ADD: PATSTAT analysis

PATSTAT/patstat_data_filter_process.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -10,7 +10,7 @@
      "output_type": "stream",
      "text": [
       "CPU times: total: 125 ms\n",
-      "Wall time: 247 ms\n"
+      "Wall time: 143 ms\n"
      ]
     }
    ],
@@ -21,14 +21,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "text/plain": "<dask.config.set at 0x215813bc370>"
+      "text/plain": "<dask.config.set at 0x197d05e7220>"
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -39,14 +39,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "text/plain": "<dask.config.set at 0x2159c19c580>"
+      "text/plain": "<dask.config.set at 0x197d0c03ac0>"
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -57,14 +57,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": "{'temporary-directory': 'D:\\\\PATSTAT\\\\dask_temp',\n 'visualization': {'engine': None},\n 'tokenize': {'ensure-deterministic': False},\n 'dataframe': {'backend': 'pandas',\n  'shuffle': {'method': None, 'compression': None},\n  'parquet': {'metadata-task-size-local': 512, 'metadata-task-size-remote': 1},\n  'dtype_backend': 'pandas',\n  'convert_string': False},\n 'array': {'backend': 'numpy',\n  'rechunk': {'method': 'tasks'},\n  'svg': {'size': 120},\n  'slicing': {'split-large-chunks': None}},\n 'optimization': {'annotations': {'fuse': True},\n  'fuse': {'active': None,\n   'ave-width': 1,\n   'max-width': None,\n   'max-height': inf,\n   'max-depth-new-edges': None,\n   'subgraphs': None,\n   'rename-keys': True}}}"
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -75,7 +75,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -84,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -107,22 +107,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": []
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: total: 39min 33s\n",
-      "Wall time: 20min 19s\n"
+      "CPU times: total: 41min 20s\n",
+      "Wall time: 18min 32s\n"
      ]
     }
    ],
@@ -136,9 +136,21 @@
     "tls_206.to_parquet(\"tls_206.parquet\")\n",
     "\n",
     "tls_207 = dd.read_csv(\"table_tls207.csv\", low_memory=False)\n",
-    "tls_207.to_parquet(\"tls_207.parquet\")"
+    "tls_207.to_parquet(\"tls_207.parquet\")\n",
+    "\n",
+    "tls_204 = dd.read_csv(\"table_tls204.csv\", low_memory=False)\n",
+    "tls_207.to_parquet(\"tls_204.parquet\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 11,