2021-07-02 17:49:38 +02:00
{
"cells": [
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 1,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [],
"source": [
"import ast\n",
"import csv\n",
"import json\n",
"import reverse_geocoder as rg\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"\n",
2021-07-06 15:23:24 +02:00
"import pycountry_convert\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib_venn import venn2, venn2_circles\n",
"\n",
2021-07-02 17:49:38 +02:00
"import plotly\n",
"from plotly.offline import iplot, init_notebook_mode\n",
"import plotly.graph_objs as go\n",
"import plotly.express as px"
]
},
2021-07-06 15:23:24 +02:00
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 1,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"def country_to_countrycode(country):\n",
" if pd.isna(country):\n",
" return np.nan\n",
" else:\n",
" try:\n",
" return pycountry_convert.country_name_to_country_alpha2(country)\n",
" except:\n",
" return np.nan\n",
"\n",
"def countrycode_to_continent(country_code):\n",
" if pd.isna(country_code):\n",
" return np.nan\n",
" else:\n",
" try:\n",
" return pycountry_convert.country_alpha2_to_continent_code(country_code)\n",
" except:\n",
" return np.nan"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Loading datasets"
]
},
2021-07-02 17:49:38 +02:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
2021-07-06 15:23:24 +02:00
"**FAIRsharing**"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
2021-07-06 15:23:24 +02:00
"execution_count": 3,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>full_name</th>\n",
" <th>short_name</th>\n",
" <th>fs_url</th>\n",
" <th>url</th>\n",
" <th>countries</th>\n",
" <th>subjects</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>GenBank</td>\n",
" <td>GenBank</td>\n",
" <td>https://fairsharing.org/10.25504/FAIRsharing.9...</td>\n",
" <td>https://www.ncbi.nlm.nih.gov/genbank/</td>\n",
" <td>[European Union, Japan, United States]</td>\n",
" <td>[Bioinformatics, Data Management, Data Submiss...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>GlycoNAVI</td>\n",
" <td>GlycoNAVI</td>\n",
" <td>https://fairsharing.org/10.25504/FAIRsharing.w...</td>\n",
" <td>https://glyconavi.org/</td>\n",
" <td>[Japan]</td>\n",
" <td>[Chemistry, Glycomics, Life Science, Organic C...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ADHDgene</td>\n",
" <td>ADHDgene</td>\n",
" <td>https://fairsharing.org/10.25504/FAIRsharing.m...</td>\n",
" <td>http://adhd.psych.ac.cn/</td>\n",
" <td>[China]</td>\n",
" <td>[Biomedical Science, Genetics]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Allele frequency resource for research and tea...</td>\n",
" <td>ALFRED</td>\n",
" <td>https://fairsharing.org/10.25504/FAIRsharing.y...</td>\n",
" <td>http://alfred.med.yale.edu</td>\n",
" <td>[United States]</td>\n",
" <td>[Life Science]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Animal Transcription Factor Database</td>\n",
" <td>AnimalTFDB</td>\n",
" <td>https://fairsharing.org/10.25504/FAIRsharing.e...</td>\n",
" <td>http://bioinfo.life.hust.edu.cn/AnimalTFDB/</td>\n",
" <td>[China]</td>\n",
" <td>[Life Science]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" full_name short_name \\\n",
"0 GenBank GenBank \n",
"1 GlycoNAVI GlycoNAVI \n",
"2 ADHDgene ADHDgene \n",
"3 Allele frequency resource for research and tea... ALFRED \n",
"4 Animal Transcription Factor Database AnimalTFDB \n",
"\n",
" fs_url \\\n",
"0 https://fairsharing.org/10.25504/FAIRsharing.9... \n",
"1 https://fairsharing.org/10.25504/FAIRsharing.w... \n",
"2 https://fairsharing.org/10.25504/FAIRsharing.m... \n",
"3 https://fairsharing.org/10.25504/FAIRsharing.y... \n",
"4 https://fairsharing.org/10.25504/FAIRsharing.e... \n",
"\n",
" url \\\n",
"0 https://www.ncbi.nlm.nih.gov/genbank/ \n",
"1 https://glyconavi.org/ \n",
"2 http://adhd.psych.ac.cn/ \n",
"3 http://alfred.med.yale.edu \n",
"4 http://bioinfo.life.hust.edu.cn/AnimalTFDB/ \n",
"\n",
" countries \\\n",
"0 [European Union, Japan, United States] \n",
"1 [Japan] \n",
"2 [China] \n",
"3 [United States] \n",
"4 [China] \n",
"\n",
" subjects \n",
"0 [Bioinformatics, Data Management, Data Submiss... \n",
"1 [Chemistry, Glycomics, Life Science, Organic C... \n",
"2 [Biomedical Science, Genetics] \n",
"3 [Life Science] \n",
"4 [Life Science] "
]
},
2021-07-06 15:23:24 +02:00
"execution_count": 3,
2021-07-02 17:49:38 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fairsharing_df = pd.read_csv('../data/raw/FAIRsharingDBrec_summary20210304.csv', \n",
" delimiter='|', header=0,\n",
" names=['full_name', 'short_name', 'fs_url', 'url', 'countries', 'subjects'])\n",
"fairsharing_df['subjects'] = fairsharing_df.subjects.str.split(pat=',')\n",
"fairsharing_df['countries'] = fairsharing_df.countries.str.split(pat=',')\n",
"fairsharing_df.head()"
]
},
{
"cell_type": "code",
2021-07-06 15:23:24 +02:00
"execution_count": 4,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>full_name</th>\n",
" <th>short_name</th>\n",
" <th>fs_url</th>\n",
" <th>url</th>\n",
" <th>countries</th>\n",
" <th>subjects</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>1752</td>\n",
" <td>1752</td>\n",
" <td>1752</td>\n",
" <td>1752</td>\n",
" <td>1749</td>\n",
" <td>1690</td>\n",
" </tr>\n",
" <tr>\n",
" <th>unique</th>\n",
" <td>1752</td>\n",
" <td>1741</td>\n",
" <td>1752</td>\n",
" <td>1752</td>\n",
" <td>178</td>\n",
" <td>834</td>\n",
" </tr>\n",
" <tr>\n",
" <th>top</th>\n",
2021-07-22 11:03:05 +02:00
" <td>SoyBase</td>\n",
2021-07-02 17:49:38 +02:00
" <td>CGD</td>\n",
2021-07-22 11:03:05 +02:00
" <td>https://fairsharing.org/bsg-d001065</td>\n",
" <td>https://ada.edu.au</td>\n",
2021-07-02 17:49:38 +02:00
" <td>[United States]</td>\n",
" <td>[Life Science]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>freq</th>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>588</td>\n",
" <td>367</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
2021-07-22 11:03:05 +02:00
" full_name short_name fs_url \\\n",
"count 1752 1752 1752 \n",
"unique 1752 1741 1752 \n",
"top SoyBase CGD https://fairsharing.org/bsg-d001065 \n",
"freq 1 3 1 \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" url countries subjects \n",
"count 1752 1749 1690 \n",
"unique 1752 178 834 \n",
"top https://ada.edu.au [United States] [Life Science] \n",
"freq 1 588 367 "
2021-07-02 17:49:38 +02:00
]
},
2021-07-06 15:23:24 +02:00
"execution_count": 4,
2021-07-02 17:49:38 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fairsharing_df.describe()"
]
},
{
2021-07-06 15:23:24 +02:00
"cell_type": "markdown",
2021-07-02 17:49:38 +02:00
"metadata": {},
2021-07-06 15:23:24 +02:00
"source": [
"**re3data**"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 42,
"metadata": {},
2021-07-02 17:49:38 +02:00
"outputs": [
{
"data": {
"text/html": [
2021-07-06 15:23:24 +02:00
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>index</th>\n",
" <th>id</th>\n",
" <th>url</th>\n",
" <th>official_name</th>\n",
" <th>english_name</th>\n",
" <th>description</th>\n",
" <th>latitude</th>\n",
" <th>longitude</th>\n",
" <th>subjects</th>\n",
2021-07-22 11:03:05 +02:00
" <th>type</th>\n",
" <th>dataprovider</th>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10|re3data_____::3f2e20af26ead0432f5470d8b739638d</td>\n",
" <td>http://planttfdb.cbi.pku.edu.cn/</td>\n",
" <td>Plant Transcription Factor Database</td>\n",
" <td>PlantTFDB</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>['Life Sciences', 'Basic Biological and Medica...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>datarepository::unknown</td>\n",
" <td>True</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>7</td>\n",
" <td>10|re3data_____::e1db3f9d2fa6c8d8067bc471ab50bdfc</td>\n",
" <td>https://spdf.gsfc.nasa.gov/</td>\n",
" <td>Space Physics Data Facility</td>\n",
" <td>NASA's Space Physics Data Facility SPDF</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>['Natural Sciences', 'Astrophysics and Astrono...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>datarepository::unknown</td>\n",
" <td>True</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>13</td>\n",
" <td>10|re3data_____::59521daca59ac29b811343cc4cd370cf</td>\n",
" <td>http://card.westgis.ac.cn/</td>\n",
" <td>Cold and Arid Regions Science Data Center at L...</td>\n",
" <td>CARD WDC for Glaciology and Geocryology World ...</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>['Natural Sciences', 'Geosciences (including G...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>datarepository::unknown</td>\n",
" <td>True</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>14</td>\n",
" <td>10|re3data_____::ec1ba1674c852466c266acb64c618d15</td>\n",
" <td>https://www.psycharchives.org/</td>\n",
" <td>Psycharchives</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>['Humanities and Social Sciences', 'Psychology...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>datarepository::unknown</td>\n",
" <td>True</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>19</td>\n",
" <td>10|re3data_____::2ada591fb1bc9aee72a6d3e0c1ae8a76</td>\n",
" <td>https://www.ihfc-iugg.org/products/global-heat...</td>\n",
" <td>The Global Heat Flow Database of the Internati...</td>\n",
" <td>International Heat-flow Database</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>['Natural Sciences', 'Geology and Palaeontolog...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>datarepository::unknown</td>\n",
" <td>True</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" index id \\\n",
"0 4 10|re3data_____::3f2e20af26ead0432f5470d8b739638d \n",
"1 7 10|re3data_____::e1db3f9d2fa6c8d8067bc471ab50bdfc \n",
"2 13 10|re3data_____::59521daca59ac29b811343cc4cd370cf \n",
"3 14 10|re3data_____::ec1ba1674c852466c266acb64c618d15 \n",
"4 19 10|re3data_____::2ada591fb1bc9aee72a6d3e0c1ae8a76 \n",
"\n",
" url \\\n",
"0 http://planttfdb.cbi.pku.edu.cn/ \n",
"1 https://spdf.gsfc.nasa.gov/ \n",
"2 http://card.westgis.ac.cn/ \n",
"3 https://www.psycharchives.org/ \n",
"4 https://www.ihfc-iugg.org/products/global-heat... \n",
"\n",
" official_name \\\n",
"0 Plant Transcription Factor Database \n",
"1 Space Physics Data Facility \n",
"2 Cold and Arid Regions Science Data Center at L... \n",
"3 Psycharchives \n",
"4 The Global Heat Flow Database of the Internati... \n",
"\n",
" english_name description latitude \\\n",
"0 PlantTFDB NaN 0.0 \n",
"1 NASA's Space Physics Data Facility SPDF NaN 0.0 \n",
"2 CARD WDC for Glaciology and Geocryology World ... NaN 0.0 \n",
"3 NaN NaN 0.0 \n",
"4 International Heat-flow Database NaN 0.0 \n",
"\n",
2021-07-22 11:03:05 +02:00
" longitude subjects \\\n",
"0 0.0 ['Life Sciences', 'Basic Biological and Medica... \n",
"1 0.0 ['Natural Sciences', 'Astrophysics and Astrono... \n",
"2 0.0 ['Natural Sciences', 'Geosciences (including G... \n",
"3 0.0 ['Humanities and Social Sciences', 'Psychology... \n",
"4 0.0 ['Natural Sciences', 'Geology and Palaeontolog... \n",
"\n",
" type dataprovider \n",
"0 datarepository::unknown True \n",
"1 datarepository::unknown True \n",
"2 datarepository::unknown True \n",
"3 datarepository::unknown True \n",
"4 datarepository::unknown True "
2021-07-02 17:49:38 +02:00
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 42,
2021-07-02 17:49:38 +02:00
"metadata": {},
2021-07-06 15:23:24 +02:00
"output_type": "execute_result"
}
],
"source": [
"re3data_df = pd.read_csv('../data/raw/re3data_opendoar.csv')\n",
2021-07-22 11:03:05 +02:00
"re3data_df = re3data_df[(re3data_df.id.str.contains('re3data'))].reset_index()\n",
2021-07-06 15:23:24 +02:00
"re3data_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"scrolled": false
},
"outputs": [
2021-07-02 17:49:38 +02:00
{
"data": {
"text/html": [
2021-07-06 15:23:24 +02:00
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>index</th>\n",
" <th>id</th>\n",
" <th>url</th>\n",
" <th>official_name</th>\n",
" <th>english_name</th>\n",
" <th>description</th>\n",
" <th>latitude</th>\n",
" <th>longitude</th>\n",
" <th>subjects</th>\n",
2021-07-22 11:03:05 +02:00
" <th>type</th>\n",
" <th>dataprovider</th>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>2693.000000</td>\n",
" <td>2693</td>\n",
" <td>2673</td>\n",
" <td>2693</td>\n",
" <td>2034</td>\n",
" <td>38</td>\n",
" <td>2693.000000</td>\n",
" <td>2693.000000</td>\n",
" <td>2693</td>\n",
2021-07-22 11:03:05 +02:00
" <td>2693</td>\n",
" <td>2693</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>unique</th>\n",
" <td>NaN</td>\n",
" <td>2693</td>\n",
" <td>2661</td>\n",
" <td>2668</td>\n",
" <td>2010</td>\n",
" <td>38</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1427</td>\n",
2021-07-22 11:03:05 +02:00
" <td>2</td>\n",
" <td>2</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>top</th>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>10|re3data_____::11b64a5229ae3a1ba4da3c9e1743a808</td>\n",
" <td>http://figshare.com/</td>\n",
" <td>Mansfeld's World Database of Agriculture and H...</td>\n",
" <td>GCMD</td>\n",
" <td>JEDI is an educational data archive service th...</td>\n",
2021-07-06 15:23:24 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>['Humanities and Social Sciences', 'Life Scien...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>datarepository::unknown</td>\n",
" <td>True</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>freq</th>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>209</td>\n",
2021-07-22 11:03:05 +02:00
" <td>2692</td>\n",
" <td>2428</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>4443.650947</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.114497</td>\n",
" <td>0.067998</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>2518.294468</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.585469</td>\n",
" <td>2.447173</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>4.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>2266.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>4506.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>6660.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>8705.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>234.000000</td>\n",
" <td>123.000000</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" index id \\\n",
"count 2693.000000 2693 \n",
"unique NaN 2693 \n",
2021-07-22 11:03:05 +02:00
"top NaN 10|re3data_____::11b64a5229ae3a1ba4da3c9e1743a808 \n",
2021-07-06 15:23:24 +02:00
"freq NaN 1 \n",
"mean 4443.650947 NaN \n",
"std 2518.294468 NaN \n",
"min 4.000000 NaN \n",
"25% 2266.000000 NaN \n",
"50% 4506.000000 NaN \n",
"75% 6660.000000 NaN \n",
"max 8705.000000 NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" url \\\n",
"count 2673 \n",
"unique 2661 \n",
"top http://figshare.com/ \n",
"freq 2 \n",
"mean NaN \n",
"std NaN \n",
"min NaN \n",
"25% NaN \n",
"50% NaN \n",
"75% NaN \n",
"max NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" official_name english_name \\\n",
"count 2693 2034 \n",
"unique 2668 2010 \n",
"top Mansfeld's World Database of Agriculture and H... GCMD \n",
"freq 2 2 \n",
"mean NaN NaN \n",
"std NaN NaN \n",
"min NaN NaN \n",
"25% NaN NaN \n",
"50% NaN NaN \n",
"75% NaN NaN \n",
"max NaN NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" description latitude \\\n",
"count 38 2693.000000 \n",
"unique 38 NaN \n",
"top JEDI is an educational data archive service th... NaN \n",
"freq 1 NaN \n",
"mean NaN 0.114497 \n",
"std NaN 4.585469 \n",
"min NaN 0.000000 \n",
"25% NaN 0.000000 \n",
"50% NaN 0.000000 \n",
"75% NaN 0.000000 \n",
"max NaN 234.000000 \n",
