[1bd6b5]: / notebooks / Journals.ipynb

Download this file

1732 lines (1731 with data), 71.8 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%run notebook_setup.ipynb"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Science Citation Index Expanded (SCIE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Web of Science Core Collection, Last Updated: June 18, 2020, downloaded from https://mjl.clarivate.com/collection-list-downloads on 2020-06-23"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pandas import read_csv, DataFrame\n",
    "\n",
    "web_of_science_journals = read_csv('data/wos-core_SCIE.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Journal title</th>\n",
       "      <th>ISSN</th>\n",
       "      <th>eISSN</th>\n",
       "      <th>Publisher name</th>\n",
       "      <th>Publisher address</th>\n",
       "      <th>Languages</th>\n",
       "      <th>Web of Science Categories</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2D MATERIALS</td>\n",
       "      <td>2053-1583</td>\n",
       "      <td>2053-1583</td>\n",
       "      <td>IOP PUBLISHING LTD</td>\n",
       "      <td>TEMPLE CIRCUS, TEMPLE WAY, BRISTOL, ENGLAND, B...</td>\n",
       "      <td>English</td>\n",
       "      <td>Materials Science, Multidisciplinary</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3 BIOTECH</td>\n",
       "      <td>2190-572X</td>\n",
       "      <td>2190-5738</td>\n",
       "      <td>SPRINGER HEIDELBERG</td>\n",
       "      <td>TIERGARTENSTRASSE 17, HEIDELBERG, GERMANY, D-6...</td>\n",
       "      <td>English</td>\n",
       "      <td>Biotechnology &amp; Applied Microbiology</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3D PRINTING AND ADDITIVE MANUFACTURING</td>\n",
       "      <td>2329-7662</td>\n",
       "      <td>2329-7670</td>\n",
       "      <td>MARY ANN LIEBERT, INC</td>\n",
       "      <td>140 HUGUENOT STREET, 3RD FL, NEW ROCHELLE, USA...</td>\n",
       "      <td>English</td>\n",
       "      <td>Materials Science, Multidisciplinary | Enginee...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4OR-A QUARTERLY JOURNAL OF OPERATIONS RESEARCH</td>\n",
       "      <td>1619-4500</td>\n",
       "      <td>1614-2411</td>\n",
       "      <td>SPRINGER HEIDELBERG</td>\n",
       "      <td>TIERGARTENSTRASSE 17, HEIDELBERG, GERMANY, D-6...</td>\n",
       "      <td>English</td>\n",
       "      <td>Operations Research &amp; Management Science</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AAPG BULLETIN</td>\n",
       "      <td>0149-1423</td>\n",
       "      <td>1558-9153</td>\n",
       "      <td>AMER ASSOC PETROLEUM GEOLOGIST</td>\n",
       "      <td>1444 S BOULDER AVE, PO BOX 979, TULSA, USA, OK...</td>\n",
       "      <td>English</td>\n",
       "      <td>Geosciences, Multidisciplinary</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>9388</th>\n",
       "      <td>ZOOSYSTEMA</td>\n",
       "      <td>1280-9551</td>\n",
       "      <td>1638-9387</td>\n",
       "      <td>PUBLICATIONS SCIENTIFIQUES DU MUSEUM, PARIS</td>\n",
       "      <td>CP 39-57, RUE CUVIER, PARIS CEDEX 05, FRANCE, ...</td>\n",
       "      <td>English</td>\n",
       "      <td>Zoology</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9389</th>\n",
       "      <td>ZOOSYSTEMATICS AND EVOLUTION</td>\n",
       "      <td>1860-0743</td>\n",
       "      <td>1860-0743</td>\n",
       "      <td>PENSOFT PUBLISHERS</td>\n",
       "      <td>12 PROF GEORGI ZLATARSKI ST, SOFIA, BULGARIA, ...</td>\n",
       "      <td>English</td>\n",
       "      <td>Zoology</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9390</th>\n",
       "      <td>ZOOTAXA</td>\n",
       "      <td>1175-5326</td>\n",
       "      <td>1175-5334</td>\n",
       "      <td>MAGNOLIA PRESS</td>\n",
       "      <td>PO BOX 41383, AUCKLAND, NEW ZEALAND, ST LUKES,...</td>\n",
       "      <td>English</td>\n",
       "      <td>Zoology</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9391</th>\n",
       "      <td>ZUCHTUNGSKUNDE</td>\n",
       "      <td>0044-5401</td>\n",
       "      <td>1867-4518</td>\n",
       "      <td>EUGEN ULMER GMBH CO</td>\n",
       "      <td>POSTFACH 700561 WOLLGRASWEG 41, STUTTGART, GER...</td>\n",
       "      <td>German</td>\n",
       "      <td>Agriculture, Dairy &amp; Animal Science</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9392</th>\n",
       "      <td>ZYGOTE</td>\n",
       "      <td>0967-1994</td>\n",
       "      <td>1469-8730</td>\n",
       "      <td>CAMBRIDGE UNIV PRESS</td>\n",
       "      <td>32 AVENUE OF THE AMERICAS, NEW YORK, USA, NY, ...</td>\n",
       "      <td>English</td>\n",
       "      <td>Developmental Biology | Cell Biology | Reprodu...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9393 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       Journal title       ISSN      eISSN  \\\n",
       "0                                       2D MATERIALS  2053-1583  2053-1583   \n",
       "1                                          3 BIOTECH  2190-572X  2190-5738   \n",
       "2             3D PRINTING AND ADDITIVE MANUFACTURING  2329-7662  2329-7670   \n",
       "3     4OR-A QUARTERLY JOURNAL OF OPERATIONS RESEARCH  1619-4500  1614-2411   \n",
       "4                                      AAPG BULLETIN  0149-1423  1558-9153   \n",
       "...                                              ...        ...        ...   \n",
       "9388                                      ZOOSYSTEMA  1280-9551  1638-9387   \n",
       "9389                    ZOOSYSTEMATICS AND EVOLUTION  1860-0743  1860-0743   \n",
       "9390                                         ZOOTAXA  1175-5326  1175-5334   \n",
       "9391                                  ZUCHTUNGSKUNDE  0044-5401  1867-4518   \n",
       "9392                                          ZYGOTE  0967-1994  1469-8730   \n",
       "\n",
       "                                   Publisher name  \\\n",
       "0                              IOP PUBLISHING LTD   \n",
       "1                             SPRINGER HEIDELBERG   \n",
       "2                           MARY ANN LIEBERT, INC   \n",
       "3                             SPRINGER HEIDELBERG   \n",
       "4                  AMER ASSOC PETROLEUM GEOLOGIST   \n",
       "...                                           ...   \n",
       "9388  PUBLICATIONS SCIENTIFIQUES DU MUSEUM, PARIS   \n",
       "9389                           PENSOFT PUBLISHERS   \n",
       "9390                               MAGNOLIA PRESS   \n",
       "9391                          EUGEN ULMER GMBH CO   \n",
       "9392                         CAMBRIDGE UNIV PRESS   \n",
       "\n",
       "                                      Publisher address Languages  \\\n",
       "0     TEMPLE CIRCUS, TEMPLE WAY, BRISTOL, ENGLAND, B...   English   \n",
       "1     TIERGARTENSTRASSE 17, HEIDELBERG, GERMANY, D-6...   English   \n",
       "2     140 HUGUENOT STREET, 3RD FL, NEW ROCHELLE, USA...   English   \n",
       "3     TIERGARTENSTRASSE 17, HEIDELBERG, GERMANY, D-6...   English   \n",
       "4     1444 S BOULDER AVE, PO BOX 979, TULSA, USA, OK...   English   \n",
       "...                                                 ...       ...   \n",
       "9388  CP 39-57, RUE CUVIER, PARIS CEDEX 05, FRANCE, ...   English   \n",
       "9389  12 PROF GEORGI ZLATARSKI ST, SOFIA, BULGARIA, ...   English   \n",
       "9390  PO BOX 41383, AUCKLAND, NEW ZEALAND, ST LUKES,...   English   \n",
       "9391  POSTFACH 700561 WOLLGRASWEG 41, STUTTGART, GER...    German   \n",
