From 41f2dab89d51264e07a39526013ebddbc21a918f Mon Sep 17 00:00:00 2001
From: Andrea Mannocci <andremann@libero.it>
Date: Tue, 23 Mar 2021 12:13:04 +0100
Subject: [PATCH] moving on with keywords

---
 notebooks/01-Exploration.ipynb | 776 ++++++++++++++++++++++++++-------
 1 file changed, 614 insertions(+), 162 deletions(-)

diff --git a/notebooks/01-Exploration.ipynb b/notebooks/01-Exploration.ipynb
index 7395104..0f8d755 100644
--- a/notebooks/01-Exploration.ipynb
+++ b/notebooks/01-Exploration.ipynb
@@ -94,12 +94,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 105,
    "metadata": {},
    "outputs": [],
    "source": [
     "JOURNAL = '0000-0003-1815-5732'\n",
-    "NOINFO= '0000-0001-5009-2052'\n",
+    "NOINFO = '0000-0001-5009-2052'\n",
+    "VALID_NO_OA = '0000-0002-5154-6404' # True profile, but not in OpenAIRE\n",
     "# todo: find group-shared ORCiD, if possible"
    ]
   },
@@ -134,12 +135,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "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",
+    "                         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'])"
@@ -575,7 +576,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 164,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -636,6 +637,13 @@
     "df['works_source'] = df[df.works_source.notna()]['works_source'].apply(lambda x: ast.literal_eval(x))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "That's how it looks like"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 16,
@@ -825,9 +833,139 @@
     "df.head(5)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Add labels to the dataframe based on their presence in OpenAIRE"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 97,
+   "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",
+       "  </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",
+       "      <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",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>2934116 rows × 1 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]"
+      ]
+     },
+     "execution_count": 97,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "openaire_orcid = pd.read_csv('../data/raw/orcid_openaire.txt', header=None, names=['orcid'])\n",
+    "openaire_orcid"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['label'] = df.orcid.isin(openaire_orcid['orcid'])\n",
+    "df[\"label\"] = df[\"label\"].astype(int)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Notable profiles inspection"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
    "metadata": {},
    "outputs": [
     {
@@ -861,13 +999,17 @@
        "      <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>...</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>label</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -883,16 +1025,21 @@
        "      <td>NaN</td>\n",
        "      <td>[[Personal website, https://andremann.github.i...</td>\n",
        "      <td>andrea.mannocci@isti.cnr.it</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Data science , science of science, scholarly ...</td>\n",
-       "      <td>[[Scopus Author ID, 55233589900]]</td>\n",
-       "      <td>[[Information engineering, Ph.D., Università d...</td>\n",
-       "      <td>[[Research Associate, Istituto di Scienza e Te...</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>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>1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>1 rows × 25 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -905,26 +1052,22 @@
        "                                                      urls  \\\n",
        "8840413  [[Personal website, https://andremann.github.i...   \n",
        "\n",
-       "                       primary_email other_emails  \\\n",
-       "8840413  andrea.mannocci@isti.cnr.it          NaN   \n",
+       "                       primary_email  ... n_works  \\\n",
+       "8840413  andrea.mannocci@isti.cnr.it  ...      37   \n",
        "\n",
-       "                                                  keywords  \\\n",
-       "8840413  [Data science , science of science, scholarly ...   \n",
+       "                                              works_source  \\\n",