2021-07-06 15:23:24 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" longitude subjects \\\n",
"count 2693.000000 2693 \n",
"unique NaN 1427 \n",
"top NaN ['Humanities and Social Sciences', 'Life Scien... \n",
"freq NaN 209 \n",
"mean 0.067998 NaN \n",
"std 2.447173 NaN \n",
"min 0.000000 NaN \n",
"25% 0.000000 NaN \n",
"50% 0.000000 NaN \n",
"75% 0.000000 NaN \n",
"max 123.000000 NaN \n",
"\n",
" type dataprovider \n",
"count 2693 2693 \n",
"unique 2 2 \n",
"top datarepository::unknown True \n",
"freq 2692 2428 \n",
"mean NaN NaN \n",
"std NaN NaN \n",
"min NaN NaN \n",
"25% NaN NaN \n",
"50% NaN NaN \n",
"75% NaN NaN \n",
"max NaN NaN "
2021-07-02 17:49:38 +02:00
]
},
2021-07-06 15:23:24 +02:00
"execution_count": 6,
2021-07-02 17:49:38 +02:00
"metadata": {},
2021-07-06 15:23:24 +02:00
"output_type": "execute_result"
2021-07-02 17:49:38 +02:00
}
],
"source": [
2021-07-06 15:23:24 +02:00
"re3data_df.describe(include='all')"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2021-07-06 15:23:24 +02:00
"**OpenDOAR**"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
2021-07-06 15:23:24 +02:00
"execution_count": 7,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
2021-07-06 15:23:24 +02:00
" <th>index</th>\n",
2021-07-02 17:49:38 +02:00
" <th>id</th>\n",
" <th>url</th>\n",
" <th>official_name</th>\n",
" <th>english_name</th>\n",
" <th>description</th>\n",
" <th>latitude</th>\n",
" <th>longitude</th>\n",
" <th>subjects</th>\n",
2021-07-22 11:03:05 +02:00
" <th>type</th>\n",
" <th>dataprovider</th>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
2021-07-06 15:23:24 +02:00
" <td>0</td>\n",
2021-07-02 17:49:38 +02:00
" <td>10|opendoar____::e833e042f509c996b1b25324d56659fb</td>\n",
" <td>http://www.bilbao.net/bld</td>\n",
" <td>BLD - Bilboko Liburutegi Digitala</td>\n",
" <td>BLD - Bilboko Liburutegi Digitala</td>\n",
" <td>BLD is a repository of digital documents, desi...</td>\n",
" <td>43.256699</td>\n",
" <td>-2.924100</td>\n",
" <td>[]</td>\n",
2021-07-22 11:03:05 +02:00
" <td>pubsrepository::institutional</td>\n",
" <td>False</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
2021-07-06 15:23:24 +02:00
" <td>1</td>\n",
2021-07-02 17:49:38 +02:00
" <td>10|opendoar____::f621585df244e9596dc70a39b579efb1</td>\n",
" <td>https://researchdirect.westernsydney.edu.au/</td>\n",
" <td>Western Sydney ResearchDirect</td>\n",
" <td>Western Sydney ResearchDirect</td>\n",
" <td>NaN</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>[]</td>\n",
2021-07-22 11:03:05 +02:00
" <td>pubsrepository::institutional</td>\n",
" <td>False</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
2021-07-06 15:23:24 +02:00
" <td>2</td>\n",
2021-07-02 17:49:38 +02:00
" <td>10|opendoar____::437d7d1d97917cd627a34a6a0fb41136</td>\n",
" <td>http://redress.lancs.ac.uk/Learning_Space/</td>\n",
" <td>Learning Space Catalogue</td>\n",
" <td>NaN</td>\n",
" <td>This repository is a Social Science e-Science ...</td>\n",
" <td>54.010760</td>\n",
" <td>-2.784990</td>\n",
" <td>['Social Sciences General', 'Science General',...</td>\n",
2021-07-22 11:03:05 +02:00
" <td>pubsrepository::unknown</td>\n",
" <td>False</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
2021-07-06 15:23:24 +02:00
" <td>3</td>\n",
2021-07-02 17:49:38 +02:00
" <td>10|opendoar____::d840cc5d906c3e9c84374c8919d2074e</td>\n",
" <td>http://digitallibrary.usc.edu/search/controlle...</td>\n",
" <td>USC Digital Library</td>\n",
" <td>USC Digital Library</td>\n",
2021-07-06 15:23:24 +02:00
" <td>This is an institutional repository providing ...</td>\n",
" <td>34.052200</td>\n",
" <td>-118.242996</td>\n",
" <td>[]</td>\n",
2021-07-22 11:03:05 +02:00
" <td>pubsrepository::institutional</td>\n",
" <td>False</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>10|opendoar____::4ba3c163cd1efd4c14e3a415fa0a3010</td>\n",
" <td>http://www.ufgd.edu.br:8080/jspui/</td>\n",
" <td>Repositório de Divulgação das Produções Cientí...</td>\n",
" <td>Repositório de Divulgação das Produções Cientí...</td>\n",
" <td>This site provides access to the research outp...</td>\n",
" <td>-22.221800</td>\n",
" <td>-54.806400</td>\n",
" <td>[]</td>\n",
2021-07-22 11:03:05 +02:00
" <td>pubsrepository::institutional</td>\n",
" <td>False</td>\n",
2021-07-06 15:23:24 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
2021-07-02 17:49:38 +02:00
"text/plain": [
2021-07-06 15:23:24 +02:00
" index id \\\n",
"0 0 10|opendoar____::e833e042f509c996b1b25324d56659fb \n",
"1 1 10|opendoar____::f621585df244e9596dc70a39b579efb1 \n",
"2 2 10|opendoar____::437d7d1d97917cd627a34a6a0fb41136 \n",
"3 3 10|opendoar____::d840cc5d906c3e9c84374c8919d2074e \n",
"4 5 10|opendoar____::4ba3c163cd1efd4c14e3a415fa0a3010 \n",
"\n",
" url \\\n",
"0 http://www.bilbao.net/bld \n",
"1 https://researchdirect.westernsydney.edu.au/ \n",
"2 http://redress.lancs.ac.uk/Learning_Space/ \n",
"3 http://digitallibrary.usc.edu/search/controlle... \n",
"4 http://www.ufgd.edu.br:8080/jspui/ \n",
"\n",
" official_name \\\n",
"0 BLD - Bilboko Liburutegi Digitala \n",
"1 Western Sydney ResearchDirect \n",
"2 Learning Space Catalogue \n",
"3 USC Digital Library \n",
"4 Repositório de Divulgação das Produções Cientí... \n",
"\n",
" english_name \\\n",
"0 BLD - Bilboko Liburutegi Digitala \n",
"1 Western Sydney ResearchDirect \n",
"2 NaN \n",
"3 USC Digital Library \n",
"4 Repositório de Divulgação das Produções Cientí... \n",
"\n",
" description latitude longitude \\\n",
"0 BLD is a repository of digital documents, desi... 43.256699 -2.924100 \n",
"1 NaN 0.000000 0.000000 \n",
"2 This repository is a Social Science e-Science ... 54.010760 -2.784990 \n",
"3 This is an institutional repository providing ... 34.052200 -118.242996 \n",
"4 This site provides access to the research outp... -22.221800 -54.806400 \n",
"\n",
2021-07-22 11:03:05 +02:00
" subjects \\\n",
"0 [] \n",
"1 [] \n",
"2 ['Social Sciences General', 'Science General',... \n",
"3 [] \n",
"4 [] \n",
"\n",
" type dataprovider \n",
"0 pubsrepository::institutional False \n",
"1 pubsrepository::institutional False \n",
"2 pubsrepository::unknown False \n",
"3 pubsrepository::institutional False \n",
"4 pubsrepository::institutional False "
2021-07-02 17:49:38 +02:00
]
},
2021-07-06 15:23:24 +02:00
"execution_count": 7,
2021-07-02 17:49:38 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2021-07-06 15:23:24 +02:00
"opendoar_df = pd.read_csv('../data/raw/re3data_opendoar.csv')\n",
2021-07-22 11:03:05 +02:00
"opendoar_df = opendoar_df[(opendoar_df.id.str.contains('opendoar'))].reset_index()\n",
2021-07-06 15:23:24 +02:00
"opendoar_df.head()"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
2021-07-06 15:23:24 +02:00
"execution_count": 8,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
2021-07-06 15:23:24 +02:00
" <th>index</th>\n",
2021-07-02 17:49:38 +02:00
" <th>id</th>\n",
" <th>url</th>\n",
" <th>official_name</th>\n",
" <th>english_name</th>\n",
" <th>description</th>\n",
" <th>latitude</th>\n",
" <th>longitude</th>\n",
" <th>subjects</th>\n",
2021-07-22 11:03:05 +02:00
" <th>type</th>\n",
" <th>dataprovider</th>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
2021-07-06 15:23:24 +02:00
" <td>6014.000000</td>\n",
2021-07-02 17:49:38 +02:00
" <td>6014</td>\n",
" <td>6013</td>\n",
" <td>6014</td>\n",
" <td>5500</td>\n",
" <td>5776</td>\n",
" <td>6014.000000</td>\n",
" <td>6014.000000</td>\n",
" <td>6014</td>\n",
2021-07-22 11:03:05 +02:00
" <td>6014</td>\n",
" <td>6014</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>unique</th>\n",
2021-07-06 15:23:24 +02:00
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" <td>6014</td>\n",
" <td>5953</td>\n",
" <td>5946</td>\n",
" <td>5413</td>\n",
" <td>4920</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>201</td>\n",
2021-07-22 11:03:05 +02:00
" <td>5</td>\n",
" <td>1</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>top</th>\n",
2021-07-06 15:23:24 +02:00
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>10|opendoar____::6e3197aae95c2ff8fcab35cb730f6a86</td>\n",
2021-07-02 17:49:38 +02:00
" <td>http://harp.lib.hiroshima-u.ac.jp/</td>\n",
2021-07-22 11:03:05 +02:00
" <td>OpenKnowledge Ecology Repository</td>\n",
2021-07-02 17:49:38 +02:00
" <td>AURA</td>\n",
" <td>This site provides access to the research outp...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[]</td>\n",
2021-07-22 11:03:05 +02:00
" <td>pubsrepository::institutional</td>\n",
" <td>False</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>freq</th>\n",
2021-07-06 15:23:24 +02:00
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" <td>1</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>98</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>5273</td>\n",
2021-07-22 11:03:05 +02:00
" <td>5368</td>\n",
" <td>6014</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
2021-07-06 15:23:24 +02:00
" <td>4312.407549</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>38.649393</td>\n",
" <td>7.810948</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
2021-07-06 15:23:24 +02:00
" <td>2510.699848</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>788.406173</td>\n",
" <td>71.689788</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
2021-07-06 15:23:24 +02:00
" <td>0.000000</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>-79.029999</td>\n",
" <td>-683.103027</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
2021-07-06 15:23:24 +02:00
" <td>2129.250000</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.644632</td>\n",
" <td>-49.273300</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
2021-07-06 15:23:24 +02:00
" <td>4297.000000</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>37.930449</td>\n",
" <td>4.788870</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
2021-07-06 15:23:24 +02:00
" <td>6476.750000</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>47.294400</td>\n",
" <td>30.685501</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
2021-07-06 15:23:24 +02:00
" <td>8706.000000</td>\n",
2021-07-02 17:49:38 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>61138.800781</td>\n",
" <td>178.438995</td>\n",
" <td>NaN</td>\n",
2021-07-22 11:03:05 +02:00
" <td>NaN</td>\n",
" <td>NaN</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
2021-07-06 15:23:24 +02:00
" index id \\\n",
"count 6014.000000 6014 \n",
"unique NaN 6014 \n",
2021-07-22 11:03:05 +02:00
"top NaN 10|opendoar____::6e3197aae95c2ff8fcab35cb730f6a86 \n",
2021-07-06 15:23:24 +02:00
"freq NaN 1 \n",
"mean 4312.407549 NaN \n",
"std 2510.699848 NaN \n",
"min 0.000000 NaN \n",
"25% 2129.250000 NaN \n",
"50% 4297.000000 NaN \n",
"75% 6476.750000 NaN \n",
"max 8706.000000 NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" url official_name \\\n",
"count 6013 6014 \n",
"unique 5953 5946 \n",
"top http://harp.lib.hiroshima-u.ac.jp/ OpenKnowledge Ecology Repository \n",
"freq 3 3 \n",
"mean NaN NaN \n",
"std NaN NaN \n",
"min NaN NaN \n",
"25% NaN NaN \n",
"50% NaN NaN \n",
"75% NaN NaN \n",
"max NaN NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" english_name description \\\n",
"count 5500 5776 \n",
"unique 5413 4920 \n",
"top AURA This site provides access to the research outp... \n",
"freq 4 98 \n",
"mean NaN NaN \n",
"std NaN NaN \n",
"min NaN NaN \n",
"25% NaN NaN \n",
"50% NaN NaN \n",
"75% NaN NaN \n",
"max NaN NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" latitude longitude subjects type \\\n",
"count 6014.000000 6014.000000 6014 6014 \n",
"unique NaN NaN 201 5 \n",
"top NaN NaN [] pubsrepository::institutional \n",
"freq NaN NaN 5273 5368 \n",
"mean 38.649393 7.810948 NaN NaN \n",
"std 788.406173 71.689788 NaN NaN \n",
"min -79.029999 -683.103027 NaN NaN \n",
"25% 4.644632 -49.273300 NaN NaN \n",
"50% 37.930449 4.788870 NaN NaN \n",
"75% 47.294400 30.685501 NaN NaN \n",
"max 61138.800781 178.438995 NaN NaN \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-22 11:03:05 +02:00
" dataprovider \n",
"count 6014 \n",
"unique 1 \n",
"top False \n",
"freq 6014 \n",
"mean NaN \n",
"std NaN \n",
"min NaN \n",
"25% NaN \n",
"50% NaN \n",
"75% NaN \n",
"max NaN "
2021-07-02 17:49:38 +02:00
]
},
2021-07-06 15:23:24 +02:00
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"opendoar_df.describe(include='all')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Basic cleaning"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**re3data**"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 ['Life Sciences', 'Basic Biological and Medica...\n",
"1 ['Natural Sciences', 'Astrophysics and Astrono...\n",
"2 ['Natural Sciences', 'Geosciences (including G...\n",
"3 ['Humanities and Social Sciences', 'Psychology...\n",
"4 ['Natural Sciences', 'Geology and Palaeontolog...\n",
" ... \n",
"2688 ['Life Sciences', 'Basic Biological and Medica...\n",
"2689 ['Natural Sciences', 'Atmospheric Science and ...\n",
"2690 ['Natural Sciences', 'Atmospheric Science and ...\n",
"2691 ['Natural Sciences', 'Atmospheric Science and ...\n",
"2692 ['Life Sciences', 'Plant Sciences', 'Plant Gen...\n",
"Name: subjects, Length: 2693, dtype: object"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 9,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"re3data_df.subjects"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 10,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"re3data_df['subjects'] = re3data_df.subjects.apply(lambda x: ast.literal_eval(x))"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 11,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"def merge_lists(lists):\n",
" res = []\n",
" for l in lists:\n",
" res = res + l\n",
" return res\n",
"\n",
"re3data_cleaned_subjects = re3data_df.explode('subjects').subjects.str.split(',| and ', expand=True)\\\n",
" .apply(lambda row: row.dropna().tolist(), axis=1)\\\n",
" .reset_index()\\\n",
" .groupby('index')[0].apply(lambda x: merge_lists(x))"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 12,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"index\n",
"0 [Life Sciences, Basic Biological, Medical Rese...\n",
"1 [Natural Sciences, Astrophysics, Astronomy, Ph...\n",
"2 [Natural Sciences, Geosciences (including Geog...\n",
"3 [Humanities, Social Sciences, Psychology, Soci...\n",
"4 [Natural Sciences, Geology, Palaeontology, Geo...\n",
" ... \n",
"2688 [Life Sciences, Basic Biological, Medical Rese...\n",
"2689 [Natural Sciences, Atmospheric Science, Oceano...\n",
"2690 [Natural Sciences, Atmospheric Science, Oceano...\n",
"2691 [Natural Sciences, Atmospheric Science, Oceano...\n",
"2692 [Life Sciences, Plant Sciences, Plant Genetics...\n",
"Name: 0, Length: 2693, dtype: object"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 12,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"re3data_cleaned_subjects"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 13,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"re3data_df = re3data_df.join(re3data_cleaned_subjects)"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 14,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"re3data_df.drop(columns=['subjects'], inplace=True)\n",
"re3data_df.rename(columns={0:'subjects'}, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**OpenDOAR**"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 15,
2021-07-06 15:23:24 +02:00
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"0 []\n",
"1 []\n",
"2 ['Social Sciences General', 'Science General',...\n",
"3 []\n",
"4 []\n",
" ... \n",
"6009 ['Multidisciplinary']\n",
"6010 []\n",
"6011 ['Business and Economics']\n",