       "9392  32 AVENUE OF THE AMERICAS, NEW YORK, USA, NY, ...   English   \n",
       "\n",
       "                              Web of Science Categories  \n",
       "0                  Materials Science, Multidisciplinary  \n",
       "1                  Biotechnology & Applied Microbiology  \n",
       "2     Materials Science, Multidisciplinary | Enginee...  \n",
       "3              Operations Research & Management Science  \n",
       "4                        Geosciences, Multidisciplinary  \n",
       "...                                                 ...  \n",
       "9388                                            Zoology  \n",
       "9389                                            Zoology  \n",
       "9390                                            Zoology  \n",
       "9391                Agriculture, Dairy & Animal Science  \n",
       "9392  Developmental Biology | Cell Biology | Reprodu...  \n",
       "\n",
       "[9393 rows x 7 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "web_of_science_journals"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### SCImago Journal Rank"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Downloaded from https://www.scimagojr.com/journalrank.php?out=xls on 2020-06-23"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Rank</th>\n",
       "      <th>Sourceid</th>\n",
       "      <th>Title</th>\n",
       "      <th>Type</th>\n",
       "      <th>Issn</th>\n",
       "      <th>SJR</th>\n",
       "      <th>SJR Best Quartile</th>\n",
       "      <th>H index</th>\n",
       "      <th>Total Docs. (2019)</th>\n",
       "      <th>Total Docs. (3years)</th>\n",
       "      <th>Total Refs.</th>\n",
       "      <th>Total Cites (3years)</th>\n",
       "      <th>Citable Docs. (3years)</th>\n",
       "      <th>Cites / Doc. (2years)</th>\n",
       "      <th>Ref. / Doc.</th>\n",
       "      <th>Country</th>\n",
       "      <th>Region</th>\n",
       "      <th>Publisher</th>\n",
       "      <th>Coverage</th>\n",
       "      <th>Categories</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>28773</td>\n",
       "      <td>CA - A Cancer Journal for Clinicians</td>\n",
       "      <td>journal</td>\n",
       "      <td>15424863, 00079235</td>\n",
       "      <td>88,192</td>\n",
       "      <td>Q1</td>\n",
       "      <td>156</td>\n",
       "      <td>36</td>\n",
       "      <td>129</td>\n",
       "      <td>2924</td>\n",
       "      <td>22644</td>\n",
       "      <td>89</td>\n",
       "      <td>255,73</td>\n",
       "      <td>81,22</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Wiley-Blackwell</td>\n",
       "      <td>1950-2020</td>\n",
       "      <td>Hematology (Q1); Oncology (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>19434</td>\n",
       "      <td>MMWR. Recommendations and reports : Morbidity ...</td>\n",
       "      <td>journal</td>\n",
       "      <td>10575987, 15458601</td>\n",
       "      <td>41,022</td>\n",
       "      <td>Q1</td>\n",
       "      <td>138</td>\n",
       "      <td>4</td>\n",
       "      <td>11</td>\n",
       "      <td>144</td>\n",
       "      <td>898</td>\n",
       "      <td>11</td>\n",
       "      <td>52,00</td>\n",
       "      <td>36,00</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Centers for Disease Control and Prevention (CDC)</td>\n",
       "      <td>1990-2020</td>\n",
       "      <td>Epidemiology (Q1); Health Information Manageme...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>21100812243</td>\n",
       "      <td>Nature Reviews Materials</td>\n",
       "      <td>journal</td>\n",
       "      <td>20588437</td>\n",
       "      <td>36,691</td>\n",
       "      <td>Q1</td>\n",
       "      <td>80</td>\n",
       "      <td>85</td>\n",
       "      <td>288</td>\n",
       "      <td>8534</td>\n",
       "      <td>12569</td>\n",
       "      <td>151</td>\n",
       "      <td>68,34</td>\n",
       "      <td>100,40</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Western Europe</td>\n",
       "      <td>Nature Publishing Group</td>\n",
       "      <td>2016-2020</td>\n",
       "      <td>Biomaterials (Q1); Electronic, Optical and Mag...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>29431</td>\n",
       "      <td>Quarterly Journal of Economics</td>\n",
       "      <td>journal</td>\n",
       "      <td>00335533, 15314650</td>\n",
       "      <td>36,220</td>\n",
       "      <td>Q1</td>\n",
       "      <td>246</td>\n",
       "      <td>30</td>\n",
       "      <td>123</td>\n",
       "      <td>1909</td>\n",
       "      <td>2020</td>\n",
       "      <td>119</td>\n",
       "      <td>12,65</td>\n",
       "      <td>63,63</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Western Europe</td>\n",
       "      <td>Oxford University Press</td>\n",
       "      <td>1886-2020</td>\n",
       "      <td>Economics and Econometrics (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>20315</td>\n",
       "      <td>Nature Reviews Molecular Cell Biology</td>\n",
       "      <td>journal</td>\n",
       "      <td>14710072, 14710080</td>\n",
       "      <td>29,997</td>\n",
       "      <td>Q1</td>\n",
       "      <td>411</td>\n",
       "      <td>115</td>\n",
       "      <td>382</td>\n",
       "      <td>9251</td>\n",
       "      <td>8074</td>\n",
       "      <td>182</td>\n",
       "      <td>47,70</td>\n",
       "      <td>80,44</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Western Europe</td>\n",
       "      <td>Nature Publishing Group</td>\n",
       "      <td>2000-2020</td>\n",
       "      <td>Cell Biology (Q1); Molecular Biology (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>58530</td>\n",
       "      <td>National vital statistics reports : from the C...</td>\n",
       "      <td>book series</td>\n",
       "      <td>15518922, 15518930</td>\n",
       "      <td>29,810</td>\n",
       "      <td>Q1</td>\n",
       "      <td>95</td>\n",
       "      <td>14</td>\n",
       "      <td>30</td>\n",
       "      <td>379</td>\n",
       "      <td>1059</td>\n",
       "      <td>30</td>\n",
       "      <td>41,61</td>\n",
       "      <td>27,07</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Public Health Services, US Dept of Health and ...</td>\n",
       "      <td>1998-2020</td>\n",
       "      <td>Life-span and Life-course Studies (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>18991</td>\n",
       "      <td>Nature Reviews Genetics</td>\n",
       "      <td>journal</td>\n",
       "      <td>14710056, 14710064</td>\n",
       "      <td>28,619</td>\n",
       "      <td>Q1</td>\n",
       "      <td>345</td>\n",
       "      <td>113</td>\n",
       "      <td>376</td>\n",
       "      <td>8586</td>\n",
       "      <td>6416</td>\n",
       "      <td>154</td>\n",
       "      <td>32,21</td>\n",
       "      <td>75,98</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Western Europe</td>\n",
       "      <td>Nature Publishing Group</td>\n",
       "      <td>2000-2020</td>\n",
       "      <td>Genetics (Q1); Genetics (clinical) (Q1); Molec...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>18434</td>\n",
       "      <td>Cell</td>\n",
       "      <td>journal</td>\n",
       "      <td>00928674, 10974172</td>\n",
       "      <td>24,698</td>\n",
       "      <td>Q1</td>\n",
       "      <td>747</td>\n",
       "      <td>581</td>\n",
       "      <td>1881</td>\n",
       "      <td>34924</td>\n",
