "                                           other_names  \\\n",
+       "0                     [professor davi barbosa delmont]   \n",
+       "1    [[kataˈʐɨna ˈɔxman], catharina ochman, cathari...   \n",
+       "3    [juan pablo wolff, pablo wolff mejia, juan p. ...   \n",
+       "4                 [trent ernest hammond (t.e.hammond)]   \n",
+       "5                                                  NaN   \n",
+       "..                                                 ...   \n",
+       "135                  [issame1982, دكتور عصام بن الشيخ]   \n",
+       "136                             [guillermo ortiz-ruiz]   \n",
+       "137                                                NaN   \n",
+       "139                                [bayu purbha sakti]   \n",
+       "140                                    [karla palafox]   \n",
+       "\n",
+       "                                                  urls  \\\n",
+       "0    [[plataforma de cursos ideia criativa, https:/...   \n",
+       "1    [[researchgate, https://www.researchgate.net/p...   \n",
+       "3    [[twitter, https://twitter.com/pablomejiam], [...   \n",
+       "4    [[academic support masters, http://trenthammon...   \n",
+       "5    [[academic journals database, http://journalda...   \n",
+       "..                                                 ...   \n",
+       "135  [[my blog web site, http://issame1982.blogspot...   \n",
+       "136  [[elsevier, https://www.elsevier.com/], [asoci...   \n",
+       "137  [[about, https://about.me/textprotocol], [gith...   \n",
+       "139  [[osf, http://osf.io/qe2ug], [inarxiv, https:/...   \n",
+       "140  [[opinión día del maestro, http://www.cronicaj...   \n",
+       "\n",
+       "                                   primary_email  ... n_doi n_arxiv n_pmc  \\\n",
+       "0                                            NaN  ...     0       0     0   \n",
+       "1                                            NaN  ...     1       0     0   \n",
+       "3                  juanpmejia@ulasallista.edu.co  ...     0       0     0   \n",
+       "4    trent.hammond@academicsupportmasters.com.au  ...     1       0     0   \n",
+       "5                      antoniimoisei@bsmu.edu.ua  ...     0       0     0   \n",
+       "..                                           ...  ...   ...     ...   ...   \n",
+       "135                                          NaN  ...     0       0     0   \n",
+       "136                                          NaN  ...    62       0     0   \n",
+       "137                                          NaN  ...     0       0     0   \n",
+       "139                                          NaN  ...     0       0     0   \n",
+       "140                                          NaN  ...     0       0     0   \n",
+       "\n",
+       "    n_other_pids label           primary_email_domain  \\\n",
+       "0              0     0                            NaN   \n",
+       "1              0     1                            NaN   \n",
+       "3              0     1             ulasallista.edu.co   \n",
+       "4              1     1  academicsupportmasters.com.au   \n",
+       "5              0     1                    bsmu.edu.ua   \n",
+       "..           ...   ...                            ...   \n",
+       "135            0     1                            NaN   \n",
+       "136           88     0                            NaN   \n",
+       "137            0     0                            NaN   \n",
+       "139            0     1                            NaN   \n",
+       "140            2     1                            NaN   \n",
+       "\n",
+       "                                   other_email_domains n_emails  \\\n",
+       "0                                                  NaN      NaN   \n",
+       "1                                                  NaN      NaN   \n",
+       "3                                                  NaN      NaN   \n",
+       "4    [health.nsw.gov.au, csu.edu.au, sociologist.co...      5.0   \n",
+       "5                                                  NaN      NaN   \n",
+       "..                                                 ...      ...   \n",
+       "135                                                NaN      NaN   \n",
+       "136                                                NaN      NaN   \n",
+       "137                                                NaN      NaN   \n",
+       "139                                                NaN      NaN   \n",
+       "140                                                NaN      NaN   \n",
+       "\n",
+       "                                           url_domains  n_urls  \n",
+       "0    [eadplataforma.com, facebook.com, youtube.com,...    39.0  \n",
+       "1    [researchgate.net, academia.edu, facebook.com,...    11.0  \n",
+       "3    [twitter.com, youtube.com, google.com, linkedi...    11.0  \n",
+       "4    [wix.com, academia.edu, researchgate.net, rese...    12.0  \n",
+       "5    [journaldatabase.info, nplu.org, acls.org, ind...    21.0  \n",
+       "..                                                 ...     ...  \n",
+       "135  [blogspot.com, researchgate.net, google.com, l...    12.0  \n",
+       "136  [elsevier.com, amci.org.co, springer.com, revi...    12.0  \n",
+       "137  [about.me, github.com, gitlab.com, gravatar.co...    12.0  \n",
+       "139  [osf.io, osf.io, academia.edu, mendeley.com, f...    12.0  \n",
+       "140  [cronicajalisco.com, youtube.com, tlaquepaque....    22.0  \n",
+       "\n",
+       "[115 rows x 29 columns]"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "exploded_sources[exploded_sources.apply(lambda x: x['works_source'].find(x['given_names']) >= 0, axis=1)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Works source"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Paste from Miriam"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## External IDs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "External IDs should come from reliable sources. ORCiD registrants cannot add them freely."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['n_ids'] = df[df['external_ids'].notna()].external_ids.str.len()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count    1.301959e+06\n",
+       "mean     1.358640e+00\n",
+       "std      6.635087e-01\n",
+       "min      1.000000e+00\n",
+       "25%      1.000000e+00\n",
+       "50%      1.000000e+00\n",
+       "75%      2.000000e+00\n",
+       "max      8.000000e+01\n",
+       "Name: n_ids, dtype: float64"
       ]
      },
      "execution_count": 50,
@@ -9584,16 +9241,13 @@
     }
    ],
    "source": [
-    "exploded_sources = df[(df['url_domains'].str.len() > 10) & (df['n_works'] > 0) & (df['works_source'].str.len() == 1)].explode('works_source').reset_index(drop=True)\n",
-    "exploded_sources"
+    "df.n_ids.describe()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 51,
-   "metadata": {
-    "scrolled": true
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -9627,640 +9281,1322 @@
        "      <th>urls</th>\n",
        "      <th>primary_email</th>\n",
        "      <th>...</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
+       "      <th>n_arxiv</th>\n",
+       "      <th>n_pmc</th>\n",
+       "      <th>n_other_pids</th>\n",
+       "      <th>label</th>\n",
        "      <th>primary_email_domain</th>\n",
        "      <th>other_email_domains</th>\n",
        "      <th>n_emails</th>\n",
        "      <th>url_domains</th>\n",
        "      <th>n_urls</th>\n",
+       "      <th>n_ids</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0000-0002-2000-8339</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Phòng khám tư nhân Hà Nội</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Sức khỏe, https://onhealth.vn/], [Khám phụ k...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>4</td>\n",
-       "      <td>Phòng khám tư nhân Hà Nội</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[onhealth.vn, onhealth.vn, onhealth.vn, onheal...</td>\n",
-       "      <td>49.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0000-0001-9293-2224</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Juan Carlos</td>\n",
-       "      <td>Garcia Hoyos</td>\n",
-       "      <td>My name is Juan Carlos García Hoyos. I was bor...</td>\n",
-       "      <td>[Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...</td>\n",
-       "      <td>[[Air Force Office of Scientific Research (WRI...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Faculty of Philosophy, History - Ph.D., Char...</td>\n",
-       "      <td>[[responsible for the Project Service Level Ag...</td>\n",
-       "      <td>20</td>\n",
-       "      <td>Juan Carlos Garcia Hoyos</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[af.mil, gst.com, govtribe.com, sbir.gov, open...</td>\n",
-       "      <td>28.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0000-0003-3045-0056</td>\n",
+       "      <th>7253330</th>\n",
+       "      <td>0000-0002-9554-6633</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
-       "      <td>Ananda</td>\n",
-       "      <td>Majumdar</td>\n",
-       "      <td>I am Ananda Majumdar, Child Care Educator at B...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Migration Scholar and Ananda , https://grfdt...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
+       "      <td>john a</td>\n",
+       "      <td>williams</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Education , B.Ed. After Degree , University ...</td>\n",
-       "      <td>[[General Coordinator- University of Alberta C...</td>\n",
-       "      <td>43</td>\n",
-       "      <td>Ananda Majumdar</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[grfdt.com, linkedin.com, academia.edu, resear...</td>\n",
-       "      <td>24.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0000-0003-1815-5732</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>JAS</td>\n",
-       "      <td>(Jurnal Akuntansi Syariah)</td>\n",
-       "      <td>JAS (Jurnal Akuntansi Syariah) published in pr...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Website, https://ejournal.stiesyariahbengkal...</td>\n",
+       "      <td>[[aston university profile page, https://resea...</td>\n",
        "      <td>NaN</td>\n",
        "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>67</td>\n",
-       "      <td>JAS (Jurnal Akuntansi Syariah)</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[stiesyariahbengkalis.ac.id, lipi.go.id, cross...</td>\n",
-       "      <td>17.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0000-0002-4379-6454</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>208</td>\n",
        "      <td>1</td>\n",
-       "      <td>Caroline Wanjiru</td>\n",
-       "      <td>Kariuki</td>\n",
-       "      <td>Caroline holds a PhD in Economics from Curtin ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Scopus Profile, https://www.scopus.com/dashb...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Economics, Doctor of Philosophy , Curtin Uni...</td>\n",
-       "      <td>[[Director, Educational Development, Strathmor...</td>\n",
-       "      <td>4</td>\n",
-       "      <td>Caroline Wanjiru Kariuki</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[scopus.com, mendeley.com, publons.com, resear...</td>\n",
-       "      <td>13.0</td>\n",
+       "      <td>[aston.ac.uk]</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>80.0</td>\n",
        "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1 rows × 30 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
+       "7253330  0000-0002-9554-6633        1               1                       1   \n",
+       "\n",
+       "        given_names family_name biography other_names  \\\n",
+       "7253330      john a    williams       NaN         NaN   \n",
+       "\n",
+       "                                                      urls primary_email  ...  \\\n",
+       "7253330  [[aston university profile page, https://resea...           NaN  ...   \n",
+       "\n",
+       "        n_arxiv n_pmc n_other_pids label primary_email_domain  \\\n",
+       "7253330       0     0          208     1                  NaN   \n",
+       "\n",
+       "         other_email_domains n_emails    url_domains n_urls  n_ids  \n",
+       "7253330                  NaN      NaN  [aston.ac.uk]    1.0   80.0  \n",
+       "\n",
+       "[1 rows x 30 columns]"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[df.n_ids == df.n_ids.max()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ids = df[['orcid', 'external_ids']].explode('external_ids').reset_index(drop=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ids['provider'] = ids[ids.external_ids.notna()]['external_ids'].apply(lambda x: x[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>orcid</th>\n",
+       "      <th>external_ids</th>\n",
+       "      <th>provider</th>\n",
        "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
        "    <tr>\n",
-       "      <th>132</th>\n",
-       "      <td>0000-0001-6352-7086</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Susan</td>\n",
-       "      <td>Hawthorne</td>\n",
-       "      <td>Susan is a poet, novelist, publisher and Sansk...</td>\n",
-       "      <td>[S. Hawthorne, Susan C. C. Hawthorne]</td>\n",
-       "      <td>[[Spinifex Press, http://www.spinifexpress.com...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>[[ResearcherID, K-6039-2018]]</td>\n",
-       "      <td>[[School of Asian Studies, Honours Sanskrit, A...</td>\n",
-       "      <td>[[Adjunct Professor, James Cook University, To...</td>\n",
-       "      <td>352</td>\n",
-       "      <td>Susan Hawthorne</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[spinifexpress.com.au, linkedin.com, twitter.c...</td>\n",
-       "      <td>12.0</td>\n",
+       "      <th>7</th>\n",
+       "      <td>0000-0001-7463-977x</td>\n",
+       "      <td>[loop profile, 371409]</td>\n",
+       "      <td>loop profile</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>133</th>\n",
-       "      <td>0000-0002-4062-3603</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>JUAN DE DIOS</td>\n",