"6012 ['Earth and Planetary Sciences', 'Ecology and ...\n",
"6013 []\n",
"Name: subjects, Length: 6014, dtype: object"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 15,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"opendoar_df.subjects"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 16,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"opendoar_df['subjects'] = opendoar_df.subjects.apply(lambda x: ast.literal_eval(x))"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 17,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"opendoar_cleaned_subjects = opendoar_df.explode('subjects').subjects.str.split(',| and ', expand=True)\\\n",
" .apply(lambda row: row.dropna().tolist(), axis=1)\\\n",
" .reset_index()\\\n",
" .groupby('index')[0].apply(lambda x: merge_lists(x))"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 18,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"index\n",
"0 []\n",
"1 []\n",
"2 [Social Sciences General, Science General, Com...\n",
"3 []\n",
"4 []\n",
" ... \n",
"6009 [Multidisciplinary]\n",
"6010 []\n",
"6011 [Business, Economics]\n",
"6012 [Earth, Planetary Sciences, Ecology, Environme...\n",
"6013 []\n",
"Name: 0, Length: 6014, dtype: object"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 18,
2021-07-02 17:49:38 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2021-07-06 15:23:24 +02:00
"opendoar_cleaned_subjects"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 19,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"opendoar_df = opendoar_df.join(opendoar_cleaned_subjects)"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 20,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"opendoar_df.drop(columns=['subjects'], inplace=True)\n",
"opendoar_df.rename(columns={0: 'subjects'}, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Subjects analysis"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 21,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"fairsharing_subjects = fairsharing_df.explode('subjects')\n",
"re3data_subjects = re3data_df.explode('subjects')\n",
"opendoar_subjects = opendoar_df.explode('subjects')"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 22,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
2021-07-06 15:23:24 +02:00
{
"data": {
"text/html": [
" <script type=\"text/javascript\">\n",
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
" if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
" if (typeof require !== 'undefined') {\n",
" require.undef(\"plotly\");\n",
" define('plotly', function(require, exports, module) {\n",
" /**\n",
"* plotly.js v1.58.4\n",
"* Copyright 2012-2020, Plotly, Inc.\n",
"* All rights reserved.\n",
"* Licensed under the MIT license\n",
"*/\n",
"!function(t){if(\"object\"==typeof exports&&\"undefined\"!=typeof module)module.exports=t();else if(\"function\"==typeof define&&define.amd)define([],t);else{(\"undefined\"!=typeof window?window:\"undefined\"!=typeof global?global:\"undefined\"!=typeof self?self:this).Plotly=t()}}((function(){return function t(e,r,n){function i(o,s){if(!r[o]){if(!e[o]){var l=\"function\"==typeof require&&require;if(!s&&l)return l(o,!0);if(a)return a(o,!0);var c=new Error(\"Cannot find module '\"+o+\"'\");throw c.code=\"MODULE_NOT_FOUND\",c}var u=r[o]={exports:{}};e[o][0].call(u.exports,(function(t){return i(e[o][1][t]||t)}),u,u.exports,t,e,r,n)}return r[o].exports}for(var a=\"function\"==typeof require&&require,o=0;o<n.length;o++)i(n[o]);return i}({1:[function(t,e,r){\"use strict\";var n=t(\"../src/lib\"),i={\"X,X div\":\"direction:ltr;font-family:'Open Sans', verdana, arial, sans-serif;margin:0;padding:0;\",\"X input,X button\":\"font-family:'Open Sans', verdana, arial, sans-serif;\",\"X input:focus,X button:focus\":\"outline:none;\",\"X a\":\"text-decoration:none;\",\"X a:hover\":\"text-decoration:none;\",\"X .crisp\":\"shape-rendering:crispEdges;\",\"X .user-select-none\":\"-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;-o-user-select:none;user-select:none;\",\"X svg\":\"overflow:hidden;\",\"X svg a\":\"fill:#447adb;\",\"X svg a:hover\":\"fill:#3c6dc5;\",\"X .main-svg\":\"position:absolute;top:0;left:0;pointer-events:none;\",\"X .main-svg .draglayer\":\"pointer-events:all;\",\"X .cursor-default\":\"cursor:default;\",\"X .cursor-pointer\":\"cursor:pointer;\",\"X .cursor-crosshair\":\"cursor:crosshair;\",\"X .cursor-move\":\"cursor:move;\",\"X .cursor-col-resize\":\"cursor:col-resize;\",\"X .cursor-row-resize\":\"cursor:row-resize;\",\"X .cursor-ns-resize\":\"cursor:ns-resize;\",\"X .cursor-ew-resize\":\"cursor:ew-resize;\",\"X .cursor-sw-resize\":\"cursor:sw-resize;\",\"X .cursor-s-resize\":\"cursor:s-resize;\",\"X .cursor-se-resize\":\"cursor:se-resize;\",\"X .cursor-w-resize\":\"cursor:w-resize;\",\"X .cursor-e-resize\":\"cursor:e-resize;\",\"X .cursor-nw-resize\":\"cursor:nw-resize;\",\"X .cursor-n-resize\":\"cursor:n-resize;\",\"X .cursor-ne-resize\":\"cursor:ne-resize;\",\"X .cursor-grab\":\"cursor:-webkit-grab;cursor:grab;\",\"X .modebar\":\"position:absolute;top:2px;right:2px;\",\"X .ease-bg\":\"-webkit-transition:background-color 0.3s ease 0s;-moz-transition:background-color 0.3s ease 0s;-ms-transition:background-color 0.3s ease 0s;-o-transition:background-color 0.3s ease 0s;transition:background-color 0.3s ease 0s;\",\"X .modebar--hover>:not(.watermark)\":\"opacity:0;-webkit-transition:opacity 0.3s ease 0s;-moz-transition:opacity 0.3s ease 0s;-ms-transition:opacity 0.3s ease 0s;-o-transition:opacity 0.3s ease 0s;transition:opacity 0.3s ease 0s;\",\"X:hover .modebar--hover .modebar-group\":\"opacity:1;\",\"X .modebar-group\":\"float:left;display:inline-block;box-sizing:border-box;padding-left:8px;position:relative;vertical-align:middle;white-space:nowrap;\",\"X .modebar-btn\":\"position:relative;font-size:16px;padding:3px 4px;height:22px;cursor:pointer;line-height:normal;box-sizing:border-box;\",\"X .modebar-btn svg\":\"position:relative;top:2px;\",\"X .modebar.vertical\":\"display:flex;flex-direction:column;flex-wrap:wrap;align-content:flex-end;max-height:100%;\",\"X .modebar.vertical svg\":\"top:-1px;\",\"X .modebar.vertical .modebar-group\":\"display:block;float:none;padding-left:0px;padding-bottom:8px;\",\"X .modebar.vertical .modebar-group .modebar-btn\":\"display:block;text-align:center;\",\"X [data-title]:before,X [data-title]:after\":\"position:absolute;-webkit-transform:translate3d(0, 0, 0);-moz-transform:translate3d(0, 0, 0);-ms-transform:translate3d(0, 0, 0);-o-transform:translate3d(0, 0, 0);transform:translate3d(0, 0, 0);display:none;opacity:0;z-index:1001;pointer-events:none;top:110%;right:50%;\",\"X [data-title]:hover:before,X [data-title]:hover:after\":\"display:block;opacity:1;\",\"X [data-title]:before\":\"content:'';position:absolute;background:transparent;border:6px solid transpa
"/*!\n",
" * The buffer module from node.js, for the browser.\n",
" *\n",
" * @author Feross Aboukhadijeh <feross@feross.org> <http://feross.org>\n",
" * @license MIT\n",
" */function i(t,e){if(t===e)return 0;for(var r=t.length,n=e.length,i=0,a=Math.min(r,n);i<a;++i)if(t[i]!==e[i]){r=t[i],n=e[i];break}return r<n?-1:n<r?1:0}function a(t){return r.Buffer&&\"function\"==typeof r.Buffer.isBuffer?r.Buffer.isBuffer(t):!(null==t||!t._isBuffer)}var o=t(\"util/\"),s=Object.prototype.hasOwnProperty,l=Array.prototype.slice,c=\"foo\"===function(){}.name;function u(t){return Object.prototype.toString.call(t)}function f(t){return!a(t)&&(\"function\"==typeof r.ArrayBuffer&&(\"function\"==typeof ArrayBuffer.isView?ArrayBuffer.isView(t):!!t&&(t instanceof DataView||!!(t.buffer&&t.buffer instanceof ArrayBuffer))))}var h=e.exports=y,p=/\\s*function\\s+([^\\(\\s]*)\\s*/;function d(t){if(o.isFunction(t)){if(c)return t.name;var e=t.toString().match(p);return e&&e[1]}}function g(t,e){return\"string\"==typeof t?t.length<e?t:t.slice(0,e):t}function m(t){if(c||!o.isFunction(t))return o.inspect(t);var e=d(t);return\"[Function\"+(e?\": \"+e:\"\")+\"]\"}function v(t,e,r,n,i){throw new h.AssertionError({message:r,actual:t,expected:e,operator:n,stackStartFunction:i})}function y(t,e){t||v(t,!0,e,\"==\",h.ok)}function x(t,e,r,n){if(t===e)return!0;if(a(t)&&a(e))return 0===i(t,e);if(o.isDate(t)&&o.isDate(e))return t.getTime()===e.getTime();if(o.isRegExp(t)&&o.isRegExp(e))return t.source===e.source&&t.global===e.global&&t.multiline===e.multiline&&t.lastIndex===e.lastIndex&&t.ignoreCase===e.ignoreCase;if(null!==t&&\"object\"==typeof t||null!==e&&\"object\"==typeof e){if(f(t)&&f(e)&&u(t)===u(e)&&!(t instanceof Float32Array||t instanceof Float64Array))return 0===i(new Uint8Array(t.buffer),new Uint8Array(e.buffer));if(a(t)!==a(e))return!1;var s=(n=n||{actual:[],expected:[]}).actual.indexOf(t);return-1!==s&&s===n.expected.indexOf(e)||(n.actual.push(t),n.expected.push(e),function(t,e,r,n){if(null==t||null==e)return!1;if(o.isPrimitive(t)||o.isPrimitive(e))return t===e;if(r&&Object.getPrototypeOf(t)!==Object.getPrototypeOf(e))return!1;var i=b(t),a=b(e);if(i&&!a||!i&&a)return!1;if(i)return t=l.call(t),e=l.call(e),x(t,e,r);var s,c,u=T(t),f=T(e);if(u.length!==f.length)return!1;for(u.sort(),f.sort(),c=u.length-1;c>=0;c--)if(u[c]!==f[c])return!1;for(c=u.length-1;c>=0;c--)if(s=u[c],!x(t[s],e[s],r,n))return!1;return!0}(t,e,r,n))}return r?t===e:t==e}function b(t){return\"[object Arguments]\"==Object.prototype.toString.call(t)}function _(t,e){if(!t||!e)return!1;if(\"[object RegExp]\"==Object.prototype.toString.call(e))return e.test(t);try{if(t instanceof e)return!0}catch(t){}return!Error.isPrototypeOf(e)&&!0===e.call({},t)}function w(t,e,r,n){var i;if(\"function\"!=typeof e)throw new TypeError('\"block\" argument must be a function');\"string\"==typeof r&&(n=r,r=null),i=function(t){var e;try{t()}catch(t){e=t}return e}(e),n=(r&&r.name?\" (\"+r.name+\").\":\".\")+(n?\" \"+n:\".\"),t&&!i&&v(i,r,\"Missing expected exception\"+n);var a=\"string\"==typeof n,s=!t&&i&&!r;if((!t&&o.isError(i)&&a&&_(i,r)||s)&&v(i,r,\"Got unwanted exception\"+n),t&&i&&r&&!_(i,r)||!t&&i)throw i}h.AssertionError=function(t){this.name=\"AssertionError\",this.actual=t.actual,this.expected=t.expected,this.operator=t.operator,t.message?(this.message=t.message,this.generatedMessage=!1):(this.message=function(t){return g(m(t.actual),128)+\" \"+t.operator+\" \"+g(m(t.expected),128)}(this),this.generatedMessage=!0);var e=t.stackStartFunction||v;if(Error.captureStackTrace)Error.captureStackTrace(this,e);else{var r=new Error;if(r.stack){var n=r.stack,i=d(e),a=n.indexOf(\"\\n\"+i);if(a>=0){var o=n.indexOf(\"\\n\",a+1);n=n.substring(o+1)}this.stack=n}}},o.inherits(h.AssertionError,Error),h.fail=v,h.ok=y,h.equal=function(t,e,r){t!=e&&v(t,e,r,\"==\",h.equal)},h.notEqual=function(t,e,r){t==e&&v(t,e,r,\"!=\",h.notEqual)},h.deepEqual=function(t,e,r){x(t,e,!1)||v(t,e,r,\"deepEqual\",h.deepEqual)},h.deepStrictEqual=function(t,e,r){x(t,e,!0)||v(t,e,r,\"deepStrictEqual\",h.deepStrictEqual)},h.notDeepEqual=function(t,e,r){x(t,e,!1)&&v(t,e,r,\"notDeepEqual\",h.notDeepEqual)},h.notDeepStrictEqual=function t(e,r,n){x(e,r,!0)&&v(e,r,n,\"notDeepStrictEqual\",t)},h.strictEqual=function(t,e
"/*!\n",
" * The buffer module from node.js, for the browser.\n",
" *\n",
" * @author Feross Aboukhadijeh <https://feross.org>\n",
" * @license MIT\n",
" */\n",
"\"use strict\";var e=t(\"base64-js\"),n=t(\"ieee754\");r.Buffer=a,r.SlowBuffer=function(t){+t!=t&&(t=0);return a.alloc(+t)},r.INSPECT_MAX_BYTES=50;function i(t){if(t>2147483647)throw new RangeError('The value \"'+t+'\" is invalid for option \"size\"');var e=new Uint8Array(t);return e.__proto__=a.prototype,e}function a(t,e,r){if(\"number\"==typeof t){if(\"string\"==typeof e)throw new TypeError('The \"string\" argument must be of type string. Received type number');return l(t)}return o(t,e,r)}function o(t,e,r){if(\"string\"==typeof t)return function(t,e){\"string\"==typeof e&&\"\"!==e||(e=\"utf8\");if(!a.isEncoding(e))throw new TypeError(\"Unknown encoding: \"+e);var r=0|f(t,e),n=i(r),o=n.write(t,e);o!==r&&(n=n.slice(0,o));return n}(t,e);if(ArrayBuffer.isView(t))return c(t);if(null==t)throw TypeError(\"The first argument must be one of type string, Buffer, ArrayBuffer, Array, or Array-like Object. Received type \"+typeof t);if(B(t,ArrayBuffer)||t&&B(t.buffer,ArrayBuffer))return function(t,e,r){if(e<0||t.byteLength<e)throw new RangeError('\"offset\" is outside of buffer bounds');if(t.byteLength<e+(r||0))throw new RangeError('\"length\" is outside of buffer bounds');var n;n=void 0===e&&void 0===r?new Uint8Array(t):void 0===r?new Uint8Array(t,e):new Uint8Array(t,e,r);return n.__proto__=a.prototype,n}(t,e,r);if(\"number\"==typeof t)throw new TypeError('The \"value\" argument must not be of type number. Received type number');var n=t.valueOf&&t.valueOf();if(null!=n&&n!==t)return a.from(n,e,r);var o=function(t){if(a.isBuffer(t)){var e=0|u(t.length),r=i(e);return 0===r.length||t.copy(r,0,0,e),r}if(void 0!==t.length)return\"number\"!=typeof t.length||N(t.length)?i(0):c(t);if(\"Buffer\"===t.type&&Array.isArray(t.data))return c(t.data)}(t);if(o)return o;if(\"undefined\"!=typeof Symbol&&null!=Symbol.toPrimitive&&\"function\"==typeof t[Symbol.toPrimitive])return a.from(t[Symbol.toPrimitive](\"string\"),e,r);throw new TypeError(\"The first argument must be one of type string, Buffer, ArrayBuffer, Array, or Array-like Object. Received type \"+typeof t)}function s(t){if(\"number\"!=typeof t)throw new TypeError('\"size\" argument must be of type number');if(t<0)throw new RangeError('The value \"'+t+'\" is invalid for option \"size\"')}function l(t){return s(t),i(t<0?0:0|u(t))}function c(t){for(var e=t.length<0?0:0|u(t.length),r=i(e),n=0;n<e;n+=1)r[n]=255&t[n];return r}function u(t){if(t>=2147483647)throw new RangeError(\"Attempt to allocate Buffer larger than maximum size: 0x\"+2147483647..toString(16)+\" bytes\");return 0|t}function f(t,e){if(a.isBuffer(t))return t.length;if(ArrayBuffer.isView(t)||B(t,ArrayBuffer))return t.byteLength;if(\"string\"!=typeof t)throw new TypeError('The \"string\" argument must be one of type string, Buffer, or ArrayBuffer. Received type '+typeof t);var r=t.length,n=arguments.length>2&&!0===arguments[2];if(!n&&0===r)return 0;for(var i=!1;;)switch(e){case\"ascii\":case\"latin1\":case\"binary\":return r;case\"utf8\":case\"utf-8\":return D(t).length;case\"ucs2\":case\"ucs-2\":case\"utf16le\":case\"utf-16le\":return 2*r;case\"hex\":return r>>>1;case\"base64\":return R(t).length;default:if(i)return n?-1:D(t).length;e=(\"\"+e).toLowerCase(),i=!0}}function h(t,e,r){var n=!1;if((void 0===e||e<0)&&(e=0),e>this.length)return\"\";if((void 0===r||r>this.length)&&(r=this.length),r<=0)return\"\";if((r>>>=0)<=(e>>>=0))return\"\";for(t||(t=\"utf8\");;)switch(t){case\"hex\":return A(this,e,r);case\"utf8\":case\"utf-8\":return T(this,e,r);case\"ascii\":return k(this,e,r);case\"latin1\":case\"binary\":return M(this,e,r);case\"base64\":return w(this,e,r);case\"ucs2\":case\"ucs-2\":case\"utf16le\":case\"utf-16le\":return S(this,e,r);default:if(n)throw new TypeError(\"Unknown encoding: \"+t);t=(t+\"\").toLowerCase(),n=!0}}function p(t,e,r){var n=t[e];t[e]=t[r],t[r]=n}function d(t,e,r,n,i){if(0===t.length)return-1;if(\"string\"==typeof r?(n=r,r=0):r>2147483647?r=2147483647:r<-2147483648&&(r=-2147483648),N(r=+r)&&(r=i?0:t.length-1),r<0&&(r=t.length+r),r>=t.length){if(i)return-1;r=t.length-1}else if(r<0){if(!i)return-1;r=0}i
"/*!\n",
" * @overview es6-promise - a tiny implementation of Promises/A+.\n",
" * @copyright Copyright (c) 2014 Yehuda Katz, Tom Dale, Stefan Penner and contributors (Conversion to ES6 API by Jake Archibald)\n",
