From 7891e57082a3cd6edeaed58dc72a82c464e516da Mon Sep 17 00:00:00 2001 From: Andrea Mannocci Date: Mon, 22 Mar 2021 19:08:20 +0100 Subject: [PATCH] progress with analysis --- notebooks/01-Exploration.ipynb | 6357 ++++++++++++++++++++++---------- 1 file changed, 4505 insertions(+), 1852 deletions(-) diff --git a/notebooks/01-Exploration.ipynb b/notebooks/01-Exploration.ipynb index 60034ab..a882c66 100644 --- a/notebooks/01-Exploration.ipynb +++ b/notebooks/01-Exploration.ipynb @@ -57,6 +57,7 @@ "import plotly\n", "from plotly.offline import iplot, init_notebook_mode\n", "import plotly.graph_objs as go\n", + "import plotly.express as px\n", "\n", "init_notebook_mode(connected=True)\n", "TOP_N = 30\n", @@ -95,7 +96,7 @@ "source": [ "JOURNAL = '0000-0003-1815-5732'\n", "NOINFO= '0000-0001-5009-2052'\n", - "# find group-shared ORCiD" + "# todo: find group-shared ORCiD, if possible" ] }, { @@ -129,7 +130,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -142,7 +143,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": { "scrolled": true }, @@ -534,7 +535,7 @@ "[2418 rows x 17 columns]" ] }, - "execution_count": 8, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -545,7 +546,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -561,7 +562,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -570,7 +571,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -579,7 +580,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ @@ -588,7 +589,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 11, "metadata": {}, "outputs": [], "source": [ @@ -597,7 +598,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 12, "metadata": {}, "outputs": [], "source": [ @@ -606,7 +607,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 13, "metadata": {}, "outputs": [], "source": [ @@ -615,7 +616,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -624,7 +625,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 15, "metadata": {}, "outputs": [], "source": [ @@ -633,7 +634,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 16, "metadata": {}, "outputs": [ { @@ -811,7 +812,7 @@ "4 NaN " ] }, - "execution_count": 18, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -822,7 +823,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 17, "metadata": {}, "outputs": [ { @@ -919,7 +920,7 @@ "8840413 [Scopus - Elsevier, Crossref Metadata Search, ... " ] }, - "execution_count": 19, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" } @@ -930,7 +931,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 18, "metadata": {}, "outputs": [ { @@ -1015,7 +1016,7 @@ "9517099 NaN NaN NaN 0 NaN " ] }, - "execution_count": 20, + "execution_count": 18, "metadata": {}, "output_type": "execute_result" } @@ -1026,7 +1027,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 19, "metadata": {}, "outputs": [ { @@ -1052,7 +1053,7 @@ "dtype: int64" ] }, - "execution_count": 21, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -1063,7 +1064,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 20, "metadata": {}, "outputs": [ { @@ -1177,7 +1178,7 @@ "4595264 [Crossref] " ] }, - "execution_count": 22, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" } @@ -1188,7 +1189,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 21, "metadata": {}, "outputs": [], "source": [ @@ -1197,7 +1198,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 22, "metadata": {}, "outputs": [ { @@ -1205,12 +1206,12 @@ "text/plain": [ "count 10744621\n", "unique 10744621\n", - "top 0000-0002-3376-9946\n", + "top 0000-0002-3936-2047\n", "freq 1\n", "Name: orcid, dtype: object" ] }, - "execution_count": 24, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } @@ -1228,20 +1229,20 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "count 121476\n", - "unique 121473\n", - "top maykin@owasp.org\n", - "freq 2\n", + "count 121476\n", + "unique 121473\n", + "top opercin@erbakan.edu.tr\n", + "freq 2\n", "Name: primary_email, dtype: object" ] }, - "execution_count": 25, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } @@ -1259,7 +1260,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 24, "metadata": {}, "outputs": [ { @@ -1271,7 +1272,7 @@ "Name: primary_email, dtype: object" ] }, - "execution_count": 26, + "execution_count": 24, "metadata": {}, "output_type": "execute_result" } @@ -1282,7 +1283,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 25, "metadata": {}, "outputs": [ { @@ -1388,7 +1389,7 @@ "7483666 NaN 0 NaN " ] }, - "execution_count": 27, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -1399,7 +1400,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 26, "metadata": {}, "outputs": [ { @@ -1509,7 +1510,7 @@ "9068234 NaN " ] }, - "execution_count": 28, + "execution_count": 26, "metadata": {}, "output_type": "execute_result" } @@ -1520,7 +1521,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 27, "metadata": {}, "outputs": [ { @@ -1634,7 +1635,7 @@ "10246485 0 NaN " ] }, - "execution_count": 29, + "execution_count": 27, "metadata": {}, "output_type": "execute_result" } @@ -1645,7 +1646,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 28, "metadata": {}, "outputs": [], "source": [ @@ -1654,7 +1655,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 29, "metadata": {}, "outputs": [ { @@ -1667,7 +1668,7 @@ "Name: primary_email_domain, dtype: object" ] }, - "execution_count": 31, + "execution_count": 29, "metadata": {}, "output_type": "execute_result" } @@ -1678,7 +1679,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 30, "metadata": {}, "outputs": [ { @@ -1777,7 +1778,7 @@ "[17047 rows x 1 columns]" ] }, - "execution_count": 32, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -1789,7 +1790,7 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 31, "metadata": {}, "outputs": [ { @@ -2692,9 +2693,9 @@ } }, "text/html": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "data = [\n", - " go.Bar(\n", - " x=grouped_urls[:30].sort_values(by=['orcid'], ascending=False).index,\n", - " y=grouped_urls[:30].sort_values(by=['orcid'], ascending=False)['orcid']\n", - " )\n", - "]\n", - "\n", - "layout = go.Layout(\n", - " title='Top 30 URL domains',\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": 48, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
url_domains
orcid
0000-0002-1234-835X219
0000-0001-7478-4539174
0000-0002-7392-3792169
0000-0002-6938-9638152
0000-0003-2450-090X114
......
0000-0002-1883-05690
0000-0002-1883-05770
0000-0002-1883-05850
0000-0002-1883-06060
0000-0003-5000-00010
\n", - "