-       "      <td>BELTRÁN MANCILLA</td>\n",
-       "      <td>JUAN DE DIOS BELTRÁN MANCILLA (*) Filósofo aut...</td>\n",
-       "      <td>[Juan de Dios Beltrán Mancilla, FILÓSOFO AUTOD...</td>\n",
-       "      <td>[[01.- Juan de Dios Beltrán Mancilla. Teoría O...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, DIPLOMADO EN PRACTICAS DIRECTIVAS  PARA OR...</td>\n",
-       "      <td>[[INSPECTOR GENERAL JORNADA VESPERTINA // De 2...</td>\n",
-       "      <td>11</td>\n",
-       "      <td>JUAN DE DIOS BELTR´´ÁN MANCILLA</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[yumpu.com, ijopm.org, google.com, blogspot.co...</td>\n",
-       "      <td>69.0</td>\n",
+       "      <th>9</th>\n",
+       "      <td>0000-0001-8718-0056</td>\n",
+       "      <td>[scopus author id, 55466912100]</td>\n",
+       "      <td>scopus author id</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>134</th>\n",
-       "      <td>0000-0002-1324-7171</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Vanesa Natalia</td>\n",
-       "      <td>Rodriguez</td>\n",
-       "      <td>Nombre y Apellido: Vanesa Natalia Rodriguez.  ...</td>\n",
-       "      <td>[Vanesa Rodriguez, Vanesa N. Rodriguez]</td>\n",
-       "      <td>[[De rufianes y franchutas Representaciones y ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, Maestría en Ciencias Sociales con Mención ...</td>\n",
-       "      <td>[[Profesora, Universidad Nacional de La Matanz...</td>\n",
-       "      <td>7</td>\n",
-       "      <td>Vanesa Natalia Rodriguez</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[unlam.edu.ar, unirioja.es, amazon.fr, abebook...</td>\n",
-       "      <td>19.0</td>\n",
+       "      <th>10</th>\n",
+       "      <td>0000-0001-8718-0056</td>\n",
+       "      <td>[scopus author id, 7102015452]</td>\n",
+       "      <td>scopus author id</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>136</th>\n",
-       "      <td>0000-0003-2676-4431</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Benny</td>\n",
-       "      <td>Soewandi</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Benny Soewandi]</td>\n",
-       "      <td>[[Conservation Efforts as a Result of Theoreti...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Membership, Paguyuban Pelestarian Budaya Ban...</td>\n",
-       "      <td>2</td>\n",
-       "      <td>Benny Soewandi</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[wordpress.com, wordpress.com, linkedin.com, f...</td>\n",
-       "      <td>11.0</td>\n",
+       "      <th>14</th>\n",
+       "      <td>0000-0001-9708-5570</td>\n",
+       "      <td>[researcherid, p-5112-2015]</td>\n",
+       "      <td>researcherid</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>138</th>\n",
-       "      <td>0000-0002-9874-1450</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>FENGZHI</td>\n",
-       "      <td>WU</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[A Systematic Study on the Dynamic Softening ...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3</td>\n",
-       "      <td>FENGZHI WU</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[springer.com, sciencedirect.com, sciencedirec...</td>\n",
-       "      <td>23.0</td>\n",
+       "      <th>15</th>\n",
+       "      <td>0000-0001-9708-5570</td>\n",
+       "      <td>[scopus author id, 42062216900]</td>\n",
+       "      <td>scopus author id</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>108 rows × 22 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                   orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "1    0000-0002-2000-8339        1               1                       1   \n",
-       "2    0000-0001-9293-2224        1               1                       1   \n",
-       "3    0000-0003-3045-0056        1               1                       1   \n",
-       "4    0000-0003-1815-5732        1               1                       1   \n",
-       "5    0000-0002-4379-6454        1               1                       1   \n",
-       "..                   ...      ...             ...                     ...   \n",
-       "132  0000-0001-6352-7086        1               1                       1   \n",
-       "133  0000-0002-4062-3603        1               1                       1   \n",
-       "134  0000-0002-1324-7171        1               1                       1   \n",
-       "136  0000-0003-2676-4431        1               1                       1   \n",
-       "138  0000-0002-9874-1450        1               1                       1   \n",
-       "\n",
-       "                   given_names                 family_name  \\\n",
-       "1    Phòng khám tư nhân Hà Nội                         NaN   \n",
-       "2                  Juan Carlos                Garcia Hoyos   \n",
-       "3                       Ananda                    Majumdar   \n",
-       "4                          JAS  (Jurnal Akuntansi Syariah)   \n",
-       "5             Caroline Wanjiru                     Kariuki   \n",
-       "..                         ...                         ...   \n",
-       "132                      Susan                   Hawthorne   \n",
-       "133              JUAN DE DIOS            BELTRÁN MANCILLA    \n",
-       "134             Vanesa Natalia                   Rodriguez   \n",
-       "136                      Benny                    Soewandi   \n",
-       "138                    FENGZHI                          WU   \n",
-       "\n",
-       "                                             biography  \\\n",
-       "1                                                  NaN   \n",
-       "2    My name is Juan Carlos García Hoyos. I was bor...   \n",
-       "3    I am Ananda Majumdar, Child Care Educator at B...   \n",
-       "4    JAS (Jurnal Akuntansi Syariah) published in pr...   \n",
-       "5    Caroline holds a PhD in Economics from Curtin ...   \n",
-       "..                                                 ...   \n",
-       "132  Susan is a poet, novelist, publisher and Sansk...   \n",
-       "133  JUAN DE DIOS BELTRÁN MANCILLA (*) Filósofo aut...   \n",
-       "134  Nombre y Apellido: Vanesa Natalia Rodriguez.  ...   \n",
-       "136                                                NaN   \n",
-       "138                                                NaN   \n",
-       "\n",
-       "                                           other_names  \\\n",
-       "1                                                  NaN   \n",
-       "2    [Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...   \n",
-       "3                                                  NaN   \n",
-       "4                                                  NaN   \n",
-       "5                                                  NaN   \n",
-       "..                                                 ...   \n",
-       "132              [S. Hawthorne, Susan C. C. Hawthorne]   \n",
-       "133  [Juan de Dios Beltrán Mancilla, FILÓSOFO AUTOD...   \n",
-       "134            [Vanesa Rodriguez, Vanesa N. Rodriguez]   \n",
-       "136                                   [Benny Soewandi]   \n",
-       "138                                                NaN   \n",
-       "\n",
-       "                                                  urls primary_email  ...  \\\n",
-       "1    [[Sức khỏe, https://onhealth.vn/], [Khám phụ k...           NaN  ...   \n",
-       "2    [[Air Force Office of Scientific Research (WRI...           NaN  ...   \n",
-       "3    [[Migration Scholar and Ananda , https://grfdt...           NaN  ...   \n",
-       "4    [[Website, https://ejournal.stiesyariahbengkal...           NaN  ...   \n",
-       "5    [[Scopus Profile, https://www.scopus.com/dashb...           NaN  ...   \n",
-       "..                                                 ...           ...  ...   \n",
-       "132  [[Spinifex Press, http://www.spinifexpress.com...           NaN  ...   \n",
-       "133  [[01.- Juan de Dios Beltrán Mancilla. Teoría O...           NaN  ...   \n",
-       "134  [[De rufianes y franchutas Representaciones y ...           NaN  ...   \n",
-       "136  [[Conservation Efforts as a Result of Theoreti...           NaN  ...   \n",
-       "138  [[A Systematic Study on the Dynamic Softening ...           NaN  ...   \n",
-       "\n",
-       "                      external_ids  \\\n",
-       "1                              NaN   \n",
-       "2                              NaN   \n",
-       "3                              NaN   \n",
-       "4                              NaN   \n",
-       "5                              NaN   \n",
-       "..                             ...   \n",
-       "132  [[ResearcherID, K-6039-2018]]   \n",
-       "133                            NaN   \n",
-       "134                            NaN   \n",
-       "136                            NaN   \n",
-       "138                            NaN   \n",
-       "\n",
-       "                                             education  \\\n",
-       "1                                                  NaN   \n",
-       "2    [[Faculty of Philosophy, History - Ph.D., Char...   \n",
-       "3    [[Education , B.Ed. After Degree , University ...   \n",
-       "4                                                  NaN   \n",
-       "5    [[Economics, Doctor of Philosophy , Curtin Uni...   \n",
-       "..                                                 ...   \n",
-       "132  [[School of Asian Studies, Honours Sanskrit, A...   \n",
-       "133  [[, DIPLOMADO EN PRACTICAS DIRECTIVAS  PARA OR...   \n",
-       "134  [[, Maestría en Ciencias Sociales con Mención ...   \n",
-       "136                                                NaN   \n",
-       "138                                                NaN   \n",
+       "                  orcid                     external_ids          provider\n",
+       "7   0000-0001-7463-977x           [loop profile, 371409]      loop profile\n",
+       "9   0000-0001-8718-0056  [scopus author id, 55466912100]  scopus author id\n",
+       "10  0000-0001-8718-0056   [scopus author id, 7102015452]  scopus author id\n",
+       "14  0000-0001-9708-5570      [researcherid, p-5112-2015]      researcherid\n",
+       "15  0000-0001-9708-5570  [scopus author id, 42062216900]  scopus author id"
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ids[ids.provider.notna()].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.plotly.v1+json": {
+       "config": {
+        "linkText": "Export to plot.ly",
+        "plotlyServerURL": "https://plot.ly",
+        "showLink": false
+       },
+       "data": [
+        {
+         "type": "bar",
+         "x": [
+          "scopus author id",
+          "researcherid",
+          "loop profile",
+          "ciência id",
+          "researcher name resolver id",
+          "中国科学家在线",
+          "sciprofile",
+          "isni",
+          "gnd",
+          "pitt id",
+          "technical university of denmark cwis",
+          "researcher id",
+          "id dialnet",
+          "digital author id",
+          "scopus author id: ",
+          "authenticusid",
+          "hku researcherpage",
+          "uow scholars",
+          "cti vitae",
+          "scopus author id:",
+          "hkust profile",
+          "chalmers id",
+          "scopus  id",
+          "iauthor",
+          "google scholar",
+          "digital author id (dai)",
+          "authid",
+          "dai",
+          "us epa vivo",
+          "scopus id",
+          "authenticus",
+          "smithsonian profiles",
+          "github",
+          "escientist",
+          "vivo cornell",
+          "researcherid:",
+          "id dialnet:",
+          "dialnet id",
+          "sciprofiles",
+          "kaken",
+          "une researcher id",
+          "researcherid: ",
+          "orcid",
+          "scienceopen",
+          "profile system identifier",
+          "orcid id",
+          "custom"
+         ],
+         "y": [
+          1030807,
+          544825,
+          117325,
+          36666,
+          7907,
+          4804,
+          4411,
+          3075,
+          2954,
+          2674,
+          2483,
+          1445,
+          1168,
+          1124,
+          1077,
+          869,
+          741,
+          646,
+          581,
+          548,
+          522,
+          430,
+          254,
+          212,
+          200,
+          177,
+          175,
+          155,
+          146,
+          127,
+          83,
+          61,
+          51,
+          49,
+          46,
+          39,
+          7,
+          6,
+          5,
+          5,
+          4,
+          3,
+          2,
+          1,
+          1,
+          1,
+          1
+         ]
+        }
+       ],
+       "layout": {
+        "template": {
+         "data": {
+          "bar": [
+           {
+            "error_x": {
+             "color": "#2a3f5f"
+            },
+            "error_y": {
+             "color": "#2a3f5f"
+            },
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             }
+            },
+            "type": "bar"
+           }
+          ],
+          "barpolar": [
+           {
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             }
+            },
+            "type": "barpolar"
+           }
+          ],
+          "carpet": [
+           {
+            "aaxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "baxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "type": "carpet"
+           }
+          ],
+          "choropleth": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "choropleth"
+           }
+          ],
+          "contour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "contour"
+           }
+          ],
+          "contourcarpet": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "contourcarpet"
+           }
+          ],
+          "heatmap": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmap"
+           }
+          ],
+          "heatmapgl": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmapgl"
+           }
+          ],
+          "histogram": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "histogram"
+           }
+          ],
+          "histogram2d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2d"