" * @license Licensed under MIT license\n",
" * See https://raw.githubusercontent.com/stefanpenner/es6-promise/master/LICENSE\n",
" * @version v4.2.8+1e68dce6\n",
" */\n",
"!function(t,n){\"object\"==typeof r&&\"undefined\"!=typeof e?e.exports=n():t.ES6Promise=n()}(this,(function(){\"use strict\";function e(t){return\"function\"==typeof t}var r=Array.isArray?Array.isArray:function(t){return\"[object Array]\"===Object.prototype.toString.call(t)},a=0,o=void 0,s=void 0,l=function(t,e){g[a]=t,g[a+1]=e,2===(a+=2)&&(s?s(m):_())};var c=\"undefined\"!=typeof window?window:void 0,u=c||{},f=u.MutationObserver||u.WebKitMutationObserver,h=\"undefined\"==typeof self&&\"undefined\"!=typeof n&&\"[object process]\"==={}.toString.call(n),p=\"undefined\"!=typeof Uint8ClampedArray&&\"undefined\"!=typeof importScripts&&\"undefined\"!=typeof MessageChannel;function d(){var t=setTimeout;return function(){return t(m,1)}}var g=new Array(1e3);function m(){for(var t=0;t<a;t+=2){(0,g[t])(g[t+1]),g[t]=void 0,g[t+1]=void 0}a=0}var v,y,x,b,_=void 0;function w(t,e){var r=this,n=new this.constructor(M);void 0===n[k]&&D(n);var i=r._state;if(i){var a=arguments[i-1];l((function(){return z(i,n,a,r._result)}))}else I(r,n,t,e);return n}function T(t){if(t&&\"object\"==typeof t&&t.constructor===this)return t;var e=new this(M);return S(e,t),e}h?_=function(){return n.nextTick(m)}:f?(y=0,x=new f(m),b=document.createTextNode(\"\"),x.observe(b,{characterData:!0}),_=function(){b.data=y=++y%2}):p?((v=new MessageChannel).port1.onmessage=m,_=function(){return v.port2.postMessage(0)}):_=void 0===c&&\"function\"==typeof t?function(){try{var t=Function(\"return this\")().require(\"vertx\");return\"undefined\"!=typeof(o=t.runOnLoop||t.runOnContext)?function(){o(m)}:d()}catch(t){return d()}}():d();var k=Math.random().toString(36).substring(2);function M(){}function A(t,r,n){r.constructor===t.constructor&&n===w&&r.constructor.resolve===T?function(t,e){1===e._state?C(t,e._result):2===e._state?L(t,e._result):I(e,void 0,(function(e){return S(t,e)}),(function(e){return L(t,e)}))}(t,r):void 0===n?C(t,r):e(n)?function(t,e,r){l((function(t){var n=!1,i=function(t,e,r,n){try{t.call(e,r,n)}catch(t){return t}}(r,e,(function(r){n||(n=!0,e!==r?S(t,r):C(t,r))}),(function(e){n||(n=!0,L(t,e))}),t._label);!n&&i&&(n=!0,L(t,i))}),t)}(t,r,n):C(t,r)}function S(t,e){if(t===e)L(t,new TypeError(\"You cannot resolve a promise with itself\"));else if(i=typeof(n=e),null===n||\"object\"!==i&&\"function\"!==i)C(t,e);else{var r=void 0;try{r=e.then}catch(e){return void L(t,e)}A(t,e,r)}var n,i}function E(t){t._onerror&&t._onerror(t._result),P(t)}function C(t,e){void 0===t._state&&(t._result=e,t._state=1,0!==t._subscribers.length&&l(P,t))}function L(t,e){void 0===t._state&&(t._state=2,t._result=e,l(E,t))}function I(t,e,r,n){var i=t._subscribers,a=i.length;t._onerror=null,i[a]=e,i[a+1]=r,i[a+2]=n,0===a&&t._state&&l(P,t)}function P(t){var e=t._subscribers,r=t._state;if(0!==e.length){for(var n=void 0,i=void 0,a=t._result,o=0;o<e.length;o+=3)n=e[o],i=e[o+r],n?z(r,n,i,a):i(a);t._subscribers.length=0}}function z(t,r,n,i){var a=e(n),o=void 0,s=void 0,l=!0;if(a){try{o=n(i)}catch(t){l=!1,s=t}if(r===o)return void L(r,new TypeError(\"A promises callback cannot return that same promise.\"))}else o=i;void 0!==r._state||(a&&l?S(r,o):!1===l?L(r,s):1===t?C(r,o):2===t&&L(r,o))}var O=0;function D(t){t[k]=O++,t._state=void 0,t._result=void 0,t._subscribers=[]}var R=function(){function t(t,e){this._instanceConstructor=t,this.promise=new t(M),this.promise[k]||D(this.promise),r(e)?(this.length=e.length,this._remaining=e.length,this._result=new Array(this.length),0===this.length?C(this.promise,this._result):(this.length=this.length||0,this._enumerate(e),0===this._remaining&&C(this.promise,this._result))):L(this.promise,new Error(\"Array Methods must be provided an Array\"))}return t.prototype._enumerate=function(t){for(var e=0;void 0===this._state&&e<t.length;e++)this._eachEntry(t[e],e)},t.prototype._eachEntry=function(t,e){var r=this._instanceConstructor,n=r.resolve;if(n===T){var i=void 0,a=void 0,o=!1;try{i=t.then}catch(t){o=!0,a=t}if(i===w&&void 0!==t._state)this._settledAt(t._state,e,t._result);else if(\"function\"!=typeof i)this._remaining--,this._result[e]=t;else if(r===F){var s=new r
"/*!\n",
" * Determine if an object is a Buffer\n",
" *\n",
" * @author Feross Aboukhadijeh <https://feross.org>\n",
" * @license MIT\n",
" */\n",
"e.exports=function(t){return null!=t&&(n(t)||function(t){return\"function\"==typeof t.readFloatLE&&\"function\"==typeof t.slice&&n(t.slice(0,0))}(t)||!!t._isBuffer)}},{}],466:[function(t,e,r){\"use strict\";e.exports=\"undefined\"!=typeof navigator&&(/MSIE/.test(navigator.userAgent)||/Trident\\//.test(navigator.appVersion))},{}],467:[function(t,e,r){\"use strict\";e.exports=a,e.exports.isMobile=a,e.exports.default=a;var n=/(android|bb\\d+|meego).+mobile|avantgo|bada\\/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)\\/|plucker|pocket|psp|series[46]0|symbian|treo|up\\.(browser|link)|vodafone|wap|windows (ce|phone)|xda|xiino/i,i=/(android|bb\\d+|meego).+mobile|avantgo|bada\\/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)\\/|plucker|pocket|psp|series[46]0|symbian|treo|up\\.(browser|link)|vodafone|wap|windows (ce|phone)|xda|xiino|android|ipad|playbook|silk/i;function a(t){t||(t={});var e=t.ua;if(e||\"undefined\"==typeof navigator||(e=navigator.userAgent),e&&e.headers&&\"string\"==typeof e.headers[\"user-agent\"]&&(e=e.headers[\"user-agent\"]),\"string\"!=typeof e)return!1;var r=t.tablet?i.test(e):n.test(e);return!r&&t.tablet&&t.featureDetect&&navigator&&navigator.maxTouchPoints>1&&-1!==e.indexOf(\"Macintosh\")&&-1!==e.indexOf(\"Safari\")&&(r=!0),r}},{}],468:[function(t,e,r){\"use strict\";e.exports=function(t){var e=typeof t;return null!==t&&(\"object\"===e||\"function\"===e)}},{}],469:[function(t,e,r){\"use strict\";var n=Object.prototype.toString;e.exports=function(t){var e;return\"[object Object]\"===n.call(t)&&(null===(e=Object.getPrototypeOf(t))||e===Object.getPrototypeOf({}))}},{}],470:[function(t,e,r){\"use strict\";e.exports=function(t){for(var e,r=t.length,n=0;n<r;n++)if(((e=t.charCodeAt(n))<9||e>13)&&32!==e&&133!==e&&160!==e&&5760!==e&&6158!==e&&(e<8192||e>8205)&&8232!==e&&8233!==e&&8239!==e&&8287!==e&&8288!==e&&12288!==e&&65279!==e)return!1;return!0}},{}],471:[function(t,e,r){\"use strict\";e.exports=function(t){return\"string\"==typeof t&&(t=t.trim(),!!(/^[mzlhvcsqta]\\s*[-+.0-9][^mlhvzcsqta]+/i.test(t)&&/[\\dz]$/i.test(t)&&t.length>4))}},{}],472:[function(t,e,r){e.exports=function(t,e,r){return t*(1-r)+e*r}},{}],473:[function(t,e,r){!function(t,n){\"object\"==typeof r&&\"undefined\"!=typeof e?e.exports=n():(t=t||self).mapboxgl=n()}(this,(function(){\"use strict\";var t,e,r;function n(n,i){if(t)if(e){var a=\"var sharedChunk = {}; (\"+t+\")(sharedChunk); (\"+e+\")(sharedChunk);\",o={};t(o),(r=i(o)).workerUrl=window.URL.createObjectURL(new Blob([a],{type:\"text/javascript\"}))}else e=i;else t=i}return n(0,(function(t){function e(t,e){return t(e={exports:{}},e.exports),e.exports}var r=n;function n(t,e,r,n){this.cx=3*t,this.bx=3*(r-t)-this.cx,this.ax=1-this.cx-this.bx,this.cy=3*e,this.by=3*(n-e)-this.cy,this.ay=1-this.cy-this.by,this.p1x=t,this.p1y=n,this.p2x=r,this.p2y=n}n.prototype.sampleCurveX=function(t){return((this.ax*t+this.bx)*t+this.cx)*t},n.prototype.sampleCurveY=function(t){return((this.ay*t+this.by)*t+this.cy)*t},n.prototype.sampleCurveDerivativeX=function(t){return(3*this.ax*t+2*this.bx)*t+this.cx},n.prototype.solveCurveX=function(t,e){var r,n,i,a,o;for(void 0===e&&(e=1e-6),i=t,o=0;o<8;o++){if(a=this.sampleCurveX(i)-t,Math.abs(a)<e)return i;var s=this.sampleCurveDerivativeX(i);if(Math.abs(s)<1e-6)break;i-=a/s}if((i=t)<(r=0))return r;if(i>(n=1))return n;for(;r<n;){if(a=this.sampleCurveX(i),Math.abs(a-t)<e)return i;t>a?r=i:n=i,i=.5*(n-r)+r}return i},n.prototype.solve=function(t,e){return this.sampleCurveY(this.solveCurveX(t,e))};var i=a;function a(t,e){this.x=t,this.y=e}function o(t,e,n,i){var a=new r(t,e,n,i);return function(t){return a.solve(t)}}a.prototype={clone:function(){return new a(this.x,this.y)},add:function(t){return this.clone()._add(t)},sub:function(t){return this.clone()._sub(t)},multByPoint:function(t){return this.clone()._multByPoint(t)},divByPoi
"/*\n",
"object-assign\n",
"(c) Sindre Sorhus\n",
"@license MIT\n",
"*/\n",
"\"use strict\";var n=Object.getOwnPropertySymbols,i=Object.prototype.hasOwnProperty,a=Object.prototype.propertyIsEnumerable;function o(t){if(null==t)throw new TypeError(\"Object.assign cannot be called with null or undefined\");return Object(t)}e.exports=function(){try{if(!Object.assign)return!1;var t=new String(\"abc\");if(t[5]=\"de\",\"5\"===Object.getOwnPropertyNames(t)[0])return!1;for(var e={},r=0;r<10;r++)e[\"_\"+String.fromCharCode(r)]=r;if(\"0123456789\"!==Object.getOwnPropertyNames(e).map((function(t){return e[t]})).join(\"\"))return!1;var n={};return\"abcdefghijklmnopqrst\".split(\"\").forEach((function(t){n[t]=t})),\"abcdefghijklmnopqrst\"===Object.keys(Object.assign({},n)).join(\"\")}catch(t){return!1}}()?Object.assign:function(t,e){for(var r,s,l=o(t),c=1;c<arguments.length;c++){for(var u in r=Object(arguments[c]))i.call(r,u)&&(l[u]=r[u]);if(n){s=n(r);for(var f=0;f<s.length;f++)a.call(r,s[f])&&(l[s[f]]=r[s[f]])}}return l}},{}],500:[function(t,e,r){\"use strict\";e.exports=function(t,e,r,n,i,a,o,s,l,c){var u=e+a+c;if(f>0){var f=Math.sqrt(u+1);t[0]=.5*(o-l)/f,t[1]=.5*(s-n)/f,t[2]=.5*(r-a)/f,t[3]=.5*f}else{var h=Math.max(e,a,c);f=Math.sqrt(2*h-u+1);e>=h?(t[0]=.5*f,t[1]=.5*(i+r)/f,t[2]=.5*(s+n)/f,t[3]=.5*(o-l)/f):a>=h?(t[0]=.5*(r+i)/f,t[1]=.5*f,t[2]=.5*(l+o)/f,t[3]=.5*(s-n)/f):(t[0]=.5*(n+s)/f,t[1]=.5*(o+l)/f,t[2]=.5*f,t[3]=.5*(r-i)/f)}return t}},{}],501:[function(t,e,r){\"use strict\";e.exports=function(t){var e=(t=t||{}).center||[0,0,0],r=t.rotation||[0,0,0,1],n=t.radius||1;e=[].slice.call(e,0,3),u(r=[].slice.call(r,0,4),r);var i=new f(r,e,Math.log(n));i.setDistanceLimits(t.zoomMin,t.zoomMax),(\"eye\"in t||\"up\"in t)&&i.lookAt(0,t.eye,t.center,t.up);return i};var n=t(\"filtered-vector\"),i=t(\"gl-mat4/lookAt\"),a=t(\"gl-mat4/fromQuat\"),o=t(\"gl-mat4/invert\"),s=t(\"./lib/quatFromFrame\");function l(t,e,r){return Math.sqrt(Math.pow(t,2)+Math.pow(e,2)+Math.pow(r,2))}function c(t,e,r,n){return Math.sqrt(Math.pow(t,2)+Math.pow(e,2)+Math.pow(r,2)+Math.pow(n,2))}function u(t,e){var r=e[0],n=e[1],i=e[2],a=e[3],o=c(r,n,i,a);o>1e-6?(t[0]=r/o,t[1]=n/o,t[2]=i/o,t[3]=a/o):(t[0]=t[1]=t[2]=0,t[3]=1)}function f(t,e,r){this.radius=n([r]),this.center=n(e),this.rotation=n(t),this.computedRadius=this.radius.curve(0),this.computedCenter=this.center.curve(0),this.computedRotation=this.rotation.curve(0),this.computedUp=[.1,0,0],this.computedEye=[.1,0,0],this.computedMatrix=[.1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],this.recalcMatrix(0)}var h=f.prototype;h.lastT=function(){return Math.max(this.radius.lastT(),this.center.lastT(),this.rotation.lastT())},h.recalcMatrix=function(t){this.radius.curve(t),this.center.curve(t),this.rotation.curve(t);var e=this.computedRotation;u(e,e);var r=this.computedMatrix;a(r,e);var n=this.computedCenter,i=this.computedEye,o=this.computedUp,s=Math.exp(this.computedRadius[0]);i[0]=n[0]+s*r[2],i[1]=n[1]+s*r[6],i[2]=n[2]+s*r[10],o[0]=r[1],o[1]=r[5],o[2]=r[9];for(var l=0;l<3;++l){for(var c=0,f=0;f<3;++f)c+=r[l+4*f]*i[f];r[12+l]=-c}},h.getMatrix=function(t,e){this.recalcMatrix(t);var r=this.computedMatrix;if(e){for(var n=0;n<16;++n)e[n]=r[n];return e}return r},h.idle=function(t){this.center.idle(t),this.radius.idle(t),this.rotation.idle(t)},h.flush=function(t){this.center.flush(t),this.radius.flush(t),this.rotation.flush(t)},h.pan=function(t,e,r,n){e=e||0,r=r||0,n=n||0,this.recalcMatrix(t);var i=this.computedMatrix,a=i[1],o=i[5],s=i[9],c=l(a,o,s);a/=c,o/=c,s/=c;var u=i[0],f=i[4],h=i[8],p=u*a+f*o+h*s,d=l(u-=a*p,f-=o*p,h-=s*p);u/=d,f/=d,h/=d;var g=i[2],m=i[6],v=i[10],y=g*a+m*o+v*s,x=g*u+m*f+v*h,b=l(g-=y*a+x*u,m-=y*o+x*f,v-=y*s+x*h);g/=b,m/=b,v/=b;var _=u*e+a*r,w=f*e+o*r,T=h*e+s*r;this.center.move(t,_,w,T);var k=Math.exp(this.computedRadius[0]);k=Math.max(1e-4,k+n),this.radius.set(t,Math.log(k))},h.rotate=function(t,e,r,n){this.recalcMatrix(t),e=e||0,r=r||0;var i=this.computedMatrix,a=i[0],o=i[4],s=i[8],u=i[1],f=i[5],h=i[9],p=i[2],d=i[6],g=i[10],m=e*a+r*u,v=e*o+r*f,y=e*s+r*h,x=-(d*y-g*v),b=-(g*m-p*y),_=-(p*v-d*m),w=Math.sqrt(Math.max(0,1-Math.pow(x,2)-Math.pow(b,2)-Math.pow(_,2))),T=c(x,b,_,w);T>1e-6?(x/=T,b/=
"/*!\n",
" * pad-left <https://github.com/jonschlinkert/pad-left>\n",
" *\n",
" * Copyright (c) 2014-2015, Jon Schlinkert.\n",
" * Licensed under the MIT license.\n",
" */\n",
"\"use strict\";var n=t(\"repeat-string\");e.exports=function(t,e,r){return n(r=\"undefined\"!=typeof r?r+\"\":\" \",e)+t}},{\"repeat-string\":541}],503:[function(t,e,r){\"use strict\";function n(t,e){if(\"string\"!=typeof t)return[t];var r=[t];\"string\"==typeof e||Array.isArray(e)?e={brackets:e}:e||(e={});var n=e.brackets?Array.isArray(e.brackets)?e.brackets:[e.brackets]:[\"{}\",\"[]\",\"()\"],i=e.escape||\"___\",a=!!e.flat;n.forEach((function(t){var e=new RegExp([\"\\\\\",t[0],\"[^\\\\\",t[0],\"\\\\\",t[1],\"]*\\\\\",t[1]].join(\"\")),n=[];function a(e,a,o){var s=r.push(e.slice(t[0].length,-t[1].length))-1;return n.push(s),i+s+i}r.forEach((function(t,n){for(var i,o=0;t!=i;)if(i=t,t=t.replace(e,a),o++>1e4)throw Error(\"References have circular dependency. Please, check them.\");r[n]=t})),n=n.reverse(),r=r.map((function(e){return n.forEach((function(r){e=e.replace(new RegExp(\"(\\\\\"+i+r+\"\\\\\"+i+\")\",\"g\"),t[0]+\"$1\"+t[1])})),e}))}));var o=new RegExp(\"\\\\\"+i+\"([0-9]+)\\\\\"+i);return a?r:function t(e,r,n){for(var i,a=[],s=0;i=o.exec(e);){if(s++>1e4)throw Error(\"Circular references in parenthesis\");a.push(e.slice(0,i.index)),a.push(t(r[i[1]],r)),e=e.slice(i.index+i[0].length)}return a.push(e),a}(r[0],r)}function i(t,e){if(e&&e.flat){var r,n=e&&e.escape||\"___\",i=t[0];if(!i)return\"\";for(var a=new RegExp(\"\\\\\"+n+\"([0-9]+)\\\\\"+n),o=0;i!=r;){if(o++>1e4)throw Error(\"Circular references in \"+t);r=i,i=i.replace(a,s)}return i}return t.reduce((function t(e,r){return Array.isArray(r)&&(r=r.reduce(t,\"\")),e+r}),\"\");function s(e,r){if(null==t[r])throw Error(\"Reference \"+r+\"is undefined\");return t[r]}}function a(t,e){return Array.isArray(t)?i(t,e):n(t,e)}a.parse=n,a.stringify=i,e.exports=a},{}],504:[function(t,e,r){\"use strict\";var n=t(\"pick-by-alias\");e.exports=function(t){var e;arguments.length>1&&(t=arguments);\"string\"==typeof t?t=t.split(/\\s/).map(parseFloat):\"number\"==typeof t&&(t=[t]);t.length&&\"number\"==typeof t[0]?e=1===t.length?{width:t[0],height:t[0],x:0,y:0}:2===t.length?{width:t[0],height:t[1],x:0,y:0}:{x:t[0],y:t[1],width:t[2]-t[0]||0,height:t[3]-t[1]||0}:t&&(t=n(t,{left:\"x l left Left\",top:\"y t top Top\",width:\"w width W Width\",height:\"h height W Width\",bottom:\"b bottom Bottom\",right:\"r right Right\"}),e={x:t.left||0,y:t.top||0},null==t.width?t.right?e.width=t.right-e.x:e.width=0:e.width=t.width,null==t.height?t.bottom?e.height=t.bottom-e.y:e.height=0:e.height=t.height);return e}},{\"pick-by-alias\":511}],505:[function(t,e,r){e.exports=function(t){var e=[];return t.replace(i,(function(t,r,i){var o=r.toLowerCase();for(i=function(t){var e=t.match(a);return e?e.map(Number):[]}(i),\"m\"==o&&i.length>2&&(e.push([r].concat(i.splice(0,2))),o=\"l\",r=\"m\"==r?\"l\":\"L\");;){if(i.length==n[o])return i.unshift(r),e.push(i);if(i.length<n[o])throw new Error(\"malformed path data\");e.push([r].concat(i.splice(0,n[o])))}})),e};var n={a:7,c:6,h:1,l:2,m:2,q:4,s:4,t:2,v:1,z:0},i=/([astvzqmhlc])([^astvzqmhlc]*)/gi;var a=/-?[0-9]*\\.?[0-9]+(?:e[-+]?\\d+)?/gi},{}],506:[function(t,e,r){e.exports=function(t,e){e||(e=[0,\"\"]),t=String(t);var r=parseFloat(t,10);return e[0]=r,e[1]=t.match(/[\\d.\\-\\+]*\\s*(.*)/)[1]||\"\",e}},{}],507:[function(t,e,r){(function(t){(function(){\"use strict\";function r(t){if(\"string\"!=typeof t)throw new TypeError(\"Path must be a string. Received \"+JSON.stringify(t))}function n(t,e){for(var r,n=\"\",i=0,a=-1,o=0,s=0;s<=t.length;++s){if(s<t.length)r=t.charCodeAt(s);else{if(47===r)break;r=47}if(47===r){if(a===s-1||1===o);else if(a!==s-1&&2===o){if(n.length<2||2!==i||46!==n.charCodeAt(n.length-1)||46!==n.charCodeAt(n.length-2))if(n.length>2){var l=n.lastIndexOf(\"/\");if(l!==n.length-1){-1===l?(n=\"\",i=0):i=(n=n.slice(0,l)).length-1-n.lastIndexOf(\"/\"),a=s,o=0;continue}}else if(2===n.length||1===n.length){n=\"\",i=0,a=s,o=0;continue}e&&(n.length>0?n+=\"/..\":n=\"..\",i=2)}else n.length>0?n+=\"/\"+t.slice(a+1,s):n=t.slice(a+1,s),i=s-a-1;a=s,o=0}else 46===r&&-1!==o?++o:o=-1}return n}var i={resolve:function(){for(var e,i=\"\",a=!1,o=arguments.length-1;o