10744621 rows × 1 columns

\n", - "
" - ], - "text/plain": [ - " url_domains\n", - "orcid \n", - "0000-0002-1234-835X 219\n", - "0000-0001-7478-4539 174\n", - "0000-0002-7392-3792 169\n", - "0000-0002-6938-9638 152\n", - "0000-0003-2450-090X 114\n", - "... ...\n", - "0000-0002-1883-0569 0\n", - "0000-0002-1883-0577 0\n", - "0000-0002-1883-0585 0\n", - "0000-0002-1883-0606 0\n", - "0000-0003-5000-0001 0\n", - "\n", - "[10744621 rows x 1 columns]" - ] - }, - "execution_count": 48, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "grouped_most_domains = urls.groupby('orcid').count().sort_values('url_domains', ascending=False)\n", - "grouped_most_domains" - ] - }, - { - "cell_type": "code", - "execution_count": 49, + "execution_count": 45, "metadata": {}, "outputs": [ { @@ -6149,15 +5028,15 @@ "0000-0001-7478-4539", "0000-0002-7392-3792", "0000-0002-6938-9638", - "0000-0003-2450-090X", "0000-0002-5710-4041", + "0000-0003-2450-090X", "0000-0002-3920-7389", "0000-0002-6689-4129", "0000-0002-4621-5571", "0000-0001-9131-1266", "0000-0002-7754-8889", - "0000-0002-9025-8632", "0000-0002-5250-1144", + "0000-0002-9025-8632", "0000-0002-7456-3848", "0000-0003-0176-1293", "0000-0003-0321-7339", @@ -6166,85 +5045,85 @@ "0000-0001-8873-6677", "0000-0002-3997-5070", "0000-0002-1856-6905", - "0000-0002-4316-1467", "0000-0002-4062-3603", - "0000-0003-1524-6268", + "0000-0002-4316-1467", "0000-0002-0752-7513", - "0000-0003-0594-2462", "0000-0001-5880-7091", + "0000-0003-1524-6268", + "0000-0003-0594-2462", "0000-0003-2593-7134", "0000-0002-1298-5252", "0000-0003-1761-3842", "0000-0003-2383-8386", "0000-0003-3546-2312", "0000-0002-2886-9248", - "0000-0003-2183-8112", "0000-0002-1929-6054", + "0000-0003-2183-8112", "0000-0003-2407-3557", + "0000-0002-4305-4215", "0000-0003-0796-0234", "0000-0001-7133-6896", - "0000-0003-1484-6958", - "0000-0002-4305-4215", - "0000-0002-4004-6666", - "0000-0002-7568-3403", "0000-0002-9276-6921", + "0000-0002-7568-3403", + "0000-0003-1484-6958", + "0000-0002-4004-6666", "0000-0002-8208-0897", + "0000-0002-9071-5450", + "0000-0002-8116-9611", "0000-0003-4993-5555", "0000-0003-0930-6121", - "0000-0002-8116-9611", - "0000-0002-9071-5450", "0000-0003-4948-9268", - "0000-0002-3277-9659", - "0000-0001-9559-1103", "0000-0002-8122-879X", + "0000-0001-9559-1103", + "0000-0002-3277-9659", "0000-0003-2862-6315", "0000-0002-2000-8339", + "0000-0001-5300-4601", + "0000-0002-6547-0172", "0000-0003-4808-6619", "0000-0002-6254-8683", - "0000-0002-6547-0172", - "0000-0001-5300-4601", "0000-0002-0971-9375", "0000-0003-3933-0229", "0000-0002-4659-5391", "0000-0003-0694-1154", - "0000-0001-6783-2037", "0000-0002-2916-2893", - "0000-0001-6461-2573", "0000-0003-4501-3756", + "0000-0001-6783-2037", + "0000-0001-6461-2573", "0000-0001-5549-6822", - "0000-0003-4326-9336", - "0000-0002-8940-3177", - "0000-0001-8096-4333", "0000-0001-8978-4830", - "0000-0002-8593-9257", - "0000-0002-5946-1595", + "0000-0003-4326-9336", + "0000-0001-8096-4333", + "0000-0002-8940-3177", "0000-0002-6680-1703", - "0000-0002-5196-4905", + "0000-0002-5946-1595", + "0000-0002-8593-9257", "0000-0002-7653-4899", - "0000-0001-6921-0426", - "0000-0002-5139-2660", + "0000-0002-5196-4905", "0000-0001-8808-4867", + "0000-0002-5139-2660", + "0000-0001-6921-0426", + "0000-0003-1815-1993", "0000-0002-7843-8497", "0000-0003-1675-2840", "0000-0001-8644-2114", - "0000-0003-1815-1993", "0000-0003-0907-9870", - "0000-0001-7784-0583", - "0000-0002-5265-6074", - "0000-0001-7550-5802", "0000-0001-8986-2528", + "0000-0002-5265-6074", + "0000-0001-7784-0583", + "0000-0001-7550-5802", + "0000-0001-6979-4273", + "0000-0001-9102-8639", "0000-0002-3334-9386", "0000-0002-0696-8560", "0000-0002-7179-6953", - "0000-0001-6979-4273", - "0000-0001-9102-8639", - "0000-0002-5985-9114", "0000-0002-9771-600X", - "0000-0001-7193-5039", - "0000-0001-7608-9433", + "0000-0002-8797-6502", "0000-0002-5241-1026", - "0000-0001-6714-009X", - "0000-0003-2133-2648" + "0000-0001-7193-5039", + "0000-0001-9119-5955", + "0000-0003-2133-2648", + "0000-0001-9026-4795" ], "y": [ 219, @@ -7169,9 +6048,9 @@ } }, "text/html": [ - "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "data = [\n", + " go.Bar(\n", + " x=grouped_urls[:30].sort_values(by=['orcid'], ascending=False).index,\n", + " y=grouped_urls[:30].sort_values(by=['orcid'], ascending=False)['orcid']\n", + " )\n", + "]\n", + "\n", + "layout = go.Layout(\n", + " title='Top 30 URL domains',\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": 48, + "metadata": { + "scrolled": true + }, "outputs": [ { "data": { @@ -7252,8 +7099,7 @@ " other_names\n", " urls\n", " primary_email\n", - " other_emails\n", - " keywords\n", + " ...\n", " external_ids\n", " education\n", " employment\n", @@ -7261,7 +7107,9 @@ " works_source\n", " primary_email_domain\n", " other_email_domains\n", + " n_emails\n", " url_domains\n", + " n_urls\n", " \n", " \n", " \n", @@ -7277,8 +7125,7 @@ " [Gustavo Norberto Duperré, Duperré, G. N.]\n", " [[Gis in Cultural Heritage - ICOMOS România, h...\n", " gustavo.duperre@usal.edu.ar\n", - " NaN\n", - " [History of Art, Humanities, International Coo...\n", + " ...\n", " [[Scopus Author ID, 57195936346], [ResearcherI...\n", " [[Programme in History, History of Art and Ter...\n", " [[Titular Professor, Dirección General de Cult...\n", @@ -7286,7 +7133,9 @@ " [Gustavo Duperré, Scopus - Elsevier, Publons, ...\n", " usal.edu.ar\n", " NaN\n", + " NaN\n", " [icomos.ro, unirioja.es, unirioja.es, unc.edu....\n", + " 51.0\n", " \n", " \n", " 554859\n", @@ -7300,8 +7149,7 @@ " [Franklin Américo Canaza-Choque , Franklin A. ...\n", " [[Consejo Nacional de Ciencia, Tecnología e In...\n", " Leo_123fa@hotmail.com\n", - " [Leoameric123@gmail.com, Frankmericnazac@gmail...\n", - " [Justicia Global; Democracia; Derechos Humanos...\n", + " ...\n", " [[ResearcherID, P-8613-2018], [Loop profile, 8...\n", " [[Facultad de Ciencias de la Educación , Maest...\n", " [[Investigador Social, Universidad Católica de...\n", @@ -7309,7 +7157,9 @@ " [ResearcherID, BASE - Bielefeld Academic Searc...\n", " hotmail.com\n", " [gmail.com, gmail.com, hotmail.com, baldwin.ed...\n", + " 5.0\n", " [concytec.gob.pe, redalyc.org, redalyc.org, un...\n", + " 61.0\n", " \n", " \n", " 1381092\n", @@ -7323,8 +7173,7 @@ " [We procure and deliver premium cannabis strai...\n", " [[find your cannabis & marijuana dispensary , ...\n", " NaN\n", - " NaN\n", - " [cannabis, cannabis culture, cannabis communit...\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -7332,7 +7181,9 @@ " [goowonderland dispensary]\n", " NaN\n", " NaN\n", + " NaN\n", " [goowonderland.com, goowonderland.com, goowond...\n", + " 81.0\n", " \n", " \n", " 2679353\n", @@ -7346,8 +7197,7 @@ " [Abdul Aziz, Aziz, Abdul, Aziz, A., Aziz, Abd,...\n", " [[Google Scholar, https://scholar.google.com/c...\n", " NaN\n", - " NaN\n", - " [Ilmu Ekonomi, Ekonomi Islam, Metodologi Penel...\n", + " ...\n", " NaN\n", " [[Ilmu Ekonomi, Dr, Universitas Borobudur, Jak...\n", " [[Assisten Professor/Dr, Institut Agama Islam ...\n", @@ -7355,7 +7205,9 @@ " [BASE - Bielefeld Academic Search Engine, Abdu...\n", " NaN\n", " NaN\n", + " NaN\n", " [google.com, syekhnurjati.ac.id, orcid.org, bl...\n", + " 59.0\n", " \n", " \n", " 3354430\n", @@ -7369,8 +7221,7 @@ " [Alexander L. Gusev , Alexander Leonidovich Gu...\n", " [[A.L. Gusev Alternative Energy and Ecology, ...\n", " NaN\n", - " NaN\n", - " [Supercapacitors, Electrochromic, Photochromic...\n", + " ...\n", " [[ResearcherID, F-8048-2014], [Scopus Author I...\n", " [[Chemical technology and cryogenic-vacuum tec...\n", " [[General Director, Scientific Technical Centr...\n", @@ -7378,7 +7229,9 @@ " [Publons, DataCite, Scopus - Elsevier, A.L. Gu...\n", " NaN\n", " NaN\n", + " NaN\n", " [youtube.com, isjaee.com, researchgate.net, re...\n", + " 111.0\n", " \n", " \n", " 4004281\n", @@ -7392,8 +7245,7 @@ " [R.Romaniuk, R.S.Romaniuk, Ryszard Romaniuk, R...\n", " [[Scholar Google, http://scholar.google.pl/cit...\n", " rrom@ise.pw.edu.pl\n", - " [R.Romaniuk@ise.pw.edu.pl, R.Romaniuk@elka.pw....\n", - " [telecommunications, photonics, measurement sy...\n", + " ...\n", " [[ISNI, 0000000071432485], [ResearcherID, B-91...\n", " [[Faculty of Electronics and Information Techn...\n", " [[Professor, Institute Director, Politechnika ...\n", @@ -7401,7 +7253,9 @@ " [INSPIRE-HEP, ResearcherID, ISNI2ORCID search ...\n", " ise.pw.edu.pl\n", " [ise.pw.edu.pl, elka.pw.edu.pl, cern.ch]\n", + " 3.0\n", " [google.pl, publons.com, scopus.com, mendeley....\n", + " 114.0\n", " \n", " \n", " 4022480\n", @@ -7415,8 +7269,7 @@ " [Professor Eduard Babulak]\n", " [[Honorary Chair, Chief Mentor & Senior Adviso...\n", " NaN\n", - " NaN\n", - " [Computer Security, Computer Networking, Inter...\n", + " ...\n", " [[Scopus Author ID, 6506867432], [ResearcherID...\n", " [[Information Technology, Doctor Habilitated (...\n", " [[Consultant, Horizon 2020 Framework Programme...\n", @@ -7424,7 +7277,9 @@ " [The Lens, BASE - Bielefeld Academic Search En...\n", " NaN\n", " NaN\n", + " NaN\n", " [worldassessmentcouncil.org, spseke.sk, bcs.or...\n", + " 114.0\n", " \n", " \n", " 6335357\n", @@ -7438,8 +7293,7 @@ " [Jaelani, A., Jaelani, Aan]\n", " [[Microsoft Academic Research, https://academi...\n", " aan_jaelani@syekhnurjati.ac.id\n", - " [iainanjal@gmail.com]\n", - " [Islamic Economics, Tourism Industry, Islamic ...\n", + " ...\n", " [[Scopus Author ID, 57195963463], [Loop profil...\n", " [[Post Graduate, S3/Dr, Universitas Islam Nege...\n", " [[Dr, Institut Agama Islam Negeri Syekh Nurjat...\n", @@ -7447,7 +7301,9 @@ " [Publons, Aan Jaelani, Scopus - Elsevier, Dime...\n", " syekhnurjati.ac.id\n", " [gmail.com]\n", + " 1.0\n", " [microsoft.com, twitter.com, academia.edu, aca...\n", + " 67.0\n", " \n", " \n", " 6489838\n", @@ -7461,8 +7317,7 @@ " [Jaroslaw Jozef Spychala]\n", " [[RESUME, http://www.biowebspin.com/wp-content...\n", " NaN\n", - " NaN\n", - " [organic chemistry, biochemistry, photochemist...\n", + " ...\n", " [[Scopus Author ID, 7006745874]]\n", " [[Department of Chemistry, Postdoctoral Associ...\n", " [[Assistant Professor, Adam Mickiewicz Univers...\n", @@ -7470,7 +7325,9 @@ " [Scopus - Elsevier]\n", " NaN\n", " NaN\n", + " NaN\n", " [biowebspin.com, biowebspin.com, google.com, l...\n", + " 73.0\n", " \n", " \n", " 7570584\n", @@ -7484,8 +7341,7 @@ " [ Munhoz, Pelayo Olea, Olea, Pelayo, Olea, P...\n", " [[Currículo Lattes, http://lattes.cnpq.br/6209...\n", " NaN\n", - " NaN\n", - " [Inovação, Empreendedorismo, Sustentabilidade]\n", + " ...\n", " [[Scopus Author ID, 55175503300], [ResearcherI...\n", " [[, Postdoctoral in Environmental Sustainabili...\n", " [[Professor, Universidade Federal do Rio Grand...\n", @@ -7493,7 +7349,9 @@ " [The Lens, Pelayo Munhoz Olea, Dimensions, BAS...\n", " NaN\n", " NaN\n", + " NaN\n", " [cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c...\n", + " 61.0\n", " \n", " \n", " 10240510\n", @@ -7507,8 +7365,7 @@ " NaN\n", " [[ResearchGate Adolfo Catral , https://www.res...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " [[Loop profile, 747193]]\n", " [[Education, Capacitación para la enseñanza en...\n", " NaN\n", @@ -7516,7 +7373,9 @@ " [BASE - Bielefeld Academic Search Engine, Data...\n", " NaN\n", " NaN\n", + " NaN\n", " [researchgate.net, youtube.com, linkedin.com, ...\n", + " 152.0\n", " \n", " \n", " 10448304\n", @@ -7530,8 +7389,7 @@ " [Juan de Dios Beltrán Mancilla, FILÓSOFO AUTOD...\n", " [[01.- Juan de Dios Beltrán Mancilla. Teoría O...\n", " NaN\n", - " NaN\n", - " [FILOSOFIA MEDICINA ARQUITECTURA ECONOMÍA DERE...\n", + " ...\n", " NaN\n", " [[, DIPLOMADO EN PRACTICAS DIRECTIVAS PARA OR...\n", " [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2...\n", @@ -7539,7 +7397,9 @@ " [JUAN DE DIOS BELTR´´ÁN MANCILLA]\n", " NaN\n", " NaN\n", + " NaN\n", " [yumpu.com, ijopm.org, google.com, blogspot.co...\n", + " 69.0\n", " \n", " \n", " 10663894\n", @@ -7553,8 +7413,7 @@ " [Dr. PARAMESHACHARI B D]\n", " [[GSSSIETW,MYSURU, http://geethashishu.in/], [...\n", " NaN\n", - " NaN\n", - " [Professor & Head |Dept. of TCE| GSSSIET for W...\n", + " ...\n", " [[ResearcherID, F-7045-2018], [Scopus Author I...\n", " [[Electronics and Communication Engineering, P...\n", " [[ACM Distinguished Speaker (Volunteer), Assoc...\n", @@ -7562,10 +7421,13 @@ " [Publons, Multidisciplinary Digital Publishing...\n", " NaN\n", " NaN\n", + " NaN\n", " [geethashishu.in, geethashishu.in, acm.org, go...\n", + " 71.0\n", " \n", " \n", "\n", + "