+           }
+          ],
+          "histogram2dcontour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2dcontour"
+           }
+          ],
+          "mesh3d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "mesh3d"
+           }
+          ],
+          "parcoords": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "parcoords"
+           }
+          ],
+          "pie": [
+           {
+            "automargin": true,
+            "type": "pie"
+           }
+          ],
+          "scatter": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatter"
+           }
+          ],
+          "scatter3d": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatter3d"
+           }
+          ],
+          "scattercarpet": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattercarpet"
+           }
+          ],
+          "scattergeo": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergeo"
+           }
+          ],
+          "scattergl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergl"
+           }
+          ],
+          "scattermapbox": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattermapbox"
+           }
+          ],
+          "scatterpolar": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolar"
+           }
+          ],
+          "scatterpolargl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolargl"
+           }
+          ],
+          "scatterternary": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterternary"
+           }
+          ],
+          "surface": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "surface"
+           }
+          ],
+          "table": [
+           {
+            "cells": {
+             "fill": {
+              "color": "#EBF0F8"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "header": {
+             "fill": {
+              "color": "#C8D4E3"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "type": "table"
+           }
+          ]
+         },
+         "layout": {
+          "annotationdefaults": {
+           "arrowcolor": "#2a3f5f",
+           "arrowhead": 0,
+           "arrowwidth": 1
+          },
+          "autotypenumbers": "strict",
+          "coloraxis": {
+           "colorbar": {
+            "outlinewidth": 0,
+            "ticks": ""
+           }
+          },
+          "colorscale": {
+           "diverging": [
+            [
+             0,
+             "#8e0152"
+            ],
+            [
+             0.1,
+             "#c51b7d"
+            ],
+            [
+             0.2,
+             "#de77ae"
+            ],
+            [
+             0.3,
+             "#f1b6da"
+            ],
+            [
+             0.4,
+             "#fde0ef"
+            ],
+            [
+             0.5,
+             "#f7f7f7"
+            ],
+            [
+             0.6,
+             "#e6f5d0"
+            ],
+            [
+             0.7,
+             "#b8e186"
+            ],
+            [
+             0.8,
+             "#7fbc41"
+            ],
+            [
+             0.9,
+             "#4d9221"
+            ],
+            [
+             1,
+             "#276419"
+            ]
+           ],
+           "sequential": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ],
+           "sequentialminus": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ]
+          },
+          "colorway": [
+           "#636efa",
+           "#EF553B",
+           "#00cc96",
+           "#ab63fa",
+           "#FFA15A",
+           "#19d3f3",
+           "#FF6692",
+           "#B6E880",
+           "#FF97FF",
+           "#FECB52"
+          ],
+          "font": {
+           "color": "#2a3f5f"
+          },
+          "geo": {
+           "bgcolor": "white",
+           "lakecolor": "white",
+           "landcolor": "#E5ECF6",
+           "showlakes": true,
+           "showland": true,
+           "subunitcolor": "white"
+          },
+          "hoverlabel": {
+           "align": "left"
+          },
+          "hovermode": "closest",
+          "mapbox": {
+           "style": "light"
+          },
+          "paper_bgcolor": "white",
+          "plot_bgcolor": "#E5ECF6",
+          "polar": {
+           "angularaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "radialaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "scene": {
+           "xaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "yaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "zaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           }
+          },
+          "shapedefaults": {
+           "line": {
+            "color": "#2a3f5f"
+           }
+          },
+          "ternary": {
+           "aaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "baxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "caxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "title": {
+           "x": 0.05
+          },
+          "xaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          },
+          "yaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          }
+         }
+        },
+        "title": {
+         "text": "IDs provided by providers"
+        },
+        "xaxis": {
+         "tickangle": 45,
+         "tickfont": {
+          "size": 12
+         }
+        }
+       }
+      },
+      "text/html": [
+       "<div>                            <div id=\"874e7b29-a69b-483e-ab13-ee22b3def40e\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"874e7b29-a69b-483e-ab13-ee22b3def40e\")) {                    Plotly.newPlot(                        \"874e7b29-a69b-483e-ab13-ee22b3def40e\",                        [{\"type\": \"bar\", \"x\": [\"scopus author id\", \"researcherid\", \"loop profile\", \"ci\\u00eancia id\", \"researcher name resolver id\", \"\\u4e2d\\u56fd\\u79d1\\u5b66\\u5bb6\\u5728\\u7ebf\", \"sciprofile\", \"isni\", \"gnd\", \"pitt id\", \"technical university of denmark cwis\", \"researcher id\", \"id dialnet\", \"digital author id\", \"scopus author id: \", \"authenticusid\", \"hku researcherpage\", \"uow scholars\", \"cti vitae\", \"scopus author id:\", \"hkust profile\", \"chalmers id\", \"scopus  id\", \"iauthor\", \"google scholar\", \"digital author id (dai)\", \"authid\", \"dai\", \"us epa vivo\", \"scopus id\", \"authenticus\", \"smithsonian profiles\", \"github\", \"escientist\", \"vivo cornell\", \"researcherid:\", \"id dialnet:\", \"dialnet id\", \"sciprofiles\", \"kaken\", \"une researcher id\", \"researcherid: \", \"orcid\", \"scienceopen\", \"profile system identifier\", \"orcid id\", \"custom\"], \"y\": [1030807, 544825, 117325, 36666, 7907, 4804, 4411, 3075, 2954, 2674, 2483, 1445, 1168, 1124, 1077, 869, 741, 646, 581, 548, 522, 430, 254, 212, 200, 177, 175, 155, 146, 127, 83, 61, 51, 49, 46, 39, 7, 6, 5, 5, 4, 3, 2, 1, 1, 1, 1]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"IDs provided by providers\"}, \"xaxis\": {\"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "                            \n",
+       "var gd = document.getElementById('874e7b29-a69b-483e-ab13-ee22b3def40e');\n",
+       "var x = new MutationObserver(function (mutations, observer) {{\n",
+       "        var display = window.getComputedStyle(gd).display;\n",
+       "        if (!display || display === 'none') {{\n",
+       "            console.log([gd, 'removed!']);\n",
+       "            Plotly.purge(gd);\n",
+       "            observer.disconnect();\n",
+       "        }}\n",
+       "}});\n",
        "\n",
-       "                                            employment n_works  \\\n",
-       "1                                                  NaN       4   \n",
-       "2    [[responsible for the Project Service Level Ag...      20   \n",
-       "3    [[General Coordinator- University of Alberta C...      43   \n",
-       "4                                                  NaN      67   \n",
-       "5    [[Director, Educational Development, Strathmor...       4   \n",
-       "..                                                 ...     ...   \n",
-       "132  [[Adjunct Professor, James Cook University, To...     352   \n",
-       "133  [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2...      11   \n",
-       "134  [[Profesora, Universidad Nacional de La Matanz...       7   \n",
-       "136  [[Membership, Paguyuban Pelestarian Budaya Ban...       2   \n",
-       "138                                                NaN       3   \n",
-       "\n",
-       "                        works_source  primary_email_domain  \\\n",
-       "1          Phòng khám tư nhân Hà Nội                   NaN   \n",
-       "2           Juan Carlos Garcia Hoyos                   NaN   \n",
-       "3                    Ananda Majumdar                   NaN   \n",
-       "4     JAS (Jurnal Akuntansi Syariah)                   NaN   \n",
-       "5           Caroline Wanjiru Kariuki                   NaN   \n",
-       "..                               ...                   ...   \n",
-       "132                  Susan Hawthorne                   NaN   \n",
-       "133  JUAN DE DIOS BELTR´´ÁN MANCILLA                   NaN   \n",
-       "134         Vanesa Natalia Rodriguez                   NaN   \n",
-       "136                   Benny Soewandi                   NaN   \n",
-       "138                       FENGZHI WU                   NaN   \n",
-       "\n",
-       "    other_email_domains n_emails  \\\n",
-       "1                   NaN      NaN   \n",
-       "2                   NaN      NaN   \n",
-       "3                   NaN      NaN   \n",
-       "4                   NaN      NaN   \n",
-       "5                   NaN      NaN   \n",
-       "..                  ...      ...   \n",
-       "132                 NaN      NaN   \n",
-       "133                 NaN      NaN   \n",
-       "134                 NaN      NaN   \n",
-       "136                 NaN      NaN   \n",
-       "138                 NaN      NaN   \n",
+       "// Listen for the removal of the full notebook cells\n",
+       "var notebookContainer = gd.closest('#notebook-container');\n",
+       "if (notebookContainer) {{\n",
+       "    x.observe(notebookContainer, {childList: true});\n",
+       "}}\n",
        "\n",
-       "                                           url_domains  n_urls  \n",
-       "1    [onhealth.vn, onhealth.vn, onhealth.vn, onheal...    49.0  \n",
-       "2    [af.mil, gst.com, govtribe.com, sbir.gov, open...    28.0  \n",
-       "3    [grfdt.com, linkedin.com, academia.edu, resear...    24.0  \n",
-       "4    [stiesyariahbengkalis.ac.id, lipi.go.id, cross...    17.0  \n",
-       "5    [scopus.com, mendeley.com, publons.com, resear...    13.0  \n",
-       "..                                                 ...     ...  \n",
-       "132  [spinifexpress.com.au, linkedin.com, twitter.c...    12.0  \n",
-       "133  [yumpu.com, ijopm.org, google.com, blogspot.co...    69.0  \n",
-       "134  [unlam.edu.ar, unirioja.es, amazon.fr, abebook...    19.0  \n",
-       "136  [wordpress.com, wordpress.com, linkedin.com, f...    11.0  \n",
-       "138  [springer.com, sciencedirect.com, sciencedirec...    23.0  \n",
+       "// Listen for the clearing of the current output cell\n",
+       "var outputEl = gd.closest('.output');\n",
+       "if (outputEl) {{\n",
+       "    x.observe(outputEl, {childList: true});\n",
+       "}}\n",
        "\n",
-       "[108 rows x 22 columns]"
+       "                        })                };                });            </script>        </div>"
       ]
      },
-     "execution_count": 51,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
     }
    ],
    "source": [
-    "exploded_sources[exploded_sources.apply(lambda x: x['works_source'].find(x['given_names']) >= 0, axis=1)]"
+    "data = [\n",
+    "    go.Bar(\n",
+    "        x=ids.groupby('provider').count().sort_values('orcid', ascending=False).index,\n",
+    "        y=ids.groupby('provider').count().sort_values('orcid', ascending=False)['orcid']\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "layout = go.Layout(\n",
+    "    title='IDs provided by providers',\n",
+    "    xaxis=dict(tickangle=45, tickfont=dict(size=12))\n",
+    ")\n",
+    "fig = go.Figure(data=data, layout=layout)\n",
+    "plotly.offline.iplot(fig)"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 56,
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([nan, 'loop profile', 'scopus author id', 'researcherid',\n",
+       "       'scopus author id: ', 'gnd', 'isni', 'ciência id', 'pitt id',\n",
+       "       'id dialnet', 'technical university of denmark cwis',\n",
+       "       'researcher name resolver id', 'scopus author id:',\n",
+       "       'hkust profile', '中国科学家在线', 'cti vitae', 'escientist',\n",
+       "       'researcher id', 'sciprofile', 'digital author id', 'scopus  id',\n",
+       "       'uow scholars', 'authenticusid', 'authenticus', 'authid',\n",
+       "       'hku researcherpage', 'chalmers id', 'iauthor', 'us epa vivo',\n",
+       "       'digital author id (dai)', 'vivo cornell', 'smithsonian profiles',\n",
+       "       'github', 'google scholar', 'scopus id', 'researcherid:', 'dai',\n",
+       "       'kaken', 'orcid id', 'dialnet id', 'profile system identifier',\n",
+       "       'sciprofiles', 'id dialnet:', 'researcherid: ', 'scienceopen',\n",
+       "       'une researcher id', 'custom', 'orcid'], dtype=object)"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "## Works source"
+    "pd.unique(ids['provider'])"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Paste from Miriam"
+    "## Keywords"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## External IDs"
+    "This field is problematic as users can be nasty and put multiple keywords in one as opposed of having different keywords. Look this"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 57,
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['data science ',\n",
+       " 'science of science',\n",
+       " 'scholarly knowledge mining',\n",
+       " 'open science',\n",
+       " 'research infrastructures']"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "External IDs should come from reliable sources. ORCiD registrants cannot add them freely."
