progress

TODO.ipynb

@@ -31,6 +31,50 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# WOS current query:\n",
+    "\n",
+    "\"\"\"(TS=(\"artificial intelligence\") OR TS=(\"machine learning\") OR TS=(\"neural network\") OR TS=(\"big data\") OR TS=(\"deep learning\")) AND (CU=PEOPLES R CHINA AND (CU=AUSTRIA OR CU=BELGIUM OR CU=BULGARIA OR CU=CROATIA OR CU=REPUBLIC OF CYPRUS OR CU=CZECH REPUBLIC OR CU=DENMARK OR CU=ESTONIA OR CU=FINLAND OR CU=FRANCE OR CU=GERMANY OR CU=GREECE OR CU=HUNGARY OR CU=IRELAND OR CU=ITALY OR CU=LATVIA OR CU=LITHUANIA OR CU=LUXEMBOURG OR CU=MALTA OR CU=NETHERLANDS OR CU=POLAND OR CU=PORTUGAL OR CU=ROMANIA OR CU=SLOVAKIA OR CU=SLOVENIA OR CU=SPAIN OR CU=SWEDEN))\"\"\""
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "other keywords: pattern recognition, computer vision, image classification, reinforcement learning, support vector machines, recommender system, random forest, ensemble models, image processing, generative network, ai ethic, natural language processing, clustering algorithm, feature extraction, time series forecast, anomaly detection, identity fraud detection, dimensionality reduction, feature elicitation, chatbot, clustering, unsupervised learning, supervised learning, convolutional network, adversarial network\n",
+    "\n",
+    "# AI ETHICS keyword!!!"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "# Only CPC classification? Or some basic PTC? (ASEAN analysis had some)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -73,7 +117,12 @@
    "cell_type": "code",
    "execution_count": null,
    "outputs": [],
-   "source": [],
+   "source": [
+    "# Baseline of co-publications\n",
+    "#\n",
+    "# Use address instead of CU?\n",
+    "# plus countries UK Norway Switzerland | Turkey Serbia"
+   ],
    "metadata": {
     "collapsed": false,
     "pycharm": {

WOS/ai_scope_keywords.txt

@@ -0,0 +1 @@
+artificial intelligence,machine learning,neural network,big data,deep learning,pattern recognition,computer vision, image classification, reinforcement learning, support vector machines, recommender system, random forest, ensemble model, image processing, generative network, ai ethic, natural language processing, clustering algorithm, feature extraction, time series forecast, anomaly detection, identity fraud detection, dimensionality reduction, feature elicitation, chatbot, clustering, unsupervised learning, supervised learning, convolutional network, adversarial network

WOS/eu_scope_countries.txt

@@ -0,0 +1 @@
+Austria, Belgium, Bulgaria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, France, Germany, Greece, Hungary, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Poland, Portugal, Romania, Slovakia, Slovenia, Spain, Sweden, Norway, Switzerland, United Kingdom, England, Wales, Scotland, N Ireland

WOS/wos_extract/wos_query_generator.ipynb

@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "focal_countries_list = [\"Peoples R china\", \"Hong Kong\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "outputs": [],
+   "source": [
+    "country_mode = \"CU\" #CU-country-region AU-address"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "outputs": [],
+   "source": [
+    "# (TS=(\"artificial intelligence\") OR TS=(\"machine learning\") OR TS=(\"neural network\") OR TS=(\"big data\") OR TS=(\"deep learning\") OR TS=(\"computer vision\") OR TS=(\"pattern recognition\")) AND"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'TS=(\"artificial intelligence\") OR TS=(\"machine learning\") OR TS=(\"neural network\") OR TS=(\"big data\") OR TS=(\"deep learning\") OR TS=(\"pattern recognition\") OR TS=(\"computer vision\") OR TS=(\"image classification\") OR TS=(\"reinforcement learning\") OR TS=(\"support vector machines\") OR TS=(\"recommender system\") OR TS=(\"random forest\") OR TS=(\"ensemble model\") OR TS=(\"image processing\") OR TS=(\"generative network\") OR TS=(\"ai ethic\") OR TS=(\"natural language processing\") OR TS=(\"clustering algorithm\") OR TS=(\"feature extraction\") OR TS=(\"time series forecast\") OR TS=(\"anomaly detection\") OR TS=(\"identity fraud detection\") OR TS=(\"dimensionality reduction\") OR TS=(\"feature elicitation\") OR TS=(\"chatbot\") OR TS=(\"clustering\") OR TS=(\"unsupervised learning\") OR TS=(\"supervised learning\") OR TS=(\"convolutional network\") OR TS=(\"adversarial network\")'"
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "keywords_source = r'..\\ai_scope_keywords.txt'\n",
+    "with open(keywords_source,'r') as f:\n",
+    "    keywords = f.readlines()\n",
+    "\n",
+    "keywords = [c.strip() for c in keywords[0].split(\",\")]\n",
+    "\n",
+    "keywords_str = ' OR '.join('TS=(\"'+k+'\")' for k in keywords)\n",
+    "keywords_str"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'CU=AUSTRIA OR CU=BELGIUM OR CU=BULGARIA OR CU=CROATIA OR CU=CYPRUS OR CU=CZECH REPUBLIC OR CU=DENMARK OR CU=ESTONIA OR CU=FINLAND OR CU=FRANCE OR CU=GERMANY OR CU=GREECE OR CU=HUNGARY OR CU=IRELAND OR CU=ITALY OR CU=LATVIA OR CU=LITHUANIA OR CU=LUXEMBOURG OR CU=MALTA OR CU=NETHERLANDS OR CU=POLAND OR CU=PORTUGAL OR CU=ROMANIA OR CU=SLOVAKIA OR CU=SLOVENIA OR CU=SPAIN OR CU=SWEDEN OR CU=NORWAY OR CU=SWITZERLAND OR CU=UNITED KINGDOM OR CU=ENGLAND OR CU=WALES OR CU=SCOTLAND OR CU=N IRELAND'"
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "scope_country_source = r'..\\eu_scope_countries.txt'\n",
+    "\n",
+    "with open(scope_country_source,'r') as f:\n",
+    "    coop_countries = f.readlines()\n",
+    "coop_countries = [c.strip().upper() for c in coop_countries[0].split(\",\")]\n",
+    "focal_countries = [c.strip().upper() for c in focal_countries_list]\n",
+    "\n",
+    "foc_str = ' OR '.join([country_mode+'='+c for c in focal_countries])\n",
+    "coop_str = ' OR '.join([country_mode+'='+c for c in coop_countries])\n",
+    "\n",
+    "coop_str"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'CU=PEOPLES R CHINA OR CU=HONG KONG'"