13 rows × 22 columns

\n", "" ], "text/plain": [ @@ -7644,50 +7506,20 @@ "10448304 [[01.- Juan de Dios Beltrán Mancilla. Teoría O... \n", "10663894 [[GSSSIETW,MYSURU, http://geethashishu.in/], [... \n", "\n", - " primary_email \\\n", - "482862 gustavo.duperre@usal.edu.ar \n", - "554859 Leo_123fa@hotmail.com \n", - "1381092 NaN \n", - "2679353 NaN \n", - "3354430 NaN \n", - "4004281 rrom@ise.pw.edu.pl \n", - "4022480 NaN \n", - "6335357 aan_jaelani@syekhnurjati.ac.id \n", - "6489838 NaN \n", - "7570584 NaN \n", - "10240510 NaN \n", - "10448304 NaN \n", - "10663894 NaN \n", - "\n", - " other_emails \\\n", - "482862 NaN \n", - "554859 [Leoameric123@gmail.com, Frankmericnazac@gmail... \n", - "1381092 NaN \n", - "2679353 NaN \n", - "3354430 NaN \n", - "4004281 [R.Romaniuk@ise.pw.edu.pl, R.Romaniuk@elka.pw.... \n", - "4022480 NaN \n", - "6335357 [iainanjal@gmail.com] \n", - "6489838 NaN \n", - "7570584 NaN \n", - "10240510 NaN \n", - "10448304 NaN \n", - "10663894 NaN \n", - "\n", - " keywords \\\n", - "482862 [History of Art, Humanities, International Coo... \n", - "554859 [Justicia Global; Democracia; Derechos Humanos... \n", - "1381092 [cannabis, cannabis culture, cannabis communit... \n", - "2679353 [Ilmu Ekonomi, Ekonomi Islam, Metodologi Penel... \n", - "3354430 [Supercapacitors, Electrochromic, Photochromic... \n", - "4004281 [telecommunications, photonics, measurement sy... \n", - "4022480 [Computer Security, Computer Networking, Inter... \n", - "6335357 [Islamic Economics, Tourism Industry, Islamic ... \n", - "6489838 [organic chemistry, biochemistry, photochemist... \n", - "7570584 [Inovação, Empreendedorismo, Sustentabilidade] \n", - "10240510 NaN \n", - "10448304 [FILOSOFIA MEDICINA ARQUITECTURA ECONOMÍA DERE... \n", - "10663894 [Professor & Head |Dept. of TCE| GSSSIET for W... \n", + " primary_email ... \\\n", + "482862 gustavo.duperre@usal.edu.ar ... \n", + "554859 Leo_123fa@hotmail.com ... \n", + "1381092 NaN ... \n", + "2679353 NaN ... \n", + "3354430 NaN ... \n", + "4004281 rrom@ise.pw.edu.pl ... \n", + "4022480 NaN ... \n", + "6335357 aan_jaelani@syekhnurjati.ac.id ... \n", + "6489838 NaN ... \n", + "7570584 NaN ... \n", + "10240510 NaN ... \n", + "10448304 NaN ... \n", + "10663894 NaN ... \n", "\n", " external_ids \\\n", "482862 [[Scopus Author ID, 57195936346], [ResearcherI... \n", @@ -7719,20 +7551,20 @@ "10448304 [[, DIPLOMADO EN PRACTICAS DIRECTIVAS PARA OR... \n", "10663894 [[Electronics and Communication Engineering, P... \n", "\n", - " employment n_works \\\n", - "482862 [[Titular Professor, Dirección General de Cult... 13 \n", - "554859 [[Investigador Social, Universidad Católica de... 38 \n", - "1381092 NaN 10 \n", - "2679353 [[Assisten Professor/Dr, Institut Agama Islam ... 72 \n", - "3354430 [[General Director, Scientific Technical Centr... 472 \n", - "4004281 [[Professor, Institute Director, Politechnika ... 5008 \n", - "4022480 [[Consultant, Horizon 2020 Framework Programme... 274 \n", - "6335357 [[Dr, Institut Agama Islam Negeri Syekh Nurjat... 79 \n", - "6489838 [[Assistant Professor, Adam Mickiewicz Univers... 29 \n", - "7570584 [[Professor, Universidade Federal do Rio Grand... 1105 \n", - "10240510 NaN 2023 \n", - "10448304 [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2... 11 \n", - "10663894 [[ACM Distinguished Speaker (Volunteer), Assoc... 93 \n", + " employment n_works \\\n", + "482862 [[Titular Professor, Dirección General de Cult... 13 \n", + "554859 [[Investigador Social, Universidad Católica de... 38 \n", + "1381092 NaN 10 \n", + "2679353 [[Assisten Professor/Dr, Institut Agama Islam ... 72 \n", + "3354430 [[General Director, Scientific Technical Centr... 472 \n", + "4004281 [[Professor, Institute Director, Politechnika ... 5008 \n", + "4022480 [[Consultant, Horizon 2020 Framework Programme... 274 \n", + "6335357 [[Dr, Institut Agama Islam Negeri Syekh Nurjat... 79 \n", + "6489838 [[Assistant Professor, Adam Mickiewicz Univers... 29 \n", + "7570584 [[Professor, Universidade Federal do Rio Grand... 1105 \n", + "10240510 NaN 2023 \n", + "10448304 [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2... 11 \n", + "10663894 [[ACM Distinguished Speaker (Volunteer), Assoc... 93 \n", "\n", " works_source \\\n", "482862 [Gustavo Duperré, Scopus - Elsevier, Publons, ... \n", @@ -7749,53 +7581,55 @@ "10448304 [JUAN DE DIOS BELTR´´ÁN MANCILLA] \n", "10663894 [Publons, Multidisciplinary Digital Publishing... \n", "\n", - " primary_email_domain \\\n", - "482862 usal.edu.ar \n", - "554859 hotmail.com \n", - "1381092 NaN \n", - "2679353 NaN \n", - "3354430 NaN \n", - "4004281 ise.pw.edu.pl \n", - "4022480 NaN \n", - "6335357 syekhnurjati.ac.id \n", - "6489838 NaN \n", - "7570584 NaN \n", - "10240510 NaN \n", - "10448304 NaN \n", - "10663894 NaN \n", + " primary_email_domain \\\n", + "482862 usal.edu.ar \n", + "554859 hotmail.com \n", + "1381092 NaN \n", + "2679353 NaN \n", + "3354430 NaN \n", + "4004281 ise.pw.edu.pl \n", + "4022480 NaN \n", + "6335357 syekhnurjati.ac.id \n", + "6489838 NaN \n", + "7570584 NaN \n", + "10240510 NaN \n", + "10448304 NaN \n", + "10663894 NaN \n", "\n", - " other_email_domains \\\n", - "482862 NaN \n", - "554859 [gmail.com, gmail.com, hotmail.com, baldwin.ed... \n", - "1381092 NaN \n", - "2679353 NaN \n", - "3354430 NaN \n", - "4004281 [ise.pw.edu.pl, elka.pw.edu.pl, cern.ch] \n", - "4022480 NaN \n", - "6335357 [gmail.com] \n", - "6489838 NaN \n", - "7570584 NaN \n", - "10240510 NaN \n", - "10448304 NaN \n", - "10663894 NaN \n", + " other_email_domains n_emails \\\n", + "482862 NaN NaN \n", + "554859 [gmail.com, gmail.com, hotmail.com, baldwin.ed... 5.0 \n", + "1381092 NaN NaN \n", + "2679353 NaN NaN \n", + "3354430 NaN NaN \n", + "4004281 [ise.pw.edu.pl, elka.pw.edu.pl, cern.ch] 3.0 \n", + "4022480 NaN NaN \n", + "6335357 [gmail.com] 1.0 \n", + "6489838 NaN NaN \n", + "7570584 NaN NaN \n", + "10240510 NaN NaN \n", + "10448304 NaN NaN \n", + "10663894 NaN NaN \n", "\n", - " url_domains \n", - "482862 [icomos.ro, unirioja.es, unirioja.es, unc.edu.... \n", - "554859 [concytec.gob.pe, redalyc.org, redalyc.org, un... \n", - "1381092 [goowonderland.com, goowonderland.com, goowond... \n", - "2679353 [google.com, syekhnurjati.ac.id, orcid.org, bl... \n", - "3354430 [youtube.com, isjaee.com, researchgate.net, re... \n", - "4004281 [google.pl, publons.com, scopus.com, mendeley.... \n", - "4022480 [worldassessmentcouncil.org, spseke.sk, bcs.or... \n", - "6335357 [microsoft.com, twitter.com, academia.edu, aca... \n", - "6489838 [biowebspin.com, biowebspin.com, google.com, l... \n", - "7570584 [cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c... \n", - "10240510 [researchgate.net, youtube.com, linkedin.com, ... \n", - "10448304 [yumpu.com, ijopm.org, google.com, blogspot.co... \n", - "10663894 [geethashishu.in, geethashishu.in, acm.org, go... " + " url_domains n_urls \n", + "482862 [icomos.ro, unirioja.es, unirioja.es, unc.edu.... 51.0 \n", + "554859 [concytec.gob.pe, redalyc.org, redalyc.org, un... 61.0 \n", + "1381092 [goowonderland.com, goowonderland.com, goowond... 81.0 \n", + "2679353 [google.com, syekhnurjati.ac.id, orcid.org, bl... 59.0 \n", + "3354430 [youtube.com, isjaee.com, researchgate.net, re... 111.0 \n", + "4004281 [google.pl, publons.com, scopus.com, mendeley.... 114.0 \n", + "4022480 [worldassessmentcouncil.org, spseke.sk, bcs.or... 114.0 \n", + "6335357 [microsoft.com, twitter.com, academia.edu, aca... 67.0 \n", + "6489838 [biowebspin.com, biowebspin.com, google.com, l... 73.0 \n", + "7570584 [cnpq.br, cnpq.br, cnpq.br, cnpq.br, publons.c... 61.0 \n", + "10240510 [researchgate.net, youtube.com, linkedin.com, ... 152.0 \n", + "10448304 [yumpu.com, ijopm.org, google.com, blogspot.co... 69.0 \n", + "10663894 [geethashishu.in, geethashishu.in, acm.org, go... 71.0 \n", + "\n", + "[13 rows x 22 columns]" ] }, - "execution_count": 50, + "execution_count": 48, "metadata": {}, "output_type": "execute_result" } @@ -7806,8 +7640,10 @@ }, { "cell_type": "code", - "execution_count": 51, - "metadata": {}, + "execution_count": 49, + "metadata": { + "scrolled": true + }, "outputs": [ { "data": { @@ -7840,8 +7676,7 @@ " other_names\n", " urls\n", " primary_email\n", - " other_emails\n", - " keywords\n", + " ...\n", " external_ids\n", " education\n", " employment\n", @@ -7849,7 +7684,9 @@ " works_source\n", " primary_email_domain\n", " other_email_domains\n", + " n_emails\n", " url_domains\n", + " n_urls\n", " \n", " \n", " \n", @@ -7865,8 +7702,7 @@ " NaN\n", " [[Adjusting to Change: American Foreign Policy...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " [[Scopus Author ID, 25649901800]]\n", " [[Political Science, Ph.D., Massachusetts Inst...\n", " [[Professor of Government and Politics, George...\n", @@ -7874,7 +7710,9 @@ " [Scopus - Elsevier]\n", " NaN\n", " NaN\n", + " NaN\n", " [wordpress.com, marknkatz.com, gmu.edu, atlant...\n", + " 16.0\n", " \n", " \n", " 72674\n", @@ -7888,8 +7726,7 @@ " NaN\n", " [[Sức khỏe, https://onhealth.vn/], [Khám phụ k...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -7897,7 +7734,9 @@ " [Phòng khám tư nhân Hà Nội]\n", " NaN\n", " NaN\n", + " NaN\n", " [onhealth.vn, onhealth.vn, onhealth.vn, onheal...\n", + " 49.0\n", " \n", " \n", " 172820\n", @@ -7911,8 +7750,7 @@ " [Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...\n", " [[Air Force Office of Scientific Research (WRI...\n", " NaN\n", - " NaN\n", - " [Exolinguistics, Ethnoastronomy, Sociology of ...\n", + " ...\n", " NaN\n", " [[Faculty of Philosophy, History - Ph.D., Char...\n", " [[responsible for the Project Service Level Ag...\n", @@ -7920,7 +7758,9 @@ " [Juan Carlos Garcia Hoyos]\n", " NaN\n", " NaN\n", + " NaN\n", " [af.mil, gst.com, govtribe.com, sbir.gov, open...\n", + " 28.0\n", " \n", " \n", " 209505\n", @@ -7934,8 +7774,7 @@ " NaN\n", " [[Migration Scholar and Ananda , https://grfdt...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " [[Education , B.Ed. After Degree , University ...\n", " [[General Coordinator- University of Alberta C...\n", @@ -7943,7 +7782,9 @@ " [Ananda Majumdar]\n", " NaN\n", " NaN\n", + " NaN\n", " [grfdt.com, linkedin.com, academia.edu, resear...\n", + " 24.0\n", " \n", " \n", " 259877\n", @@ -7957,8 +7798,7 @@ " NaN\n", " [[Website, https://ejournal.stiesyariahbengkal...\n", " NaN\n", - " NaN\n", - " [Akuntansi, Akuntansi Syariah]\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -7966,7 +7806,9 @@ " [JAS (Jurnal Akuntansi Syariah)]\n", " NaN\n", " NaN\n", + " NaN\n", " [stiesyariahbengkalis.ac.id, lipi.go.id, cross...\n", + " 17.0\n", " \n", " \n", " ...\n", @@ -7990,6 +7832,7 @@ " ...\n", " ...\n", " ...\n", + " ...\n", " \n", " \n", " 10494820\n", @@ -8003,8 +7846,7 @@ " [Vanesa Rodriguez, Vanesa N. Rodriguez]\n", " [[De rufianes y franchutas Representaciones y ...\n", " NaN\n", - " NaN\n", - " [Historia - Prostitución - Mujeres - Enfermeda...\n", + " ...\n", " NaN\n", " [[, Maestría en Ciencias Sociales con Mención ...\n", " [[Profesora, Universidad Nacional de La Matanz...\n", @@ -8012,7 +7854,9 @@ " [Vanesa Natalia Rodriguez]\n", " NaN\n", " NaN\n", + " NaN\n", " [unlam.edu.ar, unirioja.es, amazon.fr, abebook...\n", + " 19.0\n", " \n", " \n", " 10495806\n", @@ -8026,8 +7870,7 @@ " [Best Heating & Plumbing Company]\n", " [[Website, https://fix-itrite.com], [Muckrack,...\n", " NaN\n", - " NaN\n", - " [Plumber, Appliance, Refrigerator, Repair , Se...\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8035,7 +7878,9 @@ " [Fix-It Rite]\n", " NaN\n", " NaN\n", + " NaN\n", " [fix-itrite.com, muckrack.com, tumblr.com, dri...\n", + " 11.0\n", " \n", " \n", " 10633545\n", @@ -8049,8 +7894,7 @@ " [Benny Soewandi]\n", " [[Conservation Efforts as a Result of Theoreti...\n", " NaN\n", - " NaN\n", - " [Researchers-Conservator for the Architectural...\n", + " ...\n", " NaN\n", " NaN\n", " [[Membership, Paguyuban Pelestarian Budaya Ban...\n", @@ -8058,7 +7902,9 @@ " [Benny Soewandi]\n", " NaN\n", " NaN\n", + " NaN\n", " [wordpress.com, wordpress.com, linkedin.com, f...\n", + " 11.0\n", " \n", " \n", " 10648241\n", @@ -8072,8 +7918,7 @@ " [B. Yavar, Yavar Bijan]\n", " [[Web of Science (Pub) Researcher ID: A-3544-2...\n", " NaN\n", - " NaN\n", - " [Certainty and Uncertainty, Risk Analysis (Qua...\n", + " ...\n", " [[Scopus Author ID, 56556873600]]\n", " NaN\n", " NaN\n", @@ -8081,7 +7926,9 @@ " [Scopus - Elsevier]\n", " NaN\n", " NaN\n", + " NaN\n", " [publons.com, articulate.com, zenodo.org, orci...\n", + " 15.0\n", " \n", " \n", " 10679699\n", @@ -8095,8 +7942,7 @@ " NaN\n", " [[A Systematic Study on the Dynamic Softening ...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8104,11 +7950,13 @@ " [FENGZHI WU]\n", " NaN\n", " NaN\n", + " NaN\n", " [springer.com, sciencedirect.com, sciencedirec...\n", + " 23.0\n", " \n", " \n", "\n", - "

