ZSI_Reconnect_China/PATSTAT/patstat_analysis_pipeline.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "import janitor\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from matplotlib.ticker import MaxNLocator\n",
    "import math\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "outputs": [],
   "source": [
    "outdir=\"EU_CH_scope\"\n",
    "\n",
    "appln = pd.read_csv(f\"{outdir}/tls_201_scope.csv\")\n",
    "\n",
    "appln_title = pd.read_csv(f\"{outdir}/tls_202_scope.csv\")\n",
    "\n",
    "pers = pd.read_csv(f\"{outdir}/tls_206_scope.csv\")\n",
    "pers['psn_sector'] = pers['psn_sector'].fillna(\"UNKNOWN\")\n",
    "\n",
    "appln_pers = pd.read_csv(f\"{outdir}/tls_207_scope.csv\")\n",
    "\n",
    "appln_cpc = pd.read_csv(f\"{outdir}/tls_224_scope.csv\")\n",
    "\n",
    "cpc_def = pd. read_csv(\"CPC_data/cpc_defs.csv\", low_memory=False)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "outputs": [
    {
     "data": {
      "text/plain": "65136"
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(appln)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "outputs": [
    {
     "data": {
      "text/plain": "              cpc_id                                           cpc_name   \n12725   A61B1/000096                    {using artificial intelligence}  \\\n13746       A61B5/72  {Signal processing specially adapted for physi...   \n13764     A61B5/7264  {Classification of physiological signals or da...   \n13897       A61B6/52  {Devices using data or image processing specia...   \n14016       A61B8/52  {Devices using data or image processing specia...   \n...              ...                                                ...   \n246159   Y10S128/924                      using artificial intelligence   \n246160   Y10S128/925                                     Neural network   \n248454   Y10S323/909                                     Remote sensing   \n250570    Y10S706/00           Data processing: artificial intelligence   \n250571    Y10S706/90                                        Fuzzy logic   \n\n       section  class subclass  group  main_group  cpc_version   \n12725        A   61.0        B    1.0        96.0         2023  \\\n13746        A   61.0        B    5.0        72.0         2023   \n13764        A   61.0        B    5.0      7264.0         2023   \n13897        A   61.0        B    6.0        52.0         2023   \n14016        A   61.0        B    8.0        52.0         2023   \n...        ...    ...      ...    ...         ...          ...   \n246159       Y   10.0        S  128.0       924.0         2023   \n246160       Y   10.0        S  128.0       925.0         2023   \n248454       Y   10.0        S  323.0       909.0         2023   \n250570       Y   10.0        S  706.0         0.0         2023   \n250571       Y   10.0        S  706.0        90.0         2023   \n\n       version https://git-lfs.github.com/spec/v1   \n12725                                         NaN  \\\n13746                                         NaN   \n13764                                         NaN   \n13897                                         NaN   \n14016                                         NaN   \n...                                           ...   \n246159                                        NaN   \n246160                                        NaN   \n248454                                        NaN   \n250570                                        NaN   \n250571                                        NaN   \n\n                                             cpc_taxonomy   \n12725   [('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...  \\\n13746   [('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...   \n13764   [('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...   \n13897   [('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...   \n14016   [('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...   \n...                                                   ...   \n246159  [('Y', 'GENERAL TAGGING OF NEW TECHNOLOGICAL D...   \n246160  [('Y', 'GENERAL TAGGING OF NEW TECHNOLOGICAL D...   \n248454  [('Y', 'GENERAL TAGGING OF NEW TECHNOLOGICAL D...   \n250570  [('Y', 'GENERAL TAGGING OF NEW TECHNOLOGICAL D...   \n250571  [('Y', 'GENERAL TAGGING OF NEW TECHNOLOGICAL D...   \n\n                                             cpc_fullname   \n12725   HUMAN NECESSITIES<>MEDICAL OR VETERINARY SCIEN...  \\\n13746   HUMAN NECESSITIES<>MEDICAL OR VETERINARY SCIEN...   \n13764   HUMAN NECESSITIES<>MEDICAL OR VETERINARY SCIEN...   \n13897   HUMAN NECESSITIES<>MEDICAL OR VETERINARY SCIEN...   \n14016   HUMAN NECESSITIES<>MEDICAL OR VETERINARY SCIEN...   \n...                                                   ...   \n246159  GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPME...   \n246160  GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPME...   \n248454  GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPME...   \n250570  GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPME...   \n250571  GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPME...   \n\n                                              tax_level_0   \n12725                                   HUMAN NECESSITIES  \\\n13746                                   HUMAN NECESSITIES   \n13764               
      "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>cpc_id</th>\n      <th>cpc_name</th>\n      <th>section</th>\n      <th>class</th>\n      <th>subclass</th>\n      <th>group</th>\n      <th>main_group</th>\n      <th>cpc_version</th>\n      <th>version https://git-lfs.github.com/spec/v1</th>\n      <th>cpc_taxonomy</th>\n      <th>cpc_fullname</th>\n      <th>tax_level_0</th>\n      <th>tax_level_1</th>\n      <th>tax_level_2</th>\n      <th>tax_level_3</th>\n      <th>tax_level_4</th>\n      <th>tax_level_5</th>\n      <th>tax_level_6</th>\n      <th>tax_level_7</th>\n      <th>data_scope</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>12725</th>\n      <td>A61B1/000096</td>\n      <td>{using artificial intelligence}</td>\n      <td>A</td>\n      <td>61.0</td>\n      <td>B</td>\n      <td>1.0</td>\n      <td>96.0</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...</td>\n      <td>HUMAN NECESSITIES&lt;&gt;MEDICAL OR VETERINARY SCIEN...</td>\n      <td>HUMAN NECESSITIES</td>\n      <td>MEDICAL OR VETERINARY SCIENCE; HYGIENE</td>\n      <td>DIAGNOSIS; SURGERY; IDENTIFICATION (analysing ...