+    "df[df['orcid'] == AM]['keywords'].values[0]"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 52,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "df['n_ids'] = df[df['external_ids'].notna()].external_ids.str.len()"
+    "I did a good job. The following instead is dirty"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 58,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "count    1.285292e+06\n",
-       "mean     1.357162e+00\n",
-       "std      6.607097e-01\n",
-       "min      1.000000e+00\n",
-       "25%      1.000000e+00\n",
-       "50%      1.000000e+00\n",
-       "75%      2.000000e+00\n",
-       "max      8.000000e+01\n",
-       "Name: n_ids, dtype: float64"
+       "['open access, open science, libraries, repositories, social web,']"
       ]
      },
-     "execution_count": 53,
+     "execution_count": 58,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df.n_ids.describe()"
+    "df[df['orcid'] == PP]['keywords'].values[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "So the keyword field needs some cleaning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fix_keywords(lst):\n",
+    "        fixed = set()\n",
+    "        for k in lst:\n",
+    "            tokens = set(k.split(','))\n",
+    "#             tokens.remove('')\n",
+    "            for t in tokens:\n",
+    "                fixed.add(str.strip(t))\n",
+    "        fixed.discard('')\n",
+    "        return list(fixed)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['fixed_keywords'] = df[df.keywords.notna()]['keywords'].apply(lambda x: fix_keywords(x))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 61,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>orcid</th>\n",
-       "      <th>claimed</th>\n",
-       "      <th>verified_email</th>\n",
-       "      <th>verified_primary_email</th>\n",
-       "      <th>given_names</th>\n",
-       "      <th>family_name</th>\n",
-       "      <th>biography</th>\n",
-       "      <th>other_names</th>\n",
-       "      <th>urls</th>\n",
-       "      <th>primary_email</th>\n",
-       "      <th>...</th>\n",
-       "      <th>education</th>\n",
-       "      <th>employment</th>\n",
-       "      <th>n_works</th>\n",
-       "      <th>works_source</th>\n",
-       "      <th>primary_email_domain</th>\n",
-       "      <th>other_email_domains</th>\n",
-       "      <th>n_emails</th>\n",
-       "      <th>url_domains</th>\n",
-       "      <th>n_urls</th>\n",
-       "      <th>n_ids</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>9228793</th>\n",
-       "      <td>0000-0002-9554-6633</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>John A</td>\n",
-       "      <td>Williams</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[Aston University profile page, https://resea...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[[, Aston University, Birmingham, , GB, 1722, ...</td>\n",
-       "      <td>91</td>\n",
-       "      <td>[Aston Research Explorer]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[aston.ac.uk]</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>80.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>1 rows × 23 columns</p>\n",
-       "</div>"
-      ],
       "text/plain": [
-       "                       orcid  claimed  verified_email  verified_primary_email  \\\n",
-       "9228793  0000-0002-9554-6633        1               1                       1   \n",
-       "\n",
-       "        given_names family_name biography other_names  \\\n",
-       "9228793      John A    Williams       NaN         NaN   \n",
-       "\n",
-       "                                                      urls primary_email  ...  \\\n",
-       "9228793  [[Aston University profile page, https://resea...           NaN  ...   \n",
-       "\n",
-       "        education                                         employment n_works  \\\n",
-       "9228793       NaN  [[, Aston University, Birmingham, , GB, 1722, ...      91   \n",
-       "\n",
-       "                      works_source primary_email_domain  other_email_domains  \\\n",
-       "9228793  [Aston Research Explorer]                  NaN                  NaN   \n",
-       "\n",
-       "        n_emails    url_domains n_urls  n_ids  \n",
-       "9228793      NaN  [aston.ac.uk]    1.0   80.0  \n",
-       "\n",
-       "[1 rows x 23 columns]"
+       "['open science', 'repositories', 'open access', 'libraries', 'social web']"
       ]
      },
-     "execution_count": 54,
+     "execution_count": 61,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[df.n_ids == df.n_ids.max()]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ids = df[['orcid', 'external_ids']].explode('external_ids').reset_index(drop=True)"
+    "df[df['orcid'] == PP]['fixed_keywords'].values[0]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 62,
    "metadata": {},
    "outputs": [],
    "source": [
-    "ids['provider'] = ids[ids.external_ids.notna()]['external_ids'].apply(lambda x: x[0])"
+    "df['n_keywords'] = df.keywords.str.len()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 63,
    "metadata": {},
    "outputs": [
     {
@@ -10285,66 +10621,99 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>orcid</th>\n",
-       "      <th>external_ids</th>\n",
-       "      <th>provider</th>\n",
+       "      <th>n_keywords</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>0000-0001-5004-4608</td>\n",
-       "      <td>[Scopus Author ID, 40661094300]</td>\n",
-       "      <td>Scopus Author ID</td>\n",
+       "      <th>2851081</th>\n",
+       "      <td>0000-0002-0673-0341</td>\n",
+       "      <td>154.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7344151</th>\n",
+       "      <td>0000-0002-7060-4112</td>\n",
+       "      <td>141.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2235440</th>\n",
+       "      <td>0000-0002-6075-3501</td>\n",
+       "      <td>140.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2994233</th>\n",
+       "      <td>0000-0002-4071-0301</td>\n",
+       "      <td>118.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3971323</th>\n",
+       "      <td>0000-0002-9638-8091</td>\n",
+       "      <td>115.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10916569</th>\n",
+       "      <td>0000-0001-5692-7639</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>24</th>\n",
-       "      <td>0000-0001-5008-2479</td>\n",
-       "      <td>[Scopus Author ID, 12789856200]</td>\n",
-       "      <td>Scopus Author ID</td>\n",
+       "      <th>10916570</th>\n",
+       "      <td>0000-0003-1539-0999</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>25</th>\n",
-       "      <td>0000-0001-5008-2479</td>\n",
-       "      <td>[Ciência ID, 2F1C-479B-B071]</td>\n",
-       "      <td>Ciência ID</td>\n",
+       "      <th>10916571</th>\n",
+       "      <td>0000-0003-2858-5509</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>31</th>\n",
-       "      <td>0000-0001-5010-9539</td>\n",
-       "      <td>[Loop profile, 1098977]</td>\n",
-       "      <td>Loop profile</td>\n",
+       "      <th>10916572</th>\n",
+       "      <td>0000-0003-2438-9500</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>42</th>\n",
-       "      <td>0000-0001-5013-6529</td>\n",
-       "      <td>[Scopus Author ID, 8986698300]</td>\n",
-       "      <td>Scopus Author ID</td>\n",
+       "      <th>10916573</th>\n",
+       "      <td>0000-0003-4119-4772</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>10916574 rows × 2 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                  orcid                     external_ids          provider\n",
-       "13  0000-0001-5004-4608  [Scopus Author ID, 40661094300]  Scopus Author ID\n",
-       "24  0000-0001-5008-2479  [Scopus Author ID, 12789856200]  Scopus Author ID\n",
-       "25  0000-0001-5008-2479     [Ciência ID, 2F1C-479B-B071]        Ciência ID\n",
-       "31  0000-0001-5010-9539          [Loop profile, 1098977]      Loop profile\n",
-       "42  0000-0001-5013-6529   [Scopus Author ID, 8986698300]  Scopus Author ID"
+       "                        orcid  n_keywords\n",
+       "2851081   0000-0002-0673-0341       154.0\n",
+       "7344151   0000-0002-7060-4112       141.0\n",
+       "2235440   0000-0002-6075-3501       140.0\n",
+       "2994233   0000-0002-4071-0301       118.0\n",
+       "3971323   0000-0002-9638-8091       115.0\n",
+       "...                       ...         ...\n",
+       "10916569  0000-0001-5692-7639         NaN\n",
+       "10916570  0000-0003-1539-0999         NaN\n",
+       "10916571  0000-0003-2858-5509         NaN\n",
+       "10916572  0000-0003-2438-9500         NaN\n",
+       "10916573  0000-0003-4119-4772         NaN\n",
+       "\n",
+       "[10916574 rows x 2 columns]"
       ]
      },
-     "execution_count": 79,
+     "execution_count": 63,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "ids[ids.provider.notna()].head()"
+    "df.sort_values('n_keywords', ascending=False)[['orcid', 'n_keywords']]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 92,
+   "execution_count": 64,
    "metadata": {},
    "outputs": [
     {
@@ -10359,108 +10728,208 @@
         {
          "type": "bar",
          "x": [
-          "Scopus Author ID",
-          "ResearcherID",
-          "Loop profile",
-          "Ciência ID",
-          "Researcher Name Resolver ID",
-          "中国科学家在线",
-          "ISNI",
-          "GND",
-          "Pitt ID",
-          "Technical University of Denmark CWIS",
-          "Sciprofile",
-          "Researcher ID",
-          "ID Dialnet",
-          "Digital author ID",
-          "Scopus Author ID: ",
-          "AuthenticusID",
-          "HKU ResearcherPage",
-          "UOW Scholars",
-          "CTI Vitae",
-          "Scopus Author ID:",
-          "HKUST Profile",
-          "Scopus author ID",
-          "Chalmers ID",
-          "Scopus  ID",
-          "iAuthor",
-          "Google Scholar",
-          "AuthID",
-          "DAI",
-          "US EPA VIVO",
-          "Digital Author ID (DAI)",
-          "Scopus ID",
-          "Authenticus",
-          "Smithsonian Profiles",
-          "GitHub",
-          "eScientist",
-          "VIVO Cornell",
-          "ResearcherID:",
-          "Digital Author ID",
-          "Digital author ID (DAI)",
-          "ID Dialnet:",
-          "Dialnet ID",
-          "KAKEN",
-          "UNE Researcher ID",
-          "ResearcherID: ",
-          "ORCID",
-          "Custom",
-          "ORCID iD",
-          "ScienceOpen",
-          "ResearcherId",
-          "Profile system identifier"
+          "0000-0002-0673-0341",
+          "0000-0002-7060-4112",
+          "0000-0002-6075-3501",
+          "0000-0002-4071-0301",
+          "0000-0002-9638-8091",
+          "0000-0002-4235-4259",
+          "0000-0001-9462-5666",
+          "0000-0003-0076-6287",
+          "0000-0002-1878-9762",
+          "0000-0001-6537-7683",
+          "0000-0001-6307-6027",
+          "0000-0003-2273-9888",
+          "0000-0003-1799-0971",
+          "0000-0001-5287-1949",
+          "0000-0002-0937-7061",
+          "0000-0001-9715-9357",
+          "0000-0001-5696-1052",
+          "0000-0003-2998-5520",
+          "0000-0001-5869-2204",
+          "0000-0002-0156-3580",
+          "0000-0002-9625-6742",
+          "0000-0002-8401-8018",
+          "0000-0001-9985-1697",
+          "0000-0003-4246-8579",
+          "0000-0002-7710-0355",
+          "0000-0002-8083-7382",
+          "0000-0001-7654-5013",
+          "0000-0001-6939-3859",
+          "0000-0002-3061-3364",
+          "0000-0003-2509-2549",
+          "0000-0002-0463-0048",
+          "0000-0001-5230-715x",
+          "0000-0001-9336-6850",
+          "0000-0001-5458-7167",
+          "0000-0003-0209-180x",
+          "0000-0003-3584-6834",
+          "0000-0002-8227-5387",
+          "0000-0002-9381-2264",
+          "0000-0003-3340-6413",
+          "0000-0002-2935-1934",
+          "0000-0002-8644-8396",
+          "0000-0002-3123-3021",
+          "0000-0002-8659-6321",
+          "0000-0002-8449-2211",
+          "0000-0001-5167-7466",
+          "0000-0001-5637-1124",
+          "0000-0003-2532-2906",
+          "0000-0003-4673-1063",
+          "0000-0003-4608-3844",
+          "0000-0002-3532-043x",
+          "0000-0002-6347-9464",
+          "0000-0003-4505-3678",
+          "0000-0002-2683-4527",
+          "0000-0003-4374-6374",
+          "0000-0003-4511-7942",
+          "0000-0002-1103-9651",
+          "0000-0001-9280-6017",
+          "0000-0003-3720-1183",
+          "0000-0001-9586-0780",
+          "0000-0002-5306-7781",
+          "0000-0003-2218-1343",
+          "0000-0002-8499-1045",
+          "0000-0003-1863-0265",
+          "0000-0002-5539-1761",
+          "0000-0003-2550-1859",
+          "0000-0002-8072-1152",
+          "0000-0003-3342-6123",
+          "0000-0001-6861-9561",
+          "0000-0002-2252-672x",
+          "0000-0002-3597-3350",
+          "0000-0002-3907-3552",
+          "0000-0001-8689-185x",
+          "0000-0002-5274-7742",
+          "0000-0002-3186-8860",
+          "0000-0001-6843-9325",
+          "0000-0001-7133-7848",
+          "0000-0003-4486-2684",
+          "0000-0003-3343-5660",
+          "0000-0002-9014-2090",
+          "0000-0002-6282-0640",
+          "0000-0001-7857-4133",
+          "0000-0002-1294-2156",
+          "0000-0002-4432-3448",
+          "0000-0003-0097-4182",
+          "0000-0003-1245-7705",
+          "0000-0001-8445-412x",
+          "0000-0003-4153-6779",
+          "0000-0002-9125-6022",
+          "0000-0002-4598-2891",
+          "0000-0003-3387-3193",
+          "0000-0002-3866-6460",
+          "0000-0002-1411-3028",
+          "0000-0003-4283-2895",
+          "0000-0002-0211-7195",
+          "0000-0002-3898-9542",
+          "0000-0002-1545-7818",
+          "0000-0002-4963-9345",
+          "0000-0002-1770-9660",
+          "0000-0002-1960-5857",