139 rows × 20 columns

\n", + "

139 rows × 22 columns

\n", "" ], "text/plain": [ @@ -8190,31 +8038,18 @@ "10648241 [[Web of Science (Pub) Researcher ID: A-3544-2... NaN \n", "10679699 [[A Systematic Study on the Dynamic Softening ... NaN \n", "\n", - " other_emails keywords \\\n", - "45566 NaN NaN \n", - "72674 NaN NaN \n", - "172820 NaN [Exolinguistics, Ethnoastronomy, Sociology of ... \n", - "209505 NaN NaN \n", - "259877 NaN [Akuntansi, Akuntansi Syariah] \n", - "... ... ... \n", - "10494820 NaN [Historia - Prostitución - Mujeres - Enfermeda... \n", - "10495806 NaN [Plumber, Appliance, Refrigerator, Repair , Se... \n", - "10633545 NaN [Researchers-Conservator for the Architectural... \n", - "10648241 NaN [Certainty and Uncertainty, Risk Analysis (Qua... \n", - "10679699 NaN NaN \n", - "\n", - " external_ids \\\n", - "45566 [[Scopus Author ID, 25649901800]] \n", - "72674 NaN \n", - "172820 NaN \n", - "209505 NaN \n", - "259877 NaN \n", - "... ... \n", - "10494820 NaN \n", - "10495806 NaN \n", - "10633545 NaN \n", - "10648241 [[Scopus Author ID, 56556873600]] \n", - "10679699 NaN \n", + " ... external_ids \\\n", + "45566 ... [[Scopus Author ID, 25649901800]] \n", + "72674 ... NaN \n", + "172820 ... NaN \n", + "209505 ... NaN \n", + "259877 ... NaN \n", + "... ... ... \n", + "10494820 ... NaN \n", + "10495806 ... NaN \n", + "10633545 ... NaN \n", + "10648241 ... [[Scopus Author ID, 56556873600]] \n", + "10679699 ... NaN \n", "\n", " education \\\n", "45566 [[Political Science, Ph.D., Massachusetts Inst... \n", @@ -8229,62 +8064,62 @@ "10648241 NaN \n", "10679699 NaN \n", "\n", - " employment n_works \\\n", - "45566 [[Professor of Government and Politics, George... 58 \n", - "72674 NaN 4 \n", - "172820 [[responsible for the Project Service Level Ag... 20 \n", - "209505 [[General Coordinator- University of Alberta C... 43 \n", - "259877 NaN 67 \n", - "... ... ... \n", - "10494820 [[Profesora, Universidad Nacional de La Matanz... 7 \n", - "10495806 NaN 1 \n", - "10633545 [[Membership, Paguyuban Pelestarian Budaya Ban... 2 \n", - "10648241 NaN 6 \n", - "10679699 NaN 3 \n", + " employment n_works \\\n", + "45566 [[Professor of Government and Politics, George... 58 \n", + "72674 NaN 4 \n", + "172820 [[responsible for the Project Service Level Ag... 20 \n", + "209505 [[General Coordinator- University of Alberta C... 43 \n", + "259877 NaN 67 \n", + "... ... ... \n", + "10494820 [[Profesora, Universidad Nacional de La Matanz... 7 \n", + "10495806 NaN 1 \n", + "10633545 [[Membership, Paguyuban Pelestarian Budaya Ban... 2 \n", + "10648241 NaN 6 \n", + "10679699 NaN 3 \n", "\n", - " works_source primary_email_domain \\\n", - "45566 [Scopus - Elsevier] NaN \n", - "72674 [Phòng khám tư nhân Hà Nội] NaN \n", - "172820 [Juan Carlos Garcia Hoyos] NaN \n", - "209505 [Ananda Majumdar] NaN \n", - "259877 [JAS (Jurnal Akuntansi Syariah)] NaN \n", - "... ... ... \n", - "10494820 [Vanesa Natalia Rodriguez] NaN \n", - "10495806 [Fix-It Rite] NaN \n", - "10633545 [Benny Soewandi] NaN \n", - "10648241 [Scopus - Elsevier] NaN \n", - "10679699 [FENGZHI WU] NaN \n", + " works_source primary_email_domain \\\n", + "45566 [Scopus - Elsevier] NaN \n", + "72674 [Phòng khám tư nhân Hà Nội] NaN \n", + "172820 [Juan Carlos Garcia Hoyos] NaN \n", + "209505 [Ananda Majumdar] NaN \n", + "259877 [JAS (Jurnal Akuntansi Syariah)] NaN \n", + "... ... ... \n", + "10494820 [Vanesa Natalia Rodriguez] NaN \n", + "10495806 [Fix-It Rite] NaN \n", + "10633545 [Benny Soewandi] NaN \n", + "10648241 [Scopus - Elsevier] NaN \n", + "10679699 [FENGZHI WU] NaN \n", "\n", - " other_email_domains \\\n", - "45566 NaN \n", - "72674 NaN \n", - "172820 NaN \n", - "209505 NaN \n", - "259877 NaN \n", - "... ... \n", - "10494820 NaN \n", - "10495806 NaN \n", - "10633545 NaN \n", - "10648241 NaN \n", - "10679699 NaN \n", + " other_email_domains n_emails \\\n", + "45566 NaN NaN \n", + "72674 NaN NaN \n", + "172820 NaN NaN \n", + "209505 NaN NaN \n", + "259877 NaN NaN \n", + "... ... ... \n", + "10494820 NaN NaN \n", + "10495806 NaN NaN \n", + "10633545 NaN NaN \n", + "10648241 NaN NaN \n", + "10679699 NaN NaN \n", "\n", - " url_domains \n", - "45566 [wordpress.com, marknkatz.com, gmu.edu, atlant... \n", - "72674 [onhealth.vn, onhealth.vn, onhealth.vn, onheal... \n", - "172820 [af.mil, gst.com, govtribe.com, sbir.gov, open... \n", - "209505 [grfdt.com, linkedin.com, academia.edu, resear... \n", - "259877 [stiesyariahbengkalis.ac.id, lipi.go.id, cross... \n", - "... ... \n", - "10494820 [unlam.edu.ar, unirioja.es, amazon.fr, abebook... \n", - "10495806 [fix-itrite.com, muckrack.com, tumblr.com, dri... \n", - "10633545 [wordpress.com, wordpress.com, linkedin.com, f... \n", - "10648241 [publons.com, articulate.com, zenodo.org, orci... \n", - "10679699 [springer.com, sciencedirect.com, sciencedirec... \n", + " url_domains n_urls \n", + "45566 [wordpress.com, marknkatz.com, gmu.edu, atlant... 16.0 \n", + "72674 [onhealth.vn, onhealth.vn, onhealth.vn, onheal... 49.0 \n", + "172820 [af.mil, gst.com, govtribe.com, sbir.gov, open... 28.0 \n", + "209505 [grfdt.com, linkedin.com, academia.edu, resear... 24.0 \n", + "259877 [stiesyariahbengkalis.ac.id, lipi.go.id, cross... 17.0 \n", + "... ... ... \n", + "10494820 [unlam.edu.ar, unirioja.es, amazon.fr, abebook... 19.0 \n", + "10495806 [fix-itrite.com, muckrack.com, tumblr.com, dri... 11.0 \n", + "10633545 [wordpress.com, wordpress.com, linkedin.com, f... 11.0 \n", + "10648241 [publons.com, articulate.com, zenodo.org, orci... 15.0 \n", + "10679699 [springer.com, sciencedirect.com, sciencedirec... 23.0 \n", "\n", - "[139 rows x 20 columns]" + "[139 rows x 22 columns]" ] }, - "execution_count": 51, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } @@ -8295,8 +8130,10 @@ }, { "cell_type": "code", - "execution_count": 52, - "metadata": {}, + "execution_count": 50, + "metadata": { + "scrolled": true + }, "outputs": [ { "data": { @@ -8329,8 +8166,7 @@ " other_names\n", " urls\n", " primary_email\n", - " other_emails\n", - " keywords\n", + " ...\n", " external_ids\n", " education\n", " employment\n", @@ -8338,7 +8174,9 @@ " works_source\n", " primary_email_domain\n", " other_email_domains\n", + " n_emails\n", " url_domains\n", + " n_urls\n", " \n", " \n", " \n", @@ -8354,8 +8192,7 @@ " NaN\n", " [[Adjusting to Change: American Foreign Policy...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " [[Scopus Author ID, 25649901800]]\n", " [[Political Science, Ph.D., Massachusetts Inst...\n", " [[Professor of Government and Politics, George...\n", @@ -8363,7 +8200,9 @@ " Scopus - Elsevier\n", " NaN\n", " NaN\n", + " NaN\n", " [wordpress.com, marknkatz.com, gmu.edu, atlant...\n", + " 16.0\n", " \n", " \n", " 1\n", @@ -8377,8 +8216,7 @@ " NaN\n", " [[Sức khỏe, https://onhealth.vn/], [Khám phụ k...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8386,7 +8224,9 @@ " Phòng khám tư nhân Hà Nội\n", " NaN\n", " NaN\n", + " NaN\n", " [onhealth.vn, onhealth.vn, onhealth.vn, onheal...\n", + " 49.0\n", " \n", " \n", " 2\n", @@ -8400,8 +8240,7 @@ " [Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...\n", " [[Air Force Office of Scientific Research (WRI...\n", " NaN\n", - " NaN\n", - " [Exolinguistics, Ethnoastronomy, Sociology of ...\n", + " ...\n", " NaN\n", " [[Faculty of Philosophy, History - Ph.D., Char...\n", " [[responsible for the Project Service Level Ag...\n", @@ -8409,7 +8248,9 @@ " Juan Carlos Garcia Hoyos\n", " NaN\n", " NaN\n", + " NaN\n", " [af.mil, gst.com, govtribe.com, sbir.gov, open...\n", + " 28.0\n", " \n", " \n", " 3\n", @@ -8423,8 +8264,7 @@ " NaN\n", " [[Migration Scholar and Ananda , https://grfdt...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " [[Education , B.Ed. After Degree , University ...\n", " [[General Coordinator- University of Alberta C...\n", @@ -8432,7 +8272,9 @@ " Ananda Majumdar\n", " NaN\n", " NaN\n", + " NaN\n", " [grfdt.com, linkedin.com, academia.edu, resear...\n", + " 24.0\n", " \n", " \n", " 4\n", @@ -8446,8 +8288,7 @@ " NaN\n", " [[Website, https://ejournal.stiesyariahbengkal...\n", " NaN\n", - " NaN\n", - " [Akuntansi, Akuntansi Syariah]\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8455,7 +8296,9 @@ " JAS (Jurnal Akuntansi Syariah)\n", " NaN\n", " NaN\n", + " NaN\n", " [stiesyariahbengkalis.ac.id, lipi.go.id, cross...\n", + " 17.0\n", " \n", " \n", " ...\n", @@ -8479,6 +8322,7 @@ " ...\n", " ...\n", " ...\n", + " ...\n", " \n", " \n", " 134\n", @@ -8492,8 +8336,7 @@ " [Vanesa Rodriguez, Vanesa N. Rodriguez]\n", " [[De rufianes y franchutas Representaciones y ...\n", " NaN\n", - " NaN\n", - " [Historia - Prostitución - Mujeres - Enfermeda...\n", + " ...\n", " NaN\n", " [[, Maestría en Ciencias Sociales con Mención ...\n", " [[Profesora, Universidad Nacional de La Matanz...\n", @@ -8501,7 +8344,9 @@ " Vanesa Natalia Rodriguez\n", " NaN\n", " NaN\n", + " NaN\n", " [unlam.edu.ar, unirioja.es, amazon.fr, abebook...\n", + " 19.0\n", " \n", " \n", " 135\n", @@ -8515,8 +8360,7 @@ " [Best Heating & Plumbing Company]\n", " [[Website, https://fix-itrite.com], [Muckrack,...\n", " NaN\n", - " NaN\n", - " [Plumber, Appliance, Refrigerator, Repair , Se...\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8524,7 +8368,9 @@ " Fix-It Rite\n", " NaN\n", " NaN\n", + " NaN\n", " [fix-itrite.com, muckrack.com, tumblr.com, dri...\n", + " 11.0\n", " \n", " \n", " 136\n", @@ -8538,8 +8384,7 @@ " [Benny Soewandi]\n", " [[Conservation Efforts as a Result of Theoreti...\n", " NaN\n", - " NaN\n", - " [Researchers-Conservator for the Architectural...\n", + " ...\n", " NaN\n", " NaN\n", " [[Membership, Paguyuban Pelestarian Budaya Ban...\n", @@ -8547,7 +8392,9 @@ " Benny Soewandi\n", " NaN\n", " NaN\n", + " NaN\n", " [wordpress.com, wordpress.com, linkedin.com, f...\n", + " 11.0\n", " \n", " \n", " 137\n", @@ -8561,8 +8408,7 @@ " [B. Yavar, Yavar Bijan]\n", " [[Web of Science (Pub) Researcher ID: A-3544-2...\n", " NaN\n", - " NaN\n", - " [Certainty and Uncertainty, Risk Analysis (Qua...\n", + " ...\n", " [[Scopus Author ID, 56556873600]]\n", " NaN\n", " NaN\n", @@ -8570,7 +8416,9 @@ " Scopus - Elsevier\n", " NaN\n", " NaN\n", + " NaN\n", " [publons.com, articulate.com, zenodo.org, orci...\n", + " 15.0\n", " \n", " \n", " 138\n", @@ -8584,8 +8432,7 @@ " NaN\n", " [[A Systematic Study on the Dynamic Softening ...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8593,11 +8440,13 @@ " FENGZHI WU\n", " NaN\n", " NaN\n", + " NaN\n", " [springer.com, sciencedirect.com, sciencedirec...\n", + " 23.0\n", " \n", " \n", "\n", - "

