radvanyimome
/
ZSI_Reconnect_China
2
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
main
utku_inst_name_exploration
utku_keyword_suggestion
test
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '3842ec90c8'
${ noResults }
ZSI_Reconnect_China/PATSTAT/patstat_cpc_parse.ipynb

320 lines
26 KiB
Plaintext
Raw Blame History Unescape Escape

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "a8be6839",
"metadata": {},
"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": 4,
"id": "211ba466",
"metadata": {},
"outputs": [],
"source": [
"outdir=\"WESTERN_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",
"\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\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "f878b151",
"metadata": {},
"outputs": [],
"source": [
"# workdir_path=r\"CPCTitleList202302\"\n",
"# # outfile='wos_extract_complete.csv'\n",
"# # with_header=True\n",
"# cpc_ids = pd.DataFrame()\n",
"# for root, dirs, files in os.walk(workdir_path):\n",
"# for filename in files:\n",
"# path=os.path.join(root, filename)\n",
"# section = pd.read_csv(path, sep='\\t', header=None)\n",
"# cpc_ids=pd.concat([cpc_ids,section], ignore_index=True)\n",
"# cpc_ids.columns =[\"cpc_id\",\"idk\",\"cpc_name\"]\n",
"# cpc_ids = cpc_ids.drop(columns=\"idk\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "95ea20da",
"metadata": {},
"outputs": [],
"source": [
"parsed = {x: [] for x in ['code', 'title', 'section', 'class', 'subclass', 'group', 'main_group']}\n",
"for letter in 'ABCDEFGHY':\n",
" file = f'CPC_data/CPCTitleList202302/cpc-section-{letter}_20230201.txt'\n",
" with open(file) as f:\n",
" for line in f:\n",
" vals = line.strip().split('\\t')\n",
" if len(vals) == 2:\n",
" parsed['code'].append(vals[0])\n",
" parsed['title'].append(vals[1])\n",
" elif len(vals) == 3:\n",
" parsed['code'].append(vals[0])\n",
" parsed['title'].append(vals[2])\n",
"\n",
"\n",
"\n",
"for i in range(len(parsed['code'])):\n",
" code = parsed['code'][i]\n",
" main_group = code.split('/')[-1] if \"/\" in code else None\n",
" group = code.split('/')[0][4:] if len(code) >= 5 else None\n",
" subclass = code[3] if len(code) >= 4 else None\n",
" class_ = code[1:3] if len(code) >= 3 else None\n",
" section = code[0] if len(code) >= 1 else None\n",
" \n",
" parsed['main_group'].append(main_group)\n",
" parsed['group'].append(group)\n",
" parsed['subclass'].append(subclass)\n",
" parsed['class'].append(class_)\n",
" parsed['section'].append(section)\n",
"\n",
"cpc_ids2023 = pd.DataFrame.from_dict(parsed)\n",
"cpc_ids2023['cpc_version']=2023\n",
"cpc_ids2022 = pd.read_csv(\"CPC_data/cpc_titles_2022.csv\")\n",
"cpc_ids2022['cpc_version']=2022\n",
"cpc_ids = pd.concat([cpc_ids2023,cpc_ids2022], ignore_index=True)\n",
"cpc_ids = cpc_ids.rename(columns={\"code\":\"cpc_id\",\"title\":\"cpc_name\"}).drop_duplicates(subset=\"cpc_id\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "907d9c3e",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 7,
"id": "1be8971a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"70 cpc_ids not found\n",
"0.07344840249724569 % lost\n"
]
}
],
"source": [
"appln_cpc[\"cpc_id\"] = appln_cpc[\"cpc_class_symbol\"].str.replace(\" \",\"\")\n",
"appln_cpc_tax = appln_cpc.merge(cpc_ids, on=\"cpc_id\", how=\"left\")\n",
"\n",
"print(len(appln_cpc_tax[appln_cpc_tax[\"cpc_name\"].isna()][\"cpc_id\"].unique()), \"cpc_ids not found\")\n",
"print(len(appln_cpc_tax[appln_cpc_tax[\"cpc_name\"].isna()][\"cpc_id\"].unique())/len(appln_cpc_tax[\"cpc_id\"].unique())*100, \"% lost\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b1274c34",
"metadata": {},
"outputs": [],
"source": [
"cpc_dict = dict(zip(cpc_ids.cpc_id.str.replace(\" \",\"\"), cpc_ids.cpc_name))\n",
"# cpc_dict"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "2a7e39ee",
"metadata": {},
"outputs": [],
"source": [
"def cpc_classifier(id_text):\n",
" taxonomy = []\n",
" iter_text = id_text.replace(\" \",\"\")\n",
" for i in range(len(iter_text)+1):\n",
" tax_id = iter_text[:i]\n",
" tax_name = cpc_dict.get(iter_text[:i])\n",
" if tax_name:\n",
" taxonomy.append((tax_id,tax_name))\n",
" return taxonomy\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "e31a013f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": "[('A', 'HUMAN NECESSITIES'),\n ('A01',\n 'AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING'),\n ('A01B',\n 'SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL (making or covering furrows or holes for sowing, planting, or manuring A01C5/00; soil working for engineering purposes E01, E02, E21; {measuring areas for agricultural purposes G01B})'),\n ('A01B1/06',\n 'Hoes; Hand cultivators {(rakes A01D7/00; forks A01D9/00; picks B25D)}'),\n ('A01B1/065', '{powered}')]"