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "foc_str"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'(CU=PEOPLES R CHINA OR CU=HONG KONG) AND (CU=AUSTRIA OR CU=BELGIUM OR CU=BULGARIA OR CU=CROATIA OR CU=CYPRUS OR CU=CZECH REPUBLIC OR CU=DENMARK OR CU=ESTONIA OR CU=FINLAND OR CU=FRANCE OR CU=GERMANY OR CU=GREECE OR CU=HUNGARY OR CU=IRELAND OR CU=ITALY OR CU=LATVIA OR CU=LITHUANIA OR CU=LUXEMBOURG OR CU=MALTA OR CU=NETHERLANDS OR CU=POLAND OR CU=PORTUGAL OR CU=ROMANIA OR CU=SLOVAKIA OR CU=SLOVENIA OR CU=SPAIN OR CU=SWEDEN OR CU=NORWAY OR CU=SWITZERLAND OR CU=UNITED KINGDOM OR CU=ENGLAND OR CU=WALES OR CU=SCOTLAND OR CU=N IRELAND) AND (TS=(\"artificial intelligence\") OR TS=(\"machine learning\") OR TS=(\"neural network\") OR TS=(\"big data\") OR TS=(\"deep learning\") OR TS=(\"pattern recognition\") OR TS=(\"computer vision\") OR TS=(\"image classification\") OR TS=(\"reinforcement learning\") OR TS=(\"support vector machines\") OR TS=(\"recommender system\") OR TS=(\"random forest\") OR TS=(\"ensemble model\") OR TS=(\"image processing\") OR TS=(\"generative network\") OR TS=(\"ai ethic\") OR TS=(\"natural language processing\") OR TS=(\"clustering algorithm\") OR TS=(\"feature extraction\") OR TS=(\"time series forecast\") OR TS=(\"anomaly detection\") OR TS=(\"identity fraud detection\") OR TS=(\"dimensionality reduction\") OR TS=(\"feature elicitation\") OR TS=(\"chatbot\") OR TS=(\"clustering\") OR TS=(\"unsupervised learning\") OR TS=(\"supervised learning\") OR TS=(\"convolutional network\") OR TS=(\"adversarial network\"))'"
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "scope_query = f'({foc_str}) AND ({coop_str}) AND ({keywords_str})'\n",
+    "scope_query"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'(CU=AUSTRIA OR CU=BELGIUM OR CU=BULGARIA OR CU=CROATIA OR CU=CYPRUS OR CU=CZECH REPUBLIC OR CU=DENMARK OR CU=ESTONIA OR CU=FINLAND OR CU=FRANCE OR CU=GERMANY OR CU=GREECE OR CU=HUNGARY OR CU=IRELAND OR CU=ITALY OR CU=LATVIA OR CU=LITHUANIA OR CU=LUXEMBOURG OR CU=MALTA OR CU=NETHERLANDS OR CU=POLAND OR CU=PORTUGAL OR CU=ROMANIA OR CU=SLOVAKIA OR CU=SLOVENIA OR CU=SPAIN OR CU=SWEDEN OR CU=NORWAY OR CU=SWITZERLAND OR CU=UNITED KINGDOM OR CU=ENGLAND OR CU=WALES OR CU=SCOTLAND OR CU=N IRELAND) AND (TS=(\"artificial intelligence\") OR TS=(\"machine learning\") OR TS=(\"neural network\") OR TS=(\"big data\") OR TS=(\"deep learning\") OR TS=(\"pattern recognition\") OR TS=(\"computer vision\") OR TS=(\"image classification\") OR TS=(\"reinforcement learning\") OR TS=(\"support vector machines\") OR TS=(\"recommender system\") OR TS=(\"random forest\") OR TS=(\"ensemble model\") OR TS=(\"image processing\") OR TS=(\"generative network\") OR TS=(\"ai ethic\") OR TS=(\"natural language processing\") OR TS=(\"clustering algorithm\") OR TS=(\"feature extraction\") OR TS=(\"time series forecast\") OR TS=(\"anomaly detection\") OR TS=(\"identity fraud detection\") OR TS=(\"dimensionality reduction\") OR TS=(\"feature elicitation\") OR TS=(\"chatbot\") OR TS=(\"clustering\") OR TS=(\"unsupervised learning\") OR TS=(\"supervised learning\") OR TS=(\"convolutional network\") OR TS=(\"adversarial network\"))'"
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ch_scope_query = f'({coop_str}) AND ({keywords_str})'\n",
+    "ch_scope_query"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

WOS/wos_processing.ipynb

@@ -8,9 +8,9 @@
    "source": [
     "import numpy as np\n",
     "import pandas as pd\n",
-    "from tqdm import tqdm\n",
     "import os\n",
-    "import shutil"
+    "import shutil\n",
+    "from flashgeotext.geotext import GeoText"
    ]
   },
   {
@@ -121,12 +121,263 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "        UT (Unique WOS ID)                                      Keywords Plus   \n0      WOS:000852293800024  CONVOLUTIONAL NEURAL-NETWORK; DEEP LEARNING FR...  \\\n9714   WOS:000540750000002  STATE-SPACE RECONSTRUCTION; SURFACE AIR-TEMPER...   \n9697   WOS:000600708400002  COMPRESSIVE STRENGTH; MODELS; ADABOOST.RT; DUC...   \n9699   WOS:000511965100005              STRUCTURAL RELIABILITY; FAILURE MODES   \n9701   WOS:000663142500003  REFLECTED GPS SIGNALS; SOIL-MOISTURE; OCEAN; S...   \n...                    ...                                                ...   \n3066   WOS:000528727500074           LOCAL SEARCH; ALGORITHM; VARIANCE; MODEL   \n5097   WOS:000596139400001  INDUSTRY 4.0; MANAGEMENT; RISK; ANALYTICS; CHA...   \n11369  WOS:000436774300069                                                NaN   \n11368  WOS:000846290700001  PARTIAL LEAST-SQUARES; INFRARED-SPECTROSCOPY; ...   \n11362  WOS:000480527800025  MICROWAVE DIELECTRIC BEHAVIOR; GPS SIGNALS; RE...   \n\n                                         Author Keywords   \n0      Imaging; Three-dimensional displays; Electroma...  \\\n9714                                                 NaN   \n9697   Plastic hinge length; RC columns; Machine lear...   \n9699   system reliability; jacket platform; beta-unzi...   \n9701   Cyclone GNSS (CYGNSS); Sea surface wind speed;...   \n...                                                  ...   \n3066   sea surface temperature; sea surface temperatu...   \n5097   Big data finance; Big data in financial servic...   \n11369  planetary gear; fault diagnosis; VMD; center f...   \n11368  soil fertility class; reflectance spectroscopy...   \n11362  global navigation satellite system (GNSS)-refl...   \n\n                                           Article Title   \n0      Artificial Intelligence: New Frontiers in Real...  \\\n9714   Detecting causality from time series in a mach...   \n9697   Data-Driven Approach to Predict the Plastic Hi...   \n9699   System Reliability Analysis of an Offshore Jac...   \n9701   Analysis of coastal wind speed retrieval from ...   \n...                                                  ...   \n3066   Improved Particle Swarm Optimization for Sea S...   \n5097   Current landscape and influence of big data on...   \n11369  Planetary Gear Fault Diagnosis via Feature Ima...   \n11368  How Well Can Reflectance Spectroscopy Allocate...   \n11362  GNSS-R Soil Moisture Retrieval Based on a XGbo...   \n\n                                                Abstract  \n0      In recent years, artificial intelligence (AI) ...  \n9714   Detecting causality from observational data is...  \n9697   Inelastic response of reinforced concrete colu...  \n9699   This study investigates strategies for solving...  \n9701   This paper demonstrates the capability and per...  \n...                                                  ...  \n3066   The Sea Surface Temperature (SST) is one of th...  \n5097   Big data is one of the most recent business an...  \n11369  Poor working environment leads to frequent fai...  \n11368  Fertilization decisions depend on the measurem...  \n11362  Global navigation satellite system (GNSS)-refl...  \n\n[9889 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>Keywords Plus</th>\n      <th>Author Keywords</th>\n      <th>Article Title</th>\n      <th>Abstract</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>WOS:000852293800024</td>\n      <td>CONVOLUTIONAL NEURAL-NETWORK; DEEP LEARNING FR...</td>\n      <td>Imaging; Three-dimensional displays; Electroma...</td>\n      <td>Artificial Intelligence: New Frontiers in Real...</td>\n      <td>In recent years, artificial intelligence (AI) ...</td>\n    </tr>\n    <tr>\n      <th>9714</th>\n      <td>WOS:000540750000002</td>\n      <td>STATE-SPACE RECONSTRUCTION; SURFACE AIR-TEMPER...</td>\n      <td>NaN</td>\n      <td>Detecting causality from time series in a mach...</td>\n      <td>Detecting causality from observational data is...</td>\n    </tr>\n    <tr>\n      <th>9697</th>\n      <td>WOS:000600708400002</td>\n      <td>COMPRESSIVE STRENGTH; MODELS; ADABOOST.RT; DUC...</td>\n      <td>Plastic hinge length; RC columns; Machine lear...</td>\n      <td>Data-Driven Approach to Predict the Plastic Hi...</td>\n      <td>Inelastic response of reinforced concrete colu...</td>\n    </tr>\n    <tr>\n      <th>9699</th>\n      <td>WOS:000511965100005</td>\n      <td>STRUCTURAL RELIABILITY; FAILURE MODES</td>\n      <td>system reliability; jacket platform; beta-unzi...</td>\n      <td>System Reliability Analysis of an Offshore Jac...</td>\n      <td>This study investigates strategies for solving...</td>\n    </tr>\n    <tr>\n      <th>9701</th>\n      <td>WOS:000663142500003</td>\n      <td>REFLECTED GPS SIGNALS; SOIL-MOISTURE; OCEAN; S...</td>\n      <td>Cyclone GNSS (CYGNSS); Sea surface wind speed;...</td>\n      <td>Analysis of coastal wind speed retrieval from ...</td>\n      <td>This paper demonstrates the capability and per...</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>3066</th>\n      <td>WOS:000528727500074</td>\n      <td>LOCAL SEARCH; ALGORITHM; VARIANCE; MODEL</td>\n      <td>sea surface temperature; sea surface temperatu...</td>\n      <td>Improved Particle Swarm Optimization for Sea S...</td>\n      <td>The Sea Surface Temperature (SST) is one of th...</td>\n    </tr>\n    <tr>\n      <th>5097</th>\n      <td>WOS:000596139400001</td>\n      <td>INDUSTRY 4.0; MANAGEMENT; RISK; ANALYTICS; CHA...</td>\n      <td>Big data finance; Big data in financial servic...</td>\n      <td>Current landscape and influence of big data on...</td>\n      <td>Big data is one of the most recent business an...</td>\n    </tr>\n    <tr>\n      <th>11369</th>\n      <td>WOS:000436774300069</td>\n      <td>NaN</td>\n      <td>planetary gear; fault diagnosis; VMD; center f...</td>\n      <td>Planetary Gear Fault Diagnosis via Feature Ima...</td>\n      <td>Poor working environment leads to frequent fai...</td>\n    </tr>\n    <tr>\n      <th>11368</th>\n      <td>WOS:000846290700001</td>\n      <td>PARTIAL LEAST-SQUARES; INFRARED-SPECTROSCOPY; ...</td>\n      <td>soil fertility class; reflectance spectroscopy...</td>\n      <td>How Well Can Reflectance Spectroscopy Allocate...</td>\n      <td>Fertilization decisions depend on the measurem...</td>\n    </tr>\n    <tr>\n      <th>11362</th>\n      <td>WOS:000480527800025</td>\n      <td>MICROWAVE DIELECTRIC BEHAVIOR; GPS SIGNALS; RE...</td>\n      <td>global navigation satellite system (GNSS)-refl...</td>\n      <td>GNSS-R Soil Moisture Retrieval Based on a XGbo...</td>\n      <td>Global navigation satellite system (GNSS)-refl...</td>\n    </tr>\n  </tbody>\n</table>\n<p>9889 rows × 5 columns</p>\n</div>"
+     },
+     "execution_count": 11,
      "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wos[[record_col,\"Keywords Plus\",\"Author Keywords\",\"Article Title\",\"Abstract\"]]\n"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "        UT (Unique WOS ID)  level_1                           keyword\n0      WOS:000209536100003    11117                               NaN\n1      WOS:000297893800037    10831  ADAPTIVE DYNAMIC SURFACE CONTROL\n2      WOS:000297893800037    10831                NEURAL COMPENSATOR\n3      WOS:000297893800037    10831                    BUCK CONVERTER\n4      WOS:000297893800037    10831            FINITE-TIME IDENTIFIER\n...                    ...      ...                               ...\n94060  WOS:000947693400001      240                        EXPRESSION\n94061  WOS:000947693400001      240                         RNALOCATE\n94062  WOS:000947693400001      240                          PROTEINS\n94063  WOS:000947693400001      240                          RESOURCE\n94064  WOS:000947693400001      240                             CELLS\n\n[94065 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>UT (Unique WOS ID)</th>\n      <th>level_1</th>\n      <th>keyword</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>WOS:000209536100003</td>\n      <td>11117</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>WOS:000297893800037</td>\n      <td>10831</td>\n      <td>ADAPTIVE DYNAMIC SURFACE CONTROL</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>WOS:000297893800037</td>\n      <td>10831</td>\n      <td>NEURAL COMPENSATOR</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>WOS:000297893800037</td>\n      <td>10831</td>\n      <td>BUCK CONVERTER</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>WOS:000297893800037</td>\n      <td>10831</td>\n      <td>FINITE-TIME IDENTIFIER</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>94060</th>\n      <td>WOS:000947693400001</td>\n      <td>240</td>\n      <td>EXPRESSION</td>\n    </tr>\n    <tr>\n      <th>94061</th>\n      <td>WOS:000947693400001</td>\n      <td>240</td>\n      <td>RNALOCATE</td>\n    </tr>\n    <tr>\n      <th>94062</th>\n      <td>WOS:000947693400001</td>\n      <td>240</td>\n      <td>PROTEINS</td>\n    </tr>\n    <tr>\n      <th>94063</th>\n      <td>WOS:000947693400001</td>\n      <td>240</td>\n      <td>RESOURCE</td>\n    </tr>\n    <tr>\n      <th>94064</th>\n      <td>WOS:000947693400001</td>\n      <td>240</td>\n      <td>CELLS</td>\n    </tr>\n  </tbody>\n</table>\n<p>94065 rows × 3 columns</p>\n</div>"