139 rows × 20 columns

\n", + "

139 rows × 22 columns

\n", "" ], "text/plain": [ @@ -8653,31 +8502,18 @@ "137 [B. Yavar, Yavar Bijan] \n", "138 NaN \n", "\n", - " urls primary_email \\\n", - "0 [[Adjusting to Change: American Foreign Policy... NaN \n", - "1 [[Sức khỏe, https://onhealth.vn/], [Khám phụ k... NaN \n", - "2 [[Air Force Office of Scientific Research (WRI... NaN \n", - "3 [[Migration Scholar and Ananda , https://grfdt... NaN \n", - "4 [[Website, https://ejournal.stiesyariahbengkal... NaN \n", - ".. ... ... \n", - "134 [[De rufianes y franchutas Representaciones y ... NaN \n", - "135 [[Website, https://fix-itrite.com], [Muckrack,... NaN \n", - "136 [[Conservation Efforts as a Result of Theoreti... NaN \n", - "137 [[Web of Science (Pub) Researcher ID: A-3544-2... NaN \n", - "138 [[A Systematic Study on the Dynamic Softening ... NaN \n", - "\n", - " other_emails keywords \\\n", - "0 NaN NaN \n", - "1 NaN NaN \n", - "2 NaN [Exolinguistics, Ethnoastronomy, Sociology of ... \n", - "3 NaN NaN \n", - "4 NaN [Akuntansi, Akuntansi Syariah] \n", - ".. ... ... \n", - "134 NaN [Historia - Prostitución - Mujeres - Enfermeda... \n", - "135 NaN [Plumber, Appliance, Refrigerator, Repair , Se... \n", - "136 NaN [Researchers-Conservator for the Architectural... \n", - "137 NaN [Certainty and Uncertainty, Risk Analysis (Qua... \n", - "138 NaN NaN \n", + " urls primary_email ... \\\n", + "0 [[Adjusting to Change: American Foreign Policy... NaN ... \n", + "1 [[Sức khỏe, https://onhealth.vn/], [Khám phụ k... NaN ... \n", + "2 [[Air Force Office of Scientific Research (WRI... NaN ... \n", + "3 [[Migration Scholar and Ananda , https://grfdt... NaN ... \n", + "4 [[Website, https://ejournal.stiesyariahbengkal... NaN ... \n", + ".. ... ... ... \n", + "134 [[De rufianes y franchutas Representaciones y ... NaN ... \n", + "135 [[Website, https://fix-itrite.com], [Muckrack,... NaN ... \n", + "136 [[Conservation Efforts as a Result of Theoreti... NaN ... \n", + "137 [[Web of Science (Pub) Researcher ID: A-3544-2... NaN ... \n", + "138 [[A Systematic Study on the Dynamic Softening ... NaN ... \n", "\n", " external_ids \\\n", "0 [[Scopus Author ID, 25649901800]] \n", @@ -8705,49 +8541,49 @@ "137 NaN \n", "138 NaN \n", "\n", - " employment n_works \\\n", - "0 [[Professor of Government and Politics, George... 58 \n", - "1 NaN 4 \n", - "2 [[responsible for the Project Service Level Ag... 20 \n", - "3 [[General Coordinator- University of Alberta C... 43 \n", - "4 NaN 67 \n", - ".. ... ... \n", - "134 [[Profesora, Universidad Nacional de La Matanz... 7 \n", - "135 NaN 1 \n", - "136 [[Membership, Paguyuban Pelestarian Budaya Ban... 2 \n", - "137 NaN 6 \n", - "138 NaN 3 \n", + " employment n_works \\\n", + "0 [[Professor of Government and Politics, George... 58 \n", + "1 NaN 4 \n", + "2 [[responsible for the Project Service Level Ag... 20 \n", + "3 [[General Coordinator- University of Alberta C... 43 \n", + "4 NaN 67 \n", + ".. ... ... \n", + "134 [[Profesora, Universidad Nacional de La Matanz... 7 \n", + "135 NaN 1 \n", + "136 [[Membership, Paguyuban Pelestarian Budaya Ban... 2 \n", + "137 NaN 6 \n", + "138 NaN 3 \n", "\n", - " works_source primary_email_domain other_email_domains \\\n", - "0 Scopus - Elsevier NaN NaN \n", - "1 Phòng khám tư nhân Hà Nội NaN NaN \n", - "2 Juan Carlos Garcia Hoyos NaN NaN \n", - "3 Ananda Majumdar NaN NaN \n", - "4 JAS (Jurnal Akuntansi Syariah) NaN NaN \n", - ".. ... ... ... \n", - "134 Vanesa Natalia Rodriguez NaN NaN \n", - "135 Fix-It Rite NaN NaN \n", - "136 Benny Soewandi NaN NaN \n", - "137 Scopus - Elsevier NaN NaN \n", - "138 FENGZHI WU NaN NaN \n", + " works_source primary_email_domain other_email_domains \\\n", + "0 Scopus - Elsevier NaN NaN \n", + "1 Phòng khám tư nhân Hà Nội NaN NaN \n", + "2 Juan Carlos Garcia Hoyos NaN NaN \n", + "3 Ananda Majumdar NaN NaN \n", + "4 JAS (Jurnal Akuntansi Syariah) NaN NaN \n", + ".. ... ... ... \n", + "134 Vanesa Natalia Rodriguez NaN NaN \n", + "135 Fix-It Rite NaN NaN \n", + "136 Benny Soewandi NaN NaN \n", + "137 Scopus - Elsevier NaN NaN \n", + "138 FENGZHI WU NaN NaN \n", "\n", - " url_domains \n", - "0 [wordpress.com, marknkatz.com, gmu.edu, atlant... \n", - "1 [onhealth.vn, onhealth.vn, onhealth.vn, onheal... \n", - "2 [af.mil, gst.com, govtribe.com, sbir.gov, open... \n", - "3 [grfdt.com, linkedin.com, academia.edu, resear... \n", - "4 [stiesyariahbengkalis.ac.id, lipi.go.id, cross... \n", - ".. ... \n", - "134 [unlam.edu.ar, unirioja.es, amazon.fr, abebook... \n", - "135 [fix-itrite.com, muckrack.com, tumblr.com, dri... \n", - "136 [wordpress.com, wordpress.com, linkedin.com, f... \n", - "137 [publons.com, articulate.com, zenodo.org, orci... \n", - "138 [springer.com, sciencedirect.com, sciencedirec... \n", + " n_emails url_domains n_urls \n", + "0 NaN [wordpress.com, marknkatz.com, gmu.edu, atlant... 16.0 \n", + "1 NaN [onhealth.vn, onhealth.vn, onhealth.vn, onheal... 49.0 \n", + "2 NaN [af.mil, gst.com, govtribe.com, sbir.gov, open... 28.0 \n", + "3 NaN [grfdt.com, linkedin.com, academia.edu, resear... 24.0 \n", + "4 NaN [stiesyariahbengkalis.ac.id, lipi.go.id, cross... 17.0 \n", + ".. ... ... ... \n", + "134 NaN [unlam.edu.ar, unirioja.es, amazon.fr, abebook... 19.0 \n", + "135 NaN [fix-itrite.com, muckrack.com, tumblr.com, dri... 11.0 \n", + "136 NaN [wordpress.com, wordpress.com, linkedin.com, f... 11.0 \n", + "137 NaN [publons.com, articulate.com, zenodo.org, orci... 15.0 \n", + "138 NaN [springer.com, sciencedirect.com, sciencedirec... 23.0 \n", "\n", - "[139 rows x 20 columns]" + "[139 rows x 22 columns]" ] }, - "execution_count": 52, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } @@ -8759,8 +8595,10 @@ }, { "cell_type": "code", - "execution_count": 53, - "metadata": {}, + "execution_count": 51, + "metadata": { + "scrolled": true + }, "outputs": [ { "data": { @@ -8793,8 +8631,7 @@ " other_names\n", " urls\n", " primary_email\n", - " other_emails\n", - " keywords\n", + " ...\n", " external_ids\n", " education\n", " employment\n", @@ -8802,7 +8639,9 @@ " works_source\n", " primary_email_domain\n", " other_email_domains\n", + " n_emails\n", " url_domains\n", + " n_urls\n", " \n", " \n", " \n", @@ -8818,8 +8657,7 @@ " NaN\n", " [[Sức khỏe, https://onhealth.vn/], [Khám phụ k...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8827,7 +8665,9 @@ " Phòng khám tư nhân Hà Nội\n", " NaN\n", " NaN\n", + " NaN\n", " [onhealth.vn, onhealth.vn, onhealth.vn, onheal...\n", + " 49.0\n", " \n", " \n", " 2\n", @@ -8841,8 +8681,7 @@ " [Juan Carlos Garcia Hoyos /, EXTRATERRANOVAS /...\n", " [[Air Force Office of Scientific Research (WRI...\n", " NaN\n", - " NaN\n", - " [Exolinguistics, Ethnoastronomy, Sociology of ...\n", + " ...\n", " NaN\n", " [[Faculty of Philosophy, History - Ph.D., Char...\n", " [[responsible for the Project Service Level Ag...\n", @@ -8850,7 +8689,9 @@ " Juan Carlos Garcia Hoyos\n", " NaN\n", " NaN\n", + " NaN\n", " [af.mil, gst.com, govtribe.com, sbir.gov, open...\n", + " 28.0\n", " \n", " \n", " 3\n", @@ -8864,8 +8705,7 @@ " NaN\n", " [[Migration Scholar and Ananda , https://grfdt...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " [[Education , B.Ed. After Degree , University ...\n", " [[General Coordinator- University of Alberta C...\n", @@ -8873,7 +8713,9 @@ " Ananda Majumdar\n", " NaN\n", " NaN\n", + " NaN\n", " [grfdt.com, linkedin.com, academia.edu, resear...\n", + " 24.0\n", " \n", " \n", " 4\n", @@ -8887,8 +8729,7 @@ " NaN\n", " [[Website, https://ejournal.stiesyariahbengkal...\n", " NaN\n", - " NaN\n", - " [Akuntansi, Akuntansi Syariah]\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -8896,7 +8737,9 @@ " JAS (Jurnal Akuntansi Syariah)\n", " NaN\n", " NaN\n", + " NaN\n", " [stiesyariahbengkalis.ac.id, lipi.go.id, cross...\n", + " 17.0\n", " \n", " \n", " 5\n", @@ -8910,8 +8753,7 @@ " NaN\n", " [[Scopus Profile, https://www.scopus.com/dashb...\n", " NaN\n", - " NaN\n", - " [Applied Econometrics, Development Economics, ...\n", + " ...\n", " NaN\n", " [[Economics, Doctor of Philosophy , Curtin Uni...\n", " [[Director, Educational Development, Strathmor...\n", @@ -8919,7 +8761,9 @@ " Caroline Wanjiru Kariuki\n", " NaN\n", " NaN\n", + " NaN\n", " [scopus.com, mendeley.com, publons.com, resear...\n", + " 13.0\n", " \n", " \n", " ...\n", @@ -8943,6 +8787,7 @@ " ...\n", " ...\n", " ...\n", + " ...\n", " \n", " \n", " 132\n", @@ -8956,8 +8801,7 @@ " [S. Hawthorne, Susan C. C. Hawthorne]\n", " [[Spinifex Press, http://www.spinifexpress.com...\n", " NaN\n", - " NaN\n", - " [Womens Studies, Philosophy, Ancient Greek, Sa...\n", + " ...\n", " [[ResearcherID, K-6039-2018]]\n", " [[School of Asian Studies, Honours Sanskrit, A...\n", " [[Adjunct Professor, James Cook University, To...\n", @@ -8965,7 +8809,9 @@ " Susan Hawthorne\n", " NaN\n", " NaN\n", + " NaN\n", " [spinifexpress.com.au, linkedin.com, twitter.c...\n", + " 12.0\n", " \n", " \n", " 133\n", @@ -8979,8 +8825,7 @@ " [Juan de Dios Beltrán Mancilla, FILÓSOFO AUTOD...\n", " [[01.- Juan de Dios Beltrán Mancilla. Teoría O...\n", " NaN\n", - " NaN\n", - " [FILOSOFIA MEDICINA ARQUITECTURA ECONOMÍA DERE...\n", + " ...\n", " NaN\n", " [[, DIPLOMADO EN PRACTICAS DIRECTIVAS PARA OR...\n", " [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2...\n", @@ -8988,7 +8833,9 @@ " JUAN DE DIOS BELTR´´ÁN MANCILLA\n", " NaN\n", " NaN\n", + " NaN\n", " [yumpu.com, ijopm.org, google.com, blogspot.co...\n", + " 69.0\n", " \n", " \n", " 134\n", @@ -9002,8 +8849,7 @@ " [Vanesa Rodriguez, Vanesa N. Rodriguez]\n", " [[De rufianes y franchutas Representaciones y ...\n", " NaN\n", - " NaN\n", - " [Historia - Prostitución - Mujeres - Enfermeda...\n", + " ...\n", " NaN\n", " [[, Maestría en Ciencias Sociales con Mención ...\n", " [[Profesora, Universidad Nacional de La Matanz...\n", @@ -9011,7 +8857,9 @@ " Vanesa Natalia Rodriguez\n", " NaN\n", " NaN\n", + " NaN\n", " [unlam.edu.ar, unirioja.es, amazon.fr, abebook...\n", + " 19.0\n", " \n", " \n", " 136\n", @@ -9025,8 +8873,7 @@ " [Benny Soewandi]\n", " [[Conservation Efforts as a Result of Theoreti...\n", " NaN\n", - " NaN\n", - " [Researchers-Conservator for the Architectural...\n", + " ...\n", " NaN\n", " NaN\n", " [[Membership, Paguyuban Pelestarian Budaya Ban...\n", @@ -9034,7 +8881,9 @@ " Benny Soewandi\n", " NaN\n", " NaN\n", + " NaN\n", " [wordpress.com, wordpress.com, linkedin.com, f...\n", + " 11.0\n", " \n", " \n", " 138\n", @@ -9048,8 +8897,7 @@ " NaN\n", " [[A Systematic Study on the Dynamic Softening ...\n", " NaN\n", - " NaN\n", - " NaN\n", + " ...\n", " NaN\n", " NaN\n", " NaN\n", @@ -9057,11 +8905,13 @@ " FENGZHI WU\n", " NaN\n", " NaN\n", + " NaN\n", " [springer.com, sciencedirect.com, sciencedirec...\n", + " 23.0\n", " \n", " \n", "\n", - "

