diff --git a/WOS/wos_univ_normalizer.ipynb b/WOS/wos_univ_normalizer.ipynb
index 8089d5e..70ba15c 100644
--- a/WOS/wos_univ_normalizer.ipynb
+++ b/WOS/wos_univ_normalizer.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 191,
    "outputs": [],
    "source": [
     "import pandas as pd\n",
@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 192,
    "outputs": [],
    "source": [
     "def wikinorm(univ_string):\n",
@@ -43,7 +43,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 193,
    "outputs": [],
    "source": [
     "def replace_uppercase_words(text):\n",
@@ -66,7 +66,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 194,
    "outputs": [
     {
      "name": "stdout",
@@ -85,7 +85,7 @@
       "application/vnd.jupyter.widget-view+json": {
        "version_major": 2,
        "version_minor": 0,
-       "model_id": "ee2cde76498b4a46a2e87ea6c971aed9"
+       "model_id": "8551fdcfc52a43108a78c1e91915c681"
       }
      },
      "metadata": {},
@@ -115,14 +115,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 195,
    "outputs": [
     {
      "data": {
-      "text/plain": "         UT (Unique WOS ID)                   Institution         Country   \n84810   WOS:000571399800004               Univ Birmingham  United Kingdom  \\\n122264  WOS:000732918800001              Univ Southampton  United Kingdom   \n135675  WOS:000799234000004                           UCL  United Kingdom   \n153134  WOS:000900724501058                Kore Univ Enna           Italy   \n51445   WOS:000455277600005                Univ Sheffield  United Kingdom   \n...                     ...                           ...             ...   \n21043   WOS:000372583700005          Vrije Univ Amsterdam     Netherlands   \n1938    WOS:000297611600011                    Univ Essex  United Kingdom   \n64691   WOS:000490430500091  Xian Jiaotong Liverpool Univ           China   \n25740   WOS:000386793200001              Chinese Acad Sci           China   \n112682  WOS:000696110800001           Dalian Univ Technol           China   \n\n                    Institution_harm  \n84810                Univ Birmingham  \n122264              Univ Southampton  \n135675                           UCL  \n153134                Kore Univ Enna  \n51445                 Univ Sheffield  \n...                              ...  \n21043           Vrije Univ Amsterdam  \n1938                      Univ Essex  \n64691   Xian Jiaotong Liverpool Univ  \n25740               Chinese Acad Sci  \n112682           Dalian Univ Technol  \n\n[100 rows x 4 columns]",
-      "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>UT (Unique WOS ID)</th>\n      <th>Institution</th>\n      <th>Country</th>\n      <th>Institution_harm</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>84810</th>\n      <td>WOS:000571399800004</td>\n      <td>Univ Birmingham</td>\n      <td>United Kingdom</td>\n      <td>Univ Birmingham</td>\n    </tr>\n    <tr>\n      <th>122264</th>\n      <td>WOS:000732918800001</td>\n      <td>Univ Southampton</td>\n      <td>United Kingdom</td>\n      <td>Univ Southampton</td>\n    </tr>\n    <tr>\n      <th>135675</th>\n      <td>WOS:000799234000004</td>\n      <td>UCL</td>\n      <td>United Kingdom</td>\n      <td>UCL</td>\n    </tr>\n    <tr>\n      <th>153134</th>\n      <td>WOS:000900724501058</td>\n      <td>Kore Univ Enna</td>\n      <td>Italy</td>\n      <td>Kore Univ Enna</td>\n    </tr>\n    <tr>\n      <th>51445</th>\n      <td>WOS:000455277600005</td>\n      <td>Univ Sheffield</td>\n      <td>United Kingdom</td>\n      <td>Univ Sheffield</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>21043</th>\n      <td>WOS:000372583700005</td>\n      <td>Vrije Univ Amsterdam</td>\n      <td>Netherlands</td>\n      <td>Vrije Univ Amsterdam</td>\n    </tr>\n    <tr>\n      <th>1938</th>\n      <td>WOS:000297611600011</td>\n      <td>Univ Essex</td>\n      <td>United Kingdom</td>\n      <td>Univ Essex</td>\n    </tr>\n    <tr>\n      <th>64691</th>\n      <td>WOS:000490430500091</td>\n      <td>Xian Jiaotong Liverpool Univ</td>\n      <td>China</td>\n      <td>Xian Jiaotong Liverpool Univ</td>\n    </tr>\n    <tr>\n      <th>25740</th>\n      <td>WOS:000386793200001</td>\n      <td>Chinese Acad Sci</td>\n      <td>China</td>\n      <td>Chinese Acad Sci</td>\n    </tr>\n    <tr>\n      <th>112682</th>\n      <td>WOS:000696110800001</td>\n      <td>Dalian Univ Technol</td>\n      <td>China</td>\n      <td>Dalian Univ Technol</td>\n    </tr>\n  </tbody>\n</table>\n<p>100 rows × 4 columns</p>\n</div>"