+       "8840413  [Scopus - Elsevier, Crossref Metadata Search, ...   \n",
        "\n",
-       "                              external_ids  \\\n",
-       "8840413  [[Scopus Author ID, 55233589900]]   \n",
+       "        primary_email_domain other_email_domains n_emails  \\\n",
+       "8840413          isti.cnr.it                 NaN      NaN   \n",
        "\n",
-       "                                                 education  \\\n",
-       "8840413  [[Information engineering, Ph.D., Università d...   \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",
        "\n",
-       "                                                employment  n_works  \\\n",
-       "8840413  [[Research Associate, Istituto di Scienza e Te...       37   \n",
-       "\n",
-       "                                              works_source  \n",
-       "8840413  [Scopus - Elsevier, Crossref Metadata Search, ...  "
+       "[1 rows x 25 columns]"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 111,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -935,7 +1078,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 112,
    "metadata": {},
    "outputs": [
     {
@@ -969,13 +1112,17 @@
        "      <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>...</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>label</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -991,16 +1138,21 @@
        "      <td>NaN</td>\n",
        "      <td>[[Otherwhatsapp, https://otherwhatsapp.com/], ...</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Whatsapp GB, whatsapp gb 2020, whatsapp gb ba...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
        "      <td>0</td>\n",
        "      <td>NaN</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>NaN</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>1 rows × 25 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -1010,17 +1162,22 @@
        "        given_names family_name biography other_names  \\\n",
        "9517099       other    whatsapp       NaN         NaN   \n",
        "\n",
-       "                                                      urls primary_email  \\\n",
-       "9517099  [[Otherwhatsapp, https://otherwhatsapp.com/], ...           NaN   \n",
+       "                                                      urls primary_email  ...  \\\n",
+       "9517099  [[Otherwhatsapp, https://otherwhatsapp.com/], ...           NaN  ...   \n",
        "\n",
-       "        other_emails                                           keywords  \\\n",
-       "9517099          NaN  [Whatsapp GB, whatsapp gb 2020, whatsapp gb ba...   \n",
+       "        n_works works_source primary_email_domain other_email_domains  \\\n",
+       "9517099       0          NaN                  NaN                 NaN   \n",
        "\n",
-       "        external_ids education employment  n_works works_source  \n",
-       "9517099          NaN       NaN        NaN        0          NaN  "
+       "        n_emails                                        url_domains n_urls  \\\n",
+       "9517099      NaN  [otherwhatsapp.com, im-creator.com, facebook.c...   27.0   \n",
+       "\n",
+       "        n_ids n_keywords  label  \n",
+       "9517099   NaN        4.0      0  \n",
+       "\n",
+       "[1 rows x 25 columns]"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 112,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1031,18 +1188,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 103,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "orcid                     10744622\n",
-       "claimed                   10744622\n",
-       "verified_email            10744622\n",
-       "verified_primary_email    10744622\n",
-       "given_names               10716789\n",
-       "family_name               10437094\n",
+       "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",
@@ -1050,14 +1207,22 @@
        "other_emails                 47470\n",
        "keywords                    638634\n",
        "external_ids               1285292\n",
-       "education                  2402440\n",
-       "employment                 2626670\n",
-       "n_works                   10744622\n",