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kw_df = pd.DataFrame()\n",
+    "for c in [\"Keywords Plus\",\"Author Keywords\"]:\n",
+    "    kwp = wos.groupby(record_col)[c].apply(lambda x: x.str.split(';')).explode().str.strip().str.upper()\n",
+    "    kwp.name = 'keyword'\n",
+    "    kw_df = pd.concat([kwp.reset_index(),kw_df],ignore_index=True)\n",
+    "kw_df"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "Downloading pytorch_model.bin:   0%|          | 0.00/438M [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "43fb040512964c61bdcca3e35d4e9778"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "ename": "ChunkedEncodingError",
+     "evalue": "(\"Connection broken: ConnectionResetError(10054, 'A létező kapcsolatot a távoli állomás kényszerítetten bezárta', None, 10054, None)\", ConnectionResetError(10054, 'A létező kapcsolatot a távoli állomás kényszerítetten bezárta', None, 10054, None))",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[1;31mConnectionResetError\u001B[0m                      Traceback (most recent call last)",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\urllib3\\response.py:444\u001B[0m, in \u001B[0;36mHTTPResponse._error_catcher\u001B[1;34m(self)\u001B[0m\n\u001B[0;32m    443\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m--> 444\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m\n\u001B[0;32m    446\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m SocketTimeout:\n\u001B[0;32m    447\u001B[0m     \u001B[38;5;66;03m# FIXME: Ideally we'd like to include the url in the ReadTimeoutError but\u001B[39;00m\n\u001B[0;32m    448\u001B[0m     \u001B[38;5;66;03m# there is yet no clean way to get at it from this context.\u001B[39;00m\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\urllib3\\response.py:567\u001B[0m, in \u001B[0;36mHTTPResponse.read\u001B[1;34m(self, amt, decode_content, cache_content)\u001B[0m\n\u001B[0;32m    566\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_error_catcher():\n\u001B[1;32m--> 567\u001B[0m     data \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_fp_read\u001B[49m\u001B[43m(\u001B[49m\u001B[43mamt\u001B[49m\u001B[43m)\u001B[49m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m fp_closed \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;124mb\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m    568\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m amt \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\urllib3\\response.py:533\u001B[0m, in \u001B[0;36mHTTPResponse._fp_read\u001B[1;34m(self, amt)\u001B[0m\n\u001B[0;32m    531\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m    532\u001B[0m     \u001B[38;5;66;03m# StringIO doesn't like amt=None\u001B[39;00m\n\u001B[1;32m--> 533\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_fp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mread\u001B[49m\u001B[43m(\u001B[49m\u001B[43mamt\u001B[49m\u001B[43m)\u001B[49m \u001B[38;5;28;01mif\u001B[39;00m amt \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_fp\u001B[38;5;241m.\u001B[39mread()\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\http\\client.py:463\u001B[0m, in \u001B[0;36mHTTPResponse.read\u001B[1;34m(self, amt)\u001B[0m\n\u001B[0;32m    462\u001B[0m b \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mbytearray\u001B[39m(amt)\n\u001B[1;32m--> 463\u001B[0m n \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mreadinto\u001B[49m\u001B[43m(\u001B[49m\u001B[43mb\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    464\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mmemoryview\u001B[39m(b)[:n]\u001B[38;5;241m.\u001B[39mtobytes()\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\http\\client.py:507\u001B[0m, in \u001B[0;36mHTTPResponse.readinto\u001B[1;34m(self, b)\u001B[0m\n\u001B[0;32m    504\u001B[0m \u001B[38;5;66;03m# we do not use _safe_read() here because this may be a .will_close\u001B[39;00m\n\u001B[0;32m    505\u001B[0m \u001B[38;5;66;03m# connection, and the user is reading more bytes than will be provided\u001B[39;00m\n\u001B[0;32m    506\u001B[0m \u001B[38;5;66;03m# (for example, reading in 1k chunks)\u001B[39;00m\n\u001B[1;32m--> 507\u001B[0m n \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mreadinto\u001B[49m\u001B[43m(\u001B[49m\u001B[43mb\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    508\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m n \u001B[38;5;129;01mand\u001B[39;00m b:\n\u001B[0;32m    509\u001B[0m     \u001B[38;5;66;03m# Ideally, we would raise IncompleteRead if the content-length\u001B[39;00m\n\u001B[0;32m    510\u001B[0m     \u001B[38;5;66;03m# wasn't satisfied, but it might break compatibility.