ADD: PATSTAT analysis new batch of data

main
radvanyimome 1 year ago
parent 47bd6f423b
commit 15b21a1bf1

2
.gitignore vendored

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

File diff suppressed because one or more lines are too long

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 9,
"metadata": { "metadata": {
"collapsed": true "collapsed": true
}, },
@ -11,7 +11,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"C:\\Users\\radvanyi\\PycharmProjects\\ZSI_analytics\\PATSTAT\n", "D:\\PATSTAT\n",
"D:\\PATSTAT\n" "D:\\PATSTAT\n"
] ]
} }
@ -49,6 +49,21 @@
"collapsed": false "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", "cell_type": "code",
"execution_count": 3, "execution_count": 3,
@ -101,9 +116,43 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 12,
"outputs": [], "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": { "metadata": {
"collapsed": false "collapsed": false
} }

Binary file not shown.

Before

Width:  |  Height:  |  Size: 883 KiB

After

Width:  |  Height:  |  Size: 800 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 762 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 785 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 968 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 747 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 918 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 683 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 832 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 858 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 598 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 629 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 703 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 716 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 754 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 726 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 782 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 681 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 746 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 705 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 807 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 752 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 729 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 761 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 623 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 598 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 626 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 676 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 675 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 647 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 616 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 673 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 743 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 660 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 811 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 766 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 741 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 764 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 739 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 820 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 770 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 801 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 791 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 700 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 791 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 696 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 860 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 782 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 797 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 723 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 716 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 733 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 711 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.3 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 761 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 698 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 845 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 853 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 658 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 758 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 885 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 779 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 890 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.0 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 625 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 788 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.0 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 682 KiB

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:56bea3050aecda5214b185d6f3c5cafb4c81a3d699060f0920f9a41c9dabef5d
3 size 1559888383
Loading…
Cancel
Save