+      "text/plain": "         UT (Unique WOS ID)                          Institution   \n1094    WOS:000292330300050              Hong Kong Polytech Univ  \\\n21547   WOS:000374363900001               Guangdong Univ Technol   \n53778   WOS:000459846300019                          Aarhus Univ   \n153776  WOS:000907044000014                           Univ Siena   \n81562   WOS:000554591602038  China Natl Elect Import Export Corp   \n...                     ...                                  ...   \n29206   WOS:000397047200002                  Univ Duisburg Essen   \n21658   WOS:000374617600020                     Univ Southampton   \n43289   WOS:000434742800004                     Univ Strathclyde   \n37200   WOS:000418525100013                Goethe Univ Frankfurt   \n95964   WOS:000616310200013               Eindhoven Univ Technol   \n\n               Country                     Institution_harm  \n1094             China              Hong Kong Polytech Univ  \n21547            China               Guangdong Univ Technol  \n53778          Denmark                          Aarhus Univ  \n153776           Italy                           Univ Siena  \n81562            China  China Natl Elect Import Export Corp  \n...                ...                                  ...  \n29206          Germany                  Univ Duisburg Essen  \n21658   United Kingdom                     Univ Southampton  \n43289   United Kingdom                     Univ Strathclyde  \n37200          Germany                Goethe Univ Frankfurt  \n95964      Netherlands               Eindhoven Univ Technol  \n\n[100 rows x 4 columns]",
+      "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>UT (Unique WOS ID)</th>\n      <th>Institution</th>\n      <th>Country</th>\n      <th>Institution_harm</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1094</th>\n      <td>WOS:000292330300050</td>\n      <td>Hong Kong Polytech Univ</td>\n      <td>China</td>\n      <td>Hong Kong Polytech Univ</td>\n    </tr>\n    <tr>\n      <th>21547</th>\n      <td>WOS:000374363900001</td>\n      <td>Guangdong Univ Technol</td>\n      <td>China</td>\n      <td>Guangdong Univ Technol</td>\n    </tr>\n    <tr>\n      <th>53778</th>\n      <td>WOS:000459846300019</td>\n      <td>Aarhus Univ</td>\n      <td>Denmark</td>\n      <td>Aarhus Univ</td>\n    </tr>\n    <tr>\n      <th>153776</th>\n      <td>WOS:000907044000014</td>\n      <td>Univ Siena</td>\n      <td>Italy</td>\n      <td>Univ Siena</td>\n    </tr>\n    <tr>\n      <th>81562</th>\n      <td>WOS:000554591602038</td>\n      <td>China Natl Elect Import Export Corp</td>\n      <td>China</td>\n      <td>China Natl Elect Import Export Corp</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>29206</th>\n      <td>WOS:000397047200002</td>\n      <td>Univ Duisburg Essen</td>\n      <td>Germany</td>\n      <td>Univ Duisburg Essen</td>\n    </tr>\n    <tr>\n      <th>21658</th>\n      <td>WOS:000374617600020</td>\n      <td>Univ Southampton</td>\n      <td>United Kingdom</td>\n      <td>Univ Southampton</td>\n    </tr>\n    <tr>\n      <th>43289</th>\n      <td>WOS:000434742800004</td>\n      <td>Univ Strathclyde</td>\n      <td>United Kingdom</td>\n      <td>Univ Strathclyde</td>\n    </tr>\n    <tr>\n      <th>37200</th>\n      <td>WOS:000418525100013</td>\n      <td>Goethe Univ Frankfurt</td>\n      <td>Germany</td>\n      <td>Goethe Univ Frankfurt</td>\n    </tr>\n    <tr>\n      <th>95964</th>\n      <td>WOS:000616310200013</td>\n      <td>Eindhoven Univ Technol</td>\n      <td>Netherlands</td>\n      <td>Eindhoven Univ Technol</td>\n    </tr>\n  </tbody>\n</table>\n<p>100 rows × 4 columns</p>\n</div>"
      },
-     "execution_count": 39,
+     "execution_count": 195,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -136,14 +136,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 196,
    "outputs": [
     {
      "data": {
