2339 lines
96 KiB
Plaintext
2339 lines
96 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 41,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import ast\n",
|
||
"import csv\n",
|
||
"import json\n",
|
||
"\n",
|
||
"import numpy as np\n",
|
||
"import pandas as pd\n",
|
||
"\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"from matplotlib_venn import venn2, venn2_circles\n",
|
||
"\n",
|
||
"import plotly\n",
|
||
"from plotly.offline import iplot, init_notebook_mode\n",
|
||
"import plotly.graph_objs as go\n",
|
||
"import plotly.express as px\n",
|
||
"\n",
|
||
"pd.set_option('display.max_columns', None)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"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>dedup_id</th>\n",
|
||
" <th>duplicate_id</th>\n",
|
||
" <th>original_id</th>\n",
|
||
" <th>name</th>\n",
|
||
" <th>source</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>dedup::29a83a8a9641bb860a679d7e5ba52d26</td>\n",
|
||
" <td>14174</td>\n",
|
||
" <td>14174</td>\n",
|
||
" <td>OHIO Open Library | Ohio University Research</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>dedup::000871c1fc726f0b52dc86a4eeb027de</td>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>IIT Bombay Institutional Repository</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>dedup::000871c1fc726f0b52dc86a4eeb027de</td>\n",
|
||
" <td>4649</td>\n",
|
||
" <td>4649</td>\n",
|
||
" <td>IIT Bombay Institutional Repository</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>dedup::001e6d882e54c780ce269d3c46997287</td>\n",
|
||
" <td>re3data_____::4af9fe2bb93511a5e0f0c39e94d6557f</td>\n",
|
||
" <td>r3d100011306</td>\n",
|
||
" <td>RESID Database of Protein Modifications</td>\n",
|
||
" <td>re3data</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>dedup::001e6d882e54c780ce269d3c46997287</td>\n",
|
||
" <td>https://fairsharing.org/10.25504/FAIRsharing.q...</td>\n",
|
||
" <td>https://fairsharing.org/10.25504/FAIRsharing.q...</td>\n",
|
||
" <td>RESID Database of Protein Modifications</td>\n",
|
||
" <td>FAIRsharing</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>5</th>\n",
|
||
" <td>dedup::0023a1e3447fdb31836536cc903f1310</td>\n",
|
||
" <td>opendoar____::c6f798b844366ccd65d99bc7f31e0e02</td>\n",
|
||
" <td>3410</td>\n",
|
||
" <td>erucu: electronic repository of the ukrainian ...</td>\n",
|
||
" <td>OpenDOAR</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>6</th>\n",
|
||
" <td>dedup::0023a1e3447fdb31836536cc903f1310</td>\n",
|
||
" <td>10013</td>\n",
|
||
" <td>10013</td>\n",
|
||
" <td>ErUCU: Electronic repository of the Ukrainian ...</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>7</th>\n",
|
||
" <td>dedup::003ab6b40af9b488decea7c582d150a2</td>\n",
|
||
" <td>https://fairsharing.org/10.25504/FAIRsharing.d...</td>\n",
|
||
" <td>https://fairsharing.org/10.25504/FAIRsharing.d...</td>\n",
|
||
" <td>Synapse</td>\n",
|
||
" <td>FAIRsharing</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>8</th>\n",
|
||
" <td>dedup::003ab6b40af9b488decea7c582d150a2</td>\n",
|
||
" <td>re3data_____::cafc5d99b7c187e24b40d958a16a91f1</td>\n",
|
||
" <td>r3d100011894</td>\n",
|
||
" <td>Synapse</td>\n",
|
||
" <td>re3data</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>9</th>\n",
|
||
" <td>dedup::0064f599ed0adb5870a5b3ffe438e485</td>\n",
|
||
" <td>16034</td>\n",
|
||
" <td>16034</td>\n",
|
||
" <td>Giresun University Institutional Repository</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" dedup_id \\\n",
|
||
"0 dedup::29a83a8a9641bb860a679d7e5ba52d26 \n",
|
||
"1 dedup::000871c1fc726f0b52dc86a4eeb027de \n",
|
||
"2 dedup::000871c1fc726f0b52dc86a4eeb027de \n",
|
||
"3 dedup::001e6d882e54c780ce269d3c46997287 \n",
|
||
"4 dedup::001e6d882e54c780ce269d3c46997287 \n",
|
||
"5 dedup::0023a1e3447fdb31836536cc903f1310 \n",
|
||
"6 dedup::0023a1e3447fdb31836536cc903f1310 \n",
|
||
"7 dedup::003ab6b40af9b488decea7c582d150a2 \n",
|
||
"8 dedup::003ab6b40af9b488decea7c582d150a2 \n",
|
||
"9 dedup::0064f599ed0adb5870a5b3ffe438e485 \n",
|
||
"\n",
|
||
" duplicate_id \\\n",
|
||
"0 14174 \n",
|
||
"1 4612 \n",
|
||
"2 4649 \n",
|
||
"3 re3data_____::4af9fe2bb93511a5e0f0c39e94d6557f \n",
|
||
"4 https://fairsharing.org/10.25504/FAIRsharing.q... \n",
|
||
"5 opendoar____::c6f798b844366ccd65d99bc7f31e0e02 \n",
|
||
"6 10013 \n",
|
||
"7 https://fairsharing.org/10.25504/FAIRsharing.d... \n",
|
||
"8 re3data_____::cafc5d99b7c187e24b40d958a16a91f1 \n",
|
||
"9 16034 \n",
|
||
"\n",
|
||
" original_id \\\n",
|
||
"0 14174 \n",
|
||
"1 4612 \n",
|
||
"2 4649 \n",
|
||
"3 r3d100011306 \n",
|
||
"4 https://fairsharing.org/10.25504/FAIRsharing.q... \n",
|
||
"5 3410 \n",
|
||
"6 10013 \n",
|
||
"7 https://fairsharing.org/10.25504/FAIRsharing.d... \n",
|
||
"8 r3d100011894 \n",
|
||
"9 16034 \n",
|
||
"\n",
|
||
" name source \n",
|
||
"0 OHIO Open Library | Ohio University Research roar \n",
|
||
"1 IIT Bombay Institutional Repository roar \n",
|
||
"2 IIT Bombay Institutional Repository roar \n",
|
||
"3 RESID Database of Protein Modifications re3data \n",
|
||
"4 RESID Database of Protein Modifications FAIRsharing \n",
|
||
"5 erucu: electronic repository of the ukrainian ... OpenDOAR \n",
|
||
"6 ErUCU: Electronic repository of the Ukrainian ... roar \n",
|
||
"7 Synapse FAIRsharing \n",
|
||
"8 Synapse re3data \n",
|
||
"9 Giresun University Institutional Repository roar "
|
||
]
|
||
},
|
||
"execution_count": 46,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_09 = pd.read_csv('../data/interim/ds_dedup09.csv', sep=';')\n",
|
||
"df_09.head(10)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 24,
|
||
"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>dedup_id</th>\n",
|
||
" <th>duplicate_id</th>\n",
|
||
" <th>original_id</th>\n",
|
||
" <th>name</th>\n",
|
||
" <th>source</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>5115</th>\n",
|
||
" <td>dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98</td>\n",