-       "works_source               2671906\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"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 103,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1068,7 +1233,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 104,
    "metadata": {},
    "outputs": [
     {
@@ -1102,13 +1267,17 @@
        "      <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>...</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>label</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -1124,22 +1293,9 @@
        "      <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>[[Energy Systems Engineering , Doctoral, Cypru...</td>\n",
-       "      <td>[[, University of Electronic Science and Techn...</td>\n",
+       "      <td>...</td>\n",
        "      <td>3</td>\n",
        "      <td>[Multidisciplinary Digital Publishing Institut...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4595264</th>\n",
-       "      <td>0000-0002-5154-6404</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>NaN</td>\n",
        "      <td>NaN</td>\n",
@@ -1147,42 +1303,33 @@
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>[[Energy Systems Engineering , Doctoral, Cypru...</td>\n",
-       "      <td>[[, University of Electronic Science and Techn...</td>\n",
-       "      <td>2</td>\n",
-       "      <td>[Crossref]</td>\n",
+       "      <td>False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>1 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",
-       "4595264  0000-0002-5154-6404        1               1                       1   \n",
        "\n",
-       "        given_names family_name biography other_names urls primary_email  \\\n",
-       "4595263     Olusola    Bamisile       NaN         NaN  NaN           NaN   \n",
-       "4595264     Olusola    Bamisile       NaN         NaN  NaN           NaN   \n",
+       "        given_names family_name biography other_names urls primary_email  ...  \\\n",
+       "4595263     Olusola    Bamisile       NaN         NaN  NaN           NaN  ...   \n",
        "\n",
-       "        other_emails keywords external_ids  \\\n",
-       "4595263          NaN      NaN          NaN   \n",
-       "4595264          NaN      NaN          NaN   \n",
+       "        n_works                                       works_source  \\\n",
+       "4595263       3  [Multidisciplinary Digital Publishing Institut...   \n",
        "\n",
-       "                                                 education  \\\n",
-       "4595263  [[Energy Systems Engineering , Doctoral, Cypru...   \n",
-       "4595264  [[Energy Systems Engineering , Doctoral, Cypru...   \n",
+       "        primary_email_domain other_email_domains n_emails  url_domains n_urls  \\\n",
+       "4595263                  NaN                 NaN      NaN          NaN    NaN   \n",
        "\n",
-       "                                                employment  n_works  \\\n",
-       "4595263  [[, University of Electronic Science and Techn...        3   \n",
-       "4595264  [[, University of Electronic Science and Techn...        2   \n",
+       "        n_ids n_keywords  label  \n",
+       "4595263   NaN        NaN  False  \n",
        "\n",
-       "                                              works_source  \n",
-       "4595263  [Multidisciplinary Digital Publishing Institut...  \n",
-       "4595264                                         [Crossref]  "
+       "[1 rows x 25 columns]"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 104,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -10197,7 +10344,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [
     {
@@ -11125,7 +11272,7 @@
          }
         },
         "title": {
-         "text": "IDs provided"
+         "text": "IDs provided by providers"
         },
         "xaxis": {
          "tickangle": 45,
@@ -11136,9 +11283,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"fca39da2-2911-4544-8eb0-7dbbc7205c87\" 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(\"fca39da2-2911-4544-8eb0-7dbbc7205c87\")) {                    Plotly.newPlot(                        \"fca39da2-2911-4544-8eb0-7dbbc7205c87\",                        [{\"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\"}, \"xaxis\": {\"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<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('fca39da2-2911-4544-8eb0-7dbbc7205c87');\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",
