diff --git a/notebooks/01-Exploration.ipynb b/notebooks/01-Exploration.ipynb index 7781a52..1578d63 100644 --- a/notebooks/01-Exploration.ipynb +++ b/notebooks/01-Exploration.ipynb @@ -4953,43 +4953,7 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "set_top_n(100)\n", - "data = [\n", - " go.Bar(\n", - " x=df.sort_values(by=['n_urls'], ascending=False)['orcid'][:TOP_N],\n", - " y=df.sort_values(by=['n_urls'], ascending=False)['n_urls'][:TOP_N]\n", - " )\n", - "]\n", - "\n", - "layout = go.Layout(\n", - " title='Top %s ORCID with URLs' % TOP_N,\n", - " xaxis=dict(tickangle=45, tickfont=dict(size=12), range=TOP_RANGE)\n", - ")\n", - "fig = go.Figure(data=data, layout=layout)\n", - "plotly.offline.iplot(fig)" - ] - }, - { - "cell_type": "code", - "execution_count": 46, - "metadata": {}, - "outputs": [], - "source": [ - "grouped_urls = df[['orcid', 'url_domains']]\\\n", - " .explode('url_domains')\\\n", - " .reset_index(drop=True)\\\n", - " .groupby('url_domains')\\\n", - " .count()\\\n", - " .sort_values('orcid', ascending=False)" - ] - }, - { - "cell_type": "code", - "execution_count": 62, + "execution_count": 75, "metadata": {}, "outputs": [ { @@ -5004,28 +4968,208 @@ { "type": "bar", "x": [ - "linkedin.com", - "researchgate.net", - "google.com", - "cnpq.br", - "academia.edu", - "twitter.com", - "facebook.com", - "publons.com", - "wordpress.com", - "mendeley.com" + "0000-0002-1234-835X", + "0000-0001-7478-4539", + "0000-0002-7392-3792", + "0000-0002-6938-9638", + "0000-0002-5710-4041", + "0000-0003-2450-090X", + "0000-0002-3920-7389", + "0000-0002-6689-4129", + "0000-0002-4621-5571", + "0000-0001-9131-1266", + "0000-0002-7754-8889", + "0000-0002-5250-1144", + "0000-0002-9025-8632", + "0000-0002-7456-3848", + "0000-0003-0176-1293", + "0000-0003-0321-7339", + "0000-0002-8493-0402", + "0000-0002-9965-2425", + "0000-0001-8873-6677", + "0000-0002-3997-5070", + "0000-0002-1856-6905", + "0000-0002-4062-3603", + "0000-0002-4316-1467", + "0000-0002-0752-7513", + "0000-0001-5880-7091", + "0000-0003-1524-6268", + "0000-0003-0594-2462", + "0000-0003-2593-7134", + "0000-0002-1298-5252", + "0000-0003-1761-3842", + "0000-0003-2383-8386", + "0000-0003-3546-2312", + "0000-0002-2886-9248", + "0000-0002-1929-6054", + "0000-0003-2183-8112", + "0000-0003-2407-3557", + "0000-0002-4305-4215", + "0000-0003-0796-0234", + "0000-0001-7133-6896", + "0000-0002-9276-6921", + "0000-0002-7568-3403", + "0000-0003-1484-6958", + "0000-0002-4004-6666", + "0000-0002-8208-0897", + "0000-0002-9071-5450", + "0000-0002-8116-9611", + "0000-0003-4993-5555", + "0000-0003-0930-6121", + "0000-0003-4948-9268", + "0000-0002-8122-879X", + "0000-0001-9559-1103", + "0000-0002-3277-9659", + "0000-0003-2862-6315", + "0000-0002-2000-8339", + "0000-0001-5300-4601", + "0000-0002-6547-0172", + "0000-0003-4808-6619", + "0000-0002-6254-8683", + "0000-0002-0971-9375", + "0000-0003-3933-0229", + "0000-0002-4659-5391", + "0000-0003-0694-1154", + "0000-0002-2916-2893", + "0000-0003-4501-3756", + "0000-0001-6783-2037", + "0000-0001-6461-2573", + "0000-0001-5549-6822", + "0000-0001-8978-4830", + "0000-0003-4326-9336", + "0000-0001-8096-4333", + "0000-0002-8940-3177", + "0000-0002-6680-1703", + "0000-0002-5946-1595", + "0000-0002-8593-9257", + "0000-0002-7653-4899", + "0000-0002-5196-4905", + "0000-0001-8808-4867", + "0000-0002-5139-2660", + "0000-0001-6921-0426", + "0000-0003-1815-1993", + "0000-0002-7843-8497", + "0000-0003-1675-2840", + "0000-0001-8644-2114", + "0000-0003-0907-9870", + "0000-0001-8986-2528", + "0000-0002-5265-6074", + "0000-0001-7784-0583", + "0000-0001-7550-5802", + "0000-0001-6979-4273", + "0000-0001-9102-8639", + "0000-0002-3334-9386", + "0000-0002-0696-8560", + "0000-0002-7179-6953", + "0000-0002-9771-600X", + "0000-0002-8797-6502", + "0000-0002-5241-1026", + "0000-0001-7193-5039", + "0000-0001-9119-5955", + "0000-0003-2133-2648", + "0000-0001-9026-4795" ], "y": [ - 75344, - 66267, - 43468, - 23936, - 20786, - 18017, - 14552, - 10339, - 8883, - 7003 + 219, + 174, + 169, + 152, + 114, + 114, + 111, + 104, + 90, + 83, + 83, + 81, + 81, + 80, + 80, + 80, + 76, + 73, + 72, + 71, + 70, + 69, + 69, + 68, + 68, + 68, + 68, + 67, + 67, + 66, + 66, + 65, + 64, + 61, + 61, + 59, + 57, + 57, + 57, + 57, + 57, + 