-      "text/plain": "              Country                                   Institution_harm   \n7736           France                                       Yncrea Ouest  \\\n13752           Spain                                        Univ Carlos   \n15855  United Kingdom               Northumbria Univ Newcastle Upon Tyne   \n12514          Norway                                          Nord Univ   \n602             China                                Henan Polytech Univ   \n...               ...                                                ...   \n11620           Italy                                      Deep Blue Srl   \n11183           Italy                            Univ Giustino Fortunato   \n7433          Estonia                           Platinum Software Dev Co   \n5129            China  State & Local Joint Engn Lab Estuarine Hydraul Te   \n6799            China                                                MOA   \n\n       count  \n7736       9  \n13752      1  \n15855      1  \n12514      1  \n602       87  \n...      ...  \n11620      1  \n11183      3  \n7433       1  \n5129       1  \n6799       1  \n\n[100 rows x 3 columns]",
-      "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>Country</th>\n      <th>Institution_harm</th>\n      <th>count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>7736</th>\n      <td>France</td>\n      <td>Yncrea Ouest</td>\n      <td>9</td>\n    </tr>\n    <tr>\n      <th>13752</th>\n      <td>Spain</td>\n      <td>Univ Carlos</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>15855</th>\n      <td>United Kingdom</td>\n      <td>Northumbria Univ Newcastle Upon Tyne</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>12514</th>\n      <td>Norway</td>\n      <td>Nord Univ</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>602</th>\n      <td>China</td>\n      <td>Henan Polytech Univ</td>\n      <td>87</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>11620</th>\n      <td>Italy</td>\n      <td>Deep Blue Srl</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>11183</th>\n      <td>Italy</td>\n      <td>Univ Giustino Fortunato</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>7433</th>\n      <td>Estonia</td>\n      <td>Platinum Software Dev Co</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>5129</th>\n      <td>China</td>\n      <td>State &amp; Local Joint Engn Lab Estuarine Hydraul Te</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>6799</th>\n      <td>China</td>\n      <td>MOA</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n<p>100 rows × 3 columns</p>\n</div>"
+      "text/plain": "        Country                  Institution_harm  count\n12655    Poland                     Space Res Ctr      6\n12940  Portugal     Ctr Invest Energia State Grid      1\n616       China              Minist Nat Resources     78\n5561      China  PowerChina Huadong Engn Corp Ltd      1\n514       China                    Chongqing Univ    478\n...         ...                               ...    ...\n476    Bulgaria                         Tech Univ      1\n12454    Norway               Stavanger Univ Hosp      9\n5489      China               Shanghai Sports Sch      1\n768       China                        Hubei Univ     25\n13527     Spain            Jimenez Diaz Univ Hosp      2\n\n[100 rows x 3 columns]",
+      "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>Country</th>\n      <th>Institution_harm</th>\n      <th>count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>12655</th>\n      <td>Poland</td>\n      <td>Space Res Ctr</td>\n      <td>6</td>\n    </tr>\n    <tr>\n      <th>12940</th>\n      <td>Portugal</td>\n      <td>Ctr Invest Energia State Grid</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>616</th>\n      <td>China</td>\n      <td>Minist Nat Resources</td>\n      <td>78</td>\n    </tr>\n    <tr>\n      <th>5561</th>\n      <td>China</td>\n      <td>PowerChina Huadong Engn Corp Ltd</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>514</th>\n      <td>China</td>\n      <td>Chongqing Univ</td>\n      <td>478</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>476</th>\n      <td>Bulgaria</td>\n      <td>Tech Univ</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>12454</th>\n      <td>Norway</td>\n      <td>Stavanger Univ Hosp</td>\n      <td>9</td>\n    </tr>\n    <tr>\n      <th>5489</th>\n      <td>China</td>\n      <td>Shanghai Sports Sch</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>768</th>\n      <td>China</td>\n      <td>Hubei Univ</td>\n      <td>25</td>\n    </tr>\n    <tr>\n      <th>13527</th>\n      <td>Spain</td>\n      <td>Jimenez Diaz Univ Hosp</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n<p>100 rows × 3 columns</p>\n</div>"