\u001B[39;00m\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\socket.py:704\u001B[0m, in \u001B[0;36mSocketIO.readinto\u001B[1;34m(self, b)\u001B[0m\n\u001B[0;32m    703\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m--> 704\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_sock\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrecv_into\u001B[49m\u001B[43m(\u001B[49m\u001B[43mb\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    705\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m timeout:\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\ssl.py:1242\u001B[0m, in \u001B[0;36mSSLSocket.recv_into\u001B[1;34m(self, buffer, nbytes, flags)\u001B[0m\n\u001B[0;32m   1239\u001B[0m         \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mValueError\u001B[39;00m(\n\u001B[0;32m   1240\u001B[0m           \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mnon-zero flags not allowed in calls to recv_into() on \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[38;5;124m\"\u001B[39m \u001B[38;5;241m%\u001B[39m\n\u001B[0;32m   1241\u001B[0m           \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m\u001B[38;5;18m__class__\u001B[39m)\n\u001B[1;32m-> 1242\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mread\u001B[49m\u001B[43m(\u001B[49m\u001B[43mnbytes\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbuffer\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m   1243\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\ssl.py:1100\u001B[0m, in \u001B[0;36mSSLSocket.read\u001B[1;34m(self, len, buffer)\u001B[0m\n\u001B[0;32m   1099\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m buffer \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[1;32m-> 1100\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_sslobj\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mread\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mlen\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbuffer\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m   1101\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n",
+      "\u001B[1;31mConnectionResetError\u001B[0m: [WinError 10054] A létező kapcsolatot a távoli állomás kényszerítetten bezárta",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001B[1;31mProtocolError\u001B[0m                             Traceback (most recent call last)",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\requests\\models.py:816\u001B[0m, in \u001B[0;36mResponse.iter_content.<locals>.generate\u001B[1;34m()\u001B[0m\n\u001B[0;32m    815\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m--> 816\u001B[0m     \u001B[38;5;28;01myield from\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mraw\u001B[38;5;241m.\u001B[39mstream(chunk_size, decode_content\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m)\n\u001B[0;32m    817\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m ProtocolError \u001B[38;5;28;01mas\u001B[39;00m e:\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\urllib3\\response.py:628\u001B[0m, in \u001B[0;36mHTTPResponse.stream\u001B[1;34m(self, amt, decode_content)\u001B[0m\n\u001B[0;32m    627\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m is_fp_closed(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_fp):\n\u001B[1;32m--> 628\u001B[0m     data \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mread\u001B[49m\u001B[43m(\u001B[49m\u001B[43mamt\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mamt\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdecode_content\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mdecode_content\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    630\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m data:\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\urllib3\\response.py:593\u001B[0m, in \u001B[0;36mHTTPResponse.read\u001B[1;34m(self, amt, decode_content, cache_content)\u001B[0m\n\u001B[0;32m    584\u001B[0m             \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39menforce_content_length \u001B[38;5;129;01mand\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mlength_remaining \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;129;01min\u001B[39;00m (\n\u001B[0;32m    585\u001B[0m                 \u001B[38;5;241m0\u001B[39m,\n\u001B[0;32m    586\u001B[0m                 \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   (...)\u001B[0m\n\u001B[0;32m    591\u001B[0m                 \u001B[38;5;66;03m# raised during streaming, so all calls with incorrect\u001B[39;00m\n\u001B[0;32m    592\u001B[0m                 \u001B[38;5;66;03m# Content-Length are caught.\u001B[39;00m\n\u001B[1;32m--> 593\u001B[0m                 \u001B[38;5;28;01mraise\u001B[39;00m IncompleteRead(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_fp_bytes_read, \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mlength_remaining)\n\u001B[0;32m    595\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m data:\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\contextlib.py:137\u001B[0m, in \u001B[0;36m_GeneratorContextManager.__exit__\u001B[1;34m(self, typ, value, traceback)\u001B[0m\n\u001B[0;32m    136\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m--> 137\u001B[0m     \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mgen\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mthrow\u001B[49m\u001B[43m(\u001B[49m\u001B[43mtyp\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mvalue\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mtraceback\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    138\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mStopIteration\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m exc:\n\u001B[0;32m    139\u001B[0m     \u001B[38;5;66;03m# Suppress StopIteration *unless* it's the same exception that\u001B[39;00m\n\u001B[0;32m    140\u001B[0m     \u001B[38;5;66;03m# was passed to throw().  This prevents a StopIteration\u001B[39;00m\n\u001B[0;32m    141\u001B[0m     \u001B[38;5;66;03m# raised inside the \"with\" statement from being suppressed.\u001B[39;00m\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\urllib3\\response.py:461\u001B[0m, in \u001B[0;36mHTTPResponse._error_catcher\u001B[1;34m(self)\u001B[0m\n\u001B[0;32m    459\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m (HTTPException, SocketError) \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[0;32m    460\u001B[0m     \u001B[38;5;66;03m# This includes IncompleteRead.\u001B[39;00m\n\u001B[1;32m--> 461\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m ProtocolError(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mConnection broken: \u001B[39m\u001B[38;5;132;01m%r\u001B[39;00m\u001B[38;5;124m\"\u001B[39m \u001B[38;5;241m%\u001B[39m e, e)\n\u001B[0;32m    463\u001B[0m \u001B[38;5;66;03m# If no exception is thrown, we should avoid cleaning up\u001B[39;00m\n\u001B[0;32m    464\u001B[0m \u001B[38;5;66;03m# unnecessarily.\u001B[39;00m\n",