       "      <td>49252</td>\n",
       "      <td>1630</td>\n",
       "      <td>30,16</td>\n",
       "      <td>60,11</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Cell Press</td>\n",
       "      <td>1974-2020</td>\n",
       "      <td>Biochemistry, Genetics and Molecular Biology (...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>29719</td>\n",
       "      <td>Reviews of Modern Physics</td>\n",
       "      <td>journal</td>\n",
       "      <td>00346861, 15390756</td>\n",
       "      <td>21,938</td>\n",
       "      <td>Q1</td>\n",
       "      <td>316</td>\n",
       "      <td>40</td>\n",
       "      <td>131</td>\n",
       "      <td>11080</td>\n",
       "      <td>5583</td>\n",
       "      <td>121</td>\n",
       "      <td>45,73</td>\n",
       "      <td>277,00</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>American Physical Society</td>\n",
       "      <td>1929-2019</td>\n",
       "      <td>Physics and Astronomy (miscellaneous) (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>12464</td>\n",
       "      <td>Nature Reviews Cancer</td>\n",
       "      <td>journal</td>\n",
       "      <td>1474175X, 14741768</td>\n",
       "      <td>21,287</td>\n",
       "      <td>Q1</td>\n",
       "      <td>418</td>\n",
       "      <td>138</td>\n",
       "      <td>366</td>\n",
       "      <td>7641</td>\n",
       "      <td>8532</td>\n",
       "      <td>204</td>\n",
       "      <td>37,77</td>\n",
       "      <td>55,37</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Western Europe</td>\n",
       "      <td>Nature Publishing Group</td>\n",
       "      <td>2001-2020</td>\n",
       "      <td>Cancer Research (Q1); Oncology (Q1)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Rank     Sourceid                                              Title  \\\n",
       "0     1        28773               CA - A Cancer Journal for Clinicians   \n",
       "1     2        19434  MMWR. Recommendations and reports : Morbidity ...   \n",
       "2     3  21100812243                           Nature Reviews Materials   \n",
       "3     4        29431                     Quarterly Journal of Economics   \n",
       "4     5        20315              Nature Reviews Molecular Cell Biology   \n",
       "5     6        58530  National vital statistics reports : from the C...   \n",
       "6     7        18991                            Nature Reviews Genetics   \n",
       "7     8        18434                                               Cell   \n",
       "8     9        29719                          Reviews of Modern Physics   \n",
       "9    10        12464                              Nature Reviews Cancer   \n",
       "\n",
       "          Type                Issn     SJR SJR Best Quartile  H index  \\\n",
       "0      journal  15424863, 00079235  88,192                Q1      156   \n",
       "1      journal  10575987, 15458601  41,022                Q1      138   \n",
       "2      journal            20588437  36,691                Q1       80   \n",
       "3      journal  00335533, 15314650  36,220                Q1      246   \n",
       "4      journal  14710072, 14710080  29,997                Q1      411   \n",
       "5  book series  15518922, 15518930  29,810                Q1       95   \n",
       "6      journal  14710056, 14710064  28,619                Q1      345   \n",
       "7      journal  00928674, 10974172  24,698                Q1      747   \n",
       "8      journal  00346861, 15390756  21,938                Q1      316   \n",
       "9      journal  1474175X, 14741768  21,287                Q1      418   \n",
       "\n",
       "   Total Docs. (2019)  Total Docs. (3years)  Total Refs.  \\\n",
       "0                  36                   129         2924   \n",
       "1                   4                    11          144   \n",
       "2                  85                   288         8534   \n",
       "3                  30                   123         1909   \n",
       "4                 115                   382         9251   \n",
       "5                  14                    30          379   \n",
       "6                 113                   376         8586   \n",
       "7                 581                  1881        34924   \n",
       "8                  40                   131        11080   \n",
       "9                 138                   366         7641   \n",
       "\n",
       "   Total Cites (3years)  Citable Docs. (3years) Cites / Doc. (2years)  \\\n",
       "0                 22644                      89                255,73   \n",
       "1                   898                      11                 52,00   \n",
       "2                 12569                     151                 68,34   \n",
       "3                  2020                     119                 12,65   \n",
       "4                  8074                     182                 47,70   \n",
       "5                  1059                      30                 41,61   \n",
       "6                  6416                     154                 32,21   \n",
       "7                 49252                    1630                 30,16   \n",
       "8                  5583                     121                 45,73   \n",
       "9                  8532                     204                 37,77   \n",
       "\n",
       "  Ref. / Doc.         Country            Region  \\\n",
       "0       81,22   United States  Northern America   \n",
       "1       36,00   United States  Northern America   \n",
       "2      100,40  United Kingdom    Western Europe   \n",
       "3       63,63  United Kingdom    Western Europe   \n",
       "4       80,44  United Kingdom    Western Europe   \n",
       "5       27,07   United States  Northern America   \n",
       "6       75,98  United Kingdom    Western Europe   \n",
       "7       60,11   United States  Northern America   \n",
       "8      277,00   United States  Northern America   \n",
       "9       55,37  United Kingdom    Western Europe   \n",
       "\n",
       "                                           Publisher   Coverage  \\\n",
       "0                                    Wiley-Blackwell  1950-2020   \n",
       "1   Centers for Disease Control and Prevention (CDC)  1990-2020   \n",
       "2                            Nature Publishing Group  2016-2020   \n",
       "3                            Oxford University Press  1886-2020   \n",
       "4                            Nature Publishing Group  2000-2020   \n",
       "5  Public Health Services, US Dept of Health and ...  1998-2020   \n",
       "6                            Nature Publishing Group  2000-2020   \n",
       "7                                         Cell Press  1974-2020   \n",
       "8                          American Physical Society  1929-2019   \n",
       "9                            Nature Publishing Group  2001-2020   \n",
       "\n",
       "                                          Categories  \n",
       "0                     Hematology (Q1); Oncology (Q1)  \n",
       "1  Epidemiology (Q1); Health Information Manageme...  \n",
       "2  Biomaterials (Q1); Electronic, Optical and Mag...  \n",
       "3                    Economics and Econometrics (Q1)  \n",
       "4          Cell Biology (Q1); Molecular Biology (Q1)  \n",
       "5             Life-span and Life-course Studies (Q1)  \n",
       "6  Genetics (Q1); Genetics (clinical) (Q1); Molec...  \n",
       "7  Biochemistry, Genetics and Molecular Biology (...  \n",