"/*\n",
" * @copyright 2016 Sean Connelly (@voidqk), http://syntheti.cc\n",
" * @license MIT\n",
" * @preserve Project Home: https://github.com/voidqk/polybooljs\n",
" */\n",
"var n,i=t(\"./lib/build-log\"),a=t(\"./lib/epsilon\"),o=t(\"./lib/intersecter\"),s=t(\"./lib/segment-chainer\"),l=t(\"./lib/segment-selector\"),c=t(\"./lib/geojson\"),u=!1,f=a();function h(t,e,r){var i=n.segments(t),a=n.segments(e),o=r(n.combine(i,a));return n.polygon(o)}n={buildLog:function(t){return!0===t?u=i():!1===t&&(u=!1),!1!==u&&u.list},epsilon:function(t){return f.epsilon(t)},segments:function(t){var e=o(!0,f,u);return t.regions.forEach(e.addRegion),{segments:e.calculate(t.inverted),inverted:t.inverted}},combine:function(t,e){return{combined:o(!1,f,u).calculate(t.segments,t.inverted,e.segments,e.inverted),inverted1:t.inverted,inverted2:e.inverted}},selectUnion:function(t){return{segments:l.union(t.combined,u),inverted:t.inverted1||t.inverted2}},selectIntersect:function(t){return{segments:l.intersect(t.combined,u),inverted:t.inverted1&&t.inverted2}},selectDifference:function(t){return{segments:l.difference(t.combined,u),inverted:t.inverted1&&!t.inverted2}},selectDifferenceRev:function(t){return{segments:l.differenceRev(t.combined,u),inverted:!t.inverted1&&t.inverted2}},selectXor:function(t){return{segments:l.xor(t.combined,u),inverted:t.inverted1!==t.inverted2}},polygon:function(t){return{regions:s(t.segments,f,u),inverted:t.inverted}},polygonFromGeoJSON:function(t){return c.toPolygon(n,t)},polygonToGeoJSON:function(t){return c.fromPolygon(n,f,t)},union:function(t,e){return h(t,e,n.selectUnion)},intersect:function(t,e){return h(t,e,n.selectIntersect)},difference:function(t,e){return h(t,e,n.selectDifference)},differenceRev:function(t,e){return h(t,e,n.selectDifferenceRev)},xor:function(t,e){return h(t,e,n.selectXor)}},\"object\"==typeof window&&(window.PolyBool=n),e.exports=n},{\"./lib/build-log\":518,\"./lib/epsilon\":519,\"./lib/geojson\":520,\"./lib/intersecter\":521,\"./lib/segment-chainer\":523,\"./lib/segment-selector\":524}],518:[function(t,e,r){e.exports=function(){var t,e=0,r=!1;function n(e,r){return t.list.push({type:e,data:r?JSON.parse(JSON.stringify(r)):void 0}),t}return t={list:[],segmentId:function(){return e++},checkIntersection:function(t,e){return n(\"check\",{seg1:t,seg2:e})},segmentChop:function(t,e){return n(\"div_seg\",{seg:t,pt:e}),n(\"chop\",{seg:t,pt:e})},statusRemove:function(t){return n(\"pop_seg\",{seg:t})},segmentUpdate:function(t){return n(\"seg_update\",{seg:t})},segmentNew:function(t,e){return n(\"new_seg\",{seg:t,primary:e})},segmentRemove:function(t){return n(\"rem_seg\",{seg:t})},tempStatus:function(t,e,r){return n(\"temp_status\",{seg:t,above:e,below:r})},rewind:function(t){return n(\"rewind\",{seg:t})},status:function(t,e,r){return n(\"status\",{seg:t,above:e,below:r})},vert:function(e){return e===r?t:(r=e,n(\"vert\",{x:e}))},log:function(t){return\"string\"!=typeof t&&(t=JSON.stringify(t,!1,\" \")),n(\"log\",{txt:t})},reset:function(){return n(\"reset\")},selected:function(t){return n(\"selected\",{segs:t})},chainStart:function(t){return n(\"chain_start\",{seg:t})},chainRemoveHead:function(t,e){return n(\"chain_rem_head\",{index:t,pt:e})},chainRemoveTail:function(t,e){return n(\"chain_rem_tail\",{index:t,pt:e})},chainNew:function(t,e){return n(\"chain_new\",{pt1:t,pt2:e})},chainMatch:function(t){return n(\"chain_match\",{index:t})},chainClose:function(t){return n(\"chain_close\",{index:t})},chainAddHead:function(t,e){return n(\"chain_add_head\",{index:t,pt:e})},chainAddTail:function(t,e){return n(\"chain_add_tail\",{index:t,pt:e})},chainConnect:function(t,e){return n(\"chain_con\",{index1:t,index2:e})},chainReverse:function(t){return n(\"chain_rev\",{index:t})},chainJoin:function(t,e){return n(\"chain_join\",{index1:t,index2:e})},done:function(){return n(\"done\")}}}},{}],519:[function(t,e,r){e.exports=function(t){\"number\"!=typeof t&&(t=1e-10);var e={epsilon:function(e){return\"number\"==typeof e&&(t=e),t},pointAboveOrOnLine:function(e,r,n){var i=r[0],a=r[1],o=n[0],s=n[1],l=e[0];return(o-i)*(e[1]-a)-(s-a)*(l-i)>=-t},pointBetween:function(e,r,n){var i=e[1]-r[1],a=n[0]-r[0],o=e[0]-r[0],s=n[1]-r[1],l=o*a+i*s;return!(l<t)&&!(l-(a*a+s*s)>-t)},pointsSameX:function(e,r){r
"/*!\n",
" * repeat-string <https://github.com/jonschlinkert/repeat-string>\n",
" *\n",
" * Copyright (c) 2014-2015, Jon Schlinkert.\n",
" * Licensed under the MIT License.\n",
" */\n",
"\"use strict\";var n,i=\"\";e.exports=function(t,e){if(\"string\"!=typeof t)throw new TypeError(\"expected a string\");if(1===e)return t;if(2===e)return t+t;var r=t.length*e;if(n!==t||\"undefined\"==typeof n)n=t,i=\"\";else if(i.length>=r)return i.substr(0,r);for(;r>i.length&&e>1;)1&e&&(i+=t),e>>=1,t+=t;return i=(i+=t).substr(0,r)}},{}],542:[function(t,e,r){(function(t){(function(){e.exports=t.performance&&t.performance.now?function(){return performance.now()}:Date.now||function(){return+new Date}}).call(this)}).call(this,\"undefined\"!=typeof global?global:\"undefined\"!=typeof self?self:\"undefined\"!=typeof window?window:{})},{}],543:[function(t,e,r){\"use strict\";e.exports=function(t){for(var e=t.length,r=t[t.length-1],n=e,i=e-2;i>=0;--i){var a=r,o=t[i];(l=o-((r=a+o)-a))&&(t[--n]=r,r=l)}var s=0;for(i=n;i<e;++i){var l;a=t[i];(l=(o=r)-((r=a+o)-a))&&(t[s++]=l)}return t[s++]=r,t.length=s,t}},{}],544:[function(t,e,r){\"use strict\";var n=t(\"two-product\"),i=t(\"robust-sum\"),a=t(\"robust-scale\"),o=t(\"robust-compress\");function s(t,e){for(var r=new Array(t.length-1),n=1;n<t.length;++n)for(var i=r[n-1]=new Array(t.length-1),a=0,o=0;a<t.length;++a)a!==e&&(i[o++]=t[n][a]);return r}function l(t){for(var e=new Array(t),r=0;r<t;++r){e[r]=new Array(t);for(var n=0;n<t;++n)e[r][n]=[\"m[\",r,\"][\",n,\"]\"].join(\"\")}return e}function c(t){if(2===t.length)return[\"sum(prod(\",t[0][0],\",\",t[1][1],\"),prod(-\",t[0][1],\",\",t[1][0],\"))\"].join(\"\");for(var e=[],r=0;r<t.length;++r)e.push([\"scale(\",c(s(t,r)),\",\",(n=r,1&n?\"-\":\"\"),t[0][r],\")\"].join(\"\"));return function t(e){if(1===e.length)return e[0];if(2===e.length)return[\"sum(\",e[0],\",\",e[1],\")\"].join(\"\");var r=e.length>>1;return[\"sum(\",t(e.slice(0,r)),\",\",t(e.slice(r)),\")\"].join(\"\")}(e);var n}function u(t){return new Function(\"sum\",\"scale\",\"prod\",\"compress\",[\"function robustDeterminant\",t,\"(m){return compress(\",c(l(t)),\")};return robustDeterminant\",t].join(\"\"))(i,a,n,o)}var f=[function(){return[0]},function(t){return[t[0][0]]}];!function(){for(;f.length<6;)f.push(u(f.length));for(var t=[],r=[\"function robustDeterminant(m){switch(m.length){\"],n=0;n<6;++n)t.push(\"det\"+n),r.push(\"case \",n,\":return det\",n,\"(m);\");r.push(\"}var det=CACHE[m.length];if(!det)det=CACHE[m.length]=gen(m.length);return det(m);}return robustDeterminant\"),t.push(\"CACHE\",\"gen\",r.join(\"\"));var i=Function.apply(void 0,t);for(e.exports=i.apply(void 0,f.concat([f,u])),n=0;n<f.length;++n)e.exports[n]=f[n]}()},{\"robust-compress\":543,\"robust-scale\":550,\"robust-sum\":553,\"two-product\":582}],545:[function(t,e,r){\"use strict\";var n=t(\"two-product\"),i=t(\"robust-sum\");e.exports=function(t,e){for(var r=n(t[0],e[0]),a=1;a<t.length;++a)r=i(r,n(t[a],e[a]));return r}},{\"robust-sum\":553,\"two-product\":582}],546:[function(t,e,r){\"use strict\";var n=t(\"two-product\"),i=t(\"robust-sum\"),a=t(\"robust-subtract\"),o=t(\"robust-scale\");function s(t,e){for(var r=new Array(t.length-1),n=1;n<t.length;++n)for(var i=r[n-1]=new Array(t.length-1),a=0,o=0;a<t.length;++a)a!==e&&(i[o++]=t[n][a]);return r}function l(t){if(1===t.length)return t[0];if(2===t.length)return[\"sum(\",t[0],\",\",t[1],\")\"].join(\"\");var e=t.length>>1;return[\"sum(\",l(t.slice(0,e)),\",\",l(t.slice(e)),\")\"].join(\"\")}function c(t,e){if(\"m\"===t.charAt(0)){if(\"w\"===e.charAt(0)){var r=t.split(\"[\");return[\"w\",e.substr(1),\"m\",r[0].substr(1)].join(\"\")}return[\"prod(\",t,\",\",e,\")\"].join(\"\")}return c(e,t)}function u(t){if(2===t.length)return[[\"diff(\",c(t[0][0],t[1][1]),\",\",c(t[1][0],t[0][1]),\")\"].join(\"\")];for(var e=[],r=0;r<t.length;++r)e.push([\"scale(\",l(u(s(t,r))),\",\",(n=r,!0&n?\"-\":\"\"),t[0][r],\")\"].join(\"\"));return e;var n}function f(t,e){for(var r=[],n=0;n<e-2;++n)r.push([\"prod(m\",t,\"[\",n,\"],m\",t,\"[\",n,\"])\"].join(\"\"));return l(r)}function h(t){for(var e=[],r=[],c=function(t){for(var e=new Array(t),r=0;r<t;++r){e[r]=new Array(t);for(var n=0;n<t;++n)e[r][n]=[\"m\",n,\"[\",t-r-2,\"]\"].join(\"\")}return e}(t),h=0;h<t;++h)c[0][h]=\
" });\n",
" require(['plotly'], function(Plotly) {\n",
" window._Plotly = Plotly;\n",
" });\n",
" }\n",
" </script>\n",
" "
]
},
"metadata": {},
"output_type": "display_data"
},
2021-07-02 17:49:38 +02:00
{
"data": {
"application/vnd.plotly.v1+json": {
"config": {
2021-07-06 15:23:24 +02:00
"plotlyServerURL": "https://plot.ly"
2021-07-02 17:49:38 +02:00
},
"data": [
{
2021-07-06 15:23:24 +02:00
"name": "FAIRsharing",
"type": "bar",
"x": [
"Life Science",
"Biomedical Science",
"Earth Science",
"Genomics",
"Environmental Science",
"Oceanography",
"Biodiversity",
"Atmospheric Science",
"Epidemiology",
"Genetics",
"Health Science",
"Virology",
"Biology",
"Proteomics",
"Bioinformatics",
"Agriculture",
"Geology",
"Preclinical Studies",
"Transcriptomics",
"Chemistry",
"Comparative Genomics",
"Data Management",
"Clinical Studies",
"Botany",
"Functional Genomics",
"Medicine",
"Geophysics",
"Meteorology",
"Humanities and Social Sciences",
"Natural Science",
"Social Science",
"Systems Biology",
"Geography",
"Ecology",
"Data Submission",
" Annotation and Curation",
"Metabolomics",
"Engineering Science",
"Marine Biology",
"Physics",
"Economics",
"Hydrology",
"Ontology and Terminology",
"Biochemistry",
"Astrophysics and Astronomy",
"Phylogenetics",
"Molecular biology",
"Epigenetics",
"Medical Virology",
"Remote Sensing",
"Infectious Disease Medicine",
"Immunology",
"Humanities",
"Anatomy",
"Computational Biology",
"Structural Biology",
"Neurobiology",
"Plant Genetics",
"Computer Science",
"Public Health",
"Knowledge and Information Systems",
"Microbiology",
"Demographics",
"Social and Behavioural Science",
"Data Visualization",
"Oncology",
"Developmental Biology",
"Critical Care Medicine",
"Hydrogeology",
"Data Integration",
"Glycomics",
"Ecosystem Science",
"Soil Science",
"Geochemistry",
"Population Genetics",
"Drug Discovery",
"Materials Science",
"Water Research",
"Neuroscience",
"Forest Management",
"Plant Breeding",
"Metagenomics",
"Energy Engineering",
"Water Management",
"Paleontology",
"Software Engineering",
"Geodesy",
"Taxonomy",
"Cell Biology",
"Phylogenomics",
"Immunogenetics",
"Pharmacology",
"Mineralogy",
"Freshwater Science",
"Medical Informatics",
"Statistics",
"Epigenomics",
"Human Genetics",
"Phylogeny",
"Global Health",
"Animal Genetics",
"Cheminformatics",
"Evolutionary Biology",
"Zoology",
"Mathematics",
"Microbial Ecology",
"Population Dynamics",
"Political Science",
"Nanotechnology",
"Psychology",
"Physical Geography",
"Education Science",
"Drug Development",
"Culture",
"Translational Medicine",
"Pathology",
"Food Security",
"Informatics",
"Neurophysiology",
"Natural History",
"Phenomics",
"Nutritional Science",
"Computational Neuroscience",
"Biotechnology",
"Bioengineering",
"Geoinformatics",
"Data Governance",
"Cartography",
"History",
"Analytical Chemistry",
"Organic Chemistry",
"Urban Planning",
"Plant Anatomy",
"Enzymology",
"Classical Archaeology",
"Animal Husbandry",
"Maritime Engineering",
"Materials Engineering",
"Database Management",
"Cardiology",
"Anthropology",
"Architecture",
"Transportation Planning",
"Criminology",
"Primary Health Care",
"Molecular Genetics",
"Toxicology",
"Omics",
"Communication Science",
"Agronomy",
"Physiology",
"Art",
"Endocrinology",
"Fisheries Science",
"Economic and Social History",
"Drug Metabolism",
"Thermodynamics",
"Plant Ecology",
"Tropical Medicine",
"Aerospace Engineering",
"Data Quality",
"Chemical Engineering",
"Data Mining",
"Health Services Research",
"Linguistics",
"Medicinal Chemistry",
"Agricultural Engineering",
"Geriatric Medicine",
"Toxicogenomics",
"Drug Repositioning",
"Reproductive Health",
"Materials Informatics",
"Construction Engineering",
"Entomology",
"Aquaculture",
"Pediatrics",
"Agroecology",
"Civil Engineering",
"Inorganic Molecular Chemistry",
"Business Administration",
"Respiratory Medicine",
"Embryology",
"Molecular Microbiology",
"Power Engineering",
"Composite Materials",
"Molecular Infection Biology",
"Computational Chemistry",
"Synthetic Chemistry",
"Synthetic Biology",
"Building Engineering Physics",
"Farming Systems Research",
"Biomaterials",
"Pharmacy",
"Veterinary Medicine",
"Gastroenterology",
"Structural Genomics",
"Pharmacogenomics",
"Occupational Medicine",
"Community Care",
"Molecular Dynamics",
"Fine Arts",
"Ancient Cultures",
"Human Geography",
"Molecular Chemistry",
"Quantitative Genetics",
" Learning and Training",
"Human Biology",
"Rural and Agricultural Sociology",
"Social Policy",
"Social Psychology",
"Industrial Engineering",
"Jurisprudence",
"Research on Teaching",
"Limnology",
"Agricultural Economics",
"Historical Linguistics",
"Data Security",
"Prehistory",
"Geotechnics",
"Cultural Studies",
"Public Finance",
"Art History",
"Proteogenomics",
"Digital Image Processing",
"Surgery",
"Plant Cell Biology",
" Optical and Plasma Physics",
"Safety Science",
"Traditional Medicine",
" Molecular",
"Process Engineering",
"Rheumatology",
"Telecommunication Engineering",
"Plastics Engineering",
"Acoustics",
"Plant Cultivation",
"Religious Studies",
"Policy",
"Systemic Neuroscience",
"Agricultural Law",
"Technical Chemistry",
"Public Law",
"Radiology",
"Synthesis Chemistry",
"Chemical Biology",
"Physical Chemistry",
"Horticulture",
"Hematology",
"Gynecology",
"Artificial Intelligence",
"Atomic",
"Behavioural Biology",
"Biological Process Engineering",
"Functional Materials Research",
"Biological Psychology",
"Food Process Engineering",
"Biomimetic Chemistry",
"Biophysics",
"Empirical Social Research",
"Electrophysiology",
"Electrical Engineering",
"Biotherapeutics",
"Economic Theory",
"Economic Policy",
"Building Design",
"Developmental Neurobiology",
"Dermatology",
"Criminal Law",
"Component Engineering",
"Comparative Neurobiology",
"Cognitive Neuroscience",