57, + 57, + 56, + 55, + 55, + 55, + 55, + 51, + 50, + 50, + 50, + 49, + 49, + 48, + 48, + 48, + 48, + 47, + 47, + 46, + 46, + 45, + 45, + 45, + 45, + 44, + 43, + 43, + 43, + 43, + 42, + 42, + 42, + 41, + 41, + 40, + 40, + 40, + 39, + 39, + 39, + 39, + 38, + 38, + 38, + 38, + 38, + 37, + 37, + 37, + 37, + 37, + 36, + 36, + 36, + 36, + 36, + 36, + 36 ] } ], @@ -5837,12 +5981,12 @@ } }, "title": { - "text": "Top 10 URL domains" + "text": "Top 100 ORCID with URLs" }, "xaxis": { "range": [ -0.5, - 29.5 + 99.5 ], "tickangle": 45, "tickfont": { @@ -5852,9 +5996,9 @@ } }, "text/html": [ - "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "set_top_n(30)\n", "data = [\n", " go.Bar(\n", " x=grouped_urls[:TOP_N].sort_values(by=['orcid'], ascending=False).index,\n", @@ -8095,29 +9206,7 @@ }, { "cell_type": "code", - "execution_count": 56, - "metadata": {}, - "outputs": [ - { - "ename": "AttributeError", - "evalue": "'DataFrame' object has no attribute 'provider'", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mAttributeError\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[0mids\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mids\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprovider\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnotna\u001b[0m\u001b[0;34m(\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;32m~/.virtualenvs/data-science/lib/python3.8/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 5463\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\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 5464\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5465\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\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 5466\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5467\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\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[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'provider'" - ] - } - ], - "source": [ - "ids[ids.provider.notna()]" - ] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 78, "metadata": {}, "outputs": [], "source": [ @@ -8126,18 +9215,1060 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 79, "metadata": {}, - "outputs": [], + "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": 79, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "ids[ids.provider.notna()].head()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 80, "metadata": {}, - "outputs": [], + "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", @@ -8156,9 +10287,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 81, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([nan, 'Scopus Author ID', 'Ciência ID', 'Loop profile',\n", + " 'ResearcherID', 'Researcher Name Resolver ID', 'UOW Scholars',\n", + " '中国科学家在线', 'Pitt ID', 'AuthenticusID', 'Sciprofile', 'GND', 'ISNI',\n", + " 'HKU ResearcherPage', 'CTI Vitae', 'Researcher ID', 'ID Dialnet',\n", + " 'Digital author ID', 'HKUST Profile',\n", + " 'Technical University of Denmark CWIS', 'Scopus Author ID: ',\n", + " 'Digital Author ID (DAI)', 'Scopus Author ID:', 'Google Scholar',\n", + " 'AuthID', 'Digital Author ID', 'iAuthor', 'US EPA VIVO', 'GitHub',\n", + " 'Scopus author ID', 'Chalmers ID', 'Scopus ID', 'Authenticus',\n", + " 'VIVO Cornell', 'Scopus ID', 'ScienceOpen',\n", + " 'Smithsonian Profiles', 'ResearcherID:', 'DAI', 'eScientist',\n", + " 'KAKEN', 'Digital author ID (DAI)', 'ORCID', 'ID Dialnet:',\n", + " 'Dialnet ID', 'UNE Researcher ID', 'ResearcherID: ',\n", + " 'Profile system identifier', 'Custom', 'ResearcherId', 'ORCID iD'],\n", + " dtype=object)" + ] + }, + "execution_count": 81, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "pd.unique(ids['provider'])" ] @@ -8172,7 +10328,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 82, "metadata": {}, "outputs": [], "source": [ @@ -8181,18 +10337,1193 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 83, "metadata": {}, - "outputs": [], + "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", + "
orcidn_keywords
16813100000-0002-0673-0341154.0
77176990000-0002-7060-4112141.0
45976740000-0002-6075-3501140.0
20665800000-0002-4071-0301118.0
35310300000-0002-9638-8091115.0
.........