       "8         Physics and Astronomy (miscellaneous) (Q1)  \n",
       "9                Cancer Research (Q1); Oncology (Q1)  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scimago = read_csv('data/scimagojr 2019.csv', sep=';')\n",
    "scimago.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scimago.Title.duplicated().any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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 Pair ID</th>\n",
       "      <th>Title</th>\n",
       "      <th>Issn</th>\n",
       "      <th>SJR</th>\n",
       "      <th>H index</th>\n",
       "      <th>Country</th>\n",
       "      <th>Publisher</th>\n",
       "      <th>chosen</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Proceedings - Annual IEEE Symposium on Foundat...</td>\n",
       "      <td>02725428</td>\n",
       "      <td>3,203</td>\n",
       "      <td>89</td>\n",
       "      <td>France</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Proceedings - Annual IEEE Symposium on Foundat...</td>\n",
       "      <td>02725428</td>\n",
       "      <td>2,444</td>\n",
       "      <td>81</td>\n",
       "      <td>United States</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>Neurosurgery</td>\n",
       "      <td>15244040, 0148396X</td>\n",
       "      <td>1,530</td>\n",
       "      <td>192</td>\n",
       "      <td>United States</td>\n",
       "      <td>Lippincott Williams and Wilkins Ltd.</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>Clinical Neurosurgery</td>\n",
       "      <td>0148396X, 00694827</td>\n",
       "      <td>1,169</td>\n",
       "      <td>31</td>\n",
       "      <td>United States</td>\n",
       "      <td>Lippincott Williams and Wilkins Ltd.</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>Australian Journal of Psychology</td>\n",
       "      <td>00049530, 17429536</td>\n",
       "      <td>0,477</td>\n",
       "      <td>38</td>\n",
       "      <td>United States</td>\n",
       "      <td>Wiley-Blackwell</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2</td>\n",
       "      <td>Australian Journal of Political Science</td>\n",
       "      <td>10361146, 17429536</td>\n",
       "      <td>0,423</td>\n",
       "      <td>35</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Routledge</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3</td>\n",
       "      <td>Journal of Neuropathology and Experimental Neu...</td>\n",
       "      <td>15546578, 00223069</td>\n",
       "      <td>1,366</td>\n",
       "      <td>159</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Oxford University Press</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>3</td>\n",
       "      <td>American Journal of Psychotherapy</td>\n",
       "      <td>15546578, 00029564</td>\n",
       "      <td>0,326</td>\n",
       "      <td>35</td>\n",
       "      <td>United States</td>\n",
       "      <td>Association for the Advancement of Psychothera...</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>4</td>\n",
       "      <td>International Review of Aerospace Engineering</td>\n",
       "      <td>19737459, 25332279</td>\n",
       "      <td>0,618</td>\n",
       "      <td>14</td>\n",
       "      <td>Italy</td>\n",
       "      <td>Praise Worthy Prize S.r.l</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4</td>\n",
       "      <td>Chinese Journal of Physiology</td>\n",
       "      <td>03044920, 25332279</td>\n",
       "      <td>0,289</td>\n",
       "      <td>30</td>\n",
       "      <td>Taiwan</td>\n",
       "      <td>Chinese Physiological Society</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>5</td>\n",
       "      <td>International Journal of Engineering, Transact...</td>\n",
       "      <td>17359244, 17281431</td>\n",
       "      <td>0,395</td>\n",
       "      <td>15</td>\n",
       "      <td>Iran</td>\n",
       "      <td>Materials and Energy Research Center</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>5</td>\n",
       "      <td>International Journal of Engineering, Transact...</td>\n",
       "      <td>1728144X, 17359244</td>\n",
       "      <td>0,265</td>\n",
       "      <td>16</td>\n",
       "      <td>Iran</td>\n",
       "      <td>Materials and Energy Research Center</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>6</td>\n",
       "      <td>Smart Innovation, Systems and Technologies</td>\n",
       "      <td>21903026, 21903018</td>\n",
       "      <td>0,180</td>\n",
       "      <td>18</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Springer Verlag</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>6</td>\n",
       "      <td>6th International Conference on Research into ...</td>\n",
       "      <td>21903026, 21903018</td>\n",
       "      <td>0,167</td>\n",
       "      <td>4</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Springer Nature</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>7</td>\n",
       "      <td>Smart Innovation, Systems and Technologies</td>\n",
       "      <td>21903026, 21903018</td>\n",
       "      <td>0,180</td>\n",
       "      <td>18</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Springer Verlag</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>7</td>\n",
       "      <td>6th International Conference on Research into ...</td>\n",
       "      <td>21903026, 21903018</td>\n",
       "      <td>0,167</td>\n",
       "      <td>4</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Springer Nature</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>8</td>\n",
       "      <td>Proceedings of IEEE Sensors</td>\n",
       "      <td>19300395</td>\n",
       "      <td>0,173</td>\n",
       "      <td>9</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>8</td>\n",
       "      <td>Proceedings of IEEE Sensors</td>\n",
       "      <td>19300395</td>\n",
       "      <td>0,160</td>\n",
       "      <td>38</td>\n",
       "      <td>United States</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>9</td>\n",
       "      <td>Korean Journal of Microbiology and Biotechnology</td>\n",
       "      <td>22347305, 1598642X</td>\n",
       "      <td>0,162</td>\n",
       "      <td>16</td>\n",
       "      <td>South Korea</td>\n",
       "      <td>Korean Society for Microbiolog and Biotechnology</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>9</td>\n",
       "      <td>Microbiology and Biotechnology Letters</td>\n",
       "      <td>1598642X, 22347305</td>\n",
       "      <td>0,149</td>\n",
       "      <td>4</td>\n",
       "      <td>South Korea</td>\n",
       "      <td>Korean Society for Microbiolog and Biotechnology</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>10</td>\n",
       "      <td>Korean Journal of Microbiology and Biotechnology</td>\n",
       "      <td>22347305, 1598642X</td>\n",
       "      <td>0,162</td>\n",
       "      <td>16</td>\n",
       "      <td>South Korea</td>\n",
       "      <td>Korean Society for Microbiolog and Biotechnology</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>10</td>\n",
       "      <td>Microbiology and Biotechnology Letters</td>\n",
       "      <td>1598642X, 22347305</td>\n",
       "      <td>0,149</td>\n",
       "      <td>4</td>\n",
       "      <td>South Korea</td>\n",
       "      <td>Korean Society for Microbiolog and Biotechnology</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>11</td>\n",
       "      <td>Papers Presented at the Annual Conference - Ru...</td>\n",