+          "0000-0003-2054-477x"
          ],
          "y": [
-          1015175,
-          543545,
-          114316,
-          33870,
-          7810,
-          4794,
-          3054,
-          2825,
-          2672,
-          2486,
-          2441,
-          1417,
-          1167,
-          1079,
-          1076,
-          847,
-          740,
-          644,
-          581,
-          549,
-          521,
-          501,
-          430,
-          232,
-          212,
-          200,
-          175,
-          153,
-          146,
-          135,
-          127,
+          154,
+          141,
+          140,
+          118,
+          115,
+          104,
+          98,
+          94,
+          92,
+          91,
+          88,
+          86,
+          84,
           82,
+          78,
+          77,
+          76,
+          75,
+          74,
+          73,
+          71,
+          70,
+          69,
+          66,
+          64,
+          62,
           61,
+          60,
+          58,
+          57,
+          56,
+          54,
+          53,
+          53,
+          52,
+          51,
           51,
+          51,
+          51,
+          50,
+          50,
+          50,
+          50,
+          49,
+          49,
           49,
+          48,
+          48,
+          48,
+          48,
+          48,
+          48,
+          48,
+          47,
+          47,
+          46,
           46,
+          46,
+          45,
+          44,
+          44,
+          44,
+          44,
+          44,
+          44,
+          43,
+          43,
+          42,
+          42,
+          42,
+          42,
+          42,
+          42,
+          42,
+          41,
+          41,
+          41,
+          41,
+          41,
+          41,
+          40,
+          40,
+          40,
+          40,
+          40,
+          40,
           39,
-          35,
-          34,
-          7,
-          6,
-          5,
-          4,
-          3,
-          2,
-          1,
-          1,
-          1,
-          1,
-          1
+          39,
+          39,
+          39,
+          39,
+          39,
+          39,
+          39,
+          39,
+          39,
+          38,
+          38,
+          38,
+          38
          ]
         }
        ],
@@ -11270,563 +11739,204 @@
            "zerolinewidth": 2
           }
          }
-        },
-        "title": {
-         "text": "IDs provided by providers"
-        },
-        "xaxis": {
-         "tickangle": 45,
-         "tickfont": {
-          "size": 12
-         }
-        }
-       }
-      },
-      "text/html": [
-       "<div>                            <div id=\"75ecdbc2-db15-4f4c-bfe4-0915b9b9f26b\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"75ecdbc2-db15-4f4c-bfe4-0915b9b9f26b\")) {                    Plotly.newPlot(                        \"75ecdbc2-db15-4f4c-bfe4-0915b9b9f26b\",                        [{\"type\": \"bar\", \"x\": [\"Scopus Author ID\", \"ResearcherID\", \"Loop profile\", \"Ci\\u00eancia ID\", \"Researcher Name Resolver ID\", \"\\u4e2d\\u56fd\\u79d1\\u5b66\\u5bb6\\u5728\\u7ebf\", \"ISNI\", \"GND\", \"Pitt ID\", \"Technical University of Denmark CWIS\", \"Sciprofile\", \"Researcher ID\", \"ID Dialnet\", \"Digital author ID\", \"Scopus Author ID: \", \"AuthenticusID\", \"HKU ResearcherPage\", \"UOW Scholars\", \"CTI Vitae\", \"Scopus Author ID:\", \"HKUST Profile\", \"Scopus author ID\", \"Chalmers ID\", \"Scopus  ID\", \"iAuthor\", \"Google Scholar\", \"AuthID\", \"DAI\", \"US EPA VIVO\", \"Digital Author ID (DAI)\", \"Scopus ID\", \"Authenticus\", \"Smithsonian Profiles\", \"GitHub\", \"eScientist\", \"VIVO Cornell\", \"ResearcherID:\", \"Digital Author ID\", \"Digital author ID (DAI)\", \"ID Dialnet:\", \"Dialnet ID\", \"KAKEN\", \"UNE Researcher ID\", \"ResearcherID: \", \"ORCID\", \"Custom\", \"ORCID iD\", \"ScienceOpen\", \"ResearcherId\", \"Profile system identifier\"], \"y\": [1015175, 543545, 114316, 33870, 7810, 4794, 3054, 2825, 2672, 2486, 2441, 1417, 1167, 1079, 1076, 847, 740, 644, 581, 549, 521, 501, 430, 232, 212, 200, 175, 153, 146, 135, 127, 82, 61, 51, 49, 46, 39, 35, 34, 7, 6, 5, 4, 3, 2, 1, 1, 1, 1, 1]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"IDs provided by providers\"}, \"xaxis\": {\"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
-       "                            \n",
-       "var gd = document.getElementById('75ecdbc2-db15-4f4c-bfe4-0915b9b9f26b');\n",
-       "var x = new MutationObserver(function (mutations, observer) {{\n",
-       "        var display = window.getComputedStyle(gd).display;\n",
-       "        if (!display || display === 'none') {{\n",
-       "            console.log([gd, 'removed!']);\n",
-       "            Plotly.purge(gd);\n",
-       "            observer.disconnect();\n",
-       "        }}\n",
-       "}});\n",
-       "\n",
-       "// Listen for the removal of the full notebook cells\n",
-       "var notebookContainer = gd.closest('#notebook-container');\n",
-       "if (notebookContainer) {{\n",
-       "    x.observe(notebookContainer, {childList: true});\n",
-       "}}\n",
-       "\n",
-       "// Listen for the clearing of the current output cell\n",
-       "var outputEl = gd.closest('.output');\n",
-       "if (outputEl) {{\n",
-       "    x.observe(outputEl, {childList: true});\n",
-       "}}\n",
-       "\n",
-       "                        })                };                });            </script>        </div>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "data = [\n",
-    "    go.Bar(\n",
-    "        x=ids.groupby('provider').count().sort_values('orcid', ascending=False).index,\n",
-    "        y=ids.groupby('provider').count().sort_values('orcid', ascending=False)['orcid']\n",
-    "    )\n",
-    "]\n",
-    "\n",
-    "layout = go.Layout(\n",
-    "    title='IDs provided by providers',\n",
-    "    xaxis=dict(tickangle=45, tickfont=dict(size=12))\n",
-    ")\n",
-    "fig = go.Figure(data=data, layout=layout)\n",
-    "plotly.offline.iplot(fig)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 81,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([nan, 'Scopus Author ID', 'Ciência ID', 'Loop profile',\n",
-       "       'ResearcherID', 'Researcher Name Resolver ID', 'UOW Scholars',\n",
-       "       '中国科学家在线', 'Pitt ID', 'AuthenticusID', 'Sciprofile', 'GND', 'ISNI',\n",
-       "       'HKU ResearcherPage', 'CTI Vitae', 'Researcher ID', 'ID Dialnet',\n",
-       "       'Digital author ID', 'HKUST Profile',\n",
-       "       'Technical University of Denmark CWIS', 'Scopus Author ID: ',\n",
-       "       'Digital Author ID (DAI)', 'Scopus Author ID:', 'Google Scholar',\n",
-       "       'AuthID', 'Digital Author ID', 'iAuthor', 'US EPA VIVO', 'GitHub',\n",
-       "       'Scopus author ID', 'Chalmers ID', 'Scopus ID', 'Authenticus',\n",
-       "       'VIVO Cornell', 'Scopus  ID', 'ScienceOpen',\n",
-       "       'Smithsonian Profiles', 'ResearcherID:', 'DAI', 'eScientist',\n",
-       "       'KAKEN', 'Digital author ID (DAI)', 'ORCID', 'ID Dialnet:',\n",
-       "       'Dialnet ID', 'UNE Researcher ID', 'ResearcherID: ',\n",
-       "       'Profile system identifier', 'Custom', 'ResearcherId', 'ORCID iD'],\n",
-       "      dtype=object)"
-      ]
-     },
-     "execution_count": 81,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "pd.unique(ids['provider'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Keywords"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This field is problematic as users can be nasty and put multiple keywords in one as opposed of having different keywords. Look this"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 165,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['Data science ',\n",
-       " 'science of science',\n",
-       " 'scholarly knowledge mining',\n",
-       " 'open science',\n",
-       " 'research infrastructures']"
-      ]
-     },
-     "execution_count": 165,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df[df['orcid'] == AM]['keywords'].values[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "I did a good job. The following instead is dirty"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 166,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['open access, open science, libraries, repositories, social web,']"
-      ]
-     },
-     "execution_count": 166,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df[df['orcid'] == PP]['keywords'].values[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "So the keyword field needs some cleaning"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 197,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def fix_keywords(lst):\n",
-    "        fixed = set()\n",
-    "        for k in lst:\n",
-    "            tokens = set(k.split(','))\n",
-    "#             tokens.remove('')\n",
-    "            for t in tokens:\n",
-    "                fixed.add(str.strip(t))\n",
-    "        fixed.discard('')\n",
-    "        return list(fixed)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 199,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['fixed_keywords'] = df[df.keywords.notna()]['keywords'].apply(lambda x: fix_keywords(x))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 200,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['open science', 'open access', 'repositories', 'libraries', 'social web']"
+        },
+        "title": {
+         "text": "Keywords provided by ORCiD"
+        },
+        "xaxis": {
+         "range": [
+          -0.5,
+          99.5
+         ],
+         "tickangle": 45,
+         "tickfont": {
+          "size": 12
+         }
+        }
+       }
+      },
+      "text/html": [
+       "<div>                            <div id=\"9c9248f9-2926-487d-99ef-f05923c1f6bf\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"9c9248f9-2926-487d-99ef-f05923c1f6bf\")) {                    Plotly.newPlot(                        \"9c9248f9-2926-487d-99ef-f05923c1f6bf\",                        [{\"type\": \"bar\", \"x\": [\"0000-0002-0673-0341\", \"0000-0002-7060-4112\", \"0000-0002-6075-3501\", \"0000-0002-4071-0301\", \"0000-0002-9638-8091\", \"0000-0002-4235-4259\", \"0000-0001-9462-5666\", \"0000-0003-0076-6287\", \"0000-0002-1878-9762\", \"0000-0001-6537-7683\", \"0000-0001-6307-6027\", \"0000-0003-2273-9888\", \"0000-0003-1799-0971\", \"0000-0001-5287-1949\", \"0000-0002-0937-7061\", \"0000-0001-9715-9357\", \"0000-0001-5696-1052\", \"0000-0003-2998-5520\", \"0000-0001-5869-2204\", \"0000-0002-0156-3580\", \"0000-0002-9625-6742\", \"0000-0002-8401-8018\", \"0000-0001-9985-1697\", \"0000-0003-4246-8579\", \"0000-0002-7710-0355\", \"0000-0002-8083-7382\", \"0000-0001-7654-5013\", \"0000-0001-6939-3859\", \"0000-0002-3061-3364\", \"0000-0003-2509-2549\", \"0000-0002-0463-0048\", \"0000-0001-5230-715x\", \"0000-0001-9336-6850\", \"0000-0001-5458-7167\", \"0000-0003-0209-180x\", \"0000-0003-3584-6834\", \"0000-0002-8227-5387\", \"0000-0002-9381-2264\", \"0000-0003-3340-6413\", \"0000-0002-2935-1934\", \"0000-0002-8644-8396\", \"0000-0002-3123-3021\", \"0000-0002-8659-6321\", \"0000-0002-8449-2211\", \"0000-0001-5167-7466\", \"0000-0001-5637-1124\", \"0000-0003-2532-2906\", \"0000-0003-4673-1063\", \"0000-0003-4608-3844\", \"0000-0002-3532-043x\", \"0000-0002-6347-9464\", \"0000-0003-4505-3678\", \"0000-0002-2683-4527\", \"0000-0003-4374-6374\", \"0000-0003-4511-7942\", \"0000-0002-1103-9651\", \"0000-0001-9280-6017\", \"0000-0003-3720-1183\", \"0000-0001-9586-0780\", \"0000-0002-5306-7781\", \"0000-0003-2218-1343\", \"0000-0002-8499-1045\", \"0000-0003-1863-0265\", \"0000-0002-5539-1761\", \"0000-0003-2550-1859\", \"0000-0002-8072-1152\", \"0000-0003-3342-6123\", \"0000-0001-6861-9561\", \"0000-0002-2252-672x\", \"0000-0002-3597-3350\", \"0000-0002-3907-3552\", \"0000-0001-8689-185x\", \"0000-0002-5274-7742\", \"0000-0002-3186-8860\", \"0000-0001-6843-9325\", \"0000-0001-7133-7848\", \"0000-0003-4486-2684\", \"0000-0003-3343-5660\", \"0000-0002-9014-2090\", \"0000-0002-6282-0640\", \"0000-0001-7857-4133\", \"0000-0002-1294-2156\", \"0000-0002-4432-3448\", \"0000-0003-0097-4182\", \"0000-0003-1245-7705\", \"0000-0001-8445-412x\", \"0000-0003-4153-6779\", \"0000-0002-9125-6022\", \"0000-0002-4598-2891\", \"0000-0003-3387-3193\", \"0000-0002-3866-6460\", \"0000-0002-1411-3028\", \"0000-0003-4283-2895\", \"0000-0002-0211-7195\", \"0000-0002-3898-9542\", \"0000-0002-1545-7818\", \"0000-0002-4963-9345\", \"0000-0002-1770-9660\", \"0000-0002-1960-5857\", \"0000-0003-2054-477x\"], \"y\": [154.0, 141.0, 140.0, 118.0, 115.0, 104.0, 98.0, 94.0, 92.0, 91.0, 88.0, 86.0, 84.0, 82.0, 78.0, 77.0, 76.0, 75.0, 74.0, 73.0, 71.0, 70.0, 69.0, 66.0, 64.0, 62.0, 61.0, 60.0, 58.0, 57.0, 56.0, 54.0, 53.0, 53.0, 52.0, 51.0, 51.0, 51.0, 51.0, 50.0, 50.0, 50.0, 50.0, 49.0, 49.0, 49.0, 48.0, 48.0, 48.0, 48.0, 48.0, 48.0, 48.0, 47.0, 47.0, 46.0, 46.0, 46.0, 45.0, 44.0, 44.0, 44.0, 44.0, 44.0, 44.0, 43.0, 43.0, 42.0, 42.0, 42.0, 42.0, 42.0, 42.0, 42.0, 41.0, 41.0, 41.0, 41.0, 41.0, 41.0, 40.0, 40.0, 40.0, 40.0, 40.0, 40.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 38.0, 38.0, 38.0, 38.0]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Keywords provided by ORCiD\"}, \"xaxis\": {\"range\": [-0.5, 99.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "                            \n",
+       "var gd = document.getElementById('9c9248f9-2926-487d-99ef-f05923c1f6bf');\n",
+       "var x = new MutationObserver(function (mutations, observer) {{\n",
+       "        var display = window.getComputedStyle(gd).display;\n",
+       "        if (!display || display === 'none') {{\n",
+       "            console.log([gd, 'removed!']);\n",
+       "            Plotly.purge(gd);\n",
+       "            observer.disconnect();\n",
+       "        }}\n",
+       "}});\n",
+       "\n",
+       "// Listen for the removal of the full notebook cells\n",
+       "var notebookContainer = gd.closest('#notebook-container');\n",
+       "if (notebookContainer) {{\n",