      },
-     "execution_count": 71,
+     "execution_count": 196,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -159,7 +159,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 197,
    "outputs": [],
    "source": [
     "# from pandarallel import pandarallel\n",
@@ -173,27 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "['Austria', 'Belgium']"
-     },
-     "execution_count": 73,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "list(univ_norm[\"Country\"].unique())[0:2]"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 95,
+   "execution_count": 198,
    "outputs": [],
    "source": [
     "def ngrams(string, n=3):\n",
@@ -296,26 +276,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 130,
+   "execution_count": 199,
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "30it [00:00, 53.27it/s]\n"
+      "100%|██████████| 31/31 [00:00<00:00, 32.89it/s]\n"
      ]
     }
    ],
    "source": [
     "merger = pd.DataFrame()\n",
     "\n",
-    "for i in tqdm(filter(lambda c: c!=\"China\", list(univ_norm[\"Country\"].unique()))):\n",
+    "# for i in tqdm(filter(lambda c: c!=\"China\", list(univ_norm[\"Country\"].unique()))):\n",
+    "for i in tqdm(list(univ_norm[\"Country\"].unique())):\n",
     "    sub_inst = univ_norm[univ_norm[\"Country\"]==i].reset_index()\n",
     "    types = sub_inst['Institution_harm']\n",
     "    vectorizer = TfidfVectorizer(min_df=1, analyzer=ngrams)\n",
     "    tf_idf_matrix = vectorizer.fit_transform(types)\n",
     "    t1 = time.time()\n",
-    "    matches = awesome_cossim_top(tf_idf_matrix, tf_idf_matrix.transpose(), 10, 0.8)\n",
+    "    matches = awesome_cossim_top(tf_idf_matrix, tf_idf_matrix.transpose(), 10, 0.8 if i!=\"China\" else 0.9)\n",
     "    t = time.time()-t1\n",
     "\n",
     "    # store the  matches into new dataframe called matched_df and printing 10 samples\n",
@@ -353,20 +334,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 131,
+   "execution_count": 200,
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1192\n"
+      "1538\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "1192it [00:44, 26.68it/s]\n"
+      "1538it [01:04, 23.79it/s]\n"
      ]
     }
    ],
@@ -387,6 +368,27 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 201,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "     Country                                         low_side   \n0      China  Logist Univ Chinese Peoples Armed Police Forces  \\\n9      China                  Flight Automat Control Res Inst   \n10     China         Northwest Elect Power Design Inst Co Ltd   \n11     China   Northwest Elect Power Design Inst Co Ltd China   \n12     China           Northwest Inst Ecoenvironm & Resources   \n...      ...                                              ...   \n1531   China                      Chinese Univ Hong Kong Hong   \n1532   China                       Huazhong Univ Sci & Techno   \n1533   China                Hong Kong Polytech Univ Hong Kong   \n1534   China                          Kong Kong Polytech Univ   \n1537   China                    Univ Elect Sci & Technol Chin   \n\n                                              high_side  high_count   \n0        Logist Univ Chinese Peoples Armed Police Force           1  \\\n9                  Xian Flight Automat Control Res Inst           1   \n10       Northwest Elect Power Design Inst Co Ltd China           1   \n11             Northwest Elect Power Design Inst Co Ltd           1   \n12    Northwest Inst Ecoenvironm & Resources Chinese Ac           1   \n...                                                 ...         ...   \n1531                             Chinese Univ Hong Kong         728   \n1532                        Huazhong Univ Sci & Technol         729   \n1533                            Hong Kong Polytech Univ         809   \n1534                            Hong Kong Polytech Univ         809   \n1537                     Univ Elect Sci & Technol China        1076   \n\n      low_count  similarity  \n0             1    0.988072  \n9             1    0.905747  \n10            1    0.926984  \n11            1    0.926984  \n12            1    0.910630  \n...         ...         ...  \n1531          1    0.935944  \n1532          1    0.989260  \n1533          1    0.917345  \n1534          1    0.939416  \n1537          1    0.983258  \n\n[346 rows x 6 columns]",
+      "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>Country</th>\n      <th>low_side</th>\n      <th>high_side</th>\n      <th>high_count</th>\n      <th>low_count</th>\n      <th>similarity</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>China</td>\n      <td>Logist Univ Chinese Peoples Armed Police Forces</td>\n      <td>Logist Univ Chinese Peoples Armed Police Force</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0.988072</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>China</td>\n      <td>Flight Automat Control Res Inst</td>\n      <td>Xian Flight Automat Control Res Inst</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0.905747</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>China</td>\n      <td>Northwest Elect Power Design Inst Co Ltd</td>\n      <td>Northwest Elect Power Design Inst Co Ltd China</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0.926984</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>China</td>\n      <td>Northwest Elect Power Design Inst Co Ltd China</td>\n      <td>Northwest Elect Power Design Inst Co Ltd</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0.926984</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>China</td>\n      <td>Northwest Inst Ecoenvironm &amp; Resources</td>\n      <td>Northwest Inst Ecoenvironm &amp; Resources Chinese Ac</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0.910630</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    </tr>\n    <tr>\n      <th>1531</th>\n      <td>China</td>\n      <td>Chinese Univ Hong Kong Hong</td>\n      <td>Chinese Univ Hong Kong</td>\n      <td>728</td>\n      <td>1</td>\n      <td>0.935944</td>\n    </tr>\n    <tr>\n      <th>1532</th>\n      <td>China</td>\n      <td>Huazhong Univ Sci &amp; Techno</td>\n      <td>Huazhong Univ Sci &amp; Technol</td>\n      <td>729</td>\n      <td>1</td>\n      <td>0.989260</td>\n    </tr>\n    <tr>\n      <th>1533</th>\n      <td>China</td>\n      <td>Hong Kong Polytech Univ Hong Kong</td>\n      <td>Hong Kong Polytech Univ</td>\n      <td>809</td>\n      <td>1</td>\n      <td>0.917345</td>\n    </tr>\n    <tr>\n      <th>1534</th>\n      <td>China</td>\n      <td>Kong Kong Polytech Univ</td>\n      <td>Hong Kong Polytech Univ</td>\n      <td>809</td>\n      <td>1</td>\n      <td>0.939416</td>\n    </tr>\n    <tr>\n      <th>1537</th>\n      <td>China</td>\n      <td>Univ Elect Sci &amp; Technol Chin</td>\n      <td>Univ Elect Sci &amp; Technol China</td>\n      <td>1076</td>\n      <td>1</td>\n      <td>0.983258</td>\n    </tr>\n  </tbody>\n</table>\n<p>346 rows × 6 columns</p>\n</div>"
+     },
+     "execution_count": 201,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# fuzzymerger[fuzzymerger[\"Country\"]==\"China\"]"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "markdown",
    "source": [],
@@ -396,20 +398,64 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 120,