|
||
" <td>1126</td>\n",
|
||
" <td>1126</td>\n",
|
||
" <td>RIT Digital Media Library</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>5116</th>\n",
|
||
" <td>dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98</td>\n",
|
||
" <td>opendoar____::443cb001c138b2561a0d90720d6ce111</td>\n",
|
||
" <td>648</td>\n",
|
||
" <td>rit digital media library</td>\n",
|
||
" <td>OpenDOAR</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" dedup_id \\\n",
|
||
"5115 dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98 \n",
|
||
"5116 dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98 \n",
|
||
"\n",
|
||
" duplicate_id original_id \\\n",
|
||
"5115 1126 1126 \n",
|
||
"5116 opendoar____::443cb001c138b2561a0d90720d6ce111 648 \n",
|
||
"\n",
|
||
" name source \n",
|
||
"5115 RIT Digital Media Library roar \n",
|
||
"5116 rit digital media library OpenDOAR "
|
||
]
|
||
},
|
||
"execution_count": 24,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_09[df_09.dedup_id == 'dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 25,
|
||
"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>dedup_id</th>\n",
|
||
" <th>duplicate_id</th>\n",
|
||
" <th>original_id</th>\n",
|
||
" <th>name</th>\n",
|
||
" <th>source</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>40</th>\n",
|
||
" <td>dedup::01846ae470651e97d2f73fce979406a9</td>\n",
|
||
" <td>opendoar____::b4d6f2b565ca0eef1f9245403aac366a</td>\n",
|
||
" <td>7668</td>\n",
|
||
" <td>digital commons at michigan state university c...</td>\n",
|
||
" <td>OpenDOAR</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" dedup_id \\\n",
|
||
"40 dedup::01846ae470651e97d2f73fce979406a9 \n",
|
||
"\n",
|
||
" duplicate_id original_id \\\n",
|
||
"40 opendoar____::b4d6f2b565ca0eef1f9245403aac366a 7668 \n",
|
||
"\n",
|
||
" name source \n",
|
||
"40 digital commons at michigan state university c... OpenDOAR "
|
||
]
|
||
},
|
||
"execution_count": 25,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_09[df_09.dedup_id == 'dedup::01846ae470651e97d2f73fce979406a9']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"re3data_df = pd.read_csv('../data/raw/re3data.tsv', delimiter='\\t', \n",
|
||
" converters={'subject': ast.literal_eval,\n",
|
||
" 'keyword': ast.literal_eval,\n",
|
||
" 'additional_name': ast.literal_eval,\n",
|
||
" 'repository_id': ast.literal_eval,\n",
|
||
" 'type': ast.literal_eval,\n",
|
||
" 'content_type': ast.literal_eval,\n",
|
||
" 'provider_type': ast.literal_eval,\n",
|
||
" 'institution': ast.literal_eval\n",
|
||
" })"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"opendoar_df = pd.read_csv('../data/raw/openDoar.tsv', delimiter='\\t',\n",
|
||
" converters={'subject': ast.literal_eval,\n",
|
||
" 'additional_name': ast.literal_eval,\n",
|
||
" 'opendoar_id': ast.literal_eval,\n",
|
||
" 'content_type': ast.literal_eval,\n",
|
||
" 'institution': ast.literal_eval\n",
|
||
" })"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"roar_df = pd.read_csv('../data/raw/export_roar_CSV.csv', dtype='str')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"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'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"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>dedup_id</th>\n",
|
||
" <th>duplicate_id</th>\n",
|
||
" <th>original_id</th>\n",
|
||
" <th>name</th>\n",
|
||
" <th>source</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>dedup::29a83a8a9641bb860a679d7e5ba52d26</td>\n",
|
||
" <td>14174</td>\n",
|
||
" <td>14174</td>\n",
|
||
" <td>OHIO Open Library | Ohio University Research</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>dedup::000871c1fc726f0b52dc86a4eeb027de</td>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>IIT Bombay Institutional Repository</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>dedup::000871c1fc726f0b52dc86a4eeb027de</td>\n",
|
||
" <td>4649</td>\n",
|
||
" <td>4649</td>\n",
|
||
" <td>IIT Bombay Institutional Repository</td>\n",
|
||
" <td>roar</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>dedup::001e6d882e54c780ce269d3c46997287</td>\n",
|
||
" <td>re3data_____::4af9fe2bb93511a5e0f0c39e94d6557f</td>\n",
|
||
" <td>r3d100011306</td>\n",
|
||
" <td>RESID Database of Protein Modifications</td>\n",
|
||
" <td>re3data</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>dedup::001e6d882e54c780ce269d3c46997287</td>\n",
|
||
" <td>https://fairsharing.org/10.25504/FAIRsharing.q...</td>\n",
|
||
" <td>https://fairsharing.org/10.25504/FAIRsharing.q...</td>\n",
|
||
" <td>RESID Database of Protein Modifications</td>\n",
|
||
" <td>FAIRsharing</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" dedup_id \\\n",
|
||
"0 dedup::29a83a8a9641bb860a679d7e5ba52d26 \n",
|
||
"1 dedup::000871c1fc726f0b52dc86a4eeb027de \n",
|
||
"2 dedup::000871c1fc726f0b52dc86a4eeb027de \n",
|
||
"3 dedup::001e6d882e54c780ce269d3c46997287 \n",
|
||
"4 dedup::001e6d882e54c780ce269d3c46997287 \n",
|
||
"\n",
|
||
" duplicate_id \\\n",
|
||
"0 14174 \n",
|
||
"1 4612 \n",
|
||
"2 4649 \n",
|
||
"3 re3data_____::4af9fe2bb93511a5e0f0c39e94d6557f \n",
|
||
"4 https://fairsharing.org/10.25504/FAIRsharing.q... \n",
|
||
"\n",
|
||
" original_id \\\n",
|
||
"0 14174 \n",
|
||
"1 4612 \n",
|
||
"2 4649 \n",
|
||
"3 r3d100011306 \n",
|
||
"4 https://fairsharing.org/10.25504/FAIRsharing.q... \n",
|
||
"\n",
|
||
" name source \n",
|
||
"0 OHIO Open Library | Ohio University Research roar \n",
|
||
"1 IIT Bombay Institutional Repository roar \n",
|
||
"2 IIT Bombay Institutional Repository roar \n",
|
||
"3 RESID Database of Protein Modifications re3data \n",
|
||
"4 RESID Database of Protein Modifications FAIRsharing "
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df_09.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"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>duplicate_id</th>\n",
|
||
" <th>original_id</th>\n",