+       "    x.observe(notebookContainer, {childList: true});\n",
+       "}}\n",
+       "\n",
+       "// Listen for the clearing of the current output cell\n",
+       "var outputEl = gd.closest('.output');\n",
+       "if (outputEl) {{\n",
+       "    x.observe(outputEl, {childList: true});\n",
+       "}}\n",
+       "\n",
+       "                        })                };                });            </script>        </div>"
       ]
      },
-     "execution_count": 200,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
     }
    ],
    "source": [
-    "df[df['orcid'] == PP]['fixed_keywords'].values[0]"
+    "set_top_n(100)\n",
+    "data = [\n",
+    "    go.Bar(\n",
+    "        x=df.sort_values('n_keywords', ascending=False)['orcid'][:TOP_N],\n",
+    "        y=df.sort_values('n_keywords', ascending=False)['n_keywords'][:TOP_N]\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "layout = go.Layout(\n",
+    "    title='Keywords provided by ORCiD',\n",
+    "    xaxis=dict(tickangle=45, tickfont=dict(size=12), range=TOP_RANGE)\n",
+    ")\n",
+    "fig = go.Figure(data=data, layout=layout)\n",
+    "plotly.offline.iplot(fig)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 201,
+   "execution_count": 65,
    "metadata": {},
    "outputs": [],
    "source": [
-    "df['n_keywords'] = df.keywords.str.len()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 83,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>orcid</th>\n",
-       "      <th>n_keywords</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1681310</th>\n",
-       "      <td>0000-0002-0673-0341</td>\n",
-       "      <td>154.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7717699</th>\n",
-       "      <td>0000-0002-7060-4112</td>\n",
-       "      <td>141.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4597674</th>\n",
-       "      <td>0000-0002-6075-3501</td>\n",
-       "      <td>140.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2066580</th>\n",
-       "      <td>0000-0002-4071-0301</td>\n",
-       "      <td>118.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3531030</th>\n",
-       "      <td>0000-0002-9638-8091</td>\n",
-       "      <td>115.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10747035</th>\n",
-       "      <td>0000-0003-4998-1551</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10747036</th>\n",
-       "      <td>0000-0003-4998-4111</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10747037</th>\n",
-       "      <td>0000-0003-4998-6045</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10747038</th>\n",
-       "      <td>0000-0003-4998-8868</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10747039</th>\n",
-       "      <td>0000-0003-4999-7916</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>10744621 rows × 2 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                        orcid  n_keywords\n",
-       "1681310   0000-0002-0673-0341       154.0\n",
-       "7717699   0000-0002-7060-4112       141.0\n",
-       "4597674   0000-0002-6075-3501       140.0\n",
-       "2066580   0000-0002-4071-0301       118.0\n",
-       "3531030   0000-0002-9638-8091       115.0\n",
-       "...                       ...         ...\n",
-       "10747035  0000-0003-4998-1551         NaN\n",
-       "10747036  0000-0003-4998-4111         NaN\n",
-       "10747037  0000-0003-4998-6045         NaN\n",
-       "10747038  0000-0003-4998-8868         NaN\n",
-       "10747039  0000-0003-4999-7916         NaN\n",
-       "\n",
-       "[10744621 rows x 2 columns]"
-      ]
-     },
-     "execution_count": 83,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.sort_values('n_keywords', ascending=False)[['orcid', 'n_keywords']]"
+    "grouped_keywords = df[['orcid', 'keywords']]\\\n",
+    "                .explode('keywords')\\\n",
+    "                .reset_index(drop=True)\\\n",
+    "                .groupby('keywords')\\\n",
+    "                .count()\\\n",
+    "                .sort_values('orcid', ascending=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 205,
+   "execution_count": 66,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.plotly.v1+json": {
-       "config": {
-        "linkText": "Export to plot.ly",
-        "plotlyServerURL": "https://plot.ly",
-        "showLink": false
-       },
-       "data": [
-        {
-         "type": "bar",
-         "x": [
-          "0000-0002-0673-0341",
-          "0000-0002-7060-4112",
-          "0000-0002-6075-3501",
-          "0000-0002-4071-0301",
-          "0000-0002-9638-8091",
-          "0000-0002-4235-4259",
-          "0000-0001-9462-5666",
-          "0000-0003-0076-6287",
-          "0000-0002-1878-9762",
-          "0000-0001-6537-7683",
-          "0000-0001-6307-6027",
-          "0000-0003-2273-9888",
-          "0000-0003-1799-0971",
-          "0000-0001-5287-1949",
-          "0000-0002-0937-7061",
-          "0000-0001-9715-9357",
-          "0000-0001-5696-1052",
-          "0000-0003-2998-5520",
-          "0000-0001-5869-2204",
-          "0000-0002-0156-3580",
-          "0000-0002-9625-6742",
-          "0000-0002-8401-8018",
-          "0000-0001-9985-1697",
-          "0000-0003-4246-8579",
-          "0000-0002-7710-0355",
-          "0000-0002-8083-7382",
-          "0000-0001-7654-5013",
-          "0000-0001-6939-3859",
-          "0000-0002-3061-3364",
-          "0000-0003-2509-2549",
-          "0000-0002-0463-0048",
-          "0000-0001-5230-715X",
-          "0000-0001-9336-6850",
-          "0000-0001-5458-7167",
-          "0000-0003-0209-180X",
-          "0000-0003-3584-6834",
-          "0000-0002-9381-2264",
-          "0000-0002-8227-5387",
-          "0000-0003-3340-6413",
-          "0000-0002-2935-1934",
-          "0000-0002-3123-3021",
-          "0000-0002-8659-6321",
-          "0000-0002-8644-8396",
-          "0000-0001-5637-1124",
-          "0000-0002-8449-2211",
-          "0000-0001-5167-7466",
-          "0000-0003-4608-3844",
-          "0000-0002-2683-4527",
-          "0000-0002-6347-9464",
-          "0000-0003-4505-3678",
-          "0000-0002-3532-043X",
-          "0000-0003-2532-2906",
-          "0000-0003-4511-7942",
-          "0000-0003-4374-6374",
-          "0000-0003-3720-1183",
-          "0000-0002-1103-9651",
-          "0000-0001-9280-6017",
-          "0000-0003-4673-1063",
-          "0000-0001-9586-0780",
-          "0000-0003-2218-1343",
-          "0000-0003-2550-1859",
-          "0000-0002-5539-1761",
-          "0000-0002-8499-1045",
-          "0000-0002-5306-7781",
-          "0000-0003-1863-0265",
-          "0000-0003-3342-6123",
-          "0000-0002-8072-1152",
-          "0000-0002-3907-3552",
-          "0000-0001-6861-9561",
-          "0000-0002-5274-7742",
-          "0000-0002-3597-3350",
-          "0000-0002-3186-8860",
-          "0000-0002-2252-672X",
-          "0000-0001-6843-9325",
-          "0000-0002-9014-2090",
-          "0000-0003-4486-2684",
-          "0000-0003-3343-5660",
-          "0000-0001-8689-185X",
-          "0000-0001-7133-7848",
-          "0000-0002-6282-0640",
-          "0000-0002-1294-2156",
-          "0000-0001-7857-4133",
-          "0000-0003-1245-7705",
-          "0000-0002-4432-3448",
-          "0000-0003-0097-4182",
-          "0000-0001-8445-412X",
-          "0000-0002-3866-6460",
-          "0000-0003-4153-6779",
-          "0000-0002-1545-7818",
-          "0000-0003-3387-3193",
-          "0000-0002-4598-2891",
-          "0000-0002-3898-9542",
-          "0000-0002-0211-7195",
-          "0000-0003-4283-2895",
-          "0000-0002-1411-3028",
-          "0000-0002-9125-6022",
-          "0000-0003-2640-6757",
-          "0000-0002-1960-5857",
-          "0000-0002-4963-9345",
-          "0000-0002-1770-9660"
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.plotly.v1+json": {
+       "config": {
+        "linkText": "Export to plot.ly",
+        "plotlyServerURL": "https://plot.ly",
+        "showLink": false
+       },
+       "data": [
+        {
+         "type": "bar",
+         "x": [
+          "machine learning",
+          "bioinformatics",
+          "molecular biology",
+          "artificial intelligence",
+          "education",
+          "epidemiology",
+          "neuroscience",
+          "public health",
+          "cancer",
+          "immunology",
+          "microbiology",
+          "ecology",
+          "remote sensing",
+          "genetics",
+          "climate change",
+          "deep learning",
+          "genomics",
+          "biochemistry",
+          "data science",
+          "computer vision",
+          "psychology",
+          "sustainability",
+          "biotechnology",
+          "nanotechnology",
+          "robotics",
+          "data mining",
+          "statistics",
+          "image processing",
+          "gis",
+          "nutrition",
+          "chemistry",
+          "optimization",
+          "computer science",
+          "marketing",
+          "biomaterials",
+          "nanomaterials",
+          "renewable energy",
+          "organic chemistry",
+          "electrochemistry",
+          "educação",
+          "diabetes",
+          "analytical chemistry",
+          "innovation",
+          "materials science",
+          "mass spectrometry",
+          "architecture",
+          "evolution",
+          "epigenetics",
+          "physics",
+          "biomechanics"
          ],
          "y": [
-          154,
-          141,
-          140,
-          118,
-          115,
-          104,
-          98,
-          94,
-          92,
-          91,
-          88,
-          86,
-          84,
-          82,
-          78,
-          77,
-          76,
-          75,
-          74,
-          73,
-          71,
-          70,
-          69,
-          66,
-          64,
-          62,
-          61,
-          60,
-          58,
-          57,
-          56,
-          54,
-          53,
-          53,
-          52,
-          51,
-          51,
-          51,
-          51,
-          50,
-          50,
-          50,
-          50,
-          49,
-          49,
-          49,
-          48,
-          48,
-          48,
-          48,
-          48,
-          48,
-          47,
-          47,
-          46,
-          46,
-          46,
-          45,
-          45,
-          44,
-          44,
-          44,
-          44,
-          44,
-          44,
-          43,
-          43,
-          42,
-          42,
-          42,
-          42,
-          42,
-          42,
-          41,
-          41,
-          41,
-          41,
-          41,
-          41,
-          41,
-          40,
-          40,
-          40,
-          40,
-          40,
-          40,
-          39,
-          39,
-          39,
-          39,
-          39,
-          39,
-          39,
-          39,
-          39,
-          39,
-          38,
-          38,
-          38,
-          38
+          5090,
+          3299,
+          2377,
+          2322,
+          2218,
+          2121,
+          2010,
+          1973,
+          1956,
+          1829,
+          1805,
+          1788,
+          1688,
+          1648,
+          1621,
+          1485,
+          1451,
+          1398,
+          1363,
+          1339,
+          1331,
+          1313,
+          1298,
+          1294,
+          1149,
+          1135,
+          1134,
+          1104,
+          1075,
+          1071,
+          1064,
+          1042,
+          1037,
+          1030,
+          1013,
+          1010,
+          1005,
+          977,
+          977,
+          959,
+          958,
+          953,
+          937,
+          917,
+          910,
+          895,
+          892,
+          884,
+          883,
+          882
          ]
         }
        ],
@@ -12638,13 +12748,9 @@
          }
         },
         "title": {
-         "text": "Keywords provided"
+         "text": "Top-50 keywords occurrence"
         },
         "xaxis": {
-         "range": [
-          -0.5,
-          99.5
-         ],
          "tickangle": 45,
          "tickfont": {
           "size": 12