</td>\n      <td>Instruments for performing medical examination...</td>\n      <td>{of image signals during a use of endoscope}</td>\n      <td>{using artificial intelligence}</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>13746</th>\n      <td>A61B5/72</td>\n      <td>{Signal processing specially adapted for physi...</td>\n      <td>A</td>\n      <td>61.0</td>\n      <td>B</td>\n      <td>5.0</td>\n      <td>72.0</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...</td>\n      <td>HUMAN NECESSITIES&lt;&gt;MEDICAL OR VETERINARY SCIEN...</td>\n      <td>HUMAN NECESSITIES</td>\n      <td>MEDICAL OR VETERINARY SCIENCE; HYGIENE</td>\n      <td>DIAGNOSIS; SURGERY; IDENTIFICATION (analysing ...</td>\n      <td>{Signal processing specially adapted for physi...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>13764</th>\n      <td>A61B5/7264</td>\n      <td>{Classification of physiological signals or da...</td>\n      <td>A</td>\n      <td>61.0</td>\n      <td>B</td>\n      <td>5.0</td>\n      <td>7264.0</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...</td>\n      <td>HUMAN NECESSITIES&lt;&gt;MEDICAL OR VETERINARY SCIEN...</td>\n      <td>HUMAN NECESSITIES</td>\n      <td>MEDICAL OR VETERINARY SCIENCE; HYGIENE</td>\n      <td>DIAGNOSIS; SURGERY; IDENTIFICATION (analysing ...</td>\n      <td>{Signal processing specially adapted for physi...</td>\n      <td>{using Wavelet transforms}</td>\n      <td>{Classification of physiological signals or da...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>13897</th>\n      <td>A61B6/52</td>\n      <td>{Devices using data or image processing specia...</td>\n      <td>A</td>\n      <td>61.0</td>\n      <td>B</td>\n      <td>6.0</td>\n      <td>52.0</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[('A', 'HUMAN NECESSITIES'), ('A61', 'MEDICAL ...</td>\n      <td>HUMAN NECESSITIES&lt;&gt;MEDICAL OR VETERINARY SCIEN...</td>\n      <td>HUMAN NECESSITIES</td>\n      <td>MEDICAL OR VETERINARY SCIENCE; HYGIENE</td>\n      <td>DIAGNOSIS; SURGERY; IDENTIFICATION (analysing ...</td>\n      <td>{Devices using data or image processing specia...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>14016</th>\n      <td>A61B8/52</td>\n  
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cpc_def[cpc_def[\"data_scope\"]==True]"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "outputs": [
    {
     "data": {
      "text/plain": "        appln_id appln_auth      appln_nr appln_kind appln_filing_date   \n33934  497577215         BR  112014017433         A         2013-01-15  \\\n2981   375177905         TW     100128243         A         2011-08-08   \n34857  500398671         US  201815918757         A         2018-03-12   \n14330  425909090         US  201313948663         A         2013-07-23   \n12337  421949639         US  201313799810         A         2013-03-13   \n...          ...        ...           ...        ...               ...   \n20853  451232832         US  201314892356         A         2013-06-05   \n57178  558607779         WO    2020082459         W         2020-03-31   \n60907  571924211         WO    2022025191         W         2022-04-27   \n36638  505223478         CA       3027451         A         2017-06-14   \n33120  496062856         US  201615739023         A         2016-06-21   \n\n       appln_filing_year appln_nr_original ipr_type receiving_office   \n33934               2013      112014017433       PI                   \\\n2981                2011         100128243       PI                    \n34857               2018          15918757       PI                    \n14330               2013          13948663       PI                    \n12337               2013          13799810       PI                    \n...                  ...               ...      ...              ...   \n20853               2013          14892356       PI                    \n57178               2020     CN2020/082459       PI               CN   \n60907               2022     EP2022/025191       PI               EP   \n36638               2017           3027451       PI                    \n33120               2016          15739023       PI                    \n\n       internat_appln_id  ... earliest_publn_date earliest_publn_year   \n33934          379982555  ...          2017-06-13                2017  \\\n2981                   0  ...          2012-04-01                2012   \n34857          329543408  ...          2018-09-27                2018   \n14330                  0  ...          2015-01-29                2015   \n12337                  0  ...          2014-09-18                2014   \n...                  ...  ...                 ...                 ...   \n20853          424456242  ...          2016-04-14                2016   \n57178                  0  ...          2021-10-07                2021   \n60907                  0  ...          2022-11-24                2022   \n36638          479992612  ...          2017-12-21                2017   \n33120          473240582  ...          2018-06-21                2018   \n\n      earliest_pat_publn_id granted  docdb_family_id  inpadoc_family_id   \n33934             490635945       N         47605490          379982555  \\\n2981              380050378       N         44677979          336552941   \n34857             500398672       Y         43858368          273565445   \n14330             425909091       Y         51167733          419869995   \n12337             421949640       Y         50241294          416000492   \n...                     ...     ...              ...                ...   \n20853             451232833       Y         52007415          424456242   \n57178             558607780       N         77927568          558607779   \n60907             583339295       N         81756758          571924211   \n36638             505223479       N         58241906          476382802   \n33120             496062857       Y         53496595          442016492   \n\n      docdb_family_size  nb_citing_docdb_fam  nb_applicants nb_inventors  \n33934                 9                    6              1            4  \n2981                  5                    6              1            3  \n34857                12                   17              1            3  \n14330                 3                   19              1            4  \n12337                 4                   19              1            2  \n...                 ...       