|
||
" <th>name</th>\n",
|
||
" <th>source</th>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup_id</th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::000871c1fc726f0b52dc86a4eeb027de</th>\n",
|
||
" <td>[4612, 4649]</td>\n",
|
||
" <td>[4612, 4649]</td>\n",
|
||
" <td>[IIT Bombay Institutional Repository, IIT Bomb...</td>\n",
|
||
" <td>[roar, roar]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::001e6d882e54c780ce269d3c46997287</th>\n",
|
||
" <td>[re3data_____::4af9fe2bb93511a5e0f0c39e94d6557...</td>\n",
|
||
" <td>[r3d100011306, https://fairsharing.org/10.2550...</td>\n",
|
||
" <td>[RESID Database of Protein Modifications, RESI...</td>\n",
|
||
" <td>[re3data, FAIRsharing]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::0023a1e3447fdb31836536cc903f1310</th>\n",
|
||
" <td>[opendoar____::c6f798b844366ccd65d99bc7f31e0e0...</td>\n",
|
||
" <td>[3410, 10013]</td>\n",
|
||
" <td>[erucu: electronic repository of the ukrainian...</td>\n",
|
||
" <td>[OpenDOAR, roar]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::003ab6b40af9b488decea7c582d150a2</th>\n",
|
||
" <td>[https://fairsharing.org/10.25504/FAIRsharing....</td>\n",
|
||
" <td>[https://fairsharing.org/10.25504/FAIRsharing....</td>\n",
|
||
" <td>[Synapse, Synapse]</td>\n",
|
||
" <td>[FAIRsharing, re3data]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::0064f599ed0adb5870a5b3ffe438e485</th>\n",
|
||
" <td>[16034, opendoar____::d1f157379ea7e51d4a8c07af...</td>\n",
|
||
" <td>[16034, 9647]</td>\n",
|
||
" <td>[Giresun University Institutional Repository, ...</td>\n",
|
||
" <td>[roar, OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::ff49cc40a8890e6a60f40ff3026d2730</th>\n",
|
||
" <td>[1333, opendoar____::2bd7f907b7f5b6bbd91822c0c...</td>\n",
|
||
" <td>[1333, 1389]</td>\n",
|
||
" <td>[UnissResearch, unissresearch]</td>\n",
|
||
" <td>[roar, OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::ff4d70de478038c72282b7e4af1d4260</th>\n",
|
||
" <td>[opendoar____::95a0810a93a87065bf7b28490817e9e...</td>\n",
|
||
" <td>[9752, 16367]</td>\n",
|
||
" <td>[european xfel publication database, European ...</td>\n",
|
||
" <td>[OpenDOAR, roar]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::ff826ce6ee85809389f18a5fafe72366</th>\n",
|
||
" <td>[opendoar____::62e7f2e090fe150ef8deb4466fdc81b...</td>\n",
|
||
" <td>[3601, 2608]</td>\n",
|
||
" <td>[electronic odessa national economic universit...</td>\n",
|
||
" <td>[OpenDOAR, OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::ffbd6cbb019a1413183c8d08f2929307</th>\n",
|
||
" <td>[3108, opendoar____::ff7d0f525b3be596a51fb9194...</td>\n",
|
||
" <td>[3108, 1912]</td>\n",
|
||
" <td>[Fotografía Sobre España en el Siglo XIX, foto...</td>\n",
|
||
" <td>[roar, OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98</th>\n",
|
||
" <td>[1126, opendoar____::443cb001c138b2561a0d90720...</td>\n",
|
||
" <td>[1126, 648]</td>\n",
|
||
" <td>[RIT Digital Media Library, rit digital media ...</td>\n",
|
||
" <td>[roar, OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>2453 rows × 4 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" duplicate_id \\\n",
|
||
"dedup_id \n",
|
||
"dedup::000871c1fc726f0b52dc86a4eeb027de [4612, 4649] \n",
|
||
"dedup::001e6d882e54c780ce269d3c46997287 [re3data_____::4af9fe2bb93511a5e0f0c39e94d6557... \n",
|
||
"dedup::0023a1e3447fdb31836536cc903f1310 [opendoar____::c6f798b844366ccd65d99bc7f31e0e0... \n",
|
||
"dedup::003ab6b40af9b488decea7c582d150a2 [https://fairsharing.org/10.25504/FAIRsharing.... \n",
|
||
"dedup::0064f599ed0adb5870a5b3ffe438e485 [16034, opendoar____::d1f157379ea7e51d4a8c07af... \n",
|
||
"... ... \n",
|
||
"dedup::ff49cc40a8890e6a60f40ff3026d2730 [1333, opendoar____::2bd7f907b7f5b6bbd91822c0c... \n",
|
||
"dedup::ff4d70de478038c72282b7e4af1d4260 [opendoar____::95a0810a93a87065bf7b28490817e9e... \n",
|
||
"dedup::ff826ce6ee85809389f18a5fafe72366 [opendoar____::62e7f2e090fe150ef8deb4466fdc81b... \n",
|
||
"dedup::ffbd6cbb019a1413183c8d08f2929307 [3108, opendoar____::ff7d0f525b3be596a51fb9194... \n",
|
||
"dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98 [1126, opendoar____::443cb001c138b2561a0d90720... \n",
|
||
"\n",
|
||
" original_id \\\n",
|
||
"dedup_id \n",
|
||
"dedup::000871c1fc726f0b52dc86a4eeb027de [4612, 4649] \n",
|
||
"dedup::001e6d882e54c780ce269d3c46997287 [r3d100011306, https://fairsharing.org/10.2550... \n",
|
||
"dedup::0023a1e3447fdb31836536cc903f1310 [3410, 10013] \n",
|
||
"dedup::003ab6b40af9b488decea7c582d150a2 [https://fairsharing.org/10.25504/FAIRsharing.... \n",
|
||
"dedup::0064f599ed0adb5870a5b3ffe438e485 [16034, 9647] \n",
|
||
"... ... \n",
|
||
"dedup::ff49cc40a8890e6a60f40ff3026d2730 [1333, 1389] \n",
|
||
"dedup::ff4d70de478038c72282b7e4af1d4260 [9752, 16367] \n",
|
||
"dedup::ff826ce6ee85809389f18a5fafe72366 [3601, 2608] \n",
|
||
"dedup::ffbd6cbb019a1413183c8d08f2929307 [3108, 1912] \n",
|
||
"dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98 [1126, 648] \n",
|
||
"\n",
|
||
" name \\\n",
|
||
"dedup_id \n",
|
||
"dedup::000871c1fc726f0b52dc86a4eeb027de [IIT Bombay Institutional Repository, IIT Bomb... \n",
|
||
"dedup::001e6d882e54c780ce269d3c46997287 [RESID Database of Protein Modifications, RESI... \n",
|
||
"dedup::0023a1e3447fdb31836536cc903f1310 [erucu: electronic repository of the ukrainian... \n",
|
||
"dedup::003ab6b40af9b488decea7c582d150a2 [Synapse, Synapse] \n",
|
||
"dedup::0064f599ed0adb5870a5b3ffe438e485 [Giresun University Institutional Repository, ... \n",
|
||
"... ... \n",
|
||
"dedup::ff49cc40a8890e6a60f40ff3026d2730 [UnissResearch, unissresearch] \n",
|
||
"dedup::ff4d70de478038c72282b7e4af1d4260 [european xfel publication database, European ... \n",
|
||
"dedup::ff826ce6ee85809389f18a5fafe72366 [electronic odessa national economic universit... \n",
|
||
"dedup::ffbd6cbb019a1413183c8d08f2929307 [Fotografía Sobre España en el Siglo XIX, foto... \n",
|
||
"dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98 [RIT Digital Media Library, rit digital media ... \n",
|
||
"\n",
|
||
" source \n",
|
||
"dedup_id \n",
|
||
"dedup::000871c1fc726f0b52dc86a4eeb027de [roar, roar] \n",
|
||
"dedup::001e6d882e54c780ce269d3c46997287 [re3data, FAIRsharing] \n",
|
||
"dedup::0023a1e3447fdb31836536cc903f1310 [OpenDOAR, roar] \n",
|
||
"dedup::003ab6b40af9b488decea7c582d150a2 [FAIRsharing, re3data] \n",
|
||
"dedup::0064f599ed0adb5870a5b3ffe438e485 [roar, OpenDOAR] \n",
|
||
"... ... \n",
|
||
"dedup::ff49cc40a8890e6a60f40ff3026d2730 [roar, OpenDOAR] \n",
|
||
"dedup::ff4d70de478038c72282b7e4af1d4260 [OpenDOAR, roar] \n",
|
||
"dedup::ff826ce6ee85809389f18a5fafe72366 [OpenDOAR, OpenDOAR] \n",
|
||
"dedup::ffbd6cbb019a1413183c8d08f2929307 [roar, OpenDOAR] \n",
|
||
"dedup::ffeed84c7cb1ae7bf4ec4bd78275bb98 [roar, OpenDOAR] \n",
|
||
"\n",
|
||
"[2453 rows x 4 columns]"
|
||
]
|
||
},
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"dup = df_09.groupby('dedup_id').aggregate(list)\n",
|
||
"dup"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"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>duplicate_id</th>\n",
|
||
" <th>original_id</th>\n",
|
||
" <th>name</th>\n",
|
||
" <th>source</th>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup_id</th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::01846ae470651e97d2f73fce979406a9</th>\n",
|
||
" <td>[opendoar____::b4d6f2b565ca0eef1f9245403aac366a]</td>\n",
|
||
" <td>[7668]</td>\n",
|
||
" <td>[digital commons at michigan state university ...</td>\n",
|
||
" <td>[OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::022036087426786cfd0f7f41fa7a2665</th>\n",
|
||
" <td>[https://fairsharing.org/10.25504/FAIRsharing....</td>\n",
|
||
" <td>[https://fairsharing.org/10.25504/FAIRsharing....</td>\n",
|
||
" <td>[World Data Center for Climate at DRKZ]</td>\n",
|
||
" <td>[FAIRsharing]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::07e8b472e1e4af17a6b20ce083baf29f</th>\n",
|
||
" <td>[15036]</td>\n",
|
||
" <td>[15036]</td>\n",
|
||
" <td>[MiCISAN]</td>\n",
|
||
" <td>[roar]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::0894634a3244e3050d8057a453e17e57</th>\n",
|
||
" <td>[https://fairsharing.org/10.25504/FAIRsharing....</td>\n",
|
||
" <td>[https://fairsharing.org/10.25504/FAIRsharing....</td>\n",
|
||
" <td>[European Variation Archive]</td>\n",
|
||
" <td>[FAIRsharing]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::0a54b19a13b6712dc04d1b49215423d8</th>\n",
|
||
" <td>[opendoar____::d34ab169b70c9dcd35e62896010cd9ff]</td>\n",
|
||
" <td>[377]</td>\n",
|
||
" <td>[yale medicine thesis digital library]</td>\n",
|
||
" <td>[OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::f8306c8f16096b6d944799f4d427a976</th>\n",
|
||
" <td>[re3data_____::574b553c6c374d597d2068ab2b117889]</td>\n",
|
||
" <td>[r3d100012041]</td>\n",
|
||
" <td>[Canadian Disaster Database]</td>\n",
|
||
" <td>[re3data]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::f9d8e2daaa9144310b66bf948e50d656</th>\n",
|
||
" <td>[re3data_____::95014789f83d7611ebfddace19d0523a]</td>\n",
|
||
" <td>[r3d100011045]</td>\n",
|
||
" <td>[Index to Marine & Lacustrine Geological Samples]</td>\n",
|
||
" <td>[re3data]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::fcdbc4f504a15df8f78da88ee72fad32</th>\n",
|
||
" <td>[opendoar____::9f96f36b7aae3b1ff847c26ac94c604e]</td>\n",
|
||
" <td>[4979]</td>\n",
|
||
" <td>[university of minnesota law school]</td>\n",
|
||
" <td>[OpenDOAR]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::fcfe9c770eb9372e6961a17f7eaffd5f</th>\n",
|
||
" <td>[4637]</td>\n",
|
||
" <td>[4637]</td>\n",
|
||
" <td>[Simon Fraser University Institutional Reposit...</td>\n",
|
||
" <td>[roar]</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>dedup::fe73f687e5bc5280214e0486b273a5f9</th>\n",
|
||
" <td>[330]</td>\n",
|
||
" <td>[330]</td>\n",
|
||
" <td>[DigitalCommons@Fort Lewis College: Scholarshi...</td>\n",
|
||
" <td>[roar]</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>109 rows × 4 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" duplicate_id \\\n",
|
||
"dedup_id \n",
|
||
"dedup::01846ae470651e97d2f73fce979406a9 [opendoar____::b4d6f2b565ca0eef1f9245403aac366a] \n",
|
||
"dedup::022036087426786cfd0f7f41fa7a2665 [https://fairsharing.org/10.25504/FAIRsharing.... \n",
|
||
"dedup::07e8b472e1e4af17a6b20ce083baf29f [15036] \n",
|
||
"dedup::0894634a3244e3050d8057a453e17e57 [https://fairsharing.org/10.25504/FAIRsharing.... \n",
|
||
"dedup::0a54b19a13b6712dc04d1b49215423d8 [opendoar____::d34ab169b70c9dcd35e62896010cd9ff] \n",
|
||
"... ... \n",
|
||
"dedup::f8306c8f16096b6d944799f4d427a976 [re3data_____::574b553c6c374d597d2068ab2b117889] \n",
|
||
"dedup::f9d8e2daaa9144310b66bf948e50d656 [re3data_____::95014789f83d7611ebfddace19d0523a] \n",
|
||
"dedup::fcdbc4f504a15df8f78da88ee72fad32 [opendoar____::9f96f36b7aae3b1ff847c26ac94c604e] \n",
|
||
"dedup::fcfe9c770eb9372e6961a17f7eaffd5f [4637] \n",
|
||
"dedup::fe73f687e5bc5280214e0486b273a5f9 [330] \n",
|
||
"\n",
|
||
" original_id \\\n",
|
||
"dedup_id \n",
|
||
"dedup::01846ae470651e97d2f73fce979406a9 [7668] \n",
|
||
"dedup::022036087426786cfd0f7f41fa7a2665 [https://fairsharing.org/10.25504/FAIRsharing.... \n",
|
||
"dedup::07e8b472e1e4af17a6b20ce083baf29f [15036] \n",
|
||
"dedup::0894634a3244e3050d8057a453e17e57 [https://fairsharing.org/10.25504/FAIRsharing.... \n",
|
||
"dedup::0a54b19a13b6712dc04d1b49215423d8 [377] \n",
|
||
"... ... \n",
|
||
"dedup::f8306c8f16096b6d944799f4d427a976 [r3d100012041] \n",
|
||
"dedup::f9d8e2daaa9144310b66bf948e50d656 [r3d100011045] \n",
|
||
"dedup::fcdbc4f504a15df8f78da88ee72fad32 [4979] \n",
|
||
"dedup::fcfe9c770eb9372e6961a17f7eaffd5f [4637] \n",
|
||
"dedup::fe73f687e5bc5280214e0486b273a5f9 [330] \n",
|
||
"\n",
|
||
" name \\\n",
|
||
"dedup_id \n",
|
||
"dedup::01846ae470651e97d2f73fce979406a9 [digital commons at michigan state university ... \n",