@@ -11176,7 +11323,7 @@
     "]\n",
     "\n",
     "layout = go.Layout(\n",
-    "    title='IDs provided',\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",
@@ -11224,9 +11371,120 @@
     "## 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": 82,
+   "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']"
+      ]
+     },
+     "execution_count": 200,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[df['orcid'] == PP]['fixed_keywords'].values[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 201,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -11352,7 +11610,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 205,
    "metadata": {},
    "outputs": [
     {
@@ -11399,74 +11657,74 @@
           "0000-0003-2509-2549",
           "0000-0002-0463-0048",
           "0000-0001-5230-715X",
-          "0000-0001-5458-7167",
           "0000-0001-9336-6850",
+          "0000-0001-5458-7167",
           "0000-0003-0209-180X",
-          "0000-0002-8227-5387",
-          "0000-0002-9381-2264",
-          "0000-0003-3340-6413",
           "0000-0003-3584-6834",
+          "0000-0002-9381-2264",
+          "0000-0002-8227-5387",
+          "0000-0003-3340-6413",
           "0000-0002-2935-1934",
-          "0000-0002-8644-8396",
-          "0000-0002-8659-6321",
           "0000-0002-3123-3021",
+          "0000-0002-8659-6321",
+          "0000-0002-8644-8396",
           "0000-0001-5637-1124",
-          "0000-0001-5167-7466",
           "0000-0002-8449-2211",
-          "0000-0003-2532-2906",
-          "0000-0002-3532-043X",
-          "0000-0002-2683-4527",
-          "0000-0003-4505-3678",
-          "0000-0002-6347-9464",
+          "0000-0001-5167-7466",
           "0000-0003-4608-3844",
-          "0000-0003-4374-6374",
+          "0000-0002-2683-4527",
+          "0000-0002-6347-9464",
+          "0000-0003-4505-3678",
+          "0000-0002-3532-043X",
+          "0000-0003-2532-2906",
           "0000-0003-4511-7942",
-          "0000-0002-1103-9651",
+          "0000-0003-4374-6374",
           "0000-0003-3720-1183",
+          "0000-0002-1103-9651",
           "0000-0001-9280-6017",
           "0000-0003-4673-1063",
           "0000-0001-9586-0780",
-          "0000-0002-5539-1761",
-          "0000-0003-2550-1859",
-          "0000-0002-8499-1045",
           "0000-0003-2218-1343",
+          "0000-0003-2550-1859",
+          "0000-0002-5539-1761",
+          "0000-0002-8499-1045",
           "0000-0002-5306-7781",
           "0000-0003-1863-0265",
-          "0000-0002-8072-1152",
           "0000-0003-3342-6123",
-          "0000-0002-2252-672X",
+          "0000-0002-8072-1152",
           "0000-0002-3907-3552",
           "0000-0001-6861-9561",
-          "0000-0002-3597-3350",
           "0000-0002-5274-7742",
+          "0000-0002-3597-3350",
           "0000-0002-3186-8860",
-          "0000-0001-8689-185X",
-          "0000-0002-6282-0640",
-          "0000-0003-3343-5660",
-          "0000-0001-7133-7848",
-          "0000-0003-4486-2684",
-          "0000-0002-9014-2090",
+          "0000-0002-2252-672X",
           "0000-0001-6843-9325",
-          "0000-0003-0097-4182",
+          "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",
-          "0000-0001-7857-4133",
-          "0000-0002-1294-2156",
+          "0000-0003-0097-4182",
           "0000-0001-8445-412X",
-          "0000-0002-1411-3028",
-          "0000-0003-3387-3193",
-          "0000-0002-1545-7818",
-          "0000-0002-9125-6022",
-          "0000-0002-3898-9542",
           "0000-0002-3866-6460",
-          "0000-0003-4283-2895",
           "0000-0003-4153-6779",
+          "0000-0002-1545-7818",
+          "0000-0003-3387-3193",
           "0000-0002-4598-2891",
+          "0000-0002-3898-9542",
           "0000-0002-0211-7195",
-          "0000-0002-1770-9660",
-          "0000-0002-1960-5857",
+          "0000-0003-4283-2895",
+          "0000-0002-1411-3028",
+          "0000-0002-9125-6022",
           "0000-0003-2640-6757",