       "      <td>07347464</td>\n",
       "      <td>0,135</td>\n",
       "      <td>12</td>\n",
       "      <td>United States</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>11</td>\n",
       "      <td>Papers - Rural Electric Power Conference</td>\n",
       "      <td>07347464</td>\n",
       "      <td>0,125</td>\n",
       "      <td>12</td>\n",
       "      <td>United States</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>12</td>\n",
       "      <td>Lloyd's Maritime Asia</td>\n",
       "      <td>02171120</td>\n",
       "      <td>0,113</td>\n",
       "      <td>0</td>\n",
       "      <td>Hong Kong</td>\n",
       "      <td>Lloyd's of London Press</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>12</td>\n",
       "      <td>MARIT. ASIA</td>\n",
       "      <td>02171120</td>\n",
       "      <td>0,108</td>\n",
       "      <td>0</td>\n",
       "      <td>China</td>\n",
       "      <td>Lloyd's of London Press</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>13</td>\n",
       "      <td>Clinical and Experimental Optometry</td>\n",
       "      <td>14440938, 08164622</td>\n",
       "      <td>0,752</td>\n",
       "      <td>51</td>\n",
       "      <td>United States</td>\n",
       "      <td>Wiley-Blackwell</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>13</td>\n",
       "      <td>The Australasian journal of optometry</td>\n",
       "      <td>0817881X, 14440938</td>\n",
       "      <td>0,108</td>\n",
       "      <td>1</td>\n",
       "      <td>Australia</td>\n",
       "      <td>Optometrists Association Australia</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>14</td>\n",
       "      <td>Journal fur Pharmakologie und Therapie</td>\n",
       "      <td>14324334</td>\n",
       "      <td>0,101</td>\n",
       "      <td>2</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Verlag Perfusion GmbH</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>14</td>\n",
       "      <td>Perfusion (Germany)</td>\n",
       "      <td>14324334, 09350020</td>\n",
       "      <td>0,100</td>\n",
       "      <td>7</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Verlag Perfusion GmbH</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Duplicate Pair ID                                              Title  \\\n",
       "0                   0  Proceedings - Annual IEEE Symposium on Foundat...   \n",
       "1                   0  Proceedings - Annual IEEE Symposium on Foundat...   \n",
       "2                   1                                       Neurosurgery   \n",
       "3                   1                              Clinical Neurosurgery   \n",
       "4                   2                   Australian Journal of Psychology   \n",
       "5                   2            Australian Journal of Political Science   \n",
       "6                   3  Journal of Neuropathology and Experimental Neu...   \n",
       "7                   3                  American Journal of Psychotherapy   \n",
       "8                   4      International Review of Aerospace Engineering   \n",
       "9                   4                      Chinese Journal of Physiology   \n",
       "10                  5  International Journal of Engineering, Transact...   \n",
       "11                  5  International Journal of Engineering, Transact...   \n",
       "12                  6         Smart Innovation, Systems and Technologies   \n",
       "13                  6  6th International Conference on Research into ...   \n",
       "14                  7         Smart Innovation, Systems and Technologies   \n",
       "15                  7  6th International Conference on Research into ...   \n",
       "16                  8                        Proceedings of IEEE Sensors   \n",
       "17                  8                        Proceedings of IEEE Sensors   \n",
       "18                  9   Korean Journal of Microbiology and Biotechnology   \n",
       "19                  9             Microbiology and Biotechnology Letters   \n",
       "20                 10   Korean Journal of Microbiology and Biotechnology   \n",
       "21                 10             Microbiology and Biotechnology Letters   \n",
       "22                 11  Papers Presented at the Annual Conference - Ru...   \n",
       "23                 11           Papers - Rural Electric Power Conference   \n",
       "24                 12                              Lloyd's Maritime Asia   \n",
       "25                 12                                        MARIT. ASIA   \n",
       "26                 13                Clinical and Experimental Optometry   \n",
       "27                 13              The Australasian journal of optometry   \n",
       "28                 14             Journal fur Pharmakologie und Therapie   \n",
       "29                 14                                Perfusion (Germany)   \n",
       "\n",
       "                  Issn    SJR  H index         Country  \\\n",
       "0             02725428  3,203       89          France   \n",
       "1             02725428  2,444       81   United States   \n",
       "2   15244040, 0148396X  1,530      192   United States   \n",
       "3   0148396X, 00694827  1,169       31   United States   \n",
       "4   00049530, 17429536  0,477       38   United States   \n",
       "5   10361146, 17429536  0,423       35  United Kingdom   \n",
       "6   15546578, 00223069  1,366      159  United Kingdom   \n",
       "7   15546578, 00029564  0,326       35   United States   \n",
       "8   19737459, 25332279  0,618       14           Italy   \n",
       "9   03044920, 25332279  0,289       30          Taiwan   \n",
       "10  17359244, 17281431  0,395       15            Iran   \n",
       "11  1728144X, 17359244  0,265       16            Iran   \n",
       "12  21903026, 21903018  0,180       18         Germany   \n",
       "13  21903026, 21903018  0,167        4         Germany   \n",
       "14  21903026, 21903018  0,180       18         Germany   \n",
       "15  21903026, 21903018  0,167        4         Germany   \n",
       "16            19300395  0,173        9  United Kingdom   \n",
       "17            19300395  0,160       38   United States   \n",
       "18  22347305, 1598642X  0,162       16     South Korea   \n",
       "19  1598642X, 22347305  0,149        4     South Korea   \n",
       "20  22347305, 1598642X  0,162       16     South Korea   \n",
       "21  1598642X, 22347305  0,149        4     South Korea   \n",
       "22            07347464  0,135       12   United States   \n",
       "23            07347464  0,125       12   United States   \n",
       "24            02171120  0,113        0       Hong Kong   \n",
       "25            02171120  0,108        0           China   \n",
       "26  14440938, 08164622  0,752       51   United States   \n",
       "27  0817881X, 14440938  0,108        1       Australia   \n",
       "28            14324334  0,101        2         Germany   \n",
       "29  14324334, 09350020  0,100        7         Germany   \n",
       "\n",
       "                                            Publisher  chosen  \n",
       "0                                                 NaN    True  \n",
       "1                                                 NaN   False  \n",
       "2                Lippincott Williams and Wilkins Ltd.    True  \n",
       "3                Lippincott Williams and Wilkins Ltd.   False  \n",
       "4                                     Wiley-Blackwell    True  \n",