      "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>appln_id</th>\n      <th>appln_auth</th>\n      <th>appln_nr</th>\n      <th>appln_kind</th>\n      <th>appln_filing_date</th>\n      <th>appln_filing_year</th>\n      <th>appln_nr_original</th>\n      <th>ipr_type</th>\n      <th>receiving_office</th>\n      <th>internat_appln_id</th>\n      <th>...</th>\n      <th>earliest_publn_date</th>\n      <th>earliest_publn_year</th>\n      <th>earliest_pat_publn_id</th>\n      <th>granted</th>\n      <th>docdb_family_id</th>\n      <th>inpadoc_family_id</th>\n      <th>docdb_family_size</th>\n      <th>nb_citing_docdb_fam</th>\n      <th>nb_applicants</th>\n      <th>nb_inventors</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>33934</th>\n      <td>497577215</td>\n      <td>BR</td>\n      <td>112014017433</td>\n      <td>A</td>\n      <td>2013-01-15</td>\n      <td>2013</td>\n      <td>112014017433</td>\n      <td>PI</td>\n      <td></td>\n      <td>379982555</td>\n      <td>...</td>\n      <td>2017-06-13</td>\n      <td>2017</td>\n      <td>490635945</td>\n      <td>N</td>\n      <td>47605490</td>\n      <td>379982555</td>\n      <td>9</td>\n      <td>6</td>\n      <td>1</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>2981</th>\n      <td>375177905</td>\n      <td>TW</td>\n      <td>100128243</td>\n      <td>A</td>\n      <td>2011-08-08</td>\n      <td>2011</td>\n      <td>100128243</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>2012-04-01</td>\n      <td>2012</td>\n      <td>380050378</td>\n      <td>N</td>\n      <td>44677979</td>\n      <td>336552941</td>\n      <td>5</td>\n      <td>6</td>\n      <td>1</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>34857</th>\n      <td>500398671</td>\n      <td>US</td>\n      <td>201815918757</td>\n      <td>A</td>\n      <td>2018-03-12</td>\n      <td>2018</td>\n      <td>15918757</td>\n      <td>PI</td>\n      <td></td>\n      <td>329543408</td>\n      <td>...</td>\n      <td>2018-09-27</td>\n      <td>2018</td>\n      <td>500398672</td>\n      <td>Y</td>\n      <td>43858368</td>\n      <td>273565445</td>\n      <td>12</td>\n      <td>17</td>\n      <td>1</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>14330</th>\n      <td>425909090</td>\n      <td>US</td>\n      <td>201313948663</td>\n      <td>A</td>\n      <td>2013-07-23</td>\n      <td>2013</td>\n      <td>13948663</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>2015-01-29</td>\n      <td>2015</td>\n      <td>425909091</td>\n      <td>Y</td>\n      <td>51167733</td>\n      <td>419869995</td>\n      <td>3</td>\n      <td>19</td>\n      <td>1</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>12337</th>\n      <td>421949639</td>\n      <td>US</td>\n      <td>201313799810</td>\n      <td>A</td>\n      <td>2013-03-13</td>\n      <td>2013</td>\n      <td>13799810</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>2014-09-18</td>\n      <td>2014</td>\n      <td>421949640</td>\n      <td>Y</td>\n      <td>50241294</td>\n      <td>416000492</td>\n      <td>4</td>\n      <td>19</td>\n      <td>1</td>\n      <td>2</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      <td>...</td>\n    </tr>\n    <tr>\n      <th>20853</th>\n      <td>451232832</td>\n      <td>U
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "appln.sample(100)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "outputs": [
    {
     "data": {
      "text/plain": "        appln_id appln_title_lg   \n46635  531117386             en  \\\n44552  526116621             en   \n45476  528352131             en   \n23619  470837180             en   \n33233  496310125             en   \n...          ...            ...   \n61597  574732234             en   \n54568  551189734             en   \n35847  503315942             en   \n49995  540002470             en   \n14915  437594613             en   \n\n                                             appln_title  \n46635  FRACTURING OPERATIONS PUMP FLEET BALANCE CONTR...  \n44552  SHEETLIKE COMPOSITE, IN PARTICULAR FOR THE PRO...  \n45476               NATURALLY SWEET ENHANCER COMPOSITION  \n23619  METHOD AND APPARATUS FOR MONITORING RADIO LINK...  \n33233  METHOD AND DEVICE FOR CONNECTING TO ACCESS POI...  \n...                                                  ...  \n61597  ADJUSTMENT MECHANISM FOR CIRCUIT BREAKER AND C...  \n54568  METHODS FOR PDCCH MONITORING, USER EQUIPMENT, ...  \n35847  SINGLE-WHEEL DRIVE COMPONENT FOR A MOTOR VEHIC...  \n49995  METHODS PROVIDING V2X APPLICATION SERVER REGIS...  \n14915  Carbon dots (c dots), method for their prepara...  \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>appln_id</th>\n      <th>appln_title_lg</th>\n      <th>appln_title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>46635</th>\n      <td>531117386</td>\n      <td>en</td>\n      <td>FRACTURING OPERATIONS PUMP FLEET BALANCE CONTR...</td>\n    </tr>\n    <tr>\n      <th>44552</th>\n      <td>526116621</td>\n      <td>en</td>\n      <td>SHEETLIKE COMPOSITE, IN PARTICULAR FOR THE PRO...</td>\n    </tr>\n    <tr>\n      <th>45476</th>\n      <td>528352131</td>\n      <td>en</td>\n      <td>NATURALLY SWEET ENHANCER COMPOSITION</td>\n    </tr>\n    <tr>\n      <th>23619</th>\n      <td>470837180</td>\n      <td>en</td>\n      <td>METHOD AND APPARATUS FOR MONITORING RADIO LINK...</td>\n    </tr>\n    <tr>\n      <th>33233</th>\n      <td>496310125</td>\n      <td>en</td>\n      <td>METHOD AND DEVICE FOR CONNECTING TO ACCESS POI...</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>61597</th>\n      <td>574732234</td>\n      <td>en</td>\n      <td>ADJUSTMENT MECHANISM FOR CIRCUIT BREAKER AND C...</td>\n    </tr>\n    <tr>\n      <th>54568</th>\n      <td>551189734</td>\n      <td>en</td>\n      <td>METHODS FOR PDCCH MONITORING, USER EQUIPMENT, ...</td>\n    </tr>\n    <tr>\n      <th>35847</th>\n      <td>503315942</td>\n      <td>en</td>\n      <td>SINGLE-WHEEL DRIVE COMPONENT FOR A MOTOR VEHIC...</td>\n    </tr>\n    <tr>\n      <th>49995</th>\n      <td>540002470</td>\n      <td>en</td>\n      <td>METHODS PROVIDING V2X APPLICATION SERVER REGIS...</td>\n    </tr>\n    <tr>\n      <th>14915</th>\n      <td>437594613</td>\n      <td>en</td>\n      <td>Carbon dots (c dots), method for their prepara...</td>\n    </tr>\n  </tbody>\n</table>\n<p>100 rows × 3 columns</p>\n</div>"