|
||
"dedup::022036087426786cfd0f7f41fa7a2665 [World Data Center for Climate at DRKZ] \n",
|
||
"dedup::07e8b472e1e4af17a6b20ce083baf29f [MiCISAN] \n",
|
||
"dedup::0894634a3244e3050d8057a453e17e57 [European Variation Archive] \n",
|
||
"dedup::0a54b19a13b6712dc04d1b49215423d8 [yale medicine thesis digital library] \n",
|
||
"... ... \n",
|
||
"dedup::f8306c8f16096b6d944799f4d427a976 [Canadian Disaster Database] \n",
|
||
"dedup::f9d8e2daaa9144310b66bf948e50d656 [Index to Marine & Lacustrine Geological Samples] \n",
|
||
"dedup::fcdbc4f504a15df8f78da88ee72fad32 [university of minnesota law school] \n",
|
||
"dedup::fcfe9c770eb9372e6961a17f7eaffd5f [Simon Fraser University Institutional Reposit... \n",
|
||
"dedup::fe73f687e5bc5280214e0486b273a5f9 [DigitalCommons@Fort Lewis College: Scholarshi... \n",
|
||
"\n",
|
||
" source \n",
|
||
"dedup_id \n",
|
||
"dedup::01846ae470651e97d2f73fce979406a9 [OpenDOAR] \n",
|
||
"dedup::022036087426786cfd0f7f41fa7a2665 [FAIRsharing] \n",
|
||
"dedup::07e8b472e1e4af17a6b20ce083baf29f [roar] \n",
|
||
"dedup::0894634a3244e3050d8057a453e17e57 [FAIRsharing] \n",
|
||
"dedup::0a54b19a13b6712dc04d1b49215423d8 [OpenDOAR] \n",
|
||
"... ... \n",
|
||
"dedup::f8306c8f16096b6d944799f4d427a976 [re3data] \n",
|
||
"dedup::f9d8e2daaa9144310b66bf948e50d656 [re3data] \n",
|
||
"dedup::fcdbc4f504a15df8f78da88ee72fad32 [OpenDOAR] \n",
|
||
"dedup::fcfe9c770eb9372e6961a17f7eaffd5f [roar] \n",
|
||
"dedup::fe73f687e5bc5280214e0486b273a5f9 [roar] \n",
|
||
"\n",
|
||
"[109 rows x 4 columns]"
|
||
]
|
||
},
|
||
"execution_count": 9,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"dup[dup.source.str.len() == 1]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([list(['r3d100013204', 'r3d100013458', 'r3d100012807', 'r3d100012808', 'r3d100012806', 'r3d100012805']),\n",
|
||
" list(['243', '5702', '5715', '5694', '5689', '5658', '5710', '5750', '5721', '5704']),\n",
|
||
" list(['2738', '4991', '2727', '2729', '2724', '2728', '2740', '174']),\n",
|
||
" list(['19', '8', '7', '11', '10', '13', '6', '12', '20', '15', '9', '5', '14', '16'])],\n",
|
||
" dtype=object)"
|
||
]
|
||
},
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"dup[dup.source.str.len() >= 6].original_id.values"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"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>0</th>\n",
|
||
" <th>1</th>\n",
|
||
" <th>2</th>\n",
|
||
" <th>3</th>\n",
|
||
" <th>4</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>[Harvard University, Institute for Quantitativ...</td>\n",
|
||
" <td>[Ontario Council of University Libraries, [CBU...</td>\n",
|
||
" <td>[Scholars Portal Dataverse, [], CAN, [general]...</td>\n",
|
||
" <td>[The Dataverse Project, [], AAA, [technical], ...</td>\n",
|
||
" <td>[University of Ottawa, Library, [Université d'...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>[Dataverse Project, [], AAA, [technical], non-...</td>\n",
|
||
" <td>[Harvard University, Institute for Quantitave ...</td>\n",
|
||
" <td>[Ontario Council of University Libraries, [CBU...</td>\n",
|
||
" <td>[University of Toronto, Libraries, [], CAN, [g...</td>\n",
|
||
" <td>None</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>[Harvard University, Institute for Quantitativ...</td>\n",
|
||
" <td>[Ontario Council of University Libraries, [CBU...</td>\n",
|
||
" <td>[Scholars Portal Dataverse, [dataverse@scholar...</td>\n",
|
||
" <td>[The Dataverse Project, [], AAA, [technical], ...</td>\n",
|
||
" <td>[University of Windsor, [], CAN, [general], no...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>[Harvard University, Institute for Quantitativ...</td>\n",
|
||
" <td>[Ontario Council of University Libraries, [CBU...</td>\n",
|
||
" <td>[Scholars Portal Dataverse, [], CAN, [general]...</td>\n",
|
||
" <td>[The Dataverse Project, [], AAA, [technical], ...</td>\n",
|
||
" <td>[University of Waterloo, [], CAN, [general], n...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>[University of Victoria, [UVic], CAN, [general...</td>\n",
|
||
" <td>[University of Victoria, Libraries, [], CAN, [...</td>\n",
|
||
" <td>None</td>\n",
|
||
" <td>None</td>\n",
|
||
" <td>None</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>5</th>\n",
|
||
" <td>[The University of British Columbia, [], CAN, ...</td>\n",
|
||
" <td>[University of British Columbia, Library, [], ...</td>\n",
|
||
" <td>None</td>\n",
|
||
" <td>None</td>\n",
|
||
" <td>None</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" 0 \\\n",
|
||
"0 [Harvard University, Institute for Quantitativ... \n",
|
||
"1 [Dataverse Project, [], AAA, [technical], non-... \n",
|
||
"2 [Harvard University, Institute for Quantitativ... \n",
|
||
"3 [Harvard University, Institute for Quantitativ... \n",
|
||
"4 [University of Victoria, [UVic], CAN, [general... \n",
|
||
"5 [The University of British Columbia, [], CAN, ... \n",
|
||
"\n",
|
||
" 1 \\\n",
|
||
"0 [Ontario Council of University Libraries, [CBU... \n",
|
||
"1 [Harvard University, Institute for Quantitave ... \n",
|
||
"2 [Ontario Council of University Libraries, [CBU... \n",
|
||
"3 [Ontario Council of University Libraries, [CBU... \n",
|
||
"4 [University of Victoria, Libraries, [], CAN, [... \n",
|
||
"5 [University of British Columbia, Library, [], ... \n",
|
||
"\n",
|
||
" 2 \\\n",
|
||
"0 [Scholars Portal Dataverse, [], CAN, [general]... \n",
|
||
"1 [Ontario Council of University Libraries, [CBU... \n",
|
||
"2 [Scholars Portal Dataverse, [dataverse@scholar... \n",
|
||
"3 [Scholars Portal Dataverse, [], CAN, [general]... \n",
|
||
"4 None \n",
|
||
"5 None \n",
|
||
"\n",
|
||
" 3 \\\n",
|
||
"0 [The Dataverse Project, [], AAA, [technical], ... \n",
|
||
"1 [University of Toronto, Libraries, [], CAN, [g... \n",
|
||
"2 [The Dataverse Project, [], AAA, [technical], ... \n",
|
||
"3 [The Dataverse Project, [], AAA, [technical], ... \n",
|
||
"4 None \n",
|
||
"5 None \n",