108 rows × 20 columns

\n", + "

108 rows × 22 columns

\n", "" ], "text/plain": [ @@ -9117,31 +8967,18 @@ "136 [Benny Soewandi] \n", "138 NaN \n", "\n", - " urls primary_email \\\n", - "1 [[Sức khỏe, https://onhealth.vn/], [Khám phụ k... NaN \n", - "2 [[Air Force Office of Scientific Research (WRI... NaN \n", - "3 [[Migration Scholar and Ananda , https://grfdt... NaN \n", - "4 [[Website, https://ejournal.stiesyariahbengkal... NaN \n", - "5 [[Scopus Profile, https://www.scopus.com/dashb... NaN \n", - ".. ... ... \n", - "132 [[Spinifex Press, http://www.spinifexpress.com... NaN \n", - "133 [[01.- Juan de Dios Beltrán Mancilla. Teoría O... NaN \n", - "134 [[De rufianes y franchutas Representaciones y ... NaN \n", - "136 [[Conservation Efforts as a Result of Theoreti... NaN \n", - "138 [[A Systematic Study on the Dynamic Softening ... NaN \n", - "\n", - " other_emails keywords \\\n", - "1 NaN NaN \n", - "2 NaN [Exolinguistics, Ethnoastronomy, Sociology of ... \n", - "3 NaN NaN \n", - "4 NaN [Akuntansi, Akuntansi Syariah] \n", - "5 NaN [Applied Econometrics, Development Economics, ... \n", - ".. ... ... \n", - "132 NaN [Womens Studies, Philosophy, Ancient Greek, Sa... \n", - "133 NaN [FILOSOFIA MEDICINA ARQUITECTURA ECONOMÍA DERE... \n", - "134 NaN [Historia - Prostitución - Mujeres - Enfermeda... \n", - "136 NaN [Researchers-Conservator for the Architectural... \n", - "138 NaN NaN \n", + " urls primary_email ... \\\n", + "1 [[Sức khỏe, https://onhealth.vn/], [Khám phụ k... NaN ... \n", + "2 [[Air Force Office of Scientific Research (WRI... NaN ... \n", + "3 [[Migration Scholar and Ananda , https://grfdt... NaN ... \n", + "4 [[Website, https://ejournal.stiesyariahbengkal... NaN ... \n", + "5 [[Scopus Profile, https://www.scopus.com/dashb... NaN ... \n", + ".. ... ... ... \n", + "132 [[Spinifex Press, http://www.spinifexpress.com... NaN ... \n", + "133 [[01.- Juan de Dios Beltrán Mancilla. Teoría O... NaN ... \n", + "134 [[De rufianes y franchutas Representaciones y ... NaN ... \n", + "136 [[Conservation Efforts as a Result of Theoreti... NaN ... \n", + "138 [[A Systematic Study on the Dynamic Softening ... NaN ... \n", "\n", " external_ids \\\n", "1 NaN \n", @@ -9169,49 +9006,62 @@ "136 NaN \n", "138 NaN \n", "\n", - " employment n_works \\\n", - "1 NaN 4 \n", - "2 [[responsible for the Project Service Level Ag... 20 \n", - "3 [[General Coordinator- University of Alberta C... 43 \n", - "4 NaN 67 \n", - "5 [[Director, Educational Development, Strathmor... 4 \n", - ".. ... ... \n", - "132 [[Adjunct Professor, James Cook University, To... 352 \n", - "133 [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2... 11 \n", - "134 [[Profesora, Universidad Nacional de La Matanz... 7 \n", - "136 [[Membership, Paguyuban Pelestarian Budaya Ban... 2 \n", - "138 NaN 3 \n", + " employment n_works \\\n", + "1 NaN 4 \n", + "2 [[responsible for the Project Service Level Ag... 20 \n", + "3 [[General Coordinator- University of Alberta C... 43 \n", + "4 NaN 67 \n", + "5 [[Director, Educational Development, Strathmor... 4 \n", + ".. ... ... \n", + "132 [[Adjunct Professor, James Cook University, To... 352 \n", + "133 [[INSPECTOR GENERAL JORNADA VESPERTINA // De 2... 11 \n", + "134 [[Profesora, Universidad Nacional de La Matanz... 7 \n", + "136 [[Membership, Paguyuban Pelestarian Budaya Ban... 2 \n", + "138 NaN 3 \n", "\n", - " works_source primary_email_domain other_email_domains \\\n", - "1 Phòng khám tư nhân Hà Nội NaN NaN \n", - "2 Juan Carlos Garcia Hoyos NaN NaN \n", - "3 Ananda Majumdar NaN NaN \n", - "4 JAS (Jurnal Akuntansi Syariah) NaN NaN \n", - "5 Caroline Wanjiru Kariuki NaN NaN \n", - ".. ... ... ... \n", - "132 Susan Hawthorne NaN NaN \n", - "133 JUAN DE DIOS BELTR´´ÁN MANCILLA NaN NaN \n", - "134 Vanesa Natalia Rodriguez NaN NaN \n", - "136 Benny Soewandi NaN NaN \n", - "138 FENGZHI WU NaN NaN \n", + " works_source primary_email_domain \\\n", + "1 Phòng khám tư nhân Hà Nội NaN \n", + "2 Juan Carlos Garcia Hoyos NaN \n", + "3 Ananda Majumdar NaN \n", + "4 JAS (Jurnal Akuntansi Syariah) NaN \n", + "5 Caroline Wanjiru Kariuki NaN \n", + ".. ... ... \n", + "132 Susan Hawthorne NaN \n", + "133 JUAN DE DIOS BELTR´´ÁN MANCILLA NaN \n", + "134 Vanesa Natalia Rodriguez NaN \n", + "136 Benny Soewandi NaN \n", + "138 FENGZHI WU NaN \n", "\n", - " url_domains \n", - "1 [onhealth.vn, onhealth.vn, onhealth.vn, onheal... \n", - "2 [af.mil, gst.com, govtribe.com, sbir.gov, open... \n", - "3 [grfdt.com, linkedin.com, academia.edu, resear... \n", - "4 [stiesyariahbengkalis.ac.id, lipi.go.id, cross... \n", - "5 [scopus.com, mendeley.com, publons.com, resear... \n", - ".. ... \n", - "132 [spinifexpress.com.au, linkedin.com, twitter.c... \n", - "133 [yumpu.com, ijopm.org, google.com, blogspot.co... \n", - "134 [unlam.edu.ar, unirioja.es, amazon.fr, abebook... \n", - "136 [wordpress.com, wordpress.com, linkedin.com, f... \n", - "138 [springer.com, sciencedirect.com, sciencedirec... \n", + " other_email_domains n_emails \\\n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "5 NaN NaN \n", + ".. ... ... \n", + "132 NaN NaN \n", + "133 NaN NaN \n", + "134 NaN NaN \n", + "136 NaN NaN \n", + "138 NaN NaN \n", "\n", - "[108 rows x 20 columns]" + " url_domains n_urls \n", + "1 [onhealth.vn, onhealth.vn, onhealth.vn, onheal... 49.0 \n", + "2 [af.mil, gst.com, govtribe.com, sbir.gov, open... 28.0 \n", + "3 [grfdt.com, linkedin.com, academia.edu, resear... 24.0 \n", + "4 [stiesyariahbengkalis.ac.id, lipi.go.id, cross... 17.0 \n", + "5 [scopus.com, mendeley.com, publons.com, resear... 13.0 \n", + ".. ... ... \n", + "132 [spinifexpress.com.au, linkedin.com, twitter.c... 12.0 \n", + "133 [yumpu.com, ijopm.org, google.com, blogspot.co... 69.0 \n", + "134 [unlam.edu.ar, unirioja.es, amazon.fr, abebook... 19.0 \n", + "136 [wordpress.com, wordpress.com, linkedin.com, f... 11.0 \n", + "138 [springer.com, sciencedirect.com, sciencedirec... 23.0 \n", + "\n", + "[108 rows x 22 columns]" ] }, - "execution_count": 53, + "execution_count": 51, "metadata": {}, "output_type": "execute_result" } @@ -9227,49 +9077,2852 @@ "## Works source" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Paste from Miriam" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## External IDs" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "External IDs should come from reliable sources. ORCiD registrants cannot add them freely." + ] + }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 52, "metadata": {}, "outputs": [], "source": [ - "def remove_own_source(lst, own):\n", - " res = []\n", - " if isinstance(lst, list) and pd.notna(own):\n", - " for ws in lst:\n", - " if ws.find(own) == -1:\n", - " res.append(ws)\n", - " return res\n", - " else:\n", - " return np.na()" + "df.loc[df['external_ids'].notna(), 'n_ids'] = df[df['external_ids'].notna()].external_ids.str.len()" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 1.285292e+06\n", + "mean 1.357162e+00\n", + "std 6.607097e-01\n", + "min 1.000000e+00\n", + "25% 1.000000e+00\n", + "50% 1.000000e+00\n", + "75% 2.000000e+00\n", + "max 8.000000e+01\n", + "Name: n_ids, dtype: float64" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.n_ids.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
orcidclaimedverified_emailverified_primary_emailgiven_namesfamily_namebiographyother_namesurlsprimary_email...educationemploymentn_worksworks_sourceprimary_email_domainother_email_domainsn_emailsurl_domainsn_urlsn_ids
92287930000-0002-9554-6633111John AWilliamsNaNNaN[[Aston University profile page, https://resea...NaN...NaN[[, Aston University, Birmingham, , GB, 1722, ...91[Aston Research Explorer]NaNNaNNaN[aston.ac.uk]1.080.0
\n", + "