+   "execution_count": 202,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "         UT (Unique WOS ID)                           Institution Country   \n244     WOS:000286472300003                            Univ Trent   Italy  \\\n364     WOS:000287586100011                            Univ Trent   Italy   \n410     WOS:000287939200011      Abdus Salam Int Ctr Theoret Phys   Italy   \n765     WOS:000290996200002                            Univ Trent   Italy   \n907     WOS:000291698400013                       INFN Sez Roma 1   Italy   \n...                     ...                                   ...     ...   \n153063  WOS:000900129900175        Univ Rome Campus Biomed Aquila   Italy   \n154775  WOS:000929737300001                    Prevent & Res Inst   Italy   \n154813  WOS:000929737300001                       Ist Super Sanit   Italy   \n154855  WOS:000933331200004                       Univ Federio II   Italy   \n154857  WOS:000933331200004  INAF Osservatorio Astron Capodimonte   Italy   \n\n                         Institution_harm  merge_iter  \n244                           Univ Trento           1  \n364                           Univ Trento           1  \n410     Abdus Salaam Int Ctr Theoret Phys           1  \n765                           Univ Trento           1  \n907                              Sez Roma           1  \n...                                   ...         ...  \n153063     Univ Rome Campus Biomed Aquila           2  \n154775                 Prevent & Res Inst           2  \n154813                   Ist Super Sanita           1  \n154855                      Univ Federico           1  \n154857          Osserv Astron Capodimonte           1  \n\n[375 rows x 5 columns]",
+      "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>UT (Unique WOS ID)</th>\n      <th>Institution</th>\n      <th>Country</th>\n      <th>Institution_harm</th>\n      <th>merge_iter</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>244</th>\n      <td>WOS:000286472300003</td>\n      <td>Univ Trent</td>\n      <td>Italy</td>\n      <td>Univ Trento</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>364</th>\n      <td>WOS:000287586100011</td>\n      <td>Univ Trent</td>\n      <td>Italy</td>\n      <td>Univ Trento</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>410</th>\n      <td>WOS:000287939200011</td>\n      <td>Abdus Salam Int Ctr Theoret Phys</td>\n      <td>Italy</td>\n      <td>Abdus Salaam Int Ctr Theoret Phys</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>765</th>\n      <td>WOS:000290996200002</td>\n      <td>Univ Trent</td>\n      <td>Italy</td>\n      <td>Univ Trento</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>907</th>\n      <td>WOS:000291698400013</td>\n      <td>INFN Sez Roma 1</td>\n      <td>Italy</td>\n      <td>Sez Roma</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>153063</th>\n      <td>WOS:000900129900175</td>\n      <td>Univ Rome Campus Biomed Aquila</td>\n      <td>Italy</td>\n      <td>Univ Rome Campus Biomed Aquila</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>154775</th>\n      <td>WOS:000929737300001</td>\n      <td>Prevent &amp; Res Inst</td>\n      <td>Italy</td>\n      <td>Prevent &amp; Res Inst</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>154813</th>\n      <td>WOS:000929737300001</td>\n      <td>Ist Super Sanit</td>\n      <td>Italy</td>\n      <td>Ist Super Sanita</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>154855</th>\n      <td>WOS:000933331200004</td>\n      <td>Univ Federio II</td>\n      <td>Italy</td>\n      <td>Univ Federico</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>154857</th>\n      <td>WOS:000933331200004</td>\n      <td>INAF Osservatorio Astron Capodimonte</td>\n      <td>Italy</td>\n      <td>Osserv Astron Capodimonte</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n<p>375 rows × 5 columns</p>\n</div>"
+     },
+     "execution_count": 202,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# univ_harm[((univ_harm[\"merge_iter\"]>0) & (univ_harm[\"Country\"]==\"Italy\"))]"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 208,
+   "outputs": [],
+   "source": [
+    "univ_harm.loc[((univ_harm[\"merge_iter\"]>0) & (univ_harm[\"Country\"]==\"Italy\")&\n",
+    "           (univ_harm[\"Institution\"].str.lower().str.contains(\"sapien\"))&\n",
+    "            (univ_harm[\"Institution\"].str.lower().str.contains(\"univ\"))), \"Institution_harm\"] = \"Sapienza Univ Rome\""
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 209,
    "outputs": [
     {
      "data": {