|
||
"\n",
|
||
" 4 \n",
|
||
"0 [University of Ottawa, Library, [Université d'... \n",
|
||
"1 None \n",
|
||
"2 [University of Windsor, [], CAN, [general], no... \n",
|
||
"3 [University of Waterloo, [], CAN, [general], n... \n",
|
||
"4 None \n",
|
||
"5 None "
|
||
]
|
||
},
|
||
"execution_count": 11,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"pd.DataFrame(re3data_df[re3data_df.re3data_id.isin(['r3d100013204', 'r3d100013458', 'r3d100012807', 'r3d100012808', 'r3d100012806', 'r3d100012805'])].institution.to_list())"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"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>eprintid</th>\n",
|
||
" <th>rev_number</th>\n",
|
||
" <th>eprint_status</th>\n",
|
||
" <th>userid</th>\n",
|
||
" <th>importid</th>\n",
|
||
" <th>source</th>\n",
|
||
" <th>dir</th>\n",
|
||
" <th>datestamp</th>\n",
|
||
" <th>lastmod</th>\n",
|
||
" <th>status_changed</th>\n",
|
||
" <th>type</th>\n",
|
||
" <th>succeeds</th>\n",
|
||
" <th>commentary</th>\n",
|
||
" <th>metadata_visibility</th>\n",
|
||
" <th>latitude</th>\n",
|
||
" <th>longitude</th>\n",
|
||
" <th>relation_type</th>\n",
|
||
" <th>relation_uri</th>\n",
|
||
" <th>item_issues_id</th>\n",
|
||
" <th>item_issues_type</th>\n",
|
||
" <th>item_issues_description</th>\n",
|
||
" <th>item_issues_timestamp</th>\n",
|
||
" <th>item_issues_status</th>\n",
|
||
" <th>item_issues_reported_by</th>\n",
|
||
" <th>item_issues_resolved_by</th>\n",
|
||
" <th>item_issues_comment</th>\n",
|
||
" <th>item_issues_count</th>\n",
|
||
" <th>sword_depositor</th>\n",
|
||
" <th>sword_slug</th>\n",
|
||
" <th>exemplar</th>\n",
|
||
" <th>home_page</th>\n",
|
||
" <th>title</th>\n",
|
||
" <th>oai_pmh</th>\n",
|
||
" <th>sword_endpoint</th>\n",
|
||
" <th>rss_feed</th>\n",
|
||
" <th>twitter_feed</th>\n",
|
||
" <th>description</th>\n",
|
||
" <th>fulltext</th>\n",
|
||
" <th>open_access</th>\n",
|
||
" <th>mandate</th>\n",
|
||
" <th>organisation_title</th>\n",
|
||
" <th>organisation_home_page</th>\n",
|
||
" <th>location_country</th>\n",
|
||
" <th>location_city</th>\n",
|
||
" <th>location_latitude</th>\n",
|
||
" <th>location_longitude</th>\n",
|
||
" <th>software</th>\n",
|
||
" <th>geoname</th>\n",
|
||
" <th>version</th>\n",
|
||
" <th>subjects</th>\n",
|
||
" <th>date</th>\n",
|
||
" <th>note</th>\n",
|
||
" <th>suggestions</th>\n",
|
||
" <th>activity_low</th>\n",
|
||
" <th>activity_medium</th>\n",
|
||
" <th>activity_high</th>\n",
|
||
" <th>recordcount</th>\n",
|
||
" <th>recordhistory</th>\n",
|
||
" <th>fulltexts_total</th>\n",
|
||
" <th>fulltexts_docs</th>\n",
|
||
" <th>fulltexts_rtotal</th>\n",
|
||
" <th>fulltexts_rdocs</th>\n",
|
||
" <th>registry_name</th>\n",
|
||
" <th>registry_id</th>\n",
|
||
" <th>submit_to</th>\n",
|
||
" <th>submitted_to_name</th>\n",
|
||
" <th>submitted_to_done</th>\n",
|
||
" <th>webometrics_rank</th>\n",
|
||
" <th>webometrics_size</th>\n",
|
||
" <th>webometrics_visibility</th>\n",
|
||
" <th>webometrics_rich_files</th>\n",
|
||
" <th>webometrics_scholar</th>\n",
|
||
" <th>monthly_deposits</th>\n",
|
||
" <th>total_deposits</th>\n",
|
||
" <th>association</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>4167</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>28</td>\n",
|
||
" <td>archive</td>\n",
|
||
" <td>1380</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>disk0/00/00/46/12</td>\n",
|
||
" <td>2012-01-08 03:17:02</td>\n",
|
||
" <td>2012-04-16 10:53:04</td>\n",
|
||
" <td>2012-01-08 03:17:02</td>\n",
|
||
" <td>institutional</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>show</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>http://dspace.library.iitb.ac.in/jspui/</td>\n",
|
||
" <td>IIT Bombay Institutional Repository</td>\n",
|
||
" <td>http://dspace.library.iitb.ac.in/oai/request</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>http://dspace.library.iitb.ac.in/xmlui/feed/at...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TRUE</td>\n",
|
||
" <td>TRUE</td>\n",
|
||
" <td>TRUE</td>\n",
|
||
" <td>IIT Bombay</td>\n",
|
||
" <td>http://www.iitb.ac.in</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Mumbai</td>\n",
|
||
" <td>19.133</td>\n",
|
||
" <td>72.9166</td>\n",
|
||
" <td>dspace</td>\n",
|
||
" <td>geoname_2_IN</td>\n",
|
||
" <td>other</td>\n",
|
||
" <td>TA</td>\n",
|
||
" <td>2011-12-15 09:01:35</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>99</td>\n",
|
||
" <td>0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,95,9...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>celestial</td>\n",
|
||
" <td>4790</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4168</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TD</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4169</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TH</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4170</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TJ</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4171</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TK</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4172</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4173</th>\n",
|
||
" <td>4612</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TP</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>16436</th>\n",
|
||
" <td>4649</td>\n",
|
||
" <td>8</td>\n",
|
||
" <td>archive</td>\n",
|
||
" <td>1380</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>disk0/00/00/46/49</td>\n",
|
||
" <td>2012-02-05 13:57:01</td>\n",
|
||
" <td>2012-04-16 10:39:58</td>\n",
|
||
" <td>2012-02-05 13:57:01</td>\n",
|
||
" <td>institutional</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>show</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>http://dspace.library.iitb.ac.in/jspui/</td>\n",
|
||
" <td>IIT Bombay Institutional Repository</td>\n",
|
||