+      "\u001B[1;31mProtocolError\u001B[0m: (\"Connection broken: ConnectionResetError(10054, 'A létező kapcsolatot a távoli állomás kényszerítetten bezárta', None, 10054, None)\", ConnectionResetError(10054, 'A létező kapcsolatot a távoli állomás kényszerítetten bezárta', None, 10054, None))",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001B[1;31mChunkedEncodingError\u001B[0m                      Traceback (most recent call last)",
+      "Cell \u001B[1;32mIn[39], line 7\u001B[0m\n\u001B[0;32m      4\u001B[0m \u001B[38;5;66;03m# Uses stopwords for english from NLTK, and all puntuation characters by\u001B[39;00m\n\u001B[0;32m      5\u001B[0m \u001B[38;5;66;03m# default\u001B[39;00m\n\u001B[0;32m      6\u001B[0m r \u001B[38;5;241m=\u001B[39m Rake()\n\u001B[1;32m----> 7\u001B[0m kw_model \u001B[38;5;241m=\u001B[39m \u001B[43mKeyBERT\u001B[49m\u001B[43m(\u001B[49m\u001B[43mmodel\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43mall-mpnet-base-v2\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\keybert\\_model.py:55\u001B[0m, in \u001B[0;36mKeyBERT.__init__\u001B[1;34m(self, model)\u001B[0m\n\u001B[0;32m     39\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m__init__\u001B[39m(\u001B[38;5;28mself\u001B[39m, model\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mall-MiniLM-L6-v2\u001B[39m\u001B[38;5;124m\"\u001B[39m):\n\u001B[0;32m     40\u001B[0m     \u001B[38;5;124;03m\"\"\"KeyBERT initialization\u001B[39;00m\n\u001B[0;32m     41\u001B[0m \n\u001B[0;32m     42\u001B[0m \u001B[38;5;124;03m    Arguments:\u001B[39;00m\n\u001B[1;32m   (...)\u001B[0m\n\u001B[0;32m     53\u001B[0m \u001B[38;5;124;03m                  * https://www.sbert.net/docs/pretrained_models.html\u001B[39;00m\n\u001B[0;32m     54\u001B[0m \u001B[38;5;124;03m    \"\"\"\u001B[39;00m\n\u001B[1;32m---> 55\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mmodel \u001B[38;5;241m=\u001B[39m \u001B[43mselect_backend\u001B[49m\u001B[43m(\u001B[49m\u001B[43mmodel\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\keybert\\backend\\_utils.py:49\u001B[0m, in \u001B[0;36mselect_backend\u001B[1;34m(embedding_model)\u001B[0m\n\u001B[0;32m     47\u001B[0m \u001B[38;5;66;03m# Create a Sentence Transformer model based on a string\u001B[39;00m\n\u001B[0;32m     48\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(embedding_model, \u001B[38;5;28mstr\u001B[39m):\n\u001B[1;32m---> 49\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mSentenceTransformerBackend\u001B[49m\u001B[43m(\u001B[49m\u001B[43membedding_model\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     51\u001B[0m \u001B[38;5;66;03m# Hugging Face embeddings\u001B[39;00m\n\u001B[0;32m     52\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(embedding_model, Pipeline):\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\keybert\\backend\\_sentencetransformers.py:42\u001B[0m, in \u001B[0;36mSentenceTransformerBackend.__init__\u001B[1;34m(self, embedding_model)\u001B[0m\n\u001B[0;32m     40\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39membedding_model \u001B[38;5;241m=\u001B[39m embedding_model\n\u001B[0;32m     41\u001B[0m \u001B[38;5;28;01melif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(embedding_model, \u001B[38;5;28mstr\u001B[39m):\n\u001B[1;32m---> 42\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39membedding_model \u001B[38;5;241m=\u001B[39m \u001B[43mSentenceTransformer\u001B[49m\u001B[43m(\u001B[49m\u001B[43membedding_model\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     43\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m     44\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mValueError\u001B[39;00m(\n\u001B[0;32m     45\u001B[0m         \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mPlease select a correct SentenceTransformers model: \u001B[39m\u001B[38;5;130;01m\\n\u001B[39;00m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m     46\u001B[0m         \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m`from sentence_transformers import SentenceTransformer` \u001B[39m\u001B[38;5;130;01m\\n\u001B[39;00m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m     47\u001B[0m         \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m`model = SentenceTransformer(\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mall-MiniLM-L6-v2\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124m)`\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m     48\u001B[0m     )\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\sentence_transformers\\SentenceTransformer.py:87\u001B[0m, in \u001B[0;36mSentenceTransformer.__init__\u001B[1;34m(self, model_name_or_path, modules, device, cache_folder, use_auth_token)\u001B[0m\n\u001B[0;32m     83\u001B[0m     model_path \u001B[38;5;241m=\u001B[39m os\u001B[38;5;241m.\u001B[39mpath\u001B[38;5;241m.\u001B[39mjoin(cache_folder, model_name_or_path\u001B[38;5;241m.\u001B[39mreplace(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m/\u001B[39m\u001B[38;5;124m\"\u001B[39m, \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m_\u001B[39m\u001B[38;5;124m\"\u001B[39m))\n\u001B[0;32m     85\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m os\u001B[38;5;241m.\u001B[39mpath\u001B[38;5;241m.\u001B[39mexists(os\u001B[38;5;241m.\u001B[39mpath\u001B[38;5;241m.