       "5                                           Routledge   False  \n",
       "6                             Oxford University Press    True  \n",
       "7   Association for the Advancement of Psychothera...   False  \n",
       "8                           Praise Worthy Prize S.r.l    True  \n",
       "9                       Chinese Physiological Society   False  \n",
       "10               Materials and Energy Research Center    True  \n",
       "11               Materials and Energy Research Center   False  \n",
       "12                                    Springer Verlag    True  \n",
       "13                                    Springer Nature   False  \n",
       "14                                    Springer Verlag    True  \n",
       "15                                    Springer Nature   False  \n",
       "16                                                NaN    True  \n",
       "17                                                NaN   False  \n",
       "18   Korean Society for Microbiolog and Biotechnology    True  \n",
       "19   Korean Society for Microbiolog and Biotechnology   False  \n",
       "20   Korean Society for Microbiolog and Biotechnology    True  \n",
       "21   Korean Society for Microbiolog and Biotechnology   False  \n",
       "22                                                NaN    True  \n",
       "23                                                NaN   False  \n",
       "24                            Lloyd's of London Press    True  \n",
       "25                            Lloyd's of London Press   False  \n",
       "26                                    Wiley-Blackwell    True  \n",
       "27                 Optometrists Association Australia   False  \n",
       "28                              Verlag Perfusion GmbH    True  \n",
       "29                              Verlag Perfusion GmbH   False  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index_by_issn = {}\n",
    "to_highlight = ['Title', 'Issn', 'SJR', 'H index', 'Country', 'Publisher']\n",
    "\n",
    "scimago_by_issn = []\n",
    "indexed_twice = []\n",
    "\n",
    "for index, issns in scimago.Issn.str.split(', ').iteritems():\n",
    "    for issn in issns:\n",
    "        if issn == '-':\n",
    "            continue\n",
    "        if issn in index_by_issn:\n",
    "            old_index = index_by_issn[issn]\n",
    "            old = scimago.iloc[old_index][to_highlight].to_dict()\n",
    "            new = scimago.iloc[index][to_highlight].to_dict()\n",
    "            duplicate_pair_id = len(indexed_twice) // 2\n",
    "            indexed_twice.append({'Duplicate Pair ID': duplicate_pair_id, **old, 'chosen': True})\n",
    "            indexed_twice.append({'Duplicate Pair ID': duplicate_pair_id, **new, 'chosen': False})\n",
    "        else:\n",
    "            index_by_issn[issn] = index\n",
    "            scimago_by_issn.append({'atomic_issn': issn, **scimago.iloc[index].to_dict()})\n",
    "\n",
    "scimago_by_issn = DataFrame(scimago_by_issn).set_index('atomic_issn').rename(columns={'Issn': 'All ISSNs'})\n",
    "indexed_twice = DataFrame(indexed_twice)\n",
    "indexed_twice"
   ]
  },
  {
   "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>Rank</th>\n",
       "      <th>Sourceid</th>\n",
       "      <th>Title</th>\n",
       "      <th>Type</th>\n",
       "      <th>All ISSNs</th>\n",
       "      <th>SJR</th>\n",
       "      <th>SJR Best Quartile</th>\n",
       "      <th>H index</th>\n",
       "      <th>Total Docs. (2019)</th>\n",
       "      <th>Total Docs. (3years)</th>\n",
       "      <th>Total Refs.</th>\n",
       "      <th>Total Cites (3years)</th>\n",
       "      <th>Citable Docs. (3years)</th>\n",
       "      <th>Cites / Doc. (2years)</th>\n",
       "      <th>Ref. / Doc.</th>\n",
       "      <th>Country</th>\n",
       "      <th>Region</th>\n",
       "      <th>Publisher</th>\n",
       "      <th>Coverage</th>\n",
       "      <th>Categories</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>atomic_issn</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>15424863</th>\n",
       "      <td>1</td>\n",
       "      <td>28773</td>\n",
       "      <td>CA - A Cancer Journal for Clinicians</td>\n",
       "      <td>journal</td>\n",
       "      <td>15424863, 00079235</td>\n",
       "      <td>88,192</td>\n",
       "      <td>Q1</td>\n",
       "      <td>156</td>\n",
       "      <td>36</td>\n",
       "      <td>129</td>\n",
       "      <td>2924</td>\n",
       "      <td>22644</td>\n",
       "      <td>89</td>\n",
       "      <td>255,73</td>\n",
       "      <td>81,22</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Wiley-Blackwell</td>\n",
       "      <td>1950-2020</td>\n",
       "      <td>Hematology (Q1); Oncology (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>00079235</th>\n",
       "      <td>1</td>\n",
       "      <td>28773</td>\n",
       "      <td>CA - A Cancer Journal for Clinicians</td>\n",
       "      <td>journal</td>\n",
       "      <td>15424863, 00079235</td>\n",
       "      <td>88,192</td>\n",
       "      <td>Q1</td>\n",
       "      <td>156</td>\n",
       "      <td>36</td>\n",
       "      <td>129</td>\n",
       "      <td>2924</td>\n",
       "      <td>22644</td>\n",
       "      <td>89</td>\n",
       "      <td>255,73</td>\n",
       "      <td>81,22</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Wiley-Blackwell</td>\n",
       "      <td>1950-2020</td>\n",
       "      <td>Hematology (Q1); Oncology (Q1)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10575987</th>\n",
       "      <td>2</td>\n",
       "      <td>19434</td>\n",
       "      <td>MMWR. Recommendations and reports : Morbidity ...</td>\n",
       "      <td>journal</td>\n",
       "      <td>10575987, 15458601</td>\n",
       "      <td>41,022</td>\n",
       "      <td>Q1</td>\n",
       "      <td>138</td>\n",
       "      <td>4</td>\n",
       "      <td>11</td>\n",
       "      <td>144</td>\n",
       "      <td>898</td>\n",
       "      <td>11</td>\n",
       "      <td>52,00</td>\n",
       "      <td>36,00</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Centers for Disease Control and Prevention (CDC)</td>\n",
       "      <td>1990-2020</td>\n",
       "      <td>Epidemiology (Q1); Health Information Manageme...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15458601</th>\n",
       "      <td>2</td>\n",
       "      <td>19434</td>\n",
       "      <td>MMWR. Recommendations and reports : Morbidity ...</td>\n",
       "      <td>journal</td>\n",
       "      <td>10575987, 15458601</td>\n",
       "      <td>41,022</td>\n",
       "      <td>Q1</td>\n",
       "      <td>138</td>\n",
       "      <td>4</td>\n",
       "      <td>11</td>\n",
       "      <td>144</td>\n",
       "      <td>898</td>\n",
       "      <td>11</td>\n",
       "      <td>52,00</td>\n",
       "      <td>36,00</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Centers for Disease Control and Prevention (CDC)</td>\n",
       "      <td>1990-2020</td>\n",
       "      <td>Epidemiology (Q1); Health Information Manageme...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20588437</th>\n",
       "      <td>3</td>\n",
       "      <td>21100812243</td>\n",
       "      <td>Nature Reviews Materials</td>\n",
       "      <td>journal</td>\n",
       "      <td>20588437</td>\n",
       "      <td>36,691</td>\n",
       "      <td>Q1</td>\n",
       "      <td>80</td>\n",