1 rows × 23 columns

\n", + "
" + ], + "text/plain": [ + " orcid claimed verified_email verified_primary_email \\\n", + "9228793 0000-0002-9554-6633 1 1 1 \n", + "\n", + " given_names family_name biography other_names \\\n", + "9228793 John A Williams NaN NaN \n", + "\n", + " urls primary_email ... \\\n", + "9228793 [[Aston University profile page, https://resea... NaN ... \n", + "\n", + " education employment n_works \\\n", + "9228793 NaN [[, Aston University, Birmingham, , GB, 1722, ... 91 \n", + "\n", + " works_source primary_email_domain other_email_domains \\\n", + "9228793 [Aston Research Explorer] NaN NaN \n", + "\n", + " n_emails url_domains n_urls n_ids \n", + "9228793 NaN [aston.ac.uk] 1.0 80.0 \n", + "\n", + "[1 rows x 23 columns]" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[df.n_ids == df.n_ids.max()]" ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, + "outputs": [], + "source": [ + "ids = df[['orcid', 'external_ids']].explode('external_ids').reset_index(drop=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, "outputs": [ { - "ename": "NameError", - "evalue": "name 'np' is not defined", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'ext_works_source'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mremove_own_source\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'works_source'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'given_names'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\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[0m", - "\u001b[0;32m~/.virtualenvs/data-science/lib/python3.8/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(self, func, axis, raw, result_type, args, **kwds)\u001b[0m\n\u001b[1;32m 7766\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 7767\u001b[0m )\n\u001b[0;32m-> 7768\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_result\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[0m\u001b[1;32m 7769\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 7770\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mapplymap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mna_action\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mOptional\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mDataFrame\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/apply.py\u001b[0m in \u001b[0;36mget_result\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 183\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_raw\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 184\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 185\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_standard\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[0m\u001b[1;32m 186\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 187\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mapply_empty_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\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~/.virtualenvs/data-science/lib/python3.8/site-packages/pandas/core/apply.py\u001b[0m in \u001b[0;36mapply_standard\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 274\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 275\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mapply_standard\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\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--> 276\u001b[0;31m \u001b[0mresults\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mres_index\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_series_generator\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[0m\u001b[1;32m 277\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 278\u001b[0m \u001b[0;31m# wrap results\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/apply.py\u001b[0m in \u001b[0;36mapply_series_generator\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mv\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mseries_gen\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 289\u001b[0m \u001b[0;31m# ignore SettingWithCopy here in case the user mutates\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 290\u001b[0;31m \u001b[0mresults\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mv\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 291\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresults\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mABCSeries\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 292\u001b[0m \u001b[0;31m# If we have a view on v, we need to make a copy because\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m(x)\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'ext_works_source'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mremove_own_source\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'works_source'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'given_names'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\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[0m", - "\u001b[0;32m\u001b[0m in \u001b[0;36mremove_own_source\u001b[0;34m(lst, own)\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mna\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[0m", - "\u001b[0;31mNameError\u001b[0m: name 'np' is not defined" - ] + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
orcidexternal_idsprovider
130000-0001-5004-4608[Scopus Author ID, 40661094300]Scopus Author ID
240000-0001-5008-2479[Scopus Author ID, 12789856200]Scopus Author ID
250000-0001-5008-2479[Ciência ID, 2F1C-479B-B071]Ciência ID
310000-0001-5010-9539[Loop profile, 1098977]Loop profile
420000-0001-5013-6529[Scopus Author ID, 8986698300]Scopus Author ID
............
112036400000-0003-4985-9169[Scopus Author ID, 23972479900]Scopus Author ID
112036420000-0003-4986-2106[Scopus Author ID, 57189299099]Scopus Author ID
112036430000-0003-4986-2106[Loop profile, 947925]Loop profile
112036530000-0003-4990-3115[Loop profile, 991591]Loop profile
112036620000-0003-4994-6043[Scopus Author ID, 55220889800]Scopus Author ID
\n", + "