@@ -12653,9 +12759,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"7af8660e-7732-4eb2-b13b-edd7b61397bb\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"7af8660e-7732-4eb2-b13b-edd7b61397bb\")) {                    Plotly.newPlot(                        \"7af8660e-7732-4eb2-b13b-edd7b61397bb\",                        [{\"type\": \"bar\", \"x\": [\"0000-0002-0673-0341\", \"0000-0002-7060-4112\", \"0000-0002-6075-3501\", \"0000-0002-4071-0301\", \"0000-0002-9638-8091\", \"0000-0002-4235-4259\", \"0000-0001-9462-5666\", \"0000-0003-0076-6287\", \"0000-0002-1878-9762\", \"0000-0001-6537-7683\", \"0000-0001-6307-6027\", \"0000-0003-2273-9888\", \"0000-0003-1799-0971\", \"0000-0001-5287-1949\", \"0000-0002-0937-7061\", \"0000-0001-9715-9357\", \"0000-0001-5696-1052\", \"0000-0003-2998-5520\", \"0000-0001-5869-2204\", \"0000-0002-0156-3580\", \"0000-0002-9625-6742\", \"0000-0002-8401-8018\", \"0000-0001-9985-1697\", \"0000-0003-4246-8579\", \"0000-0002-7710-0355\", \"0000-0002-8083-7382\", \"0000-0001-7654-5013\", \"0000-0001-6939-3859\", \"0000-0002-3061-3364\", \"0000-0003-2509-2549\", \"0000-0002-0463-0048\", \"0000-0001-5230-715X\", \"0000-0001-9336-6850\", \"0000-0001-5458-7167\", \"0000-0003-0209-180X\", \"0000-0003-3584-6834\", \"0000-0002-9381-2264\", \"0000-0002-8227-5387\", \"0000-0003-3340-6413\", \"0000-0002-2935-1934\", \"0000-0002-3123-3021\", \"0000-0002-8659-6321\", \"0000-0002-8644-8396\", \"0000-0001-5637-1124\", \"0000-0002-8449-2211\", \"0000-0001-5167-7466\", \"0000-0003-4608-3844\", \"0000-0002-2683-4527\", \"0000-0002-6347-9464\", \"0000-0003-4505-3678\", \"0000-0002-3532-043X\", \"0000-0003-2532-2906\", \"0000-0003-4511-7942\", \"0000-0003-4374-6374\", \"0000-0003-3720-1183\", \"0000-0002-1103-9651\", \"0000-0001-9280-6017\", \"0000-0003-4673-1063\", \"0000-0001-9586-0780\", \"0000-0003-2218-1343\", \"0000-0003-2550-1859\", \"0000-0002-5539-1761\", \"0000-0002-8499-1045\", \"0000-0002-5306-7781\", \"0000-0003-1863-0265\", \"0000-0003-3342-6123\", \"0000-0002-8072-1152\", \"0000-0002-3907-3552\", \"0000-0001-6861-9561\", \"0000-0002-5274-7742\", \"0000-0002-3597-3350\", \"0000-0002-3186-8860\", \"0000-0002-2252-672X\", \"0000-0001-6843-9325\", \"0000-0002-9014-2090\", \"0000-0003-4486-2684\", \"0000-0003-3343-5660\", \"0000-0001-8689-185X\", \"0000-0001-7133-7848\", \"0000-0002-6282-0640\", \"0000-0002-1294-2156\", \"0000-0001-7857-4133\", \"0000-0003-1245-7705\", \"0000-0002-4432-3448\", \"0000-0003-0097-4182\", \"0000-0001-8445-412X\", \"0000-0002-3866-6460\", \"0000-0003-4153-6779\", \"0000-0002-1545-7818\", \"0000-0003-3387-3193\", \"0000-0002-4598-2891\", \"0000-0002-3898-9542\", \"0000-0002-0211-7195\", \"0000-0003-4283-2895\", \"0000-0002-1411-3028\", \"0000-0002-9125-6022\", \"0000-0003-2640-6757\", \"0000-0002-1960-5857\", \"0000-0002-4963-9345\", \"0000-0002-1770-9660\"], \"y\": [154.0, 141.0, 140.0, 118.0, 115.0, 104.0, 98.0, 94.0, 92.0, 91.0, 88.0, 86.0, 84.0, 82.0, 78.0, 77.0, 76.0, 75.0, 74.0, 73.0, 71.0, 70.0, 69.0, 66.0, 64.0, 62.0, 61.0, 60.0, 58.0, 57.0, 56.0, 54.0, 53.0, 53.0, 52.0, 51.0, 51.0, 51.0, 51.0, 50.0, 50.0, 50.0, 50.0, 49.0, 49.0, 49.0, 48.0, 48.0, 48.0, 48.0, 48.0, 48.0, 47.0, 47.0, 46.0, 46.0, 46.0, 45.0, 45.0, 44.0, 44.0, 44.0, 44.0, 44.0, 44.0, 43.0, 43.0, 42.0, 42.0, 42.0, 42.0, 42.0, 42.0, 41.0, 41.0, 41.0, 41.0, 41.0, 41.0, 41.0, 40.0, 40.0, 40.0, 40.0, 40.0, 40.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 39.0, 38.0, 38.0, 38.0, 38.0]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Keywords provided\"}, \"xaxis\": {\"range\": [-0.5, 99.5], \"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"340562d0-8ded-4225-b510-32d718f8ce98\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"340562d0-8ded-4225-b510-32d718f8ce98\")) {                    Plotly.newPlot(                        \"340562d0-8ded-4225-b510-32d718f8ce98\",                        [{\"type\": \"bar\", \"x\": [\"machine learning\", \"bioinformatics\", \"molecular biology\", \"artificial intelligence\", \"education\", \"epidemiology\", \"neuroscience\", \"public health\", \"cancer\", \"immunology\", \"microbiology\", \"ecology\", \"remote sensing\", \"genetics\", \"climate change\", \"deep learning\", \"genomics\", \"biochemistry\", \"data science\", \"computer vision\", \"psychology\", \"sustainability\", \"biotechnology\", \"nanotechnology\", \"robotics\", \"data mining\", \"statistics\", \"image processing\", \"gis\", \"nutrition\", \"chemistry\", \"optimization\", \"computer science\", \"marketing\", \"biomaterials\", \"nanomaterials\", \"renewable energy\", \"organic chemistry\", \"electrochemistry\", \"educa\\u00e7\\u00e3o\", \"diabetes\", \"analytical chemistry\", \"innovation\", \"materials science\", \"mass spectrometry\", \"architecture\", \"evolution\", \"epigenetics\", \"physics\", \"biomechanics\"], \"y\": [5090, 3299, 2377, 2322, 2218, 2121, 2010, 1973, 1956, 1829, 1805, 1788, 1688, 1648, 1621, 1485, 1451, 1398, 1363, 1339, 1331, 1313, 1298, 1294, 1149, 1135, 1134, 1104, 1075, 1071, 1064, 1042, 1037, 1030, 1013, 1010, 1005, 977, 977, 959, 958, 953, 937, 917, 910, 895, 892, 884, 883, 882]}],                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Top-50 keywords occurrence\"}, \"xaxis\": {\"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('7af8660e-7732-4eb2-b13b-edd7b61397bb');\n",
+       "var gd = document.getElementById('340562d0-8ded-4225-b510-32d718f8ce98');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -12684,180 +12790,12 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "set_top_n(100)\n",
-    "data = [\n",
-    "    go.Bar(\n",
-    "        x=df.sort_values('n_keywords', ascending=False)['orcid'][:TOP_N],\n",
-    "        y=df.sort_values('n_keywords', ascending=False)['n_keywords'][:TOP_N]\n",
-    "    )\n",
-    "]\n",
-    "\n",
-    "layout = go.Layout(\n",
-    "    title='Keywords provided by ORCiD',\n",
-    "    xaxis=dict(tickangle=45, tickfont=dict(size=12), range=TOP_RANGE)\n",
-    ")\n",
-    "fig = go.Figure(data=data, layout=layout)\n",
-    "plotly.offline.iplot(fig)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 114,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "grouped_keywords = df[['orcid', 'keywords']]\\\n",
-    "                .explode('keywords')\\\n",
-    "                .reset_index(drop=True)\\\n",
-    "                .groupby('keywords')\\\n",
-    "                .count()\\\n",
-    "                .sort_values('orcid', ascending=False)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 207,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>orcid</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>keywords</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>Machine Learning</th>\n",
-       "      <td>3119</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Bioinformatics</th>\n",
-       "      <td>2366</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Artificial Intelligence</th>\n",
-       "      <td>1555</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Education</th>\n",
-       "      <td>1482</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Neuroscience</th>\n",
-       "      <td>1466</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>International Relations, History, South Asia, Asia-Pacific</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>International Relations, Human Rights, Refugees, Paradiplomacy</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>International Relations, Humanitarian Intervention, Humanitarian Diplomacy</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>International Relations, IOs, Lobbying, Public Diplomacy, Competitive Cities</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>ｽﾋﾟﾝﾄﾛﾆｸｽ、マルチフェロイクス、結晶成長、エレクトロニクス</th>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>795115 rows × 1 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                                    orcid\n",
-       "keywords                                                 \n",
-       "Machine Learning                                     3119\n",
-       "Bioinformatics                                       2366\n",
-       "Artificial Intelligence                              1555\n",
-       "Education                                            1482\n",
-       "Neuroscience                                         1466\n",
-       "...                                                   ...\n",
-       "International Relations, History, South Asia, A...      1\n",
-       "International Relations, Human Rights, Refugees...      1\n",
-       "International Relations, Humanitarian Intervent...      1\n",
-       "International Relations, IOs, Lobbying, Public ...      1\n",
-       "ｽﾋﾟﾝﾄﾛﾆｸｽ、マルチフェロイクス、結晶成長、エレクトロニクス                       1\n",
-       "\n",
-       "[795115 rows x 1 columns]"
-      ]
-     },
-     "execution_count": 207,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "grouped_keywords"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 206,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "KeyError",
-     "evalue": "'n_keywords'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "\u001b[0;32m~/.virtualenvs/data-science/lib/python3.8/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3079\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3080\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3081\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;31mKeyError\u001b[0m: 'n_keywords'",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-206-8d7ed000425e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      3\u001b[0m     go.Bar(\n\u001b[1;32m      4\u001b[0m         \u001b[0mx\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mgrouped_keywords\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'orcid'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mTOP_N\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m         \u001b[0my\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mgrouped_keywords\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'n_keywords'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mTOP_N\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m     )\n\u001b[1;32m      7\u001b[0m ]\n",
-      "\u001b[0;32m~/.virtualenvs/data-science/lib/python3.8/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3022\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnlevels\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3023\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3024\u001b[0;31m             \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3025\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3026\u001b[0m                 \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/.virtualenvs/data-science/lib/python3.8/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3080\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3081\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3082\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3083\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3084\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mtolerance\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mKeyError\u001b[0m: 'n_keywords'"
-     ]
-    }
-   ],
    "source": [
     "set_top_n(50)\n",
     "data = [\n",
     "    go.Bar(\n",
-    "        x=grouped_keywords['orcid'][:TOP_N],\n",
-    "        y=grouped_keywords['n_keywords'][:TOP_N]\n",
+    "        x=grouped_keywords.index[:TOP_N],\n",
+    "        y=grouped_keywords['orcid'][:TOP_N]\n",
     "    )\n",
     "]\n",
     "\n",
@@ -12878,7 +12816,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [
     {
@@ -12898,11 +12836,15 @@
           "verified_email",
           "verified_primary_email",
           "n_works",
+          "n_doi",
+          "n_arxiv",
+          "n_pmc",
+          "n_other_pids",
+          "label",
           "n_emails",
           "n_urls",
           "n_ids",
-          "n_keywords",
-          "label"
+          "n_keywords"
          ],
          "xaxis": "x",
          "y": [
@@ -12910,15 +12852,23 @@
           "verified_email",
           "verified_primary_email",
           "n_works",
+          "n_doi",
+          "n_arxiv",
+          "n_pmc",
+          "n_other_pids",
+          "label",
           "n_emails",
           "n_urls",
           "n_ids",
-          "n_keywords",
-          "label"
+          "n_keywords"
          ],
          "yaxis": "y",
          "z": [
           [
+           null,
+           null,
+           null,
+           null,
            null,
            null,
            null,
@@ -12932,89 +12882,181 @@
           [
            null,
            1,
-           0.9764600091179001,
-           0.06481728326324665,
-           0.011268135706995959,
-           0.016235518285109687,
-           0.08833871138587861,
-           0.017045184883982135,
-           0.1443748918395754
+           0.976162114192081,
+           0.0643465684083431,
+           0.06256365939443789,
+           0.004813567718545522,
+           0.022837768079663843,
+           0.0502787806136592,
+           0.1653735105575277,
+           0.011077499054971796,
+           0.01616663985261792,
+           0.0878909499747942,
+           0.01702128763665974
+          ],
+          [
+           null,
+           0.976162114192081,
+           1,
+           0.06550520343326285,
+           0.06358869411827689,
+           0.004936396077751568,
+           0.0233694641294265,
+           0.05107779193878439,
+           0.1673817151653653,
+           0.009088965040421332,
+           0.016748133920736267,
+           0.0891344788642304,
+           0.01757470891436621
+          ],
+          [
+           null,
+           0.0643465684083431,
+           0.06550520343326285,
+           1,
+           0.9422006818527181,
+           0.2510908375242561,
+           0.3452995689789822,
+           0.8507066573191994,
+           0.2193240629073337,
+           0.04012080330827889,
+           0.050551529905608905,
+           0.24172815699206937,
+           0.030991434187229255
+          ],
+          [
+           null,
+           0.06256365939443789,
+           0.06358869411827689,
+           0.9422006818527181,
+           1,
+           0.2859256869913497,
+           0.35237093272562453,
+           0.8207407571730607,
+           0.20528211794680093,
+           0.03066074418509789,
+           0.02249574354972604,
+           0.22699396525236162,
+           0.029924481047131947
+          ],
+          [
+           null,
+           0.004813567718545522,
+           0.004936396077751568,
+           0.2510908375242561,
+           0.2859256869913497,
+           1,
+           -0.0016834274457045173,
+           0.18858664921353688,
+           0.013625663523574786,
+           0.001327784437475615,
+           -0.0029341825430676785,
+           0.00551756083696426,
+           -0.0010622024587917253
           ],
           [
            null,
-           0.9764600091179001,
+           0.022837768079663843,
+           0.0233694641294265,
+           0.3452995689789822,
+           0.35237093272562453,
+           -0.0016834274457045173,
            1,
-           0.0659649633755603,
-           0.009337798958686118,
-           0.0168692743777146,
-           0.08953190210488794,
-           0.017626925761491493,
-           0.14594707482844735
+           0.2813216452145862,
+           0.06643990962625554,
+           0.0034751570518647148,
+           0.00017861447927955607,
+           0.06890564721203783,
+           0.02385706062724447
           ],
           [
            null,
-           0.06481728326324665,
-           0.0659649633755603,
+           0.0502787806136592,
+           0.05107779193878439,
+           0.8507066573191994,
+           0.8207407571730607,
+           0.18858664921353688,