"Clinical Veterinary Medicine",
"Clinical Psychology",
"Clinical Chemistry",
"Classical Philology",
"Cellular Neuroscience",
"History of Science",
"Human-Machine Systems Engineering",
"Photogrammetry",
"Hydraulic Engineering",
"Philosophy",
"Personalized Medicine",
"Parasitology",
"Organic Molecular Chemistry",
"Ophthalmology",
"Obstetrics",
"Neurology",
"Musculoskeletal Medicine",
"Animal Breeding",
"Molecular Physical Chemistry",
"Molecular Neuroscience",
"Microstructural Mechanical Properties of Materials",
"Microbial Physiology",
"Microbial Genetics",
"Metal-Cutting Manufacturing Engineering",
"Medicines Research and Development",
"Animal Physiology",
"Medical Physics",
"Media Studies",
"Mechanics",
"Mechanical Process Engineering",
"Mechanical Engineering",
"Materials Structuring and Functionalisation",
"Applied Linguistics",
"Logistics Engineering",
"Literary Studies",
"Applied Mathematics",
"Landscape Planning",
"Applied Microbiology",
"Mechanical Behaviour of Construction Materials"
],
"y": [
900,
252,
227,
166,
134,
95,
80,
78,
75,
73,
67,
66,
65,
61,
60,
58,
51,
48,
48,
46,
46,
45,
45,
44,
42,
42,
41,
40,
39,
38,
36,
35,
33,
32,
31,
31,
30,
29,
27,
26,
26,
25,
25,
25,
25,
20,
18,
18,
18,
18,
18,
18,
18,
18,
17,
17,
17,
17,
17,
16,
16,
16,
16,
16,
15,
15,
15,
15,
14,
14,
14,
14,
14,
14,
13,
13,
13,
13,
13,
13,
13,
12,
12,
12,
12,
11,
11,
11,
11,
11,
11,
10,
10,
10,
9,
9,
9,
8,
8,
8,
8,
8,
8,
7,
7,
7,
7,
7,
7,
7,
7,
7,
7,
7,
7,
6,
6,
6,
6,
6,
6,
6,
6,
6,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
]
},
{
"name": "re3data",
"type": "bar",
"visible": "legendonly",
"x": [
"Life Sciences",
"Natural Sciences",
"Humanities",
"Social Sciences",
"Medicine",
"Biology",
"Geosciences (including Geography)",
"Oceanography",
"Atmospheric Science",
"Basic Biological",
"Medical Research",
"Engineering Sciences",
"Social",
"Behavioural Sciences",
"Geodesy",
"Geophysics",
" Horticulture",
" Forestry",
"Agriculture",
"Veterinary Medicine",
"Physics",
"Zoology",
"Immunology",
"Computer Science",
"Chemistry",
"General Genetics",
"Microbiology",
" Virology",
"Plant Sciences",
"Astronomy",
"Astrophysics",
"Economics",
"Bioinformatics",
"Theoretical Biology",
"Geography",
"Water Research",
"System Engineering",
" Electrical",
" Health Services Research",
"Public Health",
" Social Medicine",
"Human Genetics",
"Geochemistry",
"Crystallography",
" Mineralogy",
"Developmental Biology",
"Empirical Social Research",
"Architecture",
"Linguistics",
" Geoinformatics",
" Remote Sensing",
" Cartogaphy",
" Photogrammetry",
"Palaeontology",
"Geology",
" Quantum Optics",
"History",
"Optics",
" Molecules",
"Animal Genetics",
" Cell",
"Construction Engineering",
"Cell Biology",
"Neurosciences",
"Ecosystem Research",
" Biodiversity",
"Biochemistry",
"Animal Ecology",
"Media Studies",
"Physics of Atoms",
"Plasmas",
" Music",
"Fine Arts",
" Theatre",
"Plant Ecology",
"Ecosystem Analysis",
"Plant Genetics",
"Ancient Cultures",
"Materials Science",
"Cultural Anthropology",
"Particles",
" Nuclei",
"Fields",
"Economic",
"Statistics",
"Econometrics",
"Education Sciences",
"Epidemiology",
" Medical Informatics",
" Medical Biometry",
"Political Science",
"Religious Studies",
"Jurisprudence",
"Social Policy",
" Hydrology",
" Integrated Water Resources Management",
"Hydrogeology",
" Urban Water Management",
" Limnology",
" Water Chemistry",
"Structural Biology",
" Social",
" Jewish Studies",
"Cultures",
"Non-European Languages",
"Molecular Chemistry",
"Mathematics",
"Engineering",
"Psychology",
"Evolution",
" Biochemistry",
"Genetics of Microorganisms",
"Metabolism",
"Soil Sciences",
"Theoretical Chemistry",
"Physical",
"Ecology of Agricultural Landscapes",
"Analytical Chemistry",
" Method Development (Chemistry)",
"Condensed Matter Physics",
"Pharmacology",
"Systems Engineering",
"Human Geography",
"Literary Studies",
"Liquids - Spectroscopy",
" Interfaces",
"Food Chemistry",
"Biophysics",
"Basic Forest Research",
" Kinetics",
"Physical Chemistry of Molecules",
" Image",
"Language Processing",
"Surface Research",
"Artificial Intelligence",
"Chemical Solid State",
"Physical Geography",
" Atoms",
"Biological Chemistry",
" Anthropology",
" Plasmas",
"Ethnology/Folklore",
"Art History",
"Thermal Engineering/Process Engineering",
"Sociology",
"Agricultural Economics",
"Theology",
"Virology",
"Cognitive Neuroscience",
"Urbanism",
" Transportation",
"Infrastructure Planning",
"Neuroimaging",
"Musicology",
" Landscape Planning",
" Spatial Planning",
"Modern",
" Transfusion Medicine",
" Oncology",
"Medical Physics",
"Plant Systematics",
"Current History",
"Hematology",
"Biomedical Technology",
" Building",
"Medical Microbiology",
" Building Design",
" Sustainable Building Technology",
"Construction History",
" Molecular Infection Biology",
"Morphology",
"Traffic",
"Electrical Engineering",
"Systematics",
"Transport Systems",
" Logistics",
"Communication Science",
"Anatomy",
"Pharmacy",
"Use of Forest Resources",
"Classical Archaeology",
"Business Administration",
"Inventory Control",
"Public Finance",
"Occupational Medicine",
"Toxicology",
"Social History",
"Physiology",
"Plant Biochemistry",
"Training",
"Plant Breeding",
"Mechanical",
"History of Science",
"Pediatric",
"Research on Teaching",
"Process Engineering",
"industrial Engineering",
" Learning",
" Technical Chemistry",
"Adolescent Medicine",
"Heat Energy Technology",
" Legal History",
" Legal Theory",
"Plant Cultivation",
"Radiology",
" Fluid Mechanics",
" Thermal Machines",
"Legal",
"Political Philosophy",
"Nuclear Medicine",
"Systemic Neuroscience",
"Microbial Ecology",
"Animal Physiology",
"Applied Microbiology",
" Behaviour",
" Computational Neuroscience",
"Jewish Studies",
"Materials Engineering",
"Organic Molecular Chemistry",
"General",
"Research on Socialization",
"Professions",
"Public Law",
"Educational Institutions",
"Software Technology",
"Typology",
"Basic Veterinary Medical Science",
"Medieval History",
"Early Modern History",
"Surfaces",
" Material Characterisation",
"Philosophy",
"Forensic Medicine",
" Historical Linguistics",
" Non-European Languages",
"Physical Chemistry of Solids",
"Pathology",
" Soft Matter",
"Modelling",
" Metabolism",
" Biological Physics",
"Theory",
"Ancient History",
"Ancient Near Eastern Studies",
"Molecular Neuroscience",
"Agricultural",
"Neurogenetics",
" Nonlinear Dynamics",
"Prehistory",
"Statistical Physics",
"Egyptology",
"Criminology",
"Inorganic Molecular Chemistry",
"Gastroenterology",
"Food Process Engineering",
"Obstetrics",
"Constructive Mechanical Engineering",
"Acoustics",
"Human Factors",
"Gynaecology",
"Oceania Studies",
"Electrical Energy Generation",
" Distribution",
" Ergonomics",
"Sensory",
" Material Synthesis",
"Mechanics",
"Plant Cell",
"Solid State",
" Human-Machine Systems",
"Biological",
"Biomimetic Chemistry",
" American",
"Surface Chemistry",
" Application",
"African",
"Behavioural Biology",
"Therapy",
" Methodology",
" Medical Psychology",
" Semitic Studies",
"Plant Nutrition",
"Radiobiology",
"Clinical Veterinary Medicine",
"Operating",
"Polymer Research",
"General Theoretical Chemistry",
" Communication",
"Islamic Studies",
"Nutritional Sciences",
" Breeding",
"Radiation Oncology",
" Clinical Psychology",
"Endocrinology",
"Theatre",
"Differential Psychology",
"Applied Linguistics",
" Arabian Studies",
" Diagnostics",
"Hygiene",
"Animal Husbandry",
"Information Systems",
"Basic Research on Pathogenesis",
"Individual Linguistics",
" Diabetology",
"History of Education",
"European",
"Developmental",
"Asian Studies",
"Plant Physiology",
"Energy Process Engineering",
"Experimental Condensed Matter Physics",
" High-Frequency",
"General Education",
" Industrial",
"Protestant Theology",
"Network Technology",
"Communication",
" Theoretical Electrical Engineering",
"American Literature",
" Hydraulic Engineering",
"Clinical Neurosciences III - Ophthalmology",
"Geotechnics",
"Social Psychology",
"Pathobiochemistry",
"Geriatric Medicine",
"Educational Psychology",
"Organisational Psychology",
"Clinical Chemistry",
"Sociological Theory",
"Gerontology",
"Rheumatology",
" Allergology",
"Dentistry",
" Construction Operation",
"Dermatology",
" Geosciences (including Geography)",
"Sructural Engineering",
" Control Systems",
"Sintered Metallic",
" Clinical Immunology",
"Roman Catholic Theology",
"Reproductive Medicine/Biology",
" Clinical Infectiology Intensive Care Medicine",
" Building Informatics",
"Geosciences (including Geography) ",
" Atmospheric Science",
"Automation",
"Veterinary Medicine ",
"Mathematical Psychology",
"Biological Process Engineering",
" Biological",
"Preparatory",
"Thermodynamics",
" Angiology",
" Robotics",
" Oral Surgery",
"Comparative Literature",
"Atmospheric Science ",
"Biomaterials",
"Law of Criminal Procedure",
"Physical Chemistry of Polymers",
"Kinetics of Materials",
"Cardiology",
" Mechatronics",
"Criminal Law",
"Cultural Studies",
"Pneumology",
"Polymer Materials",
"Ceramic Materials",
"Technical Thermodynamics",
"Theoretical Condensed Matter Physics",
"Urology",
"Electronic Semiconductors",
" Circuits",
"Traumatology",
" Chemistry",
"Theoretical Computer Science",
"Technical Chemistry",
"Thermal Process Engineering",
" Building Physics",
"Theoretical Physics of Polymers",
"Thermal Processes",
"Inter-organismic Interactions of Plants",
"Economic Theory",
" Thermomechanical Treatment of Materials",
"Cellular Neuroscience",
"Life Sciences ",
"Biological Psychiatry",
"Measurement Systems",
"Medical Research ",
"Medieval German Literature",
"Chemical",
"Metallurgical",
"Classical Philology",
"Microstructural Mechanical Properties of Materials",
"Clinical Neurosciences I - Neurology",
"History of Philosophy",
"Orthopaedics",
" Components",
" Systems",
"Comparative Neurobiology",
"Composite Materials",
" Neurosurgery",
"Construction Material Sciences",
" Life Sciences ",
"Cardiothoracic Surgery",
"Private Law",
" General Genetics",
"Experimental",
"Social Sciences ",
"Developmental Neurobiology",
" Agriculture"
],
"y": [
1440,
1325,
1238,
1222,
1014,
882,
760,
581,
535,
514,
513,
496,
451,
432,
360,
326,
317,
317,
316,
315,
308,
239,
234,
227,
224,
220,
212,
212,
210,
205,
205,
204,
175,
175,
159,
143,
142,
142,
131,
131,
131,
117,
108,
108,
108,
104,
103,
101,
101,
99,
99,
99,
99,
98,
98,
96,
96,
96,
96,
94,
94,
86,
85,
81,
79,
79,
79,
79,
78,
75,
75,
74,
74,
74,
67,
67,
65,
65,
64,
63,
63,
63,
63,
62,
62,
62,
61,
57,
57,
57,
56,
52,
50,
50,
48,
48,
48,
48,
48,
48,
45,
44,
44,
44,
44,
42,
41,
40,
38,
37,
36,
36,
36,
34,
33,
33,
31,
27,
27,
26,
25,
25,
24,
24,
23,
23,
23,
23,
23,
23,
23,
22,
22,
22,
22,
22,
22,
21,
21,
21,
21,
19,
19,
18,
18,
18,
18,
17,
17,
17,
17,
17,
17,
17,
17,
17,
16,
16,
16,
16,
16,
16,
16,
16,
15,
15,
15,
15,
15,
15,
14,
14,
14,
14,
14,
14,
14,
13,
13,
13,
13,
13,
13,
13,
12,
12,
12,
11,
11,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
8,
8,
8,
8,
8,
8,
8,
8,
8,
7,
7,
7,
7,
7,
7,
7,
7,
7,
7,
7,
7,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
5,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
]
},
{
"name": "OpenDOAR",
2021-07-02 17:49:38 +02:00
"type": "bar",
2021-07-06 15:23:24 +02:00
"visible": "legendonly",
2021-07-02 17:49:38 +02:00
"x": [
"Multidisciplinary",
"Medicine",
"Health",
"Science General",
"Technology General",
"Economics",
"Business",
"Archaeology",
"Social Sciences General",
"History",
"Politics",
"Environment",
"Ecology",
"Law",
"Computers",
"IT",
"Biology",
"Biochemistry",
"Information Science",
"Library",
"Humanities General",
"Arts",
"Education",
" Food",
"Agriculture",
"Statistics",
"Mathematics",
"Literature",
"Veterinary",
"Astronomy",
"Physics",
"Geography",
"Regional Studies",
"Language",
"Religion",
"Chemical Technology",
"Chemistry",
"Philosophy",
"Fine",
"Performing Arts",
"Planning",
"Psychology",
"Management",
"Planetary Sciences",
"Earth",
"Electrical",
"Electronic Engineering",
"Architecture",
"Civil Engineering",
"Mechanical Engineering",
"Materials",
" History",
" Philosophy",
" Health",
"Social Sciences General ",
" Language",
" Technology General",
" Law",
"Performing Arts ",
" Science General",
"Medicine ",
"IT ",
"Veterinary "
],
"y": [
466,
67,
66,
63,
53,
52,
52,
49,
48,
47,
44,
44,
44,
43,
43,
42,
40,
40,
36,
36,
35,
35,
32,
31,
31,
30,
30,
30,
30,
29,
29,
29,
29,
29,
27,
27,
27,
25,
23,
22,
17,
17,
17,
16,
16,
12,
12,
12,
8,
7,
7,
2,
2,
2,
1,
1,
1,
1,
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": {
2021-07-06 15:23:24 +02:00
"text": "Subject coverage"
2021-07-02 17:49:38 +02:00
},
"xaxis": {
"tickangle": 45,
"tickfont": {
"size": 12
}
}
}
},
"text/html": [
2021-07-22 11:03:05 +02:00
"<div> <div id=\"8693b447-5fa7-4c61-bc6e-d879529e0d70\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div> <script type=\"text/javascript\"> require([\"plotly\"], function(Plotly) { window.PLOTLYENV=window.PLOTLYENV || {}; if (document.getElementById(\"8693b447-5fa7-4c61-bc6e-d879529e0d70\")) { Plotly.newPlot( \"8693b447-5fa7-4c61-bc6e-d879529e0d70\", [{\"name\": \"FAIRsharing\", \"type\": \"bar\", \"x\": [\"Life Science\", \"Biomedical Science\", \"Earth Science\", \"Genomics\", \"Environmental Science\", \"Oceanography\", \"Biodiversity\", \"Atmospheric Science\", \"Epidemiology\", \"Genetics\", \"Health Science\", \"Virology\", \"Biology\", \"Proteomics\", \"Bioinformatics\", \"Agriculture\", \"Geology\", \"Preclinical Studies\", \"Transcriptomics\", \"Chemistry\", \"Comparative Genomics\", \"Data Management\", \"Clinical Studies\", \"Botany\", \"Functional Genomics\", \"Medicine\", \"Geophysics\", \"Meteorology\", \"Humanities and Social Sciences\", \"Natural Science\", \"Social Science\", \"Systems Biology\", \"Geography\", \"Ecology\", \"Data Submission\", \" Annotation and Curation\", \"Metabolomics\", \"Engineering Science\", \"Marine Biology\", \"Physics\", \"Economics\", \"Hydrology\", \"Ontology and Terminology\", \"Biochemistry\", \"Astrophysics and Astronomy\", \"Phylogenetics\", \"Molecular biology\", \"Epigenetics\", \"Medical Virology\", \"Remote Sensing\", \"Infectious Disease Medicine\", \"Immunology\", \"Humanities\", \"Anatomy\", \"Computational Biology\", \"Structural Biology\", \"Neurobiology\", \"Plant Genetics\", \"Computer Science\", \"Public Health\", \"Knowledge and Information Systems\", \"Microbiology\", \"Demographics\", \"Social and Behavioural Science\", \"Data Visualization\", \"Oncology\", \"Developmental Biology\", \"Critical Care Medicine\", \"Hydrogeology\", \"Data Integration\", \"Glycomics\", \"Ecosystem Science\", \"Soil Science\", \"Geochemistry\", \"Population Genetics\", \"Drug Discovery\", \"Materials Science\", \"Water Research\", \"Neuroscience\", \"Forest Management\", \"Plant Breeding\", \"Metagenomics\", \"Energy Engineering\", \"Water Management\", \"Paleontology\", \"Software Engineering\", \"Geodesy\", \"Taxonomy\", \"Cell Biology\", \"Phylogenomics\", \"Immunogenetics\", \"Pharmacology\", \"Mineralogy\", \"Freshwater Science\", \"Medical Informatics\", \"Statistics\", \"Epigenomics\", \"Human Genetics\", \"Phylogeny\", \"Global Health\", \"Animal Genetics\", \"Cheminformatics\", \"Evolutionary Biology\", \"Zoology\", \"Mathematics\", \"Microbial Ecology\", \"Population Dynamics\", \"Political Science\", \"Nanotechnology\", \"Psychology\", \"Physical Geography\", \"Education Science\", \"Drug Development\", \"Culture\", \"Translational Medicine\", \"Pathology\", \"Food Security\", \"Informatics\", \"Neurophysiology\", \"Natural History\", \"Phenomics\", \"Nutritional Science\", \"Computational Neuroscience\", \"Biotechnology\", \"Bioengineering\", \"Geoinformatics\", \"Data Governance\", \"Cartography\", \"History\", \"Analytical Chemistry\", \"Organic Chemistry\", \"Urban Planning\", \"Plant Anatomy\", \"Enzymology\", \"Classical Archaeology\", \"Animal Husbandry\", \"Maritime Engineering\", \"Materials Engineering\", \"Database Management\", \"Cardiology\", \"Anthropology\", \"Architecture\", \"Transportation Planning\", \"Criminology\", \"Primary Health Care\", \"Molecular Genetics\", \"Toxicology\", \"Omics\", \"Communication Science\", \"Agronomy\", \"Physiology\", \"Art\", \"Endocrinology\", \"Fisheries Science\", \"Economic and Social History\", \"Drug Metabolism\", \"Thermodynamics\", \"Plant Ecology\", \"Tropical Medicine\", \"Aerospace Engineering\", \"Data Quality\", \"Chemical Engineering\", \"Data Mining\", \"Health Services Research\", \"Linguistics\", \"Medicinal Chemistry\", \"Agricultural Engineering\", \"Geriatric Medicine\", \"Toxicogenomics\", \"Drug Repo