" <td>http://dspace.library.iitb.ac.in/oai</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>http://dspace.library.iitb.ac.in/xmlui/feed/rs...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TRUE</td>\n",
|
||
" <td>TRUE</td>\n",
|
||
" <td>FALSE</td>\n",
|
||
" <td>IIT Bombay</td>\n",
|
||
" <td>http://www.iitb.ac.in</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Mumbai</td>\n",
|
||
" <td>19.133</td>\n",
|
||
" <td>72.9166</td>\n",
|
||
" <td>dspace</td>\n",
|
||
" <td>geoname_2_IN</td>\n",
|
||
" <td>other</td>\n",
|
||
" <td>T1</td>\n",
|
||
" <td>2012-01-05 12:09:37</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>celestial</td>\n",
|
||
" <td>4789</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>16437</th>\n",
|
||
" <td>4649</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>TA</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" eprintid rev_number eprint_status userid importid source \\\n",
|
||
"4167 4612 28 archive 1380 NaN NaN \n",
|
||
"4168 4612 NaN NaN NaN NaN NaN \n",
|
||
"4169 4612 NaN NaN NaN NaN NaN \n",
|
||
"4170 4612 NaN NaN NaN NaN NaN \n",
|
||
"4171 4612 NaN NaN NaN NaN NaN \n",
|
||
"4172 4612 NaN NaN NaN NaN NaN \n",
|
||
"4173 4612 NaN NaN NaN NaN NaN \n",
|
||
"16436 4649 8 archive 1380 NaN NaN \n",
|
||
"16437 4649 NaN NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" dir datestamp lastmod \\\n",
|
||
"4167 disk0/00/00/46/12 2012-01-08 03:17:02 2012-04-16 10:53:04 \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 disk0/00/00/46/49 2012-02-05 13:57:01 2012-04-16 10:39:58 \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" status_changed type succeeds commentary \\\n",
|
||
"4167 2012-01-08 03:17:02 institutional NaN NaN \n",
|
||
"4168 NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN \n",
|
||
"16436 2012-02-05 13:57:01 institutional NaN NaN \n",
|
||
"16437 NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" metadata_visibility latitude longitude relation_type relation_uri \\\n",
|
||
"4167 show NaN NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN NaN \n",
|
||
"16436 show NaN NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" item_issues_id item_issues_type item_issues_description \\\n",
|
||
"4167 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" item_issues_timestamp item_issues_status item_issues_reported_by \\\n",
|
||
"4167 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" item_issues_resolved_by item_issues_comment item_issues_count \\\n",
|
||
"4167 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" sword_depositor sword_slug exemplar \\\n",
|
||
"4167 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" home_page \\\n",
|
||
"4167 http://dspace.library.iitb.ac.in/jspui/ \n",
|
||
"4168 NaN \n",
|
||
"4169 NaN \n",
|
||
"4170 NaN \n",
|
||
"4171 NaN \n",
|
||
"4172 NaN \n",
|
||
"4173 NaN \n",
|
||
"16436 http://dspace.library.iitb.ac.in/jspui/ \n",
|
||
"16437 NaN \n",
|
||
"\n",
|
||
" title \\\n",
|
||
"4167 IIT Bombay Institutional Repository \n",
|
||
"4168 NaN \n",
|
||
"4169 NaN \n",
|
||
"4170 NaN \n",
|
||
"4171 NaN \n",
|
||
"4172 NaN \n",
|
||
"4173 NaN \n",
|
||
"16436 IIT Bombay Institutional Repository \n",
|
||
"16437 NaN \n",
|
||
"\n",
|
||
" oai_pmh sword_endpoint \\\n",
|
||
"4167 http://dspace.library.iitb.ac.in/oai/request NaN \n",
|
||
"4168 NaN NaN \n",
|
||
"4169 NaN NaN \n",
|
||
"4170 NaN NaN \n",
|
||
"4171 NaN NaN \n",
|
||
"4172 NaN NaN \n",
|
||
"4173 NaN NaN \n",
|
||
"16436 http://dspace.library.iitb.ac.in/oai NaN \n",
|
||
"16437 NaN NaN \n",
|
||
"\n",
|
||
" rss_feed twitter_feed \\\n",
|
||
"4167 http://dspace.library.iitb.ac.in/xmlui/feed/at... NaN \n",
|
||
"4168 NaN NaN \n",
|
||
"4169 NaN NaN \n",
|
||
"4170 NaN NaN \n",
|
||
"4171 NaN NaN \n",
|
||
"4172 NaN NaN \n",
|
||
"4173 NaN NaN \n",
|
||
"16436 http://dspace.library.iitb.ac.in/xmlui/feed/rs... NaN \n",
|
||
"16437 NaN NaN \n",
|
||
"\n",
|
||
" description fulltext open_access mandate organisation_title \\\n",
|
||
"4167 NaN TRUE TRUE TRUE IIT Bombay \n",
|
||
"4168 NaN NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN NaN \n",
|
||
"16436 NaN TRUE TRUE FALSE IIT Bombay \n",
|
||
"16437 NaN NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" organisation_home_page location_country location_city location_latitude \\\n",
|
||
"4167 http://www.iitb.ac.in in Mumbai 19.133 \n",
|
||
"4168 NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN \n",
|
||
"16436 http://www.iitb.ac.in in Mumbai 19.133 \n",
|
||
"16437 NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" location_longitude software geoname version subjects \\\n",
|
||
"4167 72.9166 dspace geoname_2_IN other TA \n",
|
||
"4168 NaN NaN NaN NaN TD \n",
|
||
"4169 NaN NaN NaN NaN TH \n",
|
||
"4170 NaN NaN NaN NaN TJ \n",
|
||
"4171 NaN NaN NaN NaN TK \n",
|
||
"4172 NaN NaN NaN NaN TN \n",
|
||
"4173 NaN NaN NaN NaN TP \n",
|
||
"16436 72.9166 dspace geoname_2_IN other T1 \n",
|
||
"16437 NaN NaN NaN NaN TA \n",
|
||
"\n",
|
||
" date note suggestions activity_low activity_medium \\\n",
|
||
"4167 2011-12-15 09:01:35 NaN NaN 0 0 \n",
|
||
"4168 NaN NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN NaN \n",
|
||
"16436 2012-01-05 12:09:37 NaN NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" activity_high recordcount \\\n",
|
||
"4167 0 99 \n",
|
||
"4168 NaN NaN \n",
|
||
"4169 NaN NaN \n",
|
||
"4170 NaN NaN \n",
|
||
"4171 NaN NaN \n",
|
||
"4172 NaN NaN \n",
|
||
"4173 NaN NaN \n",
|
||
"16436 NaN NaN \n",
|
||
"16437 NaN NaN \n",
|
||
"\n",
|
||
" recordhistory fulltexts_total \\\n",
|
||
"4167 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,95,9... NaN \n",
|
||
"4168 NaN NaN \n",
|
||
"4169 NaN NaN \n",
|
||
"4170 NaN NaN \n",
|
||
"4171 NaN NaN \n",
|
||
"4172 NaN NaN \n",
|
||
"4173 NaN NaN \n",
|
||
"16436 NaN NaN \n",
|
||
"16437 NaN NaN \n",
|
||
"\n",
|
||
" fulltexts_docs fulltexts_rtotal fulltexts_rdocs registry_name \\\n",
|
||
"4167 NaN NaN NaN celestial \n",
|
||