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "appln_title.sample(100)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "outputs": [
    {
     "data": {
      "text/plain": "    appln_id appln_auth  appln_nr appln_kind appln_filing_date   \n0  330225325         EP  11150195         A         2011-01-05  \\\n1  330225397         EP  11150231         A         2011-01-05   \n2  330322632         EP  11150485         A         2011-01-10   \n3  330326785         EP  11150605         A         2011-01-11   \n4  330350961         EP  11150683         A         2011-01-12   \n\n   appln_filing_year appln_nr_original ipr_type receiving_office   \n0               2011          11150195       PI                   \\\n1               2011          11150231       PI                    \n2               2011          11150485       PI                    \n3               2011          11150605       PI                    \n4               2011          11150683       PI                    \n\n   internat_appln_id  ... earliest_pat_publn_id granted docdb_family_id   \n0                  0  ...             335277427       Y        43754737  \\\n1                  0  ...             335277736       Y        43619902   \n2                  0  ...             364719889       Y        43991052   \n3                  0  ...             335277720       N        43023665   \n4                  0  ...             364923578       N        43881056   \n\n  inpadoc_family_id  docdb_family_size  nb_citing_docdb_fam nb_applicants   \n0         330225325                  4                   16             1  \\\n1         330225397                  6                   56             1   \n2         330322632                  2                    5             1   \n3         328518903                  6                    9             1   \n4         330350961                  7                   13             2   \n\n   nb_inventors  appln_title_lg   \n0             1              en  \\\n1             9              en   \n2             2              en   \n3             3              en   \n4             5              en   \n\n                                         appln_title  \n0                       Beverage preparation machine  \n1  Screwdriving tool having a driving tool with a...  \n2  Method and system for recommending contextual ...  \n3  Apparatus and method for continuous casting of...  \n4  A method and an apparatus for treating at leas...  \n\n[5 rows x 28 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>appln_id</th>\n      <th>appln_auth</th>\n      <th>appln_nr</th>\n      <th>appln_kind</th>\n      <th>appln_filing_date</th>\n      <th>appln_filing_year</th>\n      <th>appln_nr_original</th>\n      <th>ipr_type</th>\n      <th>receiving_office</th>\n      <th>internat_appln_id</th>\n      <th>...</th>\n      <th>earliest_pat_publn_id</th>\n      <th>granted</th>\n      <th>docdb_family_id</th>\n      <th>inpadoc_family_id</th>\n      <th>docdb_family_size</th>\n      <th>nb_citing_docdb_fam</th>\n      <th>nb_applicants</th>\n      <th>nb_inventors</th>\n      <th>appln_title_lg</th>\n      <th>appln_title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>330225325</td>\n      <td>EP</td>\n      <td>11150195</td>\n      <td>A</td>\n      <td>2011-01-05</td>\n      <td>2011</td>\n      <td>11150195</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>335277427</td>\n      <td>Y</td>\n      <td>43754737</td>\n      <td>330225325</td>\n      <td>4</td>\n      <td>16</td>\n      <td>1</td>\n      <td>1</td>\n      <td>en</td>\n      <td>Beverage preparation machine</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>330225397</td>\n      <td>EP</td>\n      <td>11150231</td>\n      <td>A</td>\n      <td>2011-01-05</td>\n      <td>2011</td>\n      <td>11150231</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>335277736</td>\n      <td>Y</td>\n      <td>43619902</td>\n      <td>330225397</td>\n      <td>6</td>\n      <td>56</td>\n      <td>1</td>\n      <td>9</td>\n      <td>en</td>\n      <td>Screwdriving tool having a driving tool with a...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>330322632</td>\n      <td>EP</td>\n      <td>11150485</td>\n      <td>A</td>\n      <td>2011-01-10</td>\n      <td>2011</td>\n      <td>11150485</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>364719889</td>\n      <td>Y</td>\n      <td>43991052</td>\n      <td>330322632</td>\n      <td>2</td>\n      <td>5</td>\n      <td>1</td>\n      <td>2</td>\n      <td>en</td>\n      <td>Method and system for recommending contextual ...