\u001B[39mjoin(model_path, \u001B[38;5;124m'\u001B[39m\u001B[38;5;124mmodules.json\u001B[39m\u001B[38;5;124m'\u001B[39m)):\n\u001B[0;32m     86\u001B[0m         \u001B[38;5;66;03m# Download from hub with caching\u001B[39;00m\n\u001B[1;32m---> 87\u001B[0m         \u001B[43msnapshot_download\u001B[49m\u001B[43m(\u001B[49m\u001B[43mmodel_name_or_path\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m     88\u001B[0m \u001B[43m                            \u001B[49m\u001B[43mcache_dir\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcache_folder\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m     89\u001B[0m \u001B[43m                            \u001B[49m\u001B[43mlibrary_name\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43msentence-transformers\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[0;32m     90\u001B[0m \u001B[43m                            \u001B[49m\u001B[43mlibrary_version\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m__version__\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m     91\u001B[0m \u001B[43m                            \u001B[49m\u001B[43mignore_files\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m[\u001B[49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43mflax_model.msgpack\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43mrust_model.ot\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43mtf_model.h5\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m]\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m     92\u001B[0m \u001B[43m                            \u001B[49m\u001B[43muse_auth_token\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43muse_auth_token\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     94\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m os\u001B[38;5;241m.\u001B[39mpath\u001B[38;5;241m.\u001B[39mexists(os\u001B[38;5;241m.\u001B[39mpath\u001B[38;5;241m.\u001B[39mjoin(model_path, \u001B[38;5;124m'\u001B[39m\u001B[38;5;124mmodules.json\u001B[39m\u001B[38;5;124m'\u001B[39m)):    \u001B[38;5;66;03m#Load as SentenceTransformer model\u001B[39;00m\n\u001B[0;32m     95\u001B[0m     modules \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_load_sbert_model(model_path)\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\sentence_transformers\\util.py:491\u001B[0m, in \u001B[0;36msnapshot_download\u001B[1;34m(repo_id, revision, cache_dir, library_name, library_version, user_agent, ignore_files, use_auth_token)\u001B[0m\n\u001B[0;32m    486\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m version\u001B[38;5;241m.\u001B[39mparse(huggingface_hub\u001B[38;5;241m.\u001B[39m__version__) \u001B[38;5;241m>\u001B[39m\u001B[38;5;241m=\u001B[39m version\u001B[38;5;241m.\u001B[39mparse(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m0.8.1\u001B[39m\u001B[38;5;124m\"\u001B[39m):\n\u001B[0;32m    487\u001B[0m     \u001B[38;5;66;03m# huggingface_hub v0.8.1 introduces a new cache layout. We sill use a manual layout\u001B[39;00m\n\u001B[0;32m    488\u001B[0m     \u001B[38;5;66;03m# And need to pass legacy_cache_layout=True to avoid that a warning will be printed\u001B[39;00m\n\u001B[0;32m    489\u001B[0m     cached_download_args[\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mlegacy_cache_layout\u001B[39m\u001B[38;5;124m'\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mTrue\u001B[39;00m\n\u001B[1;32m--> 491\u001B[0m path \u001B[38;5;241m=\u001B[39m cached_download(\u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mcached_download_args)\n\u001B[0;32m    493\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m os\u001B[38;5;241m.\u001B[39mpath\u001B[38;5;241m.\u001B[39mexists(path \u001B[38;5;241m+\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m.lock\u001B[39m\u001B[38;5;124m\"\u001B[39m):\n\u001B[0;32m    494\u001B[0m     os\u001B[38;5;241m.\u001B[39mremove(path \u001B[38;5;241m+\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m.lock\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\huggingface_hub\\utils\\_validators.py:120\u001B[0m, in \u001B[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001B[1;34m(*args, **kwargs)\u001B[0m\n\u001B[0;32m    117\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m check_use_auth_token:\n\u001B[0;32m    118\u001B[0m     kwargs \u001B[38;5;241m=\u001B[39m smoothly_deprecate_use_auth_token(fn_name\u001B[38;5;241m=\u001B[39mfn\u001B[38;5;241m.\u001B[39m\u001B[38;5;18m__name__\u001B[39m, has_token\u001B[38;5;241m=\u001B[39mhas_token, kwargs\u001B[38;5;241m=\u001B[39mkwargs)\n\u001B[1;32m--> 120\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m fn(\u001B[38;5;241m*\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\huggingface_hub\\file_download.py:780\u001B[0m, in \u001B[0;36mcached_download\u001B[1;34m(url, library_name, library_version, cache_dir, user_agent, force_download, force_filename, proxies, etag_timeout, resume_download, token, local_files_only, legacy_cache_layout)\u001B[0m\n\u001B[0;32m    777\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m temp_file_manager() \u001B[38;5;28;01mas\u001B[39;00m temp_file:\n\u001B[0;32m    778\u001B[0m     logger\u001B[38;5;241m.\u001B[39minfo(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mdownloading \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[38;5;124m to \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[38;5;124m\"\u001B[39m, url, temp_file\u001B[38;5;241m.\u001B[39mname)\n\u001B[1;32m--> 780\u001B[0m     \u001B[43mhttp_get\u001B[49m\u001B[43m(\u001B[49m\n\u001B[0;32m    781\u001B[0m \u001B[43m        \u001B[49m\u001B[43murl_to_download\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m    782\u001B[0m \u001B[43m        \u001B[49m\u001B[43mtemp_file\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m    783\u001B[0m \u001B[43m        \u001B[49m\u001B[43mproxies\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mproxies\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m    784\u001B[0m \u001B[43m        \u001B[49m\u001B[43mresume_size\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mresume_size\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m    785\u001B[0m \u001B[43m        \u001B[49m\u001B[43mheaders\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m    786\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    788\u001B[0m logger\u001B[38;5;241m.\u001B[39minfo(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mstoring \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[38;5;124m in cache at \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[38;5;124m\"\u001B[39m, url, cache_path)\n\u001B[0;32m    789\u001B[0m _chmod_and_replace(temp_file\u001B[38;5;241m.