       "      <td>85</td>\n",
       "      <td>288</td>\n",
       "      <td>8534</td>\n",
       "      <td>12569</td>\n",
       "      <td>151</td>\n",
       "      <td>68,34</td>\n",
       "      <td>100,40</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Western Europe</td>\n",
       "      <td>Nature Publishing Group</td>\n",
       "      <td>2016-2020</td>\n",
       "      <td>Biomaterials (Q1); Electronic, Optical and Mag...</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\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>07419457</th>\n",
       "      <td>30880</td>\n",
       "      <td>22852</td>\n",
       "      <td>Yale journal on regulation</td>\n",
       "      <td>journal</td>\n",
       "      <td>07419457</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-</td>\n",
       "      <td>2</td>\n",
       "      <td>15</td>\n",
       "      <td>0</td>\n",
       "      <td>1126</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0,00</td>\n",
       "      <td>75,07</td>\n",
       "      <td>United States</td>\n",
       "      <td>Northern America</td>\n",
       "      <td>Yale Journal on Regulation</td>\n",
       "      <td>1991, 1994, 1998, 2019-2020</td>\n",
       "      <td>Law; Public Administration</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>03525007</th>\n",
       "      <td>30881</td>\n",
       "      <td>21100932639</td>\n",
       "      <td>Zbornik Matice Srpske za Slavistiku</td>\n",
       "      <td>journal</td>\n",
       "      <td>03525007</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-</td>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0,00</td>\n",
       "      <td>0,33</td>\n",
       "      <td>Serbia</td>\n",
       "      <td>Eastern Europe</td>\n",
       "      <td>Matica Srpska</td>\n",
       "      <td>2019</td>\n",
       "      <td>Language and Linguistics; Linguistics and Lang...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0044197X</th>\n",
       "      <td>30882</td>\n",
       "      <td>19509</td>\n",
       "      <td>Zdravookhranenie Rossiiskoi Federatsii / Minis...</td>\n",
       "      <td>journal</td>\n",
       "      <td>0044197X</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-</td>\n",
       "      <td>1</td>\n",
       "      <td>38</td>\n",
       "      <td>0</td>\n",
       "      <td>745</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0,00</td>\n",
       "      <td>19,61</td>\n",
       "      <td>Russian Federation</td>\n",
       "      <td>Eastern Europe</td>\n",
       "      <td>Izdatel'stvo Meditsina</td>\n",
       "      <td>1965-1980, 2019</td>\n",
       "      <td>Health Policy; Public Health, Environmental an...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26444909</th>\n",
       "      <td>30883</td>\n",
       "      <td>21100945707</td>\n",
       "      <td>Zdravotnicke Listy</td>\n",
       "      <td>journal</td>\n",
       "      <td>26444909, 13393022</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "      <td>517</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0,00</td>\n",
       "      <td>17,23</td>\n",
       "      <td>Slovakia</td>\n",
       "      <td>Eastern Europe</td>\n",
       "      <td>Faculty of Healthcare, Alexander Dubcek Univer...</td>\n",
       "      <td>2019</td>\n",
       "      <td>Nursing (miscellaneous); Occupational Therapy;...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13393022</th>\n",
       "      <td>30883</td>\n",
       "      <td>21100945707</td>\n",
       "      <td>Zdravotnicke Listy</td>\n",
       "      <td>journal</td>\n",
       "      <td>26444909, 13393022</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "      <td>517</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0,00</td>\n",
       "      <td>17,23</td>\n",
       "      <td>Slovakia</td>\n",
       "      <td>Eastern Europe</td>\n",
       "      <td>Faculty of Healthcare, Alexander Dubcek Univer...</td>\n",
       "      <td>2019</td>\n",
       "      <td>Nursing (miscellaneous); Occupational Therapy;...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>43260 rows × 20 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              Rank     Sourceid  \\\n",
       "atomic_issn                       \n",
       "15424863         1        28773   \n",
       "00079235         1        28773   \n",
       "10575987         2        19434   \n",
       "15458601         2        19434   \n",
       "20588437         3  21100812243   \n",
       "...            ...          ...   \n",
       "07419457     30880        22852   \n",
       "03525007     30881  21100932639   \n",
       "0044197X     30882        19509   \n",
       "26444909     30883  21100945707   \n",
       "13393022     30883  21100945707   \n",
       "\n",
       "                                                         Title     Type  \\\n",
       "atomic_issn                                                               \n",
       "15424863                  CA - A Cancer Journal for Clinicians  journal   \n",
       "00079235                  CA - A Cancer Journal for Clinicians  journal   \n",
       "10575987     MMWR. Recommendations and reports : Morbidity ...  journal   \n",
       "15458601     MMWR. Recommendations and reports : Morbidity ...  journal   \n",
       "20588437                              Nature Reviews Materials  journal   \n",
       "...                                                        ...      ...   \n",
       "07419457                            Yale journal on regulation  journal   \n",
       "03525007                   Zbornik Matice Srpske za Slavistiku  journal   \n",
       "0044197X     Zdravookhranenie Rossiiskoi Federatsii / Minis...  journal   \n",
       "26444909                                    Zdravotnicke Listy  journal   \n",
       "13393022                                    Zdravotnicke Listy  journal   \n",
       "\n",
       "                      All ISSNs     SJR SJR Best Quartile  H index  \\\n",
       "atomic_issn                                                          \n",
       "15424863     15424863, 00079235  88,192                Q1      156   \n",
       "00079235     15424863, 00079235  88,192                Q1      156   \n",
       "10575987     10575987, 15458601  41,022                Q1      138   \n",
       "15458601     10575987, 15458601  41,022                Q1      138   \n",
       "20588437               20588437  36,691                Q1       80   \n",
       "...                         ...     ...               ...      ...   \n",
       "07419457               07419457     NaN                 -        2   \n",
       "03525007               03525007     NaN                 -        0   \n",
       "0044197X               0044197X     NaN                 -        1   \n",
       "26444909     26444909, 13393022     NaN                 -        0   \n",
       "13393022     26444909, 13393022     NaN                 -        0   \n",
       "\n",
       "             Total Docs. (2019)  Total Docs. (3years)  Total Refs.  \\\n",
       "atomic_issn                                                          \n",
       "15424863                     36                   129         2924   \n",
       "00079235                     36                   129         2924   \n",
       "10575987                      4                    11          144   \n",
       "15458601                      4                    11          144   \n",
       "20588437                     85                   288         8534   \n",