</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>330326785</td>\n      <td>EP</td>\n      <td>11150605</td>\n      <td>A</td>\n      <td>2011-01-11</td>\n      <td>2011</td>\n      <td>11150605</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>335277720</td>\n      <td>N</td>\n      <td>43023665</td>\n      <td>328518903</td>\n      <td>6</td>\n      <td>9</td>\n      <td>1</td>\n      <td>3</td>\n      <td>en</td>\n      <td>Apparatus and method for continuous casting of...</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>330350961</td>\n      <td>EP</td>\n      <td>11150683</td>\n      <td>A</td>\n      <td>2011-01-12</td>\n      <td>2011</td>\n      <td>11150683</td>\n      <td>PI</td>\n      <td></td>\n      <td>0</td>\n      <td>...</td>\n      <td>364923578</td>\n      <td>N</td>\n      <td>43881056</td>\n      <td>330350961</td>\n      <td>7</td>\n      <td>13</td>\n      <td>2</td>\n      <td>5</td>\n      <td>en</td>\n      <td>A method and an apparatus for treating at leas...</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 28 columns</p>\n</div>"
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "appln_data = appln.merge(appln_title, on=\"appln_id\")\n",
    "appln_data.head()"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "outputs": [
    {
     "data": {
      "text/plain": "array(['EP', 'WO', 'LU', 'FI', 'NO', 'FR', 'GB', 'KR', 'ES', 'US', 'CA',\n       'DO', 'EC', 'DE', 'UY', 'IL', 'SV', 'PL', 'TR', 'CO', 'CR', 'TW',\n       'MA', 'PE', 'SG', 'CU', 'BE', 'DK', 'AR', 'AP', 'HR', 'MX', 'BR',\n       'EA', 'RU', 'AU', 'MC', 'HU', 'PT', 'NL', 'HN', 'AT', 'RO', 'SM',\n       'CH', 'SI', 'IS', 'CZ', 'HK', 'MD', 'JP', 'CN', 'RS', 'GT', 'UA',\n       'CL', 'SK', 'LT', 'PH', 'MY', 'IN', 'VN', 'TN', 'CY', 'GE', 'ZA',\n       'SE', 'ME', 'JO', 'NI', 'SA'], dtype=object)"
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "appln_data[\"appln_auth\"].unique()"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "outputs": [
    {
     "data": {
      "text/plain": "         person_id   appln_id  applt_seq_nr  invt_seq_nr\n0                1  413601768             1            0\n1               21  332015605             1            0\n2               21  333490084             1            0\n3               21  335903805             1            0\n4               76  352908776             1            0\n...            ...        ...           ...          ...\n1025446   88836321  577982223             1            0\n1025447   88836333  583342135             0            4\n1025448   88836333  583342207             0            3\n1025449   88836333  585957705             0            5\n1025450   88836337  579601496             0            1\n\n[1025451 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>person_id</th>\n      <th>appln_id</th>\n      <th>applt_seq_nr</th>\n      <th>invt_seq_nr</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>413601768</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>21</td>\n      <td>332015605</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>21</td>\n      <td>333490084</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>21</td>\n      <td>335903805</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>76</td>\n      <td>352908776</td>\n      <td>1</td>\n      <td>0</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>1025446</th>\n      <td>88836321</td>\n      <td>577982223</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1025447</th>\n      <td>88836333</td>\n      <td>583342135</td>\n      <td>0</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>1025448</th>\n      <td>88836333</td>\n      <td>583342207</td>\n      <td>0</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>1025449</th>\n      <td>88836333</td>\n      <td>585957705</td>\n      <td>0</td>\n      <td>5</td>\n    </tr>\n    <tr>\n      <th>1025450</th>\n      <td>88836337</td>\n      <td>579601496</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n<p>1025451 rows × 4 columns</p>\n</div>"
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "appln_pers"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "outputs": [
    {
     "data": {
      "text/plain": "        person_id                person_name        person_name_orig_lg   \n0               1          Nokia Corporation          Nokia Corporation  \\\n1             128  Nokia Siemens Networks Oy  Nokia Siemens Networks Oy   \n2         5217785          Nokia Corporation          Nokia Corporation   \n3         5217811          Nokia Corporation          Nokia Corporation   \n4         5232170  Nokia Siemens Networks Oy  Nokia Siemens Networks Oy   \n...           ...                        ...                        ...   \n354633   88836234             WONG, Chun Lok             WONG, Chun Lok   \n354634   88836257                XIAONING YE                XIAONING YE   \n354635   88836321           ZAI LAB (US) LLC           ZAI LAB (US) LLC   \n354636   88836333            ZHANG, Haocheng                        张皓程   \n354637   88836337             ZHANG, Yangjun             ZHANG, Yangjun   \n\n                      person_address person_ctry_code   nuts  nuts_level   \n0       Keilalahdentie 4,02150 Espoo               FI  FI1B1           3  \\\n1           Karaportti 3,02610 Espoo               FI  FI1B1           3   \n2                              Espoo               FI     FI           0   \n3                                NaN               FI     FI           0   \n4                              Espoo               FI     FI           0   \n...                              ...              ...    ...         ...   \n354633                           NaN               US    NaN           9   \n354634           Portland, Oregon US               US    NaN           9   \n354635                           NaN               US    NaN           9   \n354636                           NaN               US    NaN           9   \n354637                           NaN               US    NaN           9   \n\n        doc_std_name_id               doc_std_name     psn_id   \n0                     1                 NOKIA CORP   23782051  \\\n1                   112  NOKIA SIEMENS NETWORKS OY   23782129   \n2                     1                 NOKIA CORP   23782051   \n3                     1                 NOKIA CORP   23782051   \n4                   112  NOKIA SIEMENS NETWORKS OY   23782129   \n...                 ...                        ...        ...   \n354633         30867225              WONG CHUN LOK  188836234   \n354634          8004293                XIAONING YE  188836257   \n354635         39363494             ZAI LAB US LLC  188836321   \n354636          7682590             ZHANG HAOCHENG  188836333   \n354637          2112344              ZHANG YANGJUN  188836337   \n\n                 psn_name  psn_level psn_sector     han_id          han_name   \n0       NOKIA CORPORATION          2    COMPANY    2125445        NOKIA CORP  \\\n1          NOKIA NETWORKS          2    COMPANY    2125445        NOKIA CORP   \n2       NOKIA CORPORATION          2    COMPANY    2125445        NOKIA CORP   \n3       NOKIA CORPORATION          2    COMPANY    2125445        NOKIA CORP   \n4          NOKIA NETWORKS          2    COMPANY    2125445        NOKIA CORP   \n...                   ...        ...        ...        ...               ...   \n354633     WONG, Chun Lok          0    UNKNOWN  188836234    WONG, Chun Lok   \n354634        XIAONING YE          0    UNKNOWN  188836257       XIAONING YE   \n354635   ZAI LAB (US) LLC          0    UNKNOWN  188836321  ZAI LAB (US) LLC   \n354636    ZHANG, Haocheng          0    UNKNOWN  188836333   ZHANG, Haocheng   \n354637     ZHANG, Yangjun          0    UNKNOWN  188836337    ZHANG, Yangjun   \n\n        han_harmonized psn_sector_primary  \n0                    2            COMPANY  \n1                    2            COMPANY  \n2                    2            COMPANY  \n3                    2            COMPANY  \n4                    2            COMPANY  \n...                ...                ...  \n354633               0            UNKNOWN  \n354634               0            UNKNOWN  \n354635               0            UNKNOWN  \n354636
      "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>person_id</th>\n      <th>person_name</th>\n      <th>person_name_orig_lg</th>\n      <th>person_address</th>\n      <th>person_ctry_code</th>\n      <th>nuts</th>\n      <th>nuts_level</th>\n      <th>doc_std_name_id</th>\n      <th>doc_std_name</th>\n      <th>psn_id</th>\n      <th>psn_name</th>\n      <th>psn_level</th>\n      <th>psn_sector</th>\n      <th>han_id</th>\n      <th>han_name</th>\n      <th>han_harmonized</th>\n      <th>psn_sector_primary</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>Nokia Corporation</td>\n      <td>Nokia Corporation</td>\n      <td>Keilalahdentie 4,02150 Espoo</td>\n      <td>FI</td>\n      <td>FI1B1</td>\n      <td>3</td>\n      <td>1</td>\n      <td>NOKIA CORP</td>\n      <td>23782051</td>\n      <td>NOKIA CORPORATION</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>128</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Karaportti 3,02610 Espoo</td>\n      <td>FI</td>\n      <td>FI1B1</td>\n      <td>3</td>\n      <td>112</td>\n      <td>NOKIA SIEMENS NETWORKS OY</td>\n      <td>23782129</td>\n      <td>NOKIA NETWORKS</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>5217785</td>\n      <td>Nokia Corporation</td>\n      <td>Nokia Corporation</td>\n      <td>Espoo</td>\n      <td>FI</td>\n      <td>FI</td>\n      <td>0</td>\n      <td>1</td>\n      <td>NOKIA CORP</td>\n      <td>23782051</td>\n      <td>NOKIA CORPORATION</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>5217811</td>\n      <td>Nokia Corporation</td>\n      <td>Nokia Corporation</td>\n      <td>NaN</td>\n      <td>FI</td>\n      <td>FI</td>\n      <td>0</td>\n      <td>1</td>\n      <td>NOKIA CORP</td>\n      <td>23782051</td>\n      <td>NOKIA CORPORATION</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5232170</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Espoo</td>\n      <td>FI</td>\n      <td>FI</td>\n      <td>0</td>\n      <td>112</td>\n      <td>NOKIA SIEMENS NETWORKS OY</td>\n      <td>23782129</td>\n      <td>NOKIA NETWORKS</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</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    </tr>\n    <tr>\n      <th>354633</th>\n      <td>88836234</td>\n      <td>WONG, Chun Lok</td>\n      <td>WONG, Chun Lok</td>\n      <td>NaN</td>\n      <td>US</td>\n      <td>NaN</td>\n      <td>9</td>\n      <td>30867225</td>\n      <td>WONG CHUN LOK</td>\n      <td>188836234</td>\n      <td>WONG, Chun Lok</td>\n      <td>0</td>\n      <td>UNKNOWN</td>\n      <td>188836234</td>\n      <td>WONG, Chun Lok</td>\n      <td>0</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>354634<