107470350000-0003-4998-1551NaN
107470360000-0003-4998-4111NaN
107470370000-0003-4998-6045NaN
107470380000-0003-4998-8868NaN
107470390000-0003-4999-7916NaN
\n", + "

10744621 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " orcid n_keywords\n", + "1681310 0000-0002-0673-0341 154.0\n", + "7717699 0000-0002-7060-4112 141.0\n", + "4597674 0000-0002-6075-3501 140.0\n", + "2066580 0000-0002-4071-0301 118.0\n", + "3531030 0000-0002-9638-8091 115.0\n", + "... ... ...\n", + "10747035 0000-0003-4998-1551 NaN\n", + "10747036 0000-0003-4998-4111 NaN\n", + "10747037 0000-0003-4998-6045 NaN\n", + "10747038 0000-0003-4998-8868 NaN\n", + "10747039 0000-0003-4999-7916 NaN\n", + "\n", + "[10744621 rows x 2 columns]" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "df.sort_values('n_keywords', ascending=False)[['orcid', 'n_keywords']]" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 84, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.plotly.v1+json": { + "config": { + "linkText": "Export to plot.ly", + "plotlyServerURL": "https://plot.ly", + "showLink": false + }, + "data": [ + { + "type": "bar", + "x": [ + "0000-0002-0673-0341", + "0000-0002-7060-4112", + "0000-0002-6075-3501", + "0000-0002-4071-0301", + "0000-0002-9638-8091", + "0000-0002-4235-4259", + "0000-0001-9462-5666", + "0000-0003-0076-6287", + "0000-0002-1878-9762", + "0000-0001-6537-7683", + "0000-0001-6307-6027", + "0000-0003-2273-9888", + "0000-0003-1799-0971", + "0000-0001-5287-1949", + "0000-0002-0937-7061", + "0000-0001-9715-9357", + "0000-0001-5696-1052", + "0000-0003-2998-5520", + "0000-0001-5869-2204", + "0000-0002-0156-3580", + "0000-0002-9625-6742", + "0000-0002-8401-8018", + "0000-0001-9985-1697", + "0000-0003-4246-8579", + "0000-0002-7710-0355", + "0000-0002-8083-7382", + "0000-0001-7654-5013", + "0000-0001-6939-3859", + "0000-0002-3061-3364", + "0000-0003-2509-2549", + "0000-0002-0463-0048", + "0000-0001-5230-715X", + "0000-0001-5458-7167", + "0000-0001-9336-6850", + "0000-0003-0209-180X", + "0000-0002-8227-5387", + "0000-0002-9381-2264", + "0000-0003-3340-6413", + "0000-0003-3584-6834", + "0000-0002-2935-1934", + "0000-0002-8644-8396", + "0000-0002-8659-6321", + "0000-0002-3123-3021", + "0000-0001-5637-1124", + "0000-0001-5167-7466", + "0000-0002-8449-2211", + "0000-0003-2532-2906", + "0000-0002-3532-043X", + "0000-0002-2683-4527", + "0000-0003-4505-3678", + "0000-0002-6347-9464", + "0000-0003-4608-3844", + "0000-0003-4374-6374", + "0000-0003-4511-7942", + "0000-0002-1103-9651", + "0000-0003-3720-1183", + "0000-0001-9280-6017", + "0000-0003-4673-1063", + "0000-0001-9586-0780", + "0000-0002-5539-1761", + "0000-0003-2550-1859", + "0000-0002-8499-1045", + "0000-0003-2218-1343", + "0000-0002-5306-7781", + "0000-0003-1863-0265", + "0000-0002-8072-1152", + "0000-0003-3342-6123", + "0000-0002-2252-672X", + "0000-0002-3907-3552", + "0000-0001-6861-9561", + "0000-0002-3597-3350", + "0000-0002-5274-7742", + "0000-0002-3186-8860", + "0000-0001-8689-185X", + "0000-0002-6282-0640", + "0000-0003-3343-5660", + "0000-0001-7133-7848", + "0000-0003