-          "0000-0002-5432-9595"
+          "0000-0002-1960-5857",
+          "0000-0002-4963-9345",
+          "0000-0002-1770-9660"
          ],
          "y": [
           154,
@@ -12383,6 +12641,10 @@
          "text": "Keywords provided"
         },
         "xaxis": {
+         "range": [
+          -0.5,
+          99.5
+         ],
          "tickangle": 45,
          "tickfont": {
           "size": 12
@@ -12391,9 +12653,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"b29b0da9-72da-4673-b7c4-00097d52dd94\" 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(\"b29b0da9-72da-4673-b7c4-00097d52dd94\")) {                    Plotly.newPlot(                        \"b29b0da9-72da-4673-b7c4-00097d52dd94\",                        [{\"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\", \"0000-0001-5458-7167\", \"0000-0001-9336-6850\", \"0000-0003-0209-180X\", \"0000-0002-8227-5387\", \"0000-0002-9381-2264\", \"0000-0003-3340-6413\", \"0000-0003-3584-6834\", \"0000-0002-2935-1934\", \"0000-0002-8644-8396\", \"0000-0002-8659-6321\", \"0000-0002-3123-3021\", \"0000-0001-5637-1124\", \"0000-0001-5167-7466\", \"0000-0002-8449-2211\", \"0000-0003-2532-2906\", \"0000-0002-3532-043X\", \"0000-0002-2683-4527\", \"0000-0003-4505-3678\", \"0000-0002-6347-9464\", \"0000-0003-4608-3844\", \"0000-0003-4374-6374\", \"0000-0003-4511-7942\", \"0000-0002-1103-9651\", \"0000-0003-3720-1183\", \"0000-0001-9280-6017\", \"0000-0003-4673-1063\", \"0000-0001-9586-0780\", \"0000-0002-5539-1761\", \"0000-0003-2550-1859\", \"0000-0002-8499-1045\", \"0000-0003-2218-1343\", \"0000-0002-5306-7781\", \"0000-0003-1863-0265\", \"0000-0002-8072-1152\", \"0000-0003-3342-6123\", \"0000-0002-2252-672X\", \"0000-0002-3907-3552\", \"0000-0001-6861-9561\", \"0000-0002-3597-3350\", \"0000-0002-5274-7742\", \"0000-0002-3186-8860\", \"0000-0001-8689-185X\", \"0000-0002-6282-0640\", \"0000-0003-3343-5660\", \"0000-0001-7133-7848\", \"0000-0003-4486-2684\", \"0000-0002-9014-2090\", \"0000-0001-6843-9325\", \"0000-0003-0097-4182\", \"0000-0003-1245-7705\", \"0000-0002-4432-3448\", \"0000-0001-7857-4133\", \"0000-0002-1294-2156\", \"0000-0001-8445-412X\", \"0000-0002-1411-3028\", \"0000-0003-3387-3193\", \"0000-0002-1545-7818\", \"0000-0002-9125-6022\", \"0000-0002-3898-9542\", \"0000-0002-3866-6460\", \"0000-0003-4283-2895\", \"0000-0003-4153-6779\", \"0000-0002-4598-2891\", \"0000-0002-0211-7195\", \"0000-0002-1770-9660\", \"0000-0002-1960-5857\", \"0000-0003-2640-6757\", \"0000-0002-5432-9595\"], \"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\": {\"tickangle\": 45, \"tickfont\": {\"size\": 12}}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "<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",
        "                            \n",
-       "var gd = document.getElementById('b29b0da9-72da-4673-b7c4-00097d52dd94');\n",
+       "var gd = document.getElementById('7af8660e-7732-4eb2-b13b-edd7b61397bb');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",
@@ -12423,15 +12685,184 @@
     }
    ],
    "source": [
+    "set_top_n(100)\n",
     "data = [\n",
     "    go.Bar(\n",
-    "        x=df.sort_values('n_keywords', ascending=False)['orcid'][:100],\n",
-    "        y=df.sort_values('n_keywords', ascending=False)['n_keywords'][:100]\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',\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",
+    "    )\n",
+    "]\n",
+    "\n",
+    "layout = go.Layout(\n",
+    "    title='Top-%s keywords occurrence' % TOP_N,\n",
     "    xaxis=dict(tickangle=45, tickfont=dict(size=12))\n",
     ")\n",
     "fig = go.Figure(data=data, layout=layout)\n",
@@ -12447,7 +12878,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 113,
    "metadata": {},
    "outputs": [
     {
@@ -12470,7 +12901,8 @@
           "n_emails",
           "n_urls",
           "n_ids",
-          "n_keywords"
+          "n_keywords",
+          "label"
          ],
          "xaxis": "x",
          "y": [
@@ -12481,11 +12913,13 @@
           "n_emails",
           "n_urls",
           "n_ids",
-          "n_keywords"
+          "n_keywords",
+          "label"
          ],
          "yaxis": "y",
          "z": [
           [
+           null,
            null,