2021-07-02 17:49:38 +02:00
" \n",
2021-07-22 11:03:05 +02:00
"var gd = document.getElementById('8693b447-5fa7-4c61-bc6e-d879529e0d70');\n",
2021-07-02 17:49:38 +02:00
"var x = new MutationObserver(function (mutations, observer) {{\n",
" var display = window.getComputedStyle(gd).display;\n",
" if (!display || display === 'none') {{\n",
" console.log([gd, 'removed!']);\n",
" Plotly.purge(gd);\n",
" observer.disconnect();\n",
" }}\n",
"}});\n",
"\n",
"// Listen for the removal of the full notebook cells\n",
"var notebookContainer = gd.closest('#notebook-container');\n",
"if (notebookContainer) {{\n",
" x.observe(notebookContainer, {childList: true});\n",
"}}\n",
"\n",
"// Listen for the clearing of the current output cell\n",
"var outputEl = gd.closest('.output');\n",
"if (outputEl) {{\n",
" x.observe(outputEl, {childList: true});\n",
"}}\n",
"\n",
" }) }; }); </script> </div>"
]
},
"metadata": {},
2021-07-06 15:23:24 +02:00
"output_type": "display_data"
}
],
"source": [
"data1 = fairsharing_subjects.groupby('subjects')[['url']].count().sort_values('url', ascending=False)\n",
"data2 = re3data_subjects.groupby('subjects')[['url']].count().sort_values('url', ascending=False)\n",
"data3 = opendoar_subjects.groupby('subjects')[['url']].count().sort_values('url', ascending=False)\n",
"\n",
"plot = [\n",
" go.Bar(\n",
" x=data1.index,\n",
" y=data1['url'],\n",
" name='FAIRsharing'\n",
" ),\n",
" go.Bar(\n",
" x=data2.index,\n",
" y=data2['url'],\n",
" name='re3data',\n",
" visible = 'legendonly'\n",
" ),\n",
" go.Bar(\n",
" x=data3.index,\n",
" y=data3['url'],\n",
" name='OpenDOAR',\n",
" visible = 'legendonly'\n",
" )\n",
"]\n",
"\n",
"layout = go.Layout(\n",
" title='Subject coverage',\n",
" xaxis=dict(tickangle=45, tickfont=dict(size=12))\n",
")\n",
"\n",
"fig = go.Figure(plot, layout).show()"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 23,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"311"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 23,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(fairsharing_subjects.subjects.unique())"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 24,
2021-07-06 15:23:24 +02:00
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"414"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 24,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(re3data_subjects.subjects.unique())"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 25,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"64"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 25,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(opendoar_subjects.subjects.unique())"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 26,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([nan, 'Social Sciences General', 'Science General', 'Computers',\n",
" 'IT', 'Physics', 'Astronomy', 'Multidisciplinary', 'Arts',\n",
" 'Humanities General', 'Philosophy', 'Religion', 'Business',\n",
" 'Economics', 'Law', 'Politics', 'Psychology', 'Health', 'Medicine',\n",
" 'History', 'Archaeology', 'Education', 'Technology General',\n",
" 'Library', 'Information Science', 'Earth', 'Planetary Sciences',\n",
" 'Geography', 'Regional Studies', 'Architecture', 'Ecology',\n",
" 'Environment', 'Electrical', 'Electronic Engineering', 'Biology',\n",
" 'Biochemistry', 'Mathematics', 'Statistics', 'Civil Engineering',\n",
" 'Agriculture', ' Food', 'Veterinary', 'Language', 'Literature',\n",
" 'Chemistry', 'Chemical Technology', 'Mechanical Engineering',\n",
" 'Materials', 'Fine', 'Performing Arts', 'Management', 'Planning',\n",
" ' Language', ' Health', 'Veterinary ', ' Technology General',\n",
" 'Medicine ', ' History', 'IT ', ' Law', 'Social Sciences General ',\n",
" ' Science General', ' Philosophy', 'Performing Arts '],\n",
" dtype=object)"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 26,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"opendoar_subjects.subjects.unique()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Geographic analysis"
]
},
2021-07-22 11:03:05 +02:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**FAIRsharing**"
]
},
2021-07-06 15:23:24 +02:00
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 2,
2021-07-06 15:23:24 +02:00
"metadata": {},
2021-07-22 11:03:05 +02:00
"outputs": [
{
"ename": "NameError",
"evalue": "name 'fairsharing_df' 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<ipython-input-2-cc1be8e03668>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mfairsharing_countries\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfairsharing_df\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexplode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'countries'\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 2\u001b[0m \u001b[0mfairsharing_countries\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'countrycode'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfairsharing_countries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcountries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mc\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mcountry_to_countrycode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mc\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 3\u001b[0m \u001b[0mfairsharing_countries\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'continent'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfairsharing_countries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcountrycode\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mcc\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mcountrycode_to_continent\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcc\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;31mNameError\u001b[0m: name 'fairsharing_df' is not defined"
]
}
],
2021-07-06 15:23:24 +02:00
"source": [
"fairsharing_countries = fairsharing_df.explode('countries')\n",
"fairsharing_countries['countrycode'] = fairsharing_countries.countries.map(lambda c: country_to_countrycode(c))\n",
"fairsharing_countries['continent'] = fairsharing_countries.countrycode.map(lambda cc: countrycode_to_continent(cc))"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 3,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
2021-07-22 11:03:05 +02:00
"ename": "NameError",
"evalue": "name 'fairsharing_countries' 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<ipython-input-3-19e7f1ee3008>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mfairsharing_countries\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mfairsharing_countries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcountrycode\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcountries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munique\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 'fairsharing_countries' is not defined"
]
2021-07-06 15:23:24 +02:00
}
],
"source": [
"fairsharing_countries[fairsharing_countries.countrycode.isna()].countries.unique()"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 29,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['European Union', 'Republic of Ireland', 'Worldwide', 'Antarctica',\n",
" nan], dtype=object)"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 29,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fairsharing_countries[fairsharing_countries.continent.isna()].countries.unique()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Manually fixing exceptions"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 30,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [],
"source": [
"fairsharing_countries.loc[fairsharing_countries.countries == 'Republic of Ireland', ['countries', 'countrycode', 'continent']] = ['Ireland', 'IE', 'EU']\n",
"fairsharing_countries.loc[fairsharing_countries.countries == 'Antarctica', ['countrycode', 'continent']] = ['AQ', np.nan]\n",
"fairsharing_countries.loc[fairsharing_countries.countries == 'European Union', ['countrycode', 'continent']] = ['EU', 'EU']"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 31,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>full_name</th>\n",
" <th>short_name</th>\n",
" <th>fs_url</th>\n",
" <th>url</th>\n",
" <th>countries</th>\n",
" <th>subjects</th>\n",
" <th>countrycode</th>\n",
" <th>continent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>915</th>\n",
" <td>Antabif IPT - AntOBIS IPT - GBIF Belgium</td>\n",
" <td>Antabif IPT - AntOBIS IPT - GBIF Belgium</td>\n",
" <td>https://fairsharing.org/10.25504/FAIRsharing.e...</td>\n",
" <td>http://ipt.biodiversity.aq/</td>\n",
" <td>Antarctica</td>\n",
" <td>[Biodiversity, Life Science]</td>\n",
" <td>AQ</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" full_name \\\n",
"915 Antabif IPT - AntOBIS IPT - GBIF Belgium \n",
"\n",
" short_name \\\n",
"915 Antabif IPT - AntOBIS IPT - GBIF Belgium \n",
"\n",
" fs_url \\\n",
"915 https://fairsharing.org/10.25504/FAIRsharing.e... \n",
"\n",
" url countries subjects \\\n",
"915 http://ipt.biodiversity.aq/ Antarctica [Biodiversity, Life Science] \n",
"\n",
" countrycode continent \n",
"915 AQ NaN "
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 31,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fairsharing_countries[fairsharing_countries.countrycode == 'AQ']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2021-07-22 11:03:05 +02:00
"**re3data**"
2021-07-06 15:23:24 +02:00
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 32,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
2021-07-22 11:03:05 +02:00
"index 2693\n",
"id 2693\n",
"url 2673\n",
"official_name 2693\n",
"english_name 2034\n",
"description 38\n",
"latitude 2693\n",
"longitude 2693\n",
"type 2693\n",
"dataprovider 2693\n",
"subjects 2693\n",
2021-07-06 15:23:24 +02:00
"dtype: int64"
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 32,
2021-07-06 15:23:24 +02:00
"metadata": {},
"output_type": "execute_result"
2021-07-02 17:49:38 +02:00
}
],
"source": [
2021-07-06 15:23:24 +02:00
"re3data_df[re3data_df.latitude.notna()].count()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Location is basically absent in re3data"
]
},
2021-07-02 17:49:38 +02:00
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 33,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
2021-07-06 15:23:24 +02:00
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading formatted geocoded file...\n"
]
},
2021-07-22 11:03:05 +02:00
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>lat</th>\n",
" <th>lon</th>\n",
" <th>name</th>\n",
" <th>admin1</th>\n",
" <th>admin2</th>\n",
" <th>cc</th>\n",
" <th>continent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2688</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2689</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2690</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2691</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2692</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
" <td>AF</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2693 rows ×
"</div>"
],
"text/plain": [
" lat lon name admin1 admin2 cc continent\n",
"0 4.88447 -1.75536 Takoradi Western GH AF\n",
"1 4.88447 -1.75536 Takoradi Western GH AF\n",
"2 4.88447 -1.75536 Takoradi Western GH AF\n",
"3 4.88447 -1.75536 Takoradi Western GH AF\n",
"4 4.88447 -1.75536 Takoradi Western GH AF\n",
"... ... ... ... ... ... .. ...\n",
"2688 4.88447 -1.75536 Takoradi Western GH AF\n",
"2689 4.88447 -1.75536 Takoradi Western GH AF\n",
"2690 4.88447 -1.75536 Takoradi Western GH AF\n",
"2691 4.88447 -1.75536 Takoradi Western GH AF\n",
"2692 4.88447 -1.75536 Takoradi Western GH AF\n",
"\n",
"[2693 rows x 7 columns]"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"reverse_geocoding = pd.DataFrame(rg.search(re3data_df[['latitude', 'longitude']].apply(tuple, axis=1).tolist()))\n",
"reverse_geocoding['lat'] = reverse_geocoding['lat'].astype('float')\n",
"reverse_geocoding['lon'] = reverse_geocoding['lon'].astype('float')\n",
"reverse_geocoding['continent'] = reverse_geocoding.cc.map(countrycode_to_continent)\n",
"reverse_geocoding"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"re3data_df = re3data_df.join(reverse_geocoding)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Manual fix of null lat/lon"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"re3data_df.loc[(re3data_df.latitude == 0.0) & (re3data_df.longitude == 0.0), ['latitude', 'longitude', 'cc', 'continent']] = [np.nan, np.nan, np.nan, np.nan]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**OpenDOAR**"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
2021-07-02 17:49:38 +02:00
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>lat</th>\n",
" <th>lon</th>\n",
" <th>name</th>\n",
" <th>admin1</th>\n",
" <th>admin2</th>\n",
" <th>cc</th>\n",
2021-07-06 15:23:24 +02:00
" <th>continent</th>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>43.26271</td>\n",
" <td>-2.92528</td>\n",
" <td>Bilbao</td>\n",
" <td>Basque Country</td>\n",
" <td>Bizkaia</td>\n",
" <td>ES</td>\n",
2021-07-06 15:23:24 +02:00
" <td>EU</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.88447</td>\n",
" <td>-1.75536</td>\n",
" <td>Takoradi</td>\n",
" <td>Western</td>\n",
" <td></td>\n",
" <td>GH</td>\n",
2021-07-06 15:23:24 +02:00
" <td>AF</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>53.98333</td>\n",
" <td>-2.78333</td>\n",
" <td>Galgate</td>\n",
" <td>England</td>\n",
" <td>Lancashire</td>\n",
" <td>GB</td>\n",
2021-07-06 15:23:24 +02:00
" <td>EU</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>34.05223</td>\n",
" <td>-118.24368</td>\n",
" <td>Los Angeles</td>\n",
" <td>California</td>\n",
" <td>Los Angeles County</td>\n",
" <td>US</td>\n",
2021-07-06 15:23:24 +02:00
" <td>NA</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-22.22111</td>\n",
" <td>-54.80556</td>\n",
" <td>Dourados</td>\n",
" <td>Mato Grosso do Sul</td>\n",
" <td>Dourados</td>\n",
" <td>BR</td>\n",
2021-07-06 15:23:24 +02:00
" <td>SA</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
2021-07-06 15:23:24 +02:00
" <td>...</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>6009</th>\n",
" <td>40.85631</td>\n",
" <td>14.24641</td>\n",
" <td>Napoli</td>\n",
" <td>Campania</td>\n",
" <td>Provincia di Napoli</td>\n",
" <td>IT</td>\n",
2021-07-06 15:23:24 +02:00
" <td>EU</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>6010</th>\n",
" <td>38.19394</td>\n",
" <td>15.55256</td>\n",
" <td>Messina</td>\n",
" <td>Sicily</td>\n",
" <td>Messina</td>\n",
" <td>IT</td>\n",