+           0.2813216452145862,
            1,
-           0.05241643710974057,
-           0.05179828612278866,
-           0.23927720131732308,
-           0.030960689715636,
-           0.18836598374411756
+           0.16718354633724933,
+           0.020109885973996034,
+           0.008514311952439128,
+           0.23592717383229878,
+           0.023831895109099027
           ],
           [
            null,
-           0.011268135706995959,
-           0.009337798958686118,
-           0.05241643710974057,
+           0.1653735105575277,
+           0.1673817151653653,
+           0.2193240629073337,
+           0.20528211794680093,
+           0.013625663523574786,
+           0.06643990962625554,
+           0.16718354633724933,
            1,
-           0.11119920854300894,
-           0.04817263453943147,
-           0.04157758861961359,
-           0.01892287179981889
+           0.018556742838561485,
+           0.017316375665650897,
+           0.2141058845072524,
+           0.05566397359882779
           ],
           [
            null,
-           0.016235518285109687,
-           0.0168692743777146,
-           0.05179828612278866,
-           0.11119920854300894,
+           0.011077499054971796,
+           0.009088965040421332,
+           0.04012080330827889,
+           0.03066074418509789,
+           0.001327784437475615,
+           0.0034751570518647148,
+           0.020109885973996034,
+           0.018556742838561485,
            1,
-           0.06925708918455128,
-           0.15926017909633472,
-           0.014961341785831497
+           0.09408460253059668,
+           0.0452261998698129,
+           0.048598477595472214
           ],
           [
            null,
-           0.08833871138587861,
-           0.08953190210488794,
-           0.23927720131732308,
-           0.04817263453943147,
-           0.06925708918455128,
+           0.01616663985261792,
+           0.016748133920736267,
+           0.050551529905608905,
+           0.02249574354972604,
+           -0.0029341825430676785,
+           0.00017861447927955607,
+           0.008514311952439128,
+           0.017316375665650897,
+           0.09408460253059668,
            1,
-           0.06320236481237387,
-           0.1822877914958724
+           0.06946298201611972,
+           0.15905312700498755
           ],
           [
            null,
-           0.017045184883982135,
-           0.017626925761491493,
-           0.030960689715636,
-           0.04157758861961359,
-           0.15926017909633472,
-           0.06320236481237387,
+           0.0878909499747942,
+           0.0891344788642304,
+           0.24172815699206937,
+           0.22699396525236162,
+           0.00551756083696426,
+           0.06890564721203783,
+           0.23592717383229878,
+           0.2141058845072524,
+           0.0452261998698129,
+           0.06946298201611972,
            1,
-           0.04447286857755328
+           0.06380885961518437
           ],
           [
            null,
-           0.1443748918395754,
-           0.14594707482844735,
-           0.18836598374411756,
-           0.01892287179981889,
-           0.014961341785831497,
-           0.1822877914958724,
-           0.04447286857755328,
+           0.01702128763665974,
+           0.01757470891436621,
+           0.030991434187229255,
+           0.029924481047131947,
+           -0.0010622024587917253,
+           0.02385706062724447,
+           0.023831895109099027,
+           0.05566397359882779,
+           0.048598477595472214,
+           0.15905312700498755,
+           0.06380885961518437,
            1
           ]
          ]
@@ -13895,9 +13937,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"9bd33885-6eac-4cf4-8e9e-9c1423128b5f\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"9bd33885-6eac-4cf4-8e9e-9c1423128b5f\")) {                    Plotly.newPlot(                        \"9bd33885-6eac-4cf4-8e9e-9c1423128b5f\",                        [{\"coloraxis\": \"coloraxis\", \"hovertemplate\": \"x: %{x}<br>y: %{y}<br>color: %{z}<extra></extra>\", \"name\": \"0\", \"type\": \"heatmap\", \"x\": [\"claimed\", \"verified_email\", \"verified_primary_email\", \"n_works\", \"n_emails\", \"n_urls\", \"n_ids\", \"n_keywords\", \"label\"], \"xaxis\": \"x\", \"y\": [\"claimed\", \"verified_email\", \"verified_primary_email\", \"n_works\", \"n_emails\", \"n_urls\", \"n_ids\", \"n_keywords\", \"label\"], \"yaxis\": \"y\", \"z\": [[null, null, null, null, null, null, null, null, null], [null, 1.0, 0.9764600091179001, 0.06481728326324665, 0.011268135706995959, 0.016235518285109687, 0.08833871138587861, 0.017045184883982135, 0.1443748918395754], [null, 0.9764600091179001, 1.0, 0.0659649633755603, 0.009337798958686118, 0.0168692743777146, 0.08953190210488794, 0.017626925761491493, 0.14594707482844735], [null, 0.06481728326324665, 0.0659649633755603, 1.0, 0.05241643710974057, 0.05179828612278866, 0.23927720131732308, 0.030960689715636, 0.18836598374411756], [null, 0.011268135706995959, 0.009337798958686118, 0.05241643710974057, 1.0, 0.11119920854300894, 0.04817263453943147, 0.04157758861961359, 0.01892287179981889], [null, 0.016235518285109687, 0.0168692743777146, 0.05179828612278866, 0.11119920854300894, 1.0, 0.06925708918455128, 0.15926017909633472, 0.014961341785831497], [null, 0.08833871138587861, 0.08953190210488794, 0.23927720131732308, 0.04817263453943147, 0.06925708918455128, 1.0, 0.06320236481237387, 0.1822877914958724], [null, 0.017045184883982135, 0.017626925761491493, 0.030960689715636, 0.04157758861961359, 0.15926017909633472, 0.06320236481237387, 1.0, 0.04447286857755328], [null, 0.1443748918395754, 0.14594707482844735, 0.18836598374411756, 0.01892287179981889, 0.014961341785831497, 0.1822877914958724, 0.04447286857755328, 1.0]]}],                        {\"coloraxis\": {\"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"margin\": {\"t\": 60}, \"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"xaxis\": {\"anchor\": \"y\", \"constrain\": \"domain\", \"domain\": [0.0, 1.0], \"scaleanchor\": \"y\"}, \"yaxis\": {\"anchor\": \"x\", \"autorange\": \"reversed\", \"constrain\": \"domain\", \"domain\": [0.0, 1.0]}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<div>                            <div id=\"0e5b7e4b-0689-4a4d-a5fa-fa446c871342\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"0e5b7e4b-0689-4a4d-a5fa-fa446c871342\")) {                    Plotly.newPlot(                        \"0e5b7e4b-0689-4a4d-a5fa-fa446c871342\",                        [{\"coloraxis\": \"coloraxis\", \"hovertemplate\": \"x: %{x}<br>y: %{y}<br>color: %{z}<extra></extra>\", \"name\": \"0\", \"type\": \"heatmap\", \"x\": [\"claimed\", \"verified_email\", \"verified_primary_email\", \"n_works\", \"n_doi\", \"n_arxiv\", \"n_pmc\", \"n_other_pids\", \"label\", \"n_emails\", \"n_urls\", \"n_ids\", \"n_keywords\"], \"xaxis\": \"x\", \"y\": [\"claimed\", \"verified_email\", \"verified_primary_email\", \"n_works\", \"n_doi\", \"n_arxiv\", \"n_pmc\", \"n_other_pids\", \"label\", \"n_emails\", \"n_urls\", \"n_ids\", \"n_keywords\"], \"yaxis\": \"y\", \"z\": [[null, null, null, null, null, null, null, null, null, null, null, null, null], [null, 1.0, 0.976162114192081, 0.0643465684083431, 0.06256365939443789, 0.004813567718545522, 0.022837768079663843, 0.0502787806136592, 0.1653735105575277, 0.011077499054971796, 0.01616663985261792, 0.0878909499747942, 0.01702128763665974], [null, 0.976162114192081, 1.0, 0.06550520343326285, 0.06358869411827689, 0.004936396077751568, 0.0233694641294265, 0.05107779193878439, 0.1673817151653653, 0.009088965040421332, 0.016748133920736267, 0.0891344788642304, 0.01757470891436621], [null, 0.0643465684083431, 0.06550520343326285, 1.0, 0.9422006818527181, 0.2510908375242561, 0.3452995689789822, 0.8507066573191994, 0.2193240629073337, 0.04012080330827889, 0.050551529905608905, 0.24172815699206937, 0.030991434187229255], [null, 0.06256365939443789, 0.06358869411827689, 0.9422006818527181, 1.0, 0.2859256869913497, 0.35237093272562453, 0.8207407571730607, 0.20528211794680093, 0.03066074418509789, 0.02249574354972604, 0.22699396525236162, 0.029924481047131947], [null, 0.004813567718545522, 0.004936396077751568, 0.2510908375242561, 0.2859256869913497, 1.0, -0.0016834274457045173, 0.18858664921353688, 0.013625663523574786, 0.001327784437475615, -0.0029341825430676785, 0.00551756083696426, -0.0010622024587917253], [null, 0.022837768079663843, 0.0233694641294265, 0.3452995689789822, 0.35237093272562453, -0.0016834274457045173, 1.0, 0.2813216452145862, 0.06643990962625554, 0.0034751570518647148, 0.00017861447927955607, 0.06890564721203783, 0.02385706062724447], [null, 0.0502787806136592, 0.05107779193878439, 0.8507066573191994, 0.8207407571730607, 0.18858664921353688, 0.2813216452145862, 1.0, 0.16718354633724933, 0.020109885973996034, 0.008514311952439128, 0.23592717383229878, 0.023831895109099027], [null, 0.1653735105575277, 0.1673817151653653, 0.2193240629073337, 0.20528211794680093, 0.013625663523574786, 0.06643990962625554, 0.16718354633724933, 1.0, 0.018556742838561485, 0.017316375665650897, 0.2141058845072524, 0.05566397359882779], [null, 0.011077499054971796, 0.009088965040421332, 0.04012080330827889, 0.03066074418509789, 0.001327784437475615, 0.0034751570518647148, 0.020109885973996034, 0.018556742838561485, 1.0, 0.09408460253059668, 0.0452261998698129, 0.048598477595472214], [null, 0.01616663985261792, 0.016748133920736267, 0.050551529905608905, 0.02249574354972604, -0.0029341825430676785, 0.00017861447927955607, 0.008514311952439128, 0.017316375665650897, 0.09408460253059668, 1.0, 0.06946298201611972, 0.15905312700498755], [null, 0.0878909499747942, 0.0891344788642304, 0.24172815699206937, 0.22699396525236162, 0.00551756083696426, 0.06890564721203783, 0.23592717383229878, 0.2141058845072524, 0.0452261998698129, 0.06946298201611972, 1.0, 0.06380885961518437], [null, 0.01702128763665974, 0.01757470891436621, 0.030991434187229255, 0.029924481047131947, -0.0010622024587917253, 0.02385706062724447, 0.023831895109099027, 0.05566397359882779, 0.048598477595472214, 0.15905312700498755, 0.06380885961518437, 1.0]]}],                        {\"coloraxis\": {\"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"margin\": {\"t\": 60}, \"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"autotypenumbers\": \"strict\", \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"xaxis\": {\"anchor\": \"y\", \"constrain\": \"domain\", \"domain\": [0.0, 1.0], \"scaleanchor\": \"y\"}, \"yaxis\": {\"anchor\": \"x\", \"autorange\": \"reversed\", \"constrain\": \"domain\", \"domain\": [0.0, 1.0]}},                        {\"responsive\": true}                    ).then(function(){\n",
        "                            \n",
-       "var gd = document.getElementById('9bd33885-6eac-4cf4-8e9e-9c1423128b5f');\n",
+       "var gd = document.getElementById('0e5b7e4b-0689-4a4d-a5fa-fa446c871342');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -13931,6 +13973,13 @@
     "fig.show()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": null,
diff --git a/src/data/make_dataset.py b/src/data/make_dataset.py
index 96b377a..ca68273 100644
--- a/src/data/make_dataset.py
+++ b/src/data/make_dataset.py
@@ -3,7 +3,9 @@ import click
 import logging
 from pathlib import Path
 from dotenv import find_dotenv, load_dotenv
-
+import pandas as pd
+import ast
+import os
 
 @click.command()
 @click.argument('input_filepath', type=click.Path(exists=True))
@@ -13,8 +15,41 @@ def main(input_filepath, output_filepath):
         cleaned data ready to be analyzed (saved in ../processed).
     """
     logger = logging.getLogger(__name__)
-    logger.info('making final data set from raw data')
-
+    logger.info('Making final data set from raw data')
+    logger.info('Loading the zipped dataset')
+    df = pd.read_csv(os.path.join(input_filepath, 'initial_info_whole_20210322.tsv.gz'), compression='gzip', sep='\t', header=0,
+                         names=['orcid', 'claimed','verified_email', 'verified_primary_email', 
+                                  'given_names', 'family_name', 'biography', 'other_names', 'urls', 
+                                  'primary_email', 'other_emails', 'keywords', 'external_ids', 'education', 
+                                  'employment', 'n_works', 'works_source', 'activation_date', 'last_update_date',
+                                   'n_doi', 'n_arxiv', 'n_pmc', 'n_other_pids'])
+    
+    logger.info('Loading list columns')
+    logger.info('... other_names')
+    df['other_names'] = df[df.other_names.notna()]['other_names'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... keywords')
+    df['keywords'] = df[df.keywords.notna()]['keywords'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... urls')
+    df['urls'] = df[df.urls.notna()]['urls'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... other_emails')
+    df['other_emails'] = df[df.other_emails.notna()]['other_emails'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... education')
+    df['education'] = df[df.education.notna()]['education'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... employment')
+    df['employment'] = df[df.employment.notna()]['employment'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... external_ids')    
+    df['external_ids'] = df[df.external_ids.notna()]['external_ids'].apply(lambda x: ast.literal_eval(x))
+    logger.info('... works_source')
+    df['works_source'] = df[df.works_source.notna()]['works_source'].apply(lambda x: ast.literal_eval(x))
+    
+    openaire_orcid = pd.read_csv(os.path.join(input_filepath, 'orcid_openaire.txt'), header=None, names=['orcid'])
+    df['label'] = df.orcid.isin(openaire_orcid['orcid'])
+    df['label'] = df['label'].astype(int)
+    
+    logger.info('Serializing the dataset in ../processed')
+    df.to_pickle(os.path.join(output_filepath, 'dataset.pkl'))
+    
+    
 
 if __name__ == '__main__':
     log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'