"4168 NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN celestial \n",
|
||
"16437 NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" registry_id submit_to submitted_to_name submitted_to_done \\\n",
|
||
"4167 4790 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN NaN \n",
|
||
"16436 4789 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" webometrics_rank webometrics_size webometrics_visibility \\\n",
|
||
"4167 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" webometrics_rich_files webometrics_scholar monthly_deposits \\\n",
|
||
"4167 NaN NaN NaN \n",
|
||
"4168 NaN NaN NaN \n",
|
||
"4169 NaN NaN NaN \n",
|
||
"4170 NaN NaN NaN \n",
|
||
"4171 NaN NaN NaN \n",
|
||
"4172 NaN NaN NaN \n",
|
||
"4173 NaN NaN NaN \n",
|
||
"16436 NaN NaN NaN \n",
|
||
"16437 NaN NaN NaN \n",
|
||
"\n",
|
||
" total_deposits association \n",
|
||
"4167 NaN NaN \n",
|
||
"4168 NaN NaN \n",
|
||
"4169 NaN NaN \n",
|
||
"4170 NaN NaN \n",
|
||
"4171 NaN NaN \n",
|
||
"4172 NaN NaN \n",
|
||
"4173 NaN NaN \n",
|
||
"16436 NaN NaN \n",
|
||
"16437 NaN NaN "
|
||
]
|
||
},
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"roar_df[roar_df.eprintid.isin(['4612', '4649'])]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"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>openaire_id</th>\n",
|
||
" <th>re3data_id</th>\n",
|
||
" <th>repository_name</th>\n",
|
||
" <th>additional_name</th>\n",
|
||
" <th>repository_url</th>\n",
|
||
" <th>repository_id</th>\n",
|
||
" <th>description</th>\n",
|
||
" <th>type</th>\n",
|
||
" <th>size</th>\n",
|
||
" <th>update_date</th>\n",
|
||
" <th>start_date</th>\n",
|
||
" <th>end_date</th>\n",
|
||
" <th>subject</th>\n",
|
||
" <th>mission_statement</th>\n",
|
||
" <th>content_type</th>\n",
|
||
" <th>provider_type</th>\n",
|
||
" <th>keyword</th>\n",
|
||
" <th>institution</th>\n",
|
||
" <th>policy</th>\n",
|
||
" <th>database_access</th>\n",
|
||
" <th>database_license</th>\n",
|
||
" <th>data_access</th>\n",
|
||
" <th>data_license</th>\n",
|
||
" <th>data_upload</th>\n",
|
||
" <th>data_upload_license</th>\n",
|
||
" <th>software</th>\n",
|
||
" <th>versioning</th>\n",
|
||
" <th>api</th>\n",
|
||
" <th>pid_system</th>\n",
|
||
" <th>citation_guideline_url</th>\n",
|
||
" <th>aid_system</th>\n",
|
||
" <th>enhanced_publication</th>\n",
|
||
" <th>quality_management</th>\n",
|
||
" <th>certificate</th>\n",
|
||
" <th>metadata_standard</th>\n",
|
||
" <th>syndication</th>\n",
|
||
" <th>remarks</th>\n",
|
||
" <th>entry_date</th>\n",
|
||
" <th>last_update</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>1090</th>\n",
|
||
" <td>re3data_____::4af9fe2bb93511a5e0f0c39e94d6557f</td>\n",
|
||
" <td>r3d100011306</td>\n",
|
||
" <td>RESID Database of Protein Modifications</td>\n",
|
||
" <td>[]</td>\n",
|
||
" <td>https://pir.georgetown.edu/resid/resid.shtml</td>\n",
|
||
" <td>[FAIRsharing_doi:10.25504/FAIRsharing.qaszjp, ...</td>\n",
|
||
" <td>The RESID Database of Protein Modifications is...</td>\n",
|
||
" <td>[disciplinary]</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>2014</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>[2 Life Sciences, 201 Basic Biological and Med...</td>\n",
|
||
" <td>false</td>\n",
|
||
" <td>[Images, Structured text]</td>\n",
|
||
" <td>[dataProvider]</td>\n",
|
||
" <td>[genomes, life sciences, proteins, proteomes, ...</td>\n",
|
||
" <td>[[Georgetown University, Medical Center, [GUMC...</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>false</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>false</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>true</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>unknown</td>\n",
|
||
" <td>false</td>\n",
|
||
" <td>false</td>\n",
|
||
" <td>false</td>\n",
|
||
" <td>RESID is covered by Thomson Reuters Data Citat...</td>\n",
|
||
" <td>2014-12-05</td>\n",
|
||
" <td>2019-01-17</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" openaire_id re3data_id \\\n",
|
||
"1090 re3data_____::4af9fe2bb93511a5e0f0c39e94d6557f r3d100011306 \n",
|
||
"\n",
|
||
" repository_name additional_name \\\n",
|
||
"1090 RESID Database of Protein Modifications [] \n",
|
||
"\n",
|
||
" repository_url \\\n",
|
||
"1090 https://pir.georgetown.edu/resid/resid.shtml \n",
|
||
"\n",
|
||
" repository_id \\\n",
|
||
"1090 [FAIRsharing_doi:10.25504/FAIRsharing.qaszjp, ... \n",
|
||
"\n",
|
||
" description type size \\\n",
|
||
"1090 The RESID Database of Protein Modifications is... [disciplinary] NaN \n",
|
||
"\n",
|
||
" update_date start_date end_date \\\n",
|
||
"1090 NaN 2014 NaN \n",
|
||
"\n",
|
||
" subject mission_statement \\\n",
|
||
"1090 [2 Life Sciences, 201 Basic Biological and Med... false \n",
|
||
"\n",
|
||
" content_type provider_type \\\n",
|
||
"1090 [Images, Structured text] [dataProvider] \n",
|
||
"\n",
|
||
" keyword \\\n",
|
||
"1090 [genomes, life sciences, proteins, proteomes, ... \n",
|
||
"\n",
|
||
" institution policy \\\n",
|
||
"1090 [[Georgetown University, Medical Center, [GUMC... true \n",
|
||
"\n",
|
||
" database_access database_license data_access data_license data_upload \\\n",
|
||
"1090 true false true true true \n",
|
||
"\n",
|
||
" data_upload_license software versioning api pid_system \\\n",
|
||
"1090 false true yes true true \n",
|
||
"\n",
|
||
" citation_guideline_url aid_system enhanced_publication \\\n",
|
||
"1090 true true yes \n",
|
||
"\n",
|
||
" quality_management certificate metadata_standard syndication \\\n",
|
||
"1090 unknown false false false \n",
|
||
"\n",
|
||
" remarks entry_date \\\n",
|
||
"1090 RESID is covered by Thomson Reuters Data Citat... 2014-12-05 \n",
|
||
"\n",
|
||
" last_update \n",
|
||
"1090 2019-01-17 "
|
||
]
|
||
},
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"re3data_df[re3data_df.re3data_id == 'r3d100011306']"
|
||
]
|
||
},
|
||
{
|
||
"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
|
||
}
|