\u001B[39mname, cache_path)\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\huggingface_hub\\file_download.py:538\u001B[0m, in \u001B[0;36mhttp_get\u001B[1;34m(url, temp_file, proxies, resume_size, headers, timeout, max_retries)\u001B[0m\n\u001B[0;32m    528\u001B[0m     displayed_name \u001B[38;5;241m=\u001B[39m \u001B[38;5;124mf\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m(…)\u001B[39m\u001B[38;5;132;01m{\u001B[39;00mdisplayed_name[\u001B[38;5;241m-\u001B[39m\u001B[38;5;241m20\u001B[39m:]\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m    530\u001B[0m progress \u001B[38;5;241m=\u001B[39m tqdm(\n\u001B[0;32m    531\u001B[0m     unit\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mB\u001B[39m\u001B[38;5;124m\"\u001B[39m,\n\u001B[0;32m    532\u001B[0m     unit_scale\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m,\n\u001B[1;32m   (...)\u001B[0m\n\u001B[0;32m    536\u001B[0m     disable\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mbool\u001B[39m(logger\u001B[38;5;241m.\u001B[39mgetEffectiveLevel() \u001B[38;5;241m==\u001B[39m logging\u001B[38;5;241m.\u001B[39mNOTSET),\n\u001B[0;32m    537\u001B[0m )\n\u001B[1;32m--> 538\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m chunk \u001B[38;5;129;01min\u001B[39;00m r\u001B[38;5;241m.\u001B[39miter_content(chunk_size\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m10\u001B[39m \u001B[38;5;241m*\u001B[39m \u001B[38;5;241m1024\u001B[39m \u001B[38;5;241m*\u001B[39m \u001B[38;5;241m1024\u001B[39m):\n\u001B[0;32m    539\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m chunk:  \u001B[38;5;66;03m# filter out keep-alive new chunks\u001B[39;00m\n\u001B[0;32m    540\u001B[0m         progress\u001B[38;5;241m.\u001B[39mupdate(\u001B[38;5;28mlen\u001B[39m(chunk))\n",
+      "File \u001B[1;32m~\\Anaconda3\\envs\\MOME_BIGDATA\\lib\\site-packages\\requests\\models.py:818\u001B[0m, in \u001B[0;36mResponse.iter_content.<locals>.generate\u001B[1;34m()\u001B[0m\n\u001B[0;32m    816\u001B[0m     \u001B[38;5;28;01myield from\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mraw\u001B[38;5;241m.\u001B[39mstream(chunk_size, decode_content\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m)\n\u001B[0;32m    817\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m ProtocolError \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m--> 818\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m ChunkedEncodingError(e)\n\u001B[0;32m    819\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m DecodeError \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[0;32m    820\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m ContentDecodingError(e)\n",
+      "\u001B[1;31mChunkedEncodingError\u001B[0m: (\"Connection broken: ConnectionResetError(10054, 'A létező kapcsolatot a távoli állomás kényszerítetten bezárta', None, 10054, None)\", ConnectionResetError(10054, 'A létező kapcsolatot a távoli állomás kényszerítetten bezárta', None, 10054, None))"
+     ]
+    }
+   ],
+   "source": [
+    "from rake_nltk import Rake\n",
+    "from keybert import KeyBERT\n",
+    "\n",
+    "# Uses stopwords for english from NLTK, and all puntuation characters by\n",
+    "# default\n",
+    "r = Rake()\n",
+    "kw_model = KeyBERT(model='all-mpnet-base-v2')\n",
+    "\n",
+    "# Extraction given the text.\n",
+    "# r.extract_keywords_from_text(<text to process>)\n",
+    "\n",
+    "# keywords = kw_model.extract_keywords(full_text,\n",
+    "#\n",
+    "#                                      keyphrase_ngram_range=(1, 3),\n",
+    "#\n",
+    "#                                      stop_words='english',\n",
+    "#\n",
+    "#                                      highlight=False,\n",
+    "#\n",
+    "#                                      top_n=10)\n",
+    "#\n",
+    "# keywords_list= list(dict(keywords).keys())"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'NoneType' object has no attribute 'get_ranked_phrases'",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[1;31mAttributeError\u001B[0m                            Traceback (most recent call last)",
+      "Cell \u001B[1;32mIn[32], line 1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m \u001B[43mRake\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mextract_keywords_from_text\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmy time to shine\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget_ranked_phrases\u001B[49m()\n",
+      "\u001B[1;31mAttributeError\u001B[0m: 'NoneType' object has no attribute 'get_ranked_phrases'"
+     ]
+    }
+   ],
+   "source": [
+    "Rake().extract_keywords_from_text(\"my time to shine\").get_ranked_phrases()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
    "outputs": [],
    "source": [
-    "from flashgeotext.geotext import GeoText\n",
+    "def kwd_rake(text):\n",
+    "    r = Rake()\n",
+    "    r.extract_keywords_from_sentences(text)\n",
+    "    return r.get_ranked_phrases()\n",
     "\n",
+    "kwds_rake = wos[\"Abstract\"].fillna(\"\").map(kwd_rake)\n",
+    "# kwds_bert = wos[\"A\"]\n"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0        [brief summary could help us better understand...\n9714     [known phase space reconstruction based causal...\n9697     [column behavior requires accurate plastic hin...\n9699     [approach needs excessive computational effort...\n9701     [proposed ann model achieves good wind speed r...\n                               ...                        \n3066     [key factors affecting ocean climate change, r...\n5097     [big data influences different financial secto...\n11369    [planetary gear fault diagnosis via feature im...\n11368    [simultaneously predict various soil fertility...\n11362    [recently developed ensemble machine learning ...\nName: Abstract, Length: 9889, dtype: object"
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kwds_rake"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0        None\n9714     None\n9697     None\n9699     None\n9701     None\n         ... \n3066     None\n5097     None\n11369    None\n11368    None\n11362    None\nName: Abstract, Length: 9889, dtype: object"
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kwds_rake"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'Keywords Plus'"
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "geotext = GeoText()\n",
     "\n",
     "def extract_location(input_text, key='countries'):\n",