ADD: PATSTAT analysis new batch of data

.gitignore

@@ -7,7 +7,7 @@
 /WOS/kw_token_ranked_bibliometrics_okset.xlsx
 /PATSTAT/first_round/tls_206_scope.csv
 /PATSTAT/first_round/first-filings-with-persons-raw.csv
-/PATSTAT/first_round/first-filings-with-IPC-raw.csv
+/PATSTAT/raw_files_csv/first-filings-with-IPC-raw.csv
 /PATSTAT/first_round/first-filings-raw.csv
 /PATSTAT/raw_files_csv/01_patent_subset.csv
 /PATSTAT/raw_files_csv/04_persons_2011_2022_inv_pairs.csv

PATSTAT/person_minipipe.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 9,
    "metadata": {
     "collapsed": true
    },
@@ -11,7 +11,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "C:\\Users\\radvanyi\\PycharmProjects\\ZSI_analytics\\PATSTAT\n",
+      "D:\\PATSTAT\n",
       "D:\\PATSTAT\n"
      ]
     }
@@ -49,6 +49,21 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "outputs": [],
+   "source": [
+    "tls_209 = dd.read_csv(\"table_tls209.csv\", low_memory=False)\n",
+    "tls_209.to_parquet(\"tls_209.parquet\")\n",
+    "# %%time\n",
+    "#Person data\n",
+    "tls_209_p = dd.read_parquet(\"tls_209.parquet\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 3,
@@ -101,9 +116,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 12,
    "outputs": [],
-   "source": [],
+   "source": [
+    "appln_id_scope = appln_pers_f[\"appln_id\"].unique()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "12646904"
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(appln_id_scope)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "outputs": [],
+   "source": [
+    "tls_209_p_scope =tls_209_p[tls_209_p['appln_id'].isin(appln_id_scope)]\n",
+    "tls_209_p_scope.compute().to_csv(r\"C:\\Users\\radvanyi\\PycharmProjects\\ZSI_analytics\\PATSTAT\\first_round\\tls_209_IPC_scope.csv\",index=False)"
+   ],
    "metadata": {
     "collapsed": false
    }