2021-07-06 15:23:24 +02:00
" <td>EU</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>6011</th>\n",
" <td>54.32133</td>\n",
" <td>10.13489</td>\n",
" <td>Kiel</td>\n",
" <td>Schleswig-Holstein</td>\n",
" <td></td>\n",
" <td>DE</td>\n",
2021-07-06 15:23:24 +02:00
" <td>EU</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>6012</th>\n",
" <td>43.40785</td>\n",
" <td>-73.25955</td>\n",
" <td>Granville</td>\n",
" <td>New York</td>\n",
" <td>Washington County</td>\n",
" <td>US</td>\n",
2021-07-06 15:23:24 +02:00
" <td>NA</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" <tr>\n",
" <th>6013</th>\n",
" <td>33.96095</td>\n",
" <td>-83.37794</td>\n",
" <td>Athens</td>\n",
" <td>Georgia</td>\n",
" <td>Clarke County</td>\n",
" <td>US</td>\n",
2021-07-06 15:23:24 +02:00
" <td>NA</td>\n",
2021-07-02 17:49:38 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
2021-07-06 15:23:24 +02:00
"<p>6014 rows ×
2021-07-02 17:49:38 +02:00
"</div>"
],
"text/plain": [
" lat lon name admin1 \\\n",
"0 43.26271 -2.92528 Bilbao Basque Country \n",
"1 4.88447 -1.75536 Takoradi Western \n",
"2 53.98333 -2.78333 Galgate England \n",
"3 34.05223 -118.24368 Los Angeles California \n",
"4 -22.22111 -54.80556 Dourados Mato Grosso do Sul \n",
"... ... ... ... ... \n",
"6009 40.85631 14.24641 Napoli Campania \n",
"6010 38.19394 15.55256 Messina Sicily \n",
"6011 54.32133 10.13489 Kiel Schleswig-Holstein \n",
"6012 43.40785 -73.25955 Granville New York \n",
"6013 33.96095 -83.37794 Athens Georgia \n",
"\n",
2021-07-06 15:23:24 +02:00
" admin2 cc continent \n",
"0 Bizkaia ES EU \n",
"1 GH AF \n",
"2 Lancashire GB EU \n",
"3 Los Angeles County US NA \n",
"4 Dourados BR SA \n",
"... ... .. ... \n",
"6009 Provincia di Napoli IT EU \n",
"6010 Messina IT EU \n",
"6011 DE EU \n",
"6012 Washington County US NA \n",
"6013 Clarke County US NA \n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-06 15:23:24 +02:00
"[6014 rows x 7 columns]"
2021-07-02 17:49:38 +02:00
]
},
2021-07-22 11:03:05 +02:00
"execution_count": 36,
2021-07-02 17:49:38 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"reverse_geocoding = pd.DataFrame(rg.search(opendoar_df[['latitude', 'longitude']].apply(tuple, axis=1).tolist()))\n",
"reverse_geocoding['lat'] = reverse_geocoding['lat'].astype('float')\n",
"reverse_geocoding['lon'] = reverse_geocoding['lon'].astype('float')\n",
2021-07-06 15:23:24 +02:00
"reverse_geocoding['continent'] = reverse_geocoding.cc.map(countrycode_to_continent)\n",
2021-07-02 17:49:38 +02:00
"reverse_geocoding"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 37,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [],
"source": [
2021-07-06 15:23:24 +02:00
"opendoar_df = opendoar_df.join(reverse_geocoding)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Manual fix of null lat/lon"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 38,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [],
"source": [
2021-07-06 15:23:24 +02:00
"opendoar_df.loc[(opendoar_df.latitude == 0.0) & (opendoar_df.longitude == 0.0), ['latitude', 'longitude', 'cc', 'continent']] = [np.nan, np.nan, np.nan, np.nan]\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Country intersection**"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 39,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"venn2([set(fairsharing_countries.countrycode.dropna()), set(opendoar_df.cc.dropna())], set_labels = ('FAIRsharing', 'OpenDOAR'))\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Country coverage**"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 40,
2021-07-02 17:49:38 +02:00
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.plotly.v1+json": {
"config": {
2021-07-06 15:23:24 +02:00
"plotlyServerURL": "https://plot.ly"
2021-07-02 17:49:38 +02:00
},
"data": [
{
2021-07-06 15:23:24 +02:00
"name": "FAIRsharing",
2021-07-02 17:49:38 +02:00
"type": "bar",
"x": [
"US",
"GB",
"DE",
2021-07-06 15:23:24 +02:00
"FR",
"CH",
"CN",
"NL",
"IT",
"CA",
"BE",
2021-07-02 17:49:38 +02:00
"ES",
2021-07-06 15:23:24 +02:00
"JP",
"SE",
"CZ",
"NO",
"DK",
"EU",
"AT",
"FI",
"IE",
"AU",
"IL",
"PT",
"HU",
"GR",
"MT",
"LU",
"LT",
"IS",
"SK",
"ME",
"HR",
"IN",
"PL",
"SG",
"KR",
"RU",
"ZA",
"TW",
"MX",
2021-07-02 17:49:38 +02:00
"BR",
2021-07-06 15:23:24 +02:00
"NZ",
"SA",
"HK",
"AR",
2021-07-02 17:49:38 +02:00
"TR",
2021-07-06 15:23:24 +02:00
"BG",
"RO",
"PK",
"CR",
"MA",
"CY",
"TH",
"EE",
"UG",
"SV",
"UY",
"PA",
"TG",
"AE",
"NI",
"NG",
"BJ",
"CL",
"CM",
"CO",
"EG",
"ET",
"FO",
"GL",
"HN",
"ID",
"AQ",
"KE",
"LV",
"MG",
"ML",
"MR",
"MW",
"MZ",
"NE",
"ZW"
],
"y": [
686,
248,
192,
162,
114,
99,
96,
91,
86,
83,
83,
80,
76,
71,
69,
67,
66,
64,
63,
62,
62,
61,
60,
59,
58,
53,
52,
52,
52,
52,
51,
51,
32,
11,
10,
10,
9,
9,
8,
8,
8,
8,
6,
3,
3,
3,
3,
2,
2,
2,
2,
2,
2,
2,
2,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
]
},
{
"name": "OpenDOAR",
"type": "bar",
"x": [
"US",
"JP",
"GB",
"DE",
"ES",
"TR",
"PE",
2021-07-02 17:49:38 +02:00
"ID",
2021-07-06 15:23:24 +02:00
"BR",
2021-07-02 17:49:38 +02:00
"IT",
2021-07-06 15:23:24 +02:00
"HR",
"FR",
2021-07-02 17:49:38 +02:00
"PL",
"CA",
"IN",
2021-07-06 15:23:24 +02:00
"AU",
2021-07-02 17:49:38 +02:00
"UA",
"CO",
2021-07-06 15:23:24 +02:00
"NO",
2021-07-02 17:49:38 +02:00
"NL",
"AR",
"TW",
"CH",
2021-07-06 15:23:24 +02:00
"PT",
2021-07-02 17:49:38 +02:00
"SE",
2021-07-06 15:23:24 +02:00
"CN",
2021-07-02 17:49:38 +02:00
"MX",
"AT",
2021-07-06 15:23:24 +02:00
"GR",
"ZA",
2021-07-02 17:49:38 +02:00
"BE",
2021-07-06 15:23:24 +02:00
"HU",
2021-07-02 17:49:38 +02:00
"RU",
2021-07-06 15:23:24 +02:00
"EC",
2021-07-02 17:49:38 +02:00
"KR",
2021-07-06 15:23:24 +02:00
"KE",
"RS",
"BY",
2021-07-02 17:49:38 +02:00
"CZ",
2021-07-06 15:23:24 +02:00
"IE",
"NG",
"MY",
"FI",
"NZ",
2021-07-02 17:49:38 +02:00
"IR",
"CL",
2021-07-06 15:23:24 +02:00
"VE",
"TH",
2021-07-02 17:49:38 +02:00
"LT",
"DK",
"SD",
2021-07-06 15:23:24 +02:00
"LK",
"DZ",
2021-07-02 17:49:38 +02:00
"SI",
2021-07-06 15:23:24 +02:00
"BD",
"EG",
"NI",
"TZ",
2021-07-02 17:49:38 +02:00
"KZ",
"HK",
2021-07-06 15:23:24 +02:00
"CU",
"CR",
"UG",
"PH",
"MD",
"BG",
"ZW",
2021-07-02 17:49:38 +02:00
"SV",
2021-07-06 15:23:24 +02:00
"SA",
"EE",
"CY",
"JM",
2021-07-02 17:49:38 +02:00
"UY",
2021-07-06 15:23:24 +02:00
"RO",
2021-07-02 17:49:38 +02:00
"BW",
2021-07-06 15:23:24 +02:00
"PA",
"PS",
"MK",
2021-07-02 17:49:38 +02:00
"PK",
2021-07-06 15:23:24 +02:00
"AE",
"GH",
"LY",
"ET",
2021-07-02 17:49:38 +02:00
"DO",
2021-07-06 15:23:24 +02:00
"KG",
2021-07-02 17:49:38 +02:00
"LV",
2021-07-06 15:23:24 +02:00
"LB",
"IS",
"AZ",
"SJ",
"SN",
"HN",
"SO",
"IL",
"IQ",
"YE",
"SG",
"GE",
"BO",
"NA",
"BA",
"XK",
"TN",
"CV",
"ZM",
"BN",
"AM",
"SK",
2021-07-02 17:49:38 +02:00
"FJ",
2021-07-06 15:23:24 +02:00
"VA",
"LS",
"MV",
"PR",
"MZ",
"MN",
"MA",
"LU",
"PY",
"PW",
"GS",
"MW",
"AL",
"MR",
"MO",
"WF",
"VN",
"RW",
"NC",
"GT",
"SY",
"BJ",
"NP",
"GP",
"CM",
"TT",
"AF",
"LA",
"MT"
],
"y": [
886,
544,
328,
283,
160,
143,
138,
136,
135,
135,
135,
133,
115,
104,
101,
95,
89,
89,
83,
74,
69,
63,
61,
55,
55,
54,
46,
42,
40,
40,
39,
39,
35,
34,
33,
33,
32,
31,
27,
27,
27,
26,
26,
21,
20,
19,
18,
18,
17,
16,
15,
15,
14,
13,
13,
13,
12,
12,
12,
11,
11,
10,
9,
8,
8,
8,
8,
8,
8,
7,
6,
6,
6,
6,
5,
5,
5,
5,
4,
4,
4,
4,
4,
4,
4,
4,
4,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
3,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
2,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
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": "Country coverage"
},
"xaxis": {
"tickangle": 45,
"tickfont": {
"size": 12
}
}
}
},
"text/html": [
2021-07-22 11:03:05 +02:00
"<div> <div id=\"9b56ac9d-20ee-49c0-b32e-adb5c0130bfd\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div> <script type=\"text/javascript\"> require([\"plotly\"], function(Plotly) { window.PLOTLYENV=window.PLOTLYENV || {}; if (document.getElementById(\"9b56ac9d-20ee-49c0-b32e-adb5c0130bfd\")) { Plotly.newPlot( \"9b56ac9d-20ee-49c0-b32e-adb5c0130bfd\", [{\"name\": \"FAIRsharing\", \"type\": \"bar\", \"x\": [\"US\", \"GB\", \"DE\", \"FR\", \"CH\", \"CN\", \"NL\", \"IT\", \"CA\", \"BE\", \"ES\", \"JP\", \"SE\", \"CZ\", \"NO\", \"DK\", \"EU\", \"AT\", \"FI\", \"IE\", \"AU\", \"IL\", \"PT\", \"HU\", \"GR\", \"MT\", \"LU\", \"LT\", \"IS\", \"SK\", \"ME\", \"HR\", \"IN\", \"PL\", \"SG\", \"KR\", \"RU\", \"ZA\", \"TW\", \"MX\", \"BR\", \"NZ\", \"SA\", \"HK\", \"AR\", \"TR\", \"BG\", \"RO\", \"PK\", \"CR\", \"MA\", \"CY\", \"TH\", \"EE\", \"UG\", \"SV\", \"UY\", \"PA\", \"TG\", \"AE\", \"NI\", \"NG\", \"BJ\", \"CL\", \"CM\", \"CO\", \"EG\", \"ET\", \"FO\", \"GL\", \"HN\", \"ID\", \"AQ\", \"KE\", \"LV\", \"MG\", \"ML\", \"MR\", \"MW\", \"MZ\", \"NE\", \"ZW\"], \"y\": [686, 248, 192, 162, 114, 99, 96, 91, 86, 83, 83, 80, 76, 71, 69, 67, 66, 64, 63, 62, 62, 61, 60, 59, 58, 53, 52, 52, 52, 52, 51, 51, 32, 11, 10, 10, 9, 9, 8, 8, 8, 8, 6, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}, {\"name\": \"OpenDOAR\", \"type\": \"bar\", \"x\": [\"US\", \"JP\", \"GB\", \"DE\", \"ES\", \"TR\", \"PE\", \"ID\", \"BR\", \"IT\", \"HR\", \"FR\", \"PL\", \"CA\", \"IN\", \"AU\", \"UA\", \"CO\", \"NO\", \"NL\", \"AR\", \"TW\", \"CH\", \"PT\", \"SE\", \"CN\", \"MX\", \"AT\", \"GR\", \"ZA\", \"BE\", \"HU\", \"RU\", \"EC\", \"KR\", \"KE\", \"RS\", \"BY\", \"CZ\", \"IE\", \"NG\", \"MY\", \"FI\", \"NZ\", \"IR\", \"CL\", \"VE\", \"TH\", \"LT\", \"DK\", \"SD\", \"LK\", \"DZ\", \"SI\", \"BD\", \"EG\", \"NI\", \"TZ\", \"KZ\", \"HK\", \"CU\", \"CR\", \"UG\", \"PH\", \"MD\", \"BG\", \"ZW\", \"SV\", \"SA\", \"EE\", \"CY\", \"JM\", \"UY\", \"RO\", \"BW\", \"PA\", \"PS\", \"MK\", \"PK\", \"AE\", \"GH\", \"LY\", \"ET\", \"DO\", \"KG\", \"LV\", \"LB\", \"IS\", \"AZ\", \"SJ\", \"SN\", \"HN\", \"SO\", \"IL\", \"IQ\", \"YE\", \"SG\", \"GE\", \"BO\", \"NA\", \"BA\", \"XK\", \"TN\", \"CV\", \"ZM\", \"BN\", \"AM\", \"SK\", \"FJ\", \"VA\", \"LS\", \"MV\", \"PR\", \"MZ\", \"MN\", \"MA\", \"LU\", \"PY\", \"PW\", \"GS\", \"MW\", \"AL\", \"MR\", \"MO\", \"WF\", \"VN\", \"RW\", \"NC\", \"GT\", \"SY\", \"BJ\", \"NP\", \"GP\", \"CM\", \"TT\", \"AF\", \"LA\", \"MT\"], \"y\": [886, 544, 328, 283, 160, 143, 138, 136, 135, 135, 135, 133, 115, 104, 101, 95, 89, 89, 83, 74, 69, 63, 61, 55, 55, 54, 46, 42, 40, 40, 39, 39, 35, 34, 33, 33, 32, 31, 27, 27, 27, 26, 26, 21, 20, 19, 18, 18, 17, 16, 15, 15, 14, 13, 13, 13, 12, 12, 12, 11, 11, 10, 9, 8, 8, 8, 8, 8, 8, 7, 6, 6, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}], {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\
2021-07-06 15:23:24 +02:00
" \n",
2021-07-22 11:03:05 +02:00
"var gd = document.getElementById('9b56ac9d-20ee-49c0-b32e-adb5c0130bfd');\n",
2021-07-06 15:23:24 +02:00
"var x = new MutationObserver(function (mutations, observer) {{\n",
" var display = window.getComputedStyle(gd).display;\n",
" if (!display || display === 'none') {{\n",
" console.log([gd, 'removed!']);\n",
" Plotly.purge(gd);\n",
" observer.disconnect();\n",
" }}\n",
"}});\n",
"\n",
"// Listen for the removal of the full notebook cells\n",
"var notebookContainer = gd.closest('#notebook-container');\n",
"if (notebookContainer) {{\n",
" x.observe(notebookContainer, {childList: true});\n",
"}}\n",
"\n",
"// Listen for the clearing of the current output cell\n",
"var outputEl = gd.closest('.output');\n",
"if (outputEl) {{\n",
" x.observe(outputEl, {childList: true});\n",
"}}\n",
"\n",
" }) }; }); </script> </div>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data1 = fairsharing_countries.groupby('countrycode')[['url']].count().sort_values('url', ascending=False)\n",
"data2 = opendoar_df.groupby('cc')[['id']].count().sort_values('id', ascending=False)\n",
"\n",
"\n",
"plot = [\n",
" go.Bar(\n",
" x=data1.index,\n",
" y=data1['url'],\n",
" name='FAIRsharing'\n",
" ),\n",
" go.Bar(\n",
" x=data2.index,\n",
" y=data2['id'],\n",
" name='OpenDOAR'\n",
" )\n",
"]\n",
"\n",
"layout = go.Layout(\n",
" title='Country coverage',\n",
" xaxis=dict(tickangle=45, tickfont=dict(size=12))\n",
")\n",
"\n",
"go.Figure(plot, layout).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Continental coverage**"
]
},
{
"cell_type": "code",
2021-07-22 11:03:05 +02:00
"execution_count": 41,
2021-07-06 15:23:24 +02:00
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.plotly.v1+json": {
"config": {
"plotlyServerURL": "https://plot.ly"
},
"data": [
{
"fill": "toself",
"name": "FAIRsharing",
"r": [
27,
320,
2176,
787,
70,
14
],
"theta": [
"AF",
"AS",
"EU",
2021-07-02 17:49:38 +02:00
"NA",
2021-07-06 15:23:24 +02:00
"OC",
"SA"
2021-07-02 17:49:38 +02:00
],
2021-07-06 15:23:24 +02:00
"type": "scatterpolar"
},
{
"fill": "toself",
"name": "OpenDOAR",
"r": [
214,
1264,
2145,
1100,
121,
513
],
"theta": [
"AF",
"AS",
"EU",
"NA",
"OC",
"SA"
],
"type": "scatterpolar"
2021-07-02 17:49:38 +02:00
}
],
"layout": {
2021-07-06 15:23:24 +02:00
"polar": {
"radialaxis": {
"visible": true
}
},
2021-07-02 17:49:38 +02:00
"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
}
}
}
}
},
"text/html": [
2021-07-22 11:03:05 +02:00
"<div> <div id=\"2078da62-0ff3-40e3-82d6-b4a7f6c8cce3\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div> <script type=\"text/javascript\"> require([\"plotly\"], function(Plotly) { window.PLOTLYENV=window.PLOTLYENV || {}; if (document.getElementById(\"2078da62-0ff3-40e3-82d6-b4a7f6c8cce3\")) { Plotly.newPlot( \"2078da62-0ff3-40e3-82d6-b4a7f6c8cce3\", [{\"fill\": \"toself\", \"name\": \"FAIRsharing\", \"r\": [27, 320, 2176, 787, 70, 14], \"theta\": [\"AF\", \"AS\", \"EU\", \"NA\", \"OC\", \"SA\"], \"type\": \"scatterpolar\"}, {\"fill\": \"toself\", \"name\": \"OpenDOAR\", \"r\": [214, 1264, 2145, 1100, 121, 513], \"theta\": [\"AF\", \"AS\", \"EU\", \"NA\", \"OC\", \"SA\"], \"type\": \"scatterpolar\"}], {\"polar\": {\"radialaxis\": {\"visible\": true}}, \"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"
2021-07-02 17:49:38 +02:00
" \n",
2021-07-22 11:03:05 +02:00
"var gd = document.getElementById('2078da62-0ff3-40e3-82d6-b4a7f6c8cce3');\n",
2021-07-02 17:49:38 +02:00
"var x = new MutationObserver(function (mutations, observer) {{\n",
" var display = window.getComputedStyle(gd).display;\n",
" if (!display || display === 'none') {{\n",
" console.log([gd, 'removed!']);\n",
" Plotly.purge(gd);\n",
" observer.disconnect();\n",
" }}\n",
"}});\n",
"\n",
"// Listen for the removal of the full notebook cells\n",
"var notebookContainer = gd.closest('#notebook-container');\n",
"if (notebookContainer) {{\n",
" x.observe(notebookContainer, {childList: true});\n",
"}}\n",
"\n",
"// Listen for the clearing of the current output cell\n",
"var outputEl = gd.closest('.output');\n",
"if (outputEl) {{\n",
" x.observe(outputEl, {childList: true});\n",
"}}\n",
"\n",
" }) }; }); </script> </div>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
2021-07-06 15:23:24 +02:00
"data1 = fairsharing_countries.groupby('continent')[['url']].count()\n",
"data2 = opendoar_df.groupby('continent')[['url']].count()\n",
2021-07-02 17:49:38 +02:00
"\n",
2021-07-06 15:23:24 +02:00
"plot = [\n",
" go.Scatterpolar(\n",
" r=data1.url,\n",
" theta=data1.index,\n",
" fill='toself',\n",
" name='FAIRsharing'),\n",
" go.Scatterpolar(\n",
" r=data2.url,\n",
" theta=data2.index,\n",
" fill='toself',\n",
" name='OpenDOAR')\n",
2021-07-02 17:49:38 +02:00
"]\n",
"\n",
2021-07-06 15:23:24 +02:00
"layout = go.Layout(polar=dict(\n",
" radialaxis=dict(\n",
" visible=True\n",
" ),\n",
" )\n",
2021-07-02 17:49:38 +02:00
")\n",
2021-07-06 15:23:24 +02:00
"\n",
"go.Figure(plot, layout).show()"
2021-07-02 17:49:38 +02:00
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