1744349 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " orcid external_ids \\\n", + "13 0000-0001-5004-4608 [Scopus Author ID, 40661094300] \n", + "24 0000-0001-5008-2479 [Scopus Author ID, 12789856200] \n", + "25 0000-0001-5008-2479 [Ciência ID, 2F1C-479B-B071] \n", + "31 0000-0001-5010-9539 [Loop profile, 1098977] \n", + "42 0000-0001-5013-6529 [Scopus Author ID, 8986698300] \n", + "... ... ... \n", + "11203640 0000-0003-4985-9169 [Scopus Author ID, 23972479900] \n", + "11203642 0000-0003-4986-2106 [Scopus Author ID, 57189299099] \n", + "11203643 0000-0003-4986-2106 [Loop profile, 947925] \n", + "11203653 0000-0003-4990-3115 [Loop profile, 991591] \n", + "11203662 0000-0003-4994-6043 [Scopus Author ID, 55220889800] \n", + "\n", + " provider \n", + "13 Scopus Author ID \n", + "24 Scopus Author ID \n", + "25 Ciência ID \n", + "31 Loop profile \n", + "42 Scopus Author ID \n", + "... ... \n", + "11203640 Scopus Author ID \n", + "11203642 Scopus Author ID \n", + "11203643 Loop profile \n", + "11203653 Loop profile \n", + "11203662 Scopus Author ID \n", + "\n", + "[1744349 rows x 3 columns]" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ - "df['ext_works_source'] = df.apply(lambda x: remove_own_source(x['works_source'], x['given_names']), axis=1)" + "ids[ids.provider.notna()]" ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [], + "source": [ + "ids['provider'] = ids[ids.external_ids.notna()]['external_ids'].apply(lambda x: x[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
orcidexternal_idsprovider
130000-0001-5004-4608[Scopus Author ID, 40661094300]Scopus Author ID
240000-0001-5008-2479[Scopus Author ID, 12789856200]Scopus Author ID
250000-0001-5008-2479[Ciência ID, 2F1C-479B-B071]Ciência ID
310000-0001-5010-9539[Loop profile, 1098977]Loop profile
420000-0001-5013-6529[Scopus Author ID, 8986698300]Scopus Author ID
\n", + "
" + ], + "text/plain": [ + " orcid external_ids provider\n", + "13 0000-0001-5004-4608 [Scopus Author ID, 40661094300] Scopus Author ID\n", + "24 0000-0001-5008-2479 [Scopus Author ID, 12789856200] Scopus Author ID\n", + "25 0000-0001-5008-2479 [Ciência ID, 2F1C-479B-B071] Ciência ID\n", + "31 0000-0001-5010-9539 [Loop profile, 1098977] Loop profile\n", + "42 0000-0001-5013-6529 [Scopus Author ID, 8986698300] Scopus Author ID" + ] + }, + "execution_count": 66, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ids[ids.provider.notna()].head()" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
orcidexternal_ids
provider
Scopus Author ID10151751015175
ResearcherID543545543545
Loop profile114316114316
Ciência ID3387033870
Researcher Name Resolver ID78107810
中国科学家在线47944794
ISNI30543054
GND28252825
Pitt ID26722672
Technical University of Denmark CWIS24862486
Sciprofile24412441
Researcher ID14171417
ID Dialnet11671167
Digital author ID10791079
Scopus Author ID:10761076
AuthenticusID847847
HKU ResearcherPage740740
UOW Scholars644644
CTI Vitae581581
Scopus Author ID:549549
HKUST Profile521521
Scopus author ID501501
Chalmers ID430430
Scopus ID232232
iAuthor212212
Google Scholar200200
AuthID175175
DAI153153
US EPA VIVO146146
Digital Author ID (DAI)135135
Scopus ID127127
Authenticus8282
Smithsonian Profiles6161
GitHub5151
eScientist4949
VIVO Cornell4646
ResearcherID:3939
Digital Author ID3535
Digital author ID (DAI)3434
ID Dialnet:77
Dialnet ID66
KAKEN55
UNE Researcher ID44
ResearcherID:33
ORCID22
Custom11
ORCID iD11
ScienceOpen11
ResearcherId11
Profile system identifier11
\n", + "
" + ], + "text/plain": [ + " orcid external_ids\n", + "provider \n", + "Scopus Author ID 1015175 1015175\n", + "ResearcherID 543545 543545\n", + "Loop profile 114316 114316\n", + "Ciência ID 33870 33870\n", + "Researcher Name Resolver ID 7810 7810\n", + "中国科学家在线 4794 4794\n", + "ISNI 3054 3054\n", + "GND 2825 2825\n", + "Pitt ID 2672 2672\n", + "Technical University of Denmark CWIS 2486 2486\n", + "Sciprofile 2441 2441\n", + "Researcher ID 1417 1417\n", + "ID Dialnet 1167 1167\n", + "Digital author ID 1079 1079\n", + "Scopus Author ID: 1076 1076\n", + "AuthenticusID 847 847\n", + "HKU ResearcherPage 740 740\n", + "UOW Scholars 644 644\n", + "CTI Vitae 581 581\n", + "Scopus Author ID: 549 549\n", + "HKUST Profile 521 521\n", + "Scopus author ID 501 501\n", + "Chalmers ID 430 430\n", + "Scopus ID 232 232\n", + "iAuthor 212 212\n", + "Google Scholar 200 200\n", + "AuthID 175 175\n", + "DAI 153 153\n", + "US EPA VIVO 146 146\n", + "Digital Author ID (DAI) 135 135\n", + "Scopus ID 127 127\n", + "Authenticus 82 82\n", + "Smithsonian Profiles 61 61\n", + "GitHub 51 51\n", + "eScientist 49 49\n", + "VIVO Cornell 46 46\n", + "ResearcherID: 39 39\n", + "Digital Author ID 35 35\n", + "Digital author ID (DAI) 34 34\n", + "ID Dialnet: 7 7\n", + "Dialnet ID 6 6\n", + "KAKEN 5 5\n", + "UNE Researcher ID 4 4\n", + "ResearcherID: 3 3\n", + "ORCID 2 2\n", + "Custom 1 1\n", + "ORCID iD 1 1\n", + "ScienceOpen 1 1\n", + "ResearcherId 1 1\n", + "Profile system identifier 1 1" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ids.groupby('provider').count().sort_values('orcid', ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": {}, + "outputs": [ + { + "data": { + "application/vnd.plotly.v1+json": { + "config": { + "linkText": "Export to plot.ly", + "plotlyServerURL": "https://plot.ly", + "showLink": false + }, + "data": [ + { + "type": "bar", + "x": [ + "Scopus Author ID", + "ResearcherID", + "Loop profile", + "Ciência ID", + "Researcher Name Resolver ID", + "中国科学家在线", + "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 + ] + } + ], + "layout": { + "template": { + "data": { + "bar": [ + { + "error_x": { + "color": "#2a3f5f" + }, + "error_y": { + "color": "#2a3f5f" + }, + "marker": { + "line": { + "color": "#E5ECF6", + "width": 0.5 + } + }, + "type": "bar" + } + ], + "barpolar": [ + { + "marker": { + "line": { + "color": "#E5ECF6", + "width": 0.5 + } + }, + "type": "barpolar" + } + ], + "carpet": [ + { + "aaxis": { + "endlinecolor": "#2a3f5f", + "gridcolor": "white", + "linecolor": "white", + "minorgridcolor": "white", + "startlinecolor": "#2a3f5f" + }, + "baxis": { + "endlinecolor": "#2a3f5f", + "gridcolor": "white", + "linecolor": "white", + "minorgridcolor": "white", + "startlinecolor": "#2a3f5f" + }, + "type": "carpet" + } + ], + "choropleth": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "choropleth" + } + ], + "contour": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "contour" + } + ], + "contourcarpet": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "contourcarpet" + } + ], + "heatmap": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "heatmap" + } + ], + "heatmapgl": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "heatmapgl" + } + ], + "histogram": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "histogram" + } + ], + "histogram2d": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "histogram2d" + } + ], + "histogram2dcontour": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "histogram2dcontour" + } + ], + "mesh3d": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "mesh3d" + } + ], + "parcoords": [ + { + "line": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "parcoords" + } + ], + "pie": [ + { + "automargin": true, + "type": "pie" + } + ], + "scatter": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatter" + } + ], + "scatter3d": [ + { + "line": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatter3d" + } + ], + "scattercarpet": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattercarpet" + } + ], + "scattergeo": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattergeo" + } + ], + "scattergl": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattergl" + } + ], + "scattermapbox": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattermapbox" + } + ], + "scatterpolar": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterpolar" + } + ], + "scatterpolargl": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterpolargl" + } + ], + "scatterternary": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterternary" + } + ], + "surface": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "surface" + } + ], + "table": [ + { + "cells": { + "fill": { + "color": "#EBF0F8" + }, + "line": { + "color": "white" + } + }, + "header": { + "fill": { + "color": "#C8D4E3" + }, + "line": { + "color": "white" + } + }, + "type": "table" + } + ] + }, + "layout": { + "annotationdefaults": { + "arrowcolor": "#2a3f5f", + "arrowhead": 0, + "arrowwidth": 1 + }, + "autotypenumbers": "strict", + "coloraxis": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "colorscale": { + "diverging": [ + [ + 0, + "#8e0152" + ], + [ + 0.1, + "#c51b7d" + ], + [ + 0.2, + "#de77ae" + ], + [ + 0.3, + "#f1b6da" + ], + [ + 0.4, + "#fde0ef" + ], + [ + 0.5, + "#f7f7f7" + ], + [ + 0.6, + "#e6f5d0" + ], + [ + 0.7, + "#b8e186" + ], + [ + 0.8, + "#7fbc41" + ], + [ + 0.9, + "#4d9221" + ], + [ + 1, + "#276419" + ] + ], + "sequential": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "sequentialminus": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ] + }, + "colorway": [ + "#636efa", + "#EF553B", + "#00cc96", + "#ab63fa", + "#FFA15A", + "#19d3f3", + "#FF6692", + "#B6E880", + "#FF97FF", + "#FECB52" + ], + "font": { + "color": "#2a3f5f" + }, + "geo": { + "bgcolor": "white", + "lakecolor": "white", + "landcolor": "#E5ECF6", + "showlakes": true, + "showland": true, + "subunitcolor": "white" + }, + "hoverlabel": { + "align": "left" + }, + "hovermode": "closest", + "mapbox": { + "style": "light" + }, + "paper_bgcolor": "white", + "plot_bgcolor": "#E5ECF6", + "polar": { + "angularaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "bgcolor": "#E5ECF6", + "radialaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + } + }, + "scene": { + "xaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + }, + "yaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + }, + "zaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + } + }, + "shapedefaults": { + "line": { + "color": "#2a3f5f" + } + }, + "ternary": { + "aaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "baxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "bgcolor": "#E5ECF6", + "caxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + } + }, + "title": { + "x": 0.05 + }, + "xaxis": { + "automargin": true, + "gridcolor": "white", + "linecolor": "white", + "ticks": "", + "title": { + "standoff": 15 + }, + "zerolinecolor": "white", + "zerolinewidth": 2 + }, + "yaxis": { + "automargin": true, + "gridcolor": "white", + "linecolor": "white", + "ticks": "", + "title": { + "standoff": 15 + }, + "zerolinecolor": "white", + "zerolinewidth": 2 + } + } + }, + "title": { + "text": "IDs provided" + }, + "xaxis": { + "tickangle": 45, + "tickfont": { + "size": 12 + } + } + } + }, + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "data = [\n", + " go.Bar(\n", + " x=ids.groupby('provider').count().sort_values('orcid', ascending=False).index,\n", + " y=ids.groupby('provider').count().sort_values('orcid', ascending=False)['orcid']\n", + " )\n", + "]\n", + "\n", + "layout = go.Layout(\n", + " title='IDs provided',\n", + " xaxis=dict(tickangle=45, tickfont=dict(size=12))\n", + ")\n", + "fig = go.Figure(data=data, layout=layout)\n", + "plotly.offline.iplot(fig)" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([nan, 'Scopus Author ID', 'Ciência ID', 'Loop profile',\n", + " 'ResearcherID', 'Researcher Name Resolver ID', 'UOW Scholars',\n", + " '中国科学家在线', 'Pitt ID', 'AuthenticusID', 'Sciprofile', 'GND', 'ISNI',\n", + " 'HKU ResearcherPage', 'CTI Vitae', 'Researcher ID', 'ID Dialnet',\n", + " 'Digital author ID', 'HKUST Profile',\n", + " 'Technical University of Denmark CWIS', 'Scopus Author ID: ',\n", + " 'Digital Author ID (DAI)', 'Scopus Author ID:', 'Google Scholar',\n", + " 'AuthID', 'Digital Author ID', 'iAuthor', 'US EPA VIVO', 'GitHub',\n", + " 'Scopus author ID', 'Chalmers ID', 'Scopus ID', 'Authenticus',\n", + " 'VIVO Cornell', 'Scopus ID', 'ScienceOpen',\n", + " 'Smithsonian Profiles', 'ResearcherID:', 'DAI', 'eScientist',\n", + " 'KAKEN', 'Digital author ID (DAI)', 'ORCID', 'ID Dialnet:',\n", + " 'Dialnet ID', 'UNE Researcher ID', 'ResearcherID: ',\n", + " 'Profile system identifier', 'Custom', 'ResearcherId', 'ORCID iD'],\n", + " dtype=object)" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.unique(ids['provider'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Correlation" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": {}, + "outputs": [ + { + "data": { + "application/vnd.plotly.v1+json": { + "config": { + "plotlyServerURL": "https://plot.ly" + }, + "data": [ + { + "coloraxis": "coloraxis", + "hovertemplate": "x: %{x}
y: %{y}
color: %{z}", + "name": "0", + "type": "heatmap", + "x": [ + "claimed", + "verified_email", + "verified_primary_email", + "n_works", + "n_emails", + "n_urls", + "n_ids" + ], + "xaxis": "x", + "y": [ + "claimed", + "verified_email", + "verified_primary_email", + "n_works", + "n_emails", + "n_urls", + "n_ids" + ], + "yaxis": "y", + "z": [ + [ + null, + null, + null, + null, + null, + null, + null + ], + [ + null, + 1, + 0.9764600091179001, + 0.06481728326324665, + 0.011268135706995959, + 0.016235518285109687, + 0.08833871138587861 + ], + [ + null, + 0.9764600091179001, + 1, + 0.0659649633755603, + 0.009337798958686118, + 0.0168692743777146, + 0.08953190210488794 + ], + [ + null, + 0.06481728326324665, + 0.0659649633755603, + 1, + 0.05241643710974057, + 0.05179828612278866, + 0.23927720131732308 + ], + [ + null, + 0.011268135706995959, + 0.009337798958686118, + 0.05241643710974057, + 1, + 0.11119920854300894, + 0.04817263453943147 + ], + [ + null, + 0.016235518285109687, + 0.0168692743777146, + 0.05179828612278866, + 0.11119920854300894, + 1, + 0.06925708918455128 + ], + [ + null, + 0.08833871138587861, + 0.08953190210488794, + 0.23927720131732308, + 0.04817263453943147, + 0.06925708918455128, + 1 + ] + ] + } + ], + "layout": { + "coloraxis": { + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ] + }, + "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, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "contour" + } + ], + "contourcarpet": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "contourcarpet" + } + ], + "heatmap": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "heatmap" + } + ], + "heatmapgl": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "heatmapgl" + } + ], + "histogram": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "histogram" + } + ], + "histogram2d": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "histogram2d" + } + ], + "histogram2dcontour": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "histogram2dcontour" + } + ], + "mesh3d": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "mesh3d" + } + ], + "parcoords": [ + { + "line": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "parcoords" + } + ], + "pie": [ + { + "automargin": true, + "type": "pie" + } + ], + "scatter": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatter" + } + ], + "scatter3d": [ + { + "line": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatter3d" + } + ], + "scattercarpet": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattercarpet" + } + ], + "scattergeo": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattergeo" + } + ], + "scattergl": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattergl" + } + ], + "scattermapbox": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattermapbox" + } + ], + "scatterpolar": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterpolar" + } + ], + "scatterpolargl": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterpolargl" + } + ], + "scatterternary": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterternary" + } + ], + "surface": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "surface" + } + ], + "table": [ + { + "cells": { + "fill": { + "color": "#EBF0F8" + }, + "line": { + "color": "white" + } + }, + "header": { + "fill": { + "color": "#C8D4E3" + }, + "line": { + "color": "white" + } + }, + "type": "table" + } + ] + }, + "layout": { + "annotationdefaults": { + "arrowcolor": "#2a3f5f", + "arrowhead": 0, + "arrowwidth": 1 + }, + "autotypenumbers": "strict", + "coloraxis": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "colorscale": { + "diverging": [ + [ + 0, + "#8e0152" + ], + [ + 0.1, + "#c51b7d" + ], + [ + 0.2, + "#de77ae" + ], + [ + 0.3, + "#f1b6da" + ], + [ + 0.4, + "#fde0ef" + ], + [ + 0.5, + "#f7f7f7" + ], + [ + 0.6, + "#e6f5d0" + ], + [ + 0.7, + "#b8e186" + ], + [ + 0.8, + "#7fbc41" + ], + [ + 0.9, + "#4d9221" + ], + [ + 1, + "#276419" + ] + ], + "sequential": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "sequentialminus": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ] + }, + "colorway": [ + "#636efa", + "#EF553B", + "#00cc96", + "#ab63fa", + "#FFA15A", + "#19d3f3", + "#FF6692", + "#B6E880", + "#FF97FF", + "#FECB52" + ], + "font": { + "color": "#2a3f5f" + }, + "geo": { + "bgcolor": "white", + "lakecolor": "white", + "landcolor": "#E5ECF6", + "showlakes": true, + "showland": true, + "subunitcolor": "white" + }, + "hoverlabel": { + "align": "left" + }, + "hovermode": "closest", + "mapbox": { + "style": "light" + }, + "paper_bgcolor": "white", + "plot_bgcolor": "#E5ECF6", + "polar": { + "angularaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "bgcolor": "#E5ECF6", + "radialaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + } + }, + "scene": { + "xaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + }, + "yaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + }, + "zaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + } + }, + "shapedefaults": { + "line": { + "color": "#2a3f5f" + } + }, + "ternary": { + "aaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "baxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "bgcolor": "#E5ECF6", + "caxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + } + }, + "title": { + "x": 0.05 + }, + "xaxis": { + "automargin": true, + "gridcolor": "white", + "linecolor": "white", + "ticks": "", + "title": { + "standoff": 15 + }, + "zerolinecolor": "white", + "zerolinewidth": 2 + }, + "yaxis": { + "automargin": true, + "gridcolor": "white", + "linecolor": "white", + "ticks": "", + "title": { + "standoff": 15 + }, + "zerolinecolor": "white", + "zerolinewidth": 2 + } + } + }, + "xaxis": { + "anchor": "y", + "constrain": "domain", + "domain": [ + 0, + 1 + ], + "scaleanchor": "y" + }, + "yaxis": { + "anchor": "x", + "autorange": "reversed", + "constrain": "domain", + "domain": [ + 0, + 1 + ] + } + } + }, + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig = px.imshow(df[df.n_ids > 0].corr())\n", + "fig.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": {