            null,
            null,
@@ -12503,7 +12937,8 @@
            0.011268135706995959,
            0.016235518285109687,
            0.08833871138587861,
-           0.017045184883982135
+           0.017045184883982135,
+           0.1443748918395754
           ],
           [
            null,
@@ -12513,7 +12948,8 @@
            0.009337798958686118,
            0.0168692743777146,
            0.08953190210488794,
-           0.017626925761491493
+           0.017626925761491493,
+           0.14594707482844735
           ],
           [
            null,
@@ -12523,7 +12959,8 @@
            0.05241643710974057,
            0.05179828612278866,
            0.23927720131732308,
-           0.030960689715636
+           0.030960689715636,
+           0.18836598374411756
           ],
           [
            null,
@@ -12533,7 +12970,8 @@
            1,
            0.11119920854300894,
            0.04817263453943147,
-           0.04157758861961359
+           0.04157758861961359,
+           0.01892287179981889
           ],
           [
            null,
@@ -12543,7 +12981,8 @@
            0.11119920854300894,
            1,
            0.06925708918455128,
-           0.15926017909633472
+           0.15926017909633472,
+           0.014961341785831497
           ],
           [
            null,
@@ -12553,7 +12992,8 @@
            0.04817263453943147,
            0.06925708918455128,
            1,
-           0.06320236481237387
+           0.06320236481237387,
+           0.1822877914958724
           ],
           [
            null,
@@ -12563,6 +13003,18 @@
            0.04157758861961359,
            0.15926017909633472,
            0.06320236481237387,
+           1,
+           0.04447286857755328
+          ],
+          [
+           null,
+           0.1443748918395754,
+           0.14594707482844735,
+           0.18836598374411756,
+           0.01892287179981889,
+           0.014961341785831497,
+           0.1822877914958724,
+           0.04447286857755328,
            1
           ]
          ]
@@ -13443,9 +13895,9 @@
        }
       },
       "text/html": [
-       "<div>                            <div id=\"be0dd004-76fc-4fc5-8126-37d59a408a8a\" 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(\"be0dd004-76fc-4fc5-8126-37d59a408a8a\")) {                    Plotly.newPlot(                        \"be0dd004-76fc-4fc5-8126-37d59a408a8a\",                        [{\"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\"], \"xaxis\": \"x\", \"y\": [\"claimed\", \"verified_email\", \"verified_primary_email\", \"n_works\", \"n_emails\", \"n_urls\", \"n_ids\", \"n_keywords\"], \"yaxis\": \"y\", \"z\": [[null, null, null, null, null, null, null, null], [null, 1.0, 0.9764600091179001, 0.06481728326324665, 0.011268135706995959, 0.016235518285109687, 0.08833871138587861, 0.017045184883982135], [null, 0.9764600091179001, 1.0, 0.0659649633755603, 0.009337798958686118, 0.0168692743777146, 0.08953190210488794, 0.017626925761491493], [null, 0.06481728326324665, 0.0659649633755603, 1.0, 0.05241643710974057, 0.05179828612278866, 0.23927720131732308, 0.030960689715636], [null, 0.011268135706995959, 0.009337798958686118, 0.05241643710974057, 1.0, 0.11119920854300894, 0.04817263453943147, 0.04157758861961359], [null, 0.016235518285109687, 0.0168692743777146, 0.05179828612278866, 0.11119920854300894, 1.0, 0.06925708918455128, 0.15926017909633472], [null, 0.08833871138587861, 0.08953190210488794, 0.23927720131732308, 0.04817263453943147, 0.06925708918455128, 1.0, 0.06320236481237387], [null, 0.017045184883982135, 0.017626925761491493, 0.030960689715636, 0.04157758861961359, 0.15926017909633472, 0.06320236481237387, 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=\"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",
        "                            \n",
-       "var gd = document.getElementById('be0dd004-76fc-4fc5-8126-37d59a408a8a');\n",
+       "var gd = document.getElementById('9bd33885-6eac-4cf4-8e9e-9c1423128b5f');\n",
        "var x = new MutationObserver(function (mutations, observer) {{\n",
        "        var display = window.getComputedStyle(gd).display;\n",
        "        if (!display || display === 'none') {{\n",