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": "        person_id                person_name        person_name_orig_lg   \n0               1          Nokia Corporation          Nokia Corporation  \\\n1             128  Nokia Siemens Networks Oy  Nokia Siemens Networks Oy   \n2         5217785          Nokia Corporation          Nokia Corporation   \n3         5217811          Nokia Corporation          Nokia Corporation   \n4         5232170  Nokia Siemens Networks Oy  Nokia Siemens Networks Oy   \n...           ...                        ...                        ...   \n354633   88836234             WONG, Chun Lok             WONG, Chun Lok   \n354634   88836257                XIAONING YE                XIAONING YE   \n354635   88836321           ZAI LAB (US) LLC           ZAI LAB (US) LLC   \n354636   88836333            ZHANG, Haocheng                        张皓程   \n354637   88836337             ZHANG, Yangjun             ZHANG, Yangjun   \n\n                      person_address person_ctry_code   nuts  nuts_level   \n0       Keilalahdentie 4,02150 Espoo               FI  FI1B1           3  \\\n1           Karaportti 3,02610 Espoo               FI  FI1B1           3   \n2                              Espoo               FI     FI           0   \n3                                NaN               FI     FI           0   \n4                              Espoo               FI     FI           0   \n...                              ...              ...    ...         ...   \n354633                           NaN               US    NaN           9   \n354634           Portland, Oregon US               US    NaN           9   \n354635                           NaN               US    NaN           9   \n354636                           NaN               US    NaN           9   \n354637                           NaN               US    NaN           9   \n\n        doc_std_name_id               doc_std_name     psn_id   \n0                     1                 NOKIA CORP   23782051  \\\n1                   112  NOKIA SIEMENS NETWORKS OY   23782129   \n2                     1                 NOKIA CORP   23782051   \n3                     1                 NOKIA CORP   23782051   \n4                   112  NOKIA SIEMENS NETWORKS OY   23782129   \n...                 ...                        ...        ...   \n354633         30867225              WONG CHUN LOK  188836234   \n354634          8004293                XIAONING YE  188836257   \n354635         39363494             ZAI LAB US LLC  188836321   \n354636          7682590             ZHANG HAOCHENG  188836333   \n354637          2112344              ZHANG YANGJUN  188836337   \n\n                 psn_name  psn_level psn_sector     han_id          han_name   \n0       NOKIA CORPORATION          2    COMPANY    2125445        NOKIA CORP  \\\n1          NOKIA NETWORKS          2    COMPANY    2125445        NOKIA CORP   \n2       NOKIA CORPORATION          2    COMPANY    2125445        NOKIA CORP   \n3       NOKIA CORPORATION          2    COMPANY    2125445        NOKIA CORP   \n4          NOKIA NETWORKS          2    COMPANY    2125445        NOKIA CORP   \n...                   ...        ...        ...        ...               ...   \n354633     WONG, Chun Lok          0    UNKNOWN  188836234    WONG, Chun Lok   \n354634        XIAONING YE          0    UNKNOWN  188836257       XIAONING YE   \n354635   ZAI LAB (US) LLC          0    UNKNOWN  188836321  ZAI LAB (US) LLC   \n354636    ZHANG, Haocheng          0    UNKNOWN  188836333   ZHANG, Haocheng   \n354637     ZHANG, Yangjun          0    UNKNOWN  188836337    ZHANG, Yangjun   \n\n        han_harmonized psn_sector_primary  \n0                    2            COMPANY  \n1                    2            COMPANY  \n2                    2            COMPANY  \n3                    2            COMPANY  \n4                    2            COMPANY  \n...                ...                ...  \n354633               0            UNKNOWN  \n354634               0            UNKNOWN  \n354635               0            UNKNOWN  \n354636
      "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>person_id</th>\n      <th>person_name</th>\n      <th>person_name_orig_lg</th>\n      <th>person_address</th>\n      <th>person_ctry_code</th>\n      <th>nuts</th>\n      <th>nuts_level</th>\n      <th>doc_std_name_id</th>\n      <th>doc_std_name</th>\n      <th>psn_id</th>\n      <th>psn_name</th>\n      <th>psn_level</th>\n      <th>psn_sector</th>\n      <th>han_id</th>\n      <th>han_name</th>\n      <th>han_harmonized</th>\n      <th>psn_sector_primary</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>Nokia Corporation</td>\n      <td>Nokia Corporation</td>\n      <td>Keilalahdentie 4,02150 Espoo</td>\n      <td>FI</td>\n      <td>FI1B1</td>\n      <td>3</td>\n      <td>1</td>\n      <td>NOKIA CORP</td>\n      <td>23782051</td>\n      <td>NOKIA CORPORATION</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>128</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Karaportti 3,02610 Espoo</td>\n      <td>FI</td>\n      <td>FI1B1</td>\n      <td>3</td>\n      <td>112</td>\n      <td>NOKIA SIEMENS NETWORKS OY</td>\n      <td>23782129</td>\n      <td>NOKIA NETWORKS</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>5217785</td>\n      <td>Nokia Corporation</td>\n      <td>Nokia Corporation</td>\n      <td>Espoo</td>\n      <td>FI</td>\n      <td>FI</td>\n      <td>0</td>\n      <td>1</td>\n      <td>NOKIA CORP</td>\n      <td>23782051</td>\n      <td>NOKIA CORPORATION</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>5217811</td>\n      <td>Nokia Corporation</td>\n      <td>Nokia Corporation</td>\n      <td>NaN</td>\n      <td>FI</td>\n      <td>FI</td>\n      <td>0</td>\n      <td>1</td>\n      <td>NOKIA CORP</td>\n      <td>23782051</td>\n      <td>NOKIA CORPORATION</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5232170</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Nokia