-4486-2684", + "0000-0002-9014-2090", + "0000-0001-6843-9325", + "0000-0003-0097-4182", + "0000-0003-1245-7705", + "0000-0002-4432-3448", + "0000-0001-7857-4133", + "0000-0002-1294-2156", + "0000-0001-8445-412X", + "0000-0002-1411-3028", + "0000-0003-3387-3193", + "0000-0002-1545-7818", + "0000-0002-9125-6022", + "0000-0002-3898-9542", + "0000-0002-3866-6460", + "0000-0003-4283-2895", + "0000-0003-4153-6779", + "0000-0002-4598-2891", + "0000-0002-0211-7195", + "0000-0002-1770-9660", + "0000-0002-1960-5857", + "0000-0003-2640-6757", + "0000-0002-5432-9595" + ], + "y": [ + 154, + 141, + 140, + 118, + 115, + 104, + 98, + 94, + 92, + 91, + 88, + 86, + 84, + 82, + 78, + 77, + 76, + 75, + 74, + 73, + 71, + 70, + 69, + 66, + 64, + 62, + 61, + 60, + 58, + 57, + 56, + 54, + 53, + 53, + 52, + 51, + 51, + 51, + 51, + 50, + 50, + 50, + 50, + 49, + 49, + 49, + 48, + 48, + 48, + 48, + 48, + 48, + 47, + 47, + 46, + 46, + 46, + 45, + 45, + 44, + 44, + 44, + 44, + 44, + 44, + 43, + 43, + 42, + 42, + 42, + 42, + 42, + 42, + 41, + 41, + 41, + 41, + 41, + 41, + 41, + 40, + 40, + 40, + 40, + 40, + 40, + 39, + 39, + 39, + 39, + 39, + 39, + 39, + 39, + 39, + 39, + 38, + 38, + 38, + 38 + ] + } + ], + "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": "Keywords provided" + }, + "xaxis": { + "tickangle": 45, + "tickfont": { + "size": 12 + } + } + } + }, + "text/html": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "data = [\n", " go.Bar(\n", @@ -8218,9 +11549,1033 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 85, "metadata": {}, - "outputs": [], + "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", + "n_keywords" + ], + "xaxis": "x", + "y": [ + "claimed", + "verified_email", + "verified_primary_email", + "n_works", + "n_emails", + "n_urls", + "n_ids", + "n_keywords" + ], + "yaxis": "y", + "z": [ + [ + null, + null, + null, + null, + null, + null, + null, + null + ], + [ + null, + 1, + 0.9764600091179001, + 0.06481728326324665, + 0.011268135706995959, + 0.016235518285109687, + 0.08833871138587861, + 0.017045184883982135 + ], + [ + null, + 0.9764600091179001, + 1, + 0.0659649633755603, + 0.009337798958686118, + 0.0168692743777146, + 0.08953190210488794, + 0.017626925761491493 + ], + [ + null, + 0.06481728326324665, + 0.0659649633755603, + 1, + 0.05241643710974057, + 0.05179828612278866, + 0.23927720131732308, + 0.030960689715636 + ], + [ + null, + 0.011268135706995959, + 0.009337798958686118, + 0.05241643710974057, + 1, + 0.11119920854300894, + 0.04817263453943147, + 0.04157758861961359 + ], + [ + null, + 0.016235518285109687, + 0.0168692743777146, + 0.05179828612278866, + 0.11119920854300894, + 1, + 0.06925708918455128, + 0.15926017909633472 + ], + [ + null, + 0.08833871138587861, + 0.08953190210488794, + 0.23927720131732308, + 0.04817263453943147, + 0.06925708918455128, + 1, + 0.06320236481237387 + ], + [ + null, + 0.017045184883982135, + 0.017626925761491493, + 0.030960689715636, + 0.04157758861961359, + 0.15926017909633472, + 0.06320236481237387, + 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()"