-      "text/plain": "         UT (Unique WOS ID)                           Institution Country   \n244     WOS:000286472300003                            Univ Trent   Italy  \\\n364     WOS:000287586100011                            Univ Trent   Italy   \n410     WOS:000287939200011      Abdus Salam Int Ctr Theoret Phys   Italy   \n765     WOS:000290996200002                            Univ Trent   Italy   \n907     WOS:000291698400013                       INFN Sez Roma 1   Italy   \n...                     ...                                   ...     ...   \n153063  WOS:000900129900175        Univ Rome Campus Biomed Aquila   Italy   \n154775  WOS:000929737300001                    Prevent & Res Inst   Italy   \n154813  WOS:000929737300001                       Ist Super Sanit   Italy   \n154855  WOS:000933331200004                       Univ Federio II   Italy   \n154857  WOS:000933331200004  INAF Osservatorio Astron Capodimonte   Italy   \n\n                         Institution_harm  merge_iter  \n244                           Univ Trento           1  \n364                           Univ Trento           1  \n410     Abdus Salaam Int Ctr Theoret Phys           1  \n765                           Univ Trento           1  \n907                              Sez Roma           1  \n...                                   ...         ...  \n153063    Univ Rome Campus Biomed LAquila           1  \n154775                 Prevent & Res Inst           2  \n154813                   Ist Super Sanita           1  \n154855                       Univ Federio           2  \n154857          Osserv Astron Capodimonte           1  \n\n[375 rows x 5 columns]",
-      "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>UT (Unique WOS ID)</th>\n      <th>Institution</th>\n      <th>Country</th>\n      <th>Institution_harm</th>\n      <th>merge_iter</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>244</th>\n      <td>WOS:000286472300003</td>\n      <td>Univ Trent</td>\n      <td>Italy</td>\n      <td>Univ Trento</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>364</th>\n      <td>WOS:000287586100011</td>\n      <td>Univ Trent</td>\n      <td>Italy</td>\n      <td>Univ Trento</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>410</th>\n      <td>WOS:000287939200011</td>\n      <td>Abdus Salam Int Ctr Theoret Phys</td>\n      <td>Italy</td>\n      <td>Abdus Salaam Int Ctr Theoret Phys</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>765</th>\n      <td>WOS:000290996200002</td>\n      <td>Univ Trent</td>\n      <td>Italy</td>\n      <td>Univ Trento</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>907</th>\n      <td>WOS:000291698400013</td>\n      <td>INFN Sez Roma 1</td>\n      <td>Italy</td>\n      <td>Sez Roma</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>153063</th>\n      <td>WOS:000900129900175</td>\n      <td>Univ Rome Campus Biomed Aquila</td>\n      <td>Italy</td>\n      <td>Univ Rome Campus Biomed LAquila</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>154775</th>\n      <td>WOS:000929737300001</td>\n      <td>Prevent &amp; Res Inst</td>\n      <td>Italy</td>\n      <td>Prevent &amp; Res Inst</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>154813</th>\n      <td>WOS:000929737300001</td>\n      <td>Ist Super Sanit</td>\n      <td>Italy</td>\n      <td>Ist Super Sanita</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>154855</th>\n      <td>WOS:000933331200004</td>\n      <td>Univ Federio II</td>\n      <td>Italy</td>\n      <td>Univ Federio</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>154857</th>\n      <td>WOS:000933331200004</td>\n      <td>INAF Osservatorio Astron Capodimonte</td>\n      <td>Italy</td>\n      <td>Osserv Astron Capodimonte</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n<p>375 rows × 5 columns</p>\n</div>"
+      "text/plain": "Institution         17083\nInstitution_harm    14449\ndtype: int64"
      },
-     "execution_count": 120,
+     "execution_count": 209,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "univ_harm[((univ_harm[\"merge_iter\"]>0) & (univ_harm[\"Country\"]==\"Italy\"))]"
+    "univ_harm[[\"Institution\",\"Institution_harm\"]].nunique()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 210,
+   "outputs": [],
+   "source": [
+    "univ_harm.to_excel(f\"{outdir}/wos_institution_locations_harmonized.xlsx\", index=False)"
    ],
    "metadata": {
     "collapsed": false