Siemens Networks Oy</td>\n      <td>Espoo</td>\n      <td>FI</td>\n      <td>FI</td>\n      <td>0</td>\n      <td>112</td>\n      <td>NOKIA SIEMENS NETWORKS OY</td>\n      <td>23782129</td>\n      <td>NOKIA NETWORKS</td>\n      <td>2</td>\n      <td>COMPANY</td>\n      <td>2125445</td>\n      <td>NOKIA CORP</td>\n      <td>2</td>\n      <td>COMPANY</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    </tr>\n    <tr>\n      <th>354633</th>\n      <td>88836234</td>\n      <td>WONG, Chun Lok</td>\n      <td>WONG, Chun Lok</td>\n      <td>NaN</td>\n      <td>US</td>\n      <td>NaN</td>\n      <td>9</td>\n      <td>30867225</td>\n      <td>WONG CHUN LOK</td>\n      <td>188836234</td>\n      <td>WONG, Chun Lok</td>\n      <td>0</td>\n      <td>UNKNOWN</td>\n      <td>188836234</td>\n      <td>WONG, Chun Lok</td>\n      <td>0</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>354634<
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pers_sector_primary = pers.groupby(\"han_id\", as_index=False)[\"psn_sector\"].agg(\n",
    "    lambda x: pd.Series.mode(x)[0]).rename(columns={\"psn_sector\":\"psn_sector_primary\"})\n",
    "persn = pers.merge(pers_sector_primary, on='han_id')\n",
    "persn"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "outputs": [
    {
     "data": {
      "text/plain": "           han_id         psn_sector_primary\n0              32                    COMPANY\n1              54                    COMPANY\n2              83                    COMPANY\n3             200                    COMPANY\n4             264  GOV NON-PROFIT UNIVERSITY\n...           ...                        ...\n335519  188836234                    UNKNOWN\n335520  188836257                    UNKNOWN\n335521  188836321                    UNKNOWN\n335522  188836333                    UNKNOWN\n335523  188836337                    UNKNOWN\n\n[335524 rows x 2 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>han_id</th>\n      <th>psn_sector_primary</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>32</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>54</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>83</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>200</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>264</td>\n      <td>GOV NON-PROFIT UNIVERSITY</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>335519</th>\n      <td>188836234</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335520</th>\n      <td>188836257</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335521</th>\n      <td>188836321</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335522</th>\n      <td>188836333</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335523</th>\n      <td>188836337</td>\n      <td>UNKNOWN</td>\n    </tr>\n  </tbody>\n</table>\n<p>335524 rows × 2 columns</p>\n</div>"
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": "           han_id         psn_sector_primary\n0              32                    COMPANY\n1              54                    COMPANY\n2              83                    COMPANY\n3             200                    COMPANY\n4             264  GOV NON-PROFIT UNIVERSITY\n...           ...                        ...\n335519  188836234                    UNKNOWN\n335520  188836257                    UNKNOWN\n335521  188836321                    UNKNOWN\n335522  188836333                    UNKNOWN\n335523  188836337                    UNKNOWN\n\n[335524 rows x 2 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>han_id</th>\n      <th>psn_sector_primary</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>32</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>54</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>83</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>200</td>\n      <td>COMPANY</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>264</td>\n      <td>GOV NON-PROFIT UNIVERSITY</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>335519</th>\n      <td>188836234</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335520</th>\n      <td>188836257</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335521</th>\n      <td>188836321</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335522</th>\n      <td>188836333</td>\n      <td>UNKNOWN</td>\n    </tr>\n    <tr>\n      <th>335523</th>\n      <td>188836337</td>\n      <td>UNKNOWN</td>\n    </tr>\n  </tbody>\n</table>\n<p>335524 rows × 2 columns</p>\n</div>"
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pers_sector_primary"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "outputs": [],
   "source": [
    "appln_merge = appln.merge(appln_title, on=\"appln_id\")#.merge(appln_pers,on=\"appln_id\")\n",
    "appln_merge.to_excel(\"appln_data.xlsx\", index=False)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "outputs": [],
   "source": [
    "person_merge = appln_pers.merge(pers,on=\"person_id\")\n",
    "person_merge.to_excel(\"person_data.xlsx\", index=False)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "outputs": [
    {
     "data": {
      "text/plain": "array(['FI', 'NL', 'FR', 'CH', 'US', 'DE', 'DK', 'AT', 'SE', 'BE', 'CN',\n       'IT', 'LU', 'IE', 'SI', 'HK', 'MO', 'CZ', 'ES', 'NO', 'PL', 'HU',\n       'CY', 'SK', 'PT', 'EE', 'MT', 'GR', 'RO', 'BG', 'LT', 'HR', 'LV'],\n      dtype=object)"
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pers[\"person_ctry_code\"].unique()"
   ],
   "metadata": {
    "collapsed": false
   }
  }
 ],
 "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
}