       "...                         ...                   ...          ...   \n",
       "07419457                     15                     0         1126   \n",
       "03525007                     24                     0            8   \n",
       "0044197X                     38                     0          745   \n",
       "26444909                     30                     0          517   \n",
       "13393022                     30                     0          517   \n",
       "\n",
       "             Total Cites (3years)  Citable Docs. (3years)  \\\n",
       "atomic_issn                                                 \n",
       "15424863                    22644                      89   \n",
       "00079235                    22644                      89   \n",
       "10575987                      898                      11   \n",
       "15458601                      898                      11   \n",
       "20588437                    12569                     151   \n",
       "...                           ...                     ...   \n",
       "07419457                        0                       0   \n",
       "03525007                        0                       0   \n",
       "0044197X                        0                       0   \n",
       "26444909                        0                       0   \n",
       "13393022                        0                       0   \n",
       "\n",
       "            Cites / Doc. (2years) Ref. / Doc.             Country  \\\n",
       "atomic_issn                                                         \n",
       "15424863                   255,73       81,22       United States   \n",
       "00079235                   255,73       81,22       United States   \n",
       "10575987                    52,00       36,00       United States   \n",
       "15458601                    52,00       36,00       United States   \n",
       "20588437                    68,34      100,40      United Kingdom   \n",
       "...                           ...         ...                 ...   \n",
       "07419457                     0,00       75,07       United States   \n",
       "03525007                     0,00        0,33              Serbia   \n",
       "0044197X                     0,00       19,61  Russian Federation   \n",
       "26444909                     0,00       17,23            Slovakia   \n",
       "13393022                     0,00       17,23            Slovakia   \n",
       "\n",
       "                       Region  \\\n",
       "atomic_issn                     \n",
       "15424863     Northern America   \n",
       "00079235     Northern America   \n",
       "10575987     Northern America   \n",
       "15458601     Northern America   \n",
       "20588437       Western Europe   \n",
       "...                       ...   \n",
       "07419457     Northern America   \n",
       "03525007       Eastern Europe   \n",
       "0044197X       Eastern Europe   \n",
       "26444909       Eastern Europe   \n",
       "13393022       Eastern Europe   \n",
       "\n",
       "                                                     Publisher  \\\n",
       "atomic_issn                                                      \n",
       "15424863                                       Wiley-Blackwell   \n",
       "00079235                                       Wiley-Blackwell   \n",
       "10575987      Centers for Disease Control and Prevention (CDC)   \n",
       "15458601      Centers for Disease Control and Prevention (CDC)   \n",
       "20588437                               Nature Publishing Group   \n",
       "...                                                        ...   \n",
       "07419457                            Yale Journal on Regulation   \n",
       "03525007                                         Matica Srpska   \n",
       "0044197X                                Izdatel'stvo Meditsina   \n",
       "26444909     Faculty of Healthcare, Alexander Dubcek Univer...   \n",
       "13393022     Faculty of Healthcare, Alexander Dubcek Univer...   \n",
       "\n",
       "                                Coverage  \\\n",
       "atomic_issn                                \n",
       "15424863                       1950-2020   \n",
       "00079235                       1950-2020   \n",
       "10575987                       1990-2020   \n",
       "15458601                       1990-2020   \n",
       "20588437                       2016-2020   \n",
       "...                                  ...   \n",
       "07419457     1991, 1994, 1998, 2019-2020   \n",
       "03525007                            2019   \n",
       "0044197X                 1965-1980, 2019   \n",
       "26444909                            2019   \n",
       "13393022                            2019   \n",
       "\n",
       "                                                    Categories  \n",
       "atomic_issn                                                     \n",
       "15424863                        Hematology (Q1); Oncology (Q1)  \n",
       "00079235                        Hematology (Q1); Oncology (Q1)  \n",
       "10575987     Epidemiology (Q1); Health Information Manageme...  \n",
       "15458601     Epidemiology (Q1); Health Information Manageme...  \n",
       "20588437     Biomaterials (Q1); Electronic, Optical and Mag...  \n",
       "...                                                        ...  \n",
       "07419457                            Law; Public Administration  \n",
       "03525007     Language and Linguistics; Linguistics and Lang...  \n",
       "0044197X     Health Policy; Public Health, Environmental an...  \n",
       "26444909     Nursing (miscellaneous); Occupational Therapy;...  \n",
       "13393022     Nursing (miscellaneous); Occupational Therapy;...  \n",
       "\n",
       "[43260 rows x 20 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scimago_by_issn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "Stored:\n",
       "\n",
       " - `scimago_by_issn` (693288F1 → DDCBFB24)\n",
       " - `web_of_science_journals` (E95CE31E → E95CE31E)\n",
       "\n",
       "at Sunday, 12. Jul 2020 21:35"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {
      "text/markdown": {
       "action": "store",
       "command": "store scimago_by_issn, web_of_science_journals in journals_data",
       "finished": "2020-07-12T21:35:17.563956",
       "finished_human_readable": "Sunday, 12. Jul 2020 21:35",
       "result": [
        {
         "new_file": {
          "crc32": "DDCBFB24",
          "sha256": "B16E18A78F3247A03950A39AB7B64E92EAFA747074BB6B2DBFEBDA7DCA5902D3"
         },
         "old_file": {
          "crc32": "693288F1",
          "sha256": "CF064354E0069A8CE7192536730A786720DE65970D447D38B754F04D76CD9E8C"
         },
         "subject": "scimago_by_issn"
        },
        {
         "new_file": {
          "crc32": "E95CE31E",
          "sha256": "55F51248C28FEEC07B4E5A98AD3660519AD3566DC9B61985279E6D4C9B374BF8"
         },
         "old_file": {
          "crc32": "E95CE31E",
          "sha256": "55F51248C28FEEC07B4E5A98AD3660519AD3566DC9B61985279E6D4C9B374BF8"
         },
         "subject": "web_of_science_journals"
        }
       ],
       "started": "2020-07-12T21:35:13.616123"
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%vault store scimago_by_issn, web_of_science_journals in journals_data"
   ]
  }
 ],
 "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
}