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cpc_classifier(\"A01B1/065\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "f09a616c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": " cpc_id cpc_name section class \n0 A HUMAN NECESSITIES A None \\\n1 A01 AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTI... A 01 \n2 A01B SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS... A 01 \n3 A01B1/00 Hand tools (edge trimmers for lawns A01G3/06 ... A 01 \n4 A01B1/02 Spades; Shovels {(hand-operated dredgers E02F3... A 01 \n\n subclass group main_group cpc_version \n0 None None None 2023 \\\n1 None None None 2023 \n2 B None None 2023 \n3 B 1 00 2023 \n4 B 1 02 2023 \n\n version https://git-lfs.github.com/spec/v1 \n0 NaN \\\n1 NaN \n2 NaN \n3 NaN \n4 NaN \n\n cpc_taxonomy \n0 [(A, HUMAN NECESSITIES)] \n1 [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO... \n2 [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO... \n3 [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO... \n4 [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO... ",
"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 </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>A</td>\n <td>HUMAN NECESSITIES</td>\n <td>A</td>\n <td>None</td>\n <td>None</td>\n <td>None</td>\n <td>None</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES)]</td>\n </tr>\n <tr>\n <th>1</th>\n <td>A01</td>\n <td>AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTI...</td>\n <td>A</td>\n <td>01</td>\n <td>None</td>\n <td>None</td>\n <td>None</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n </tr>\n <tr>\n <th>2</th>\n <td>A01B</td>\n <td>SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS...</td>\n <td>A</td>\n <td>01</td>\n <td>B</td>\n <td>None</td>\n <td>None</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n </tr>\n <tr>\n <th>3</th>\n <td>A01B1/00</td>\n <td>Hand tools (edge trimmers for lawns A01G3/06 ...</td>\n <td>A</td>\n <td>01</td>\n <td>B</td>\n <td>1</td>\n <td>00</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n </tr>\n <tr>\n <th>4</th>\n <td>A01B1/02</td>\n <td>Spades; Shovels {(hand-operated dredgers E02F3...</td>\n <td>A</td>\n <td>01</td>\n <td>B</td>\n <td>1</td>\n <td>02</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cpc_ids[\"cpc_taxonomy\"] = cpc_ids[\"cpc_id\"].fillna(\"\").map(cpc_classifier)\n",
"cpc_ids.head()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "f3fa8bf3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"70 cpc_ids not found\n",
"0.07344840249724569 % lost\n"
]
}
],
"source": [
"appln_cpc[\"cpc_id\"] = appln_cpc[\"cpc_class_symbol\"].str.replace(\" \",\"\")\n",
"appln_cpc_tax = appln_cpc.merge(cpc_ids, on=\"cpc_id\", how=\"left\")\n",
"print(len(appln_cpc_tax[appln_cpc_tax[\"cpc_name\"].isna()][\"cpc_id\"].unique()), \"cpc_ids not found\")\n",
"print(len(appln_cpc_tax[appln_cpc_tax[\"cpc_name\"].isna()][\"cpc_id\"].unique())/len(appln_cpc_tax[\"cpc_id\"].unique())*100, \"% lost\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "58701721",
"metadata": {},
"outputs": [],
"source": [
"# appln_cpc_tax[appln_cpc_tax[\"cpc_name\"].isna()][\"cpc_id\"].unique()"
]
},
{
"cell_type": "markdown",
"id": "ca631acf",
"metadata": {},
"source": [
"## 'AI/Big Data' keywords"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "6c3baa5b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": " cpc_id cpc_name \n12725 A61B1/000096 {using artificial intelligence} \\\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... \n15252 A61B2018/0069 {using fuzzy logic} \n... ... ... \n250685 Y10S707/99946 Object-oriented database structure network \n250686 Y10S707/99947 Object-oriented database structure reference \n250687 Y10S707/99948 Application of database or data structure, e.g... \n250688 Y10S707/99951 File or database maintenance \n250703 Y10S715/968 interface for database querying and retrieval \n\n section class subclass group main_group cpc_version \n12725 A 61 B 1 000096 2023 \\\n13764 A 61 B 5 7264 2023 \n13897 A 61 B 6 52 2023 \n14016 A 61 B 8 52 2023 \n15252 A 61 B 2018 0069 2023 \n... ... ... ... ... ... ... \n250685 Y 10 S 707 99946 2023 \n250686 Y 10 S 707 99947 2023 \n250687 Y 10 S 707 99948 2023 \n250688 Y 10 S 707 99951 2023 \n250703 Y 10 S 715 968 2023 \n\n version https://git-lfs.github.com/spec/v1 \n12725 NaN \\\n13764 NaN \n13897 NaN \n14016 NaN \n15252 NaN \n... ... \n250685 NaN \n250686 NaN \n250687 NaN \n250688 NaN \n250703 NaN \n\n cpc_taxonomy \n12725 [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE... \n13764 [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE... \n13897 [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE... \n14016 [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE... \n15252 [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE... \n... ... \n250685 [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE... \n250686 [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE... \n250687 [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE... \n250688 [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE... \n250703 [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE... \n\n[317 rows x 10 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>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 </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</td>\n <td>B</td>\n <td>1</td>\n <td>000096</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</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</td>\n <td>B</td>\n <td>5</td>\n <td>7264</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</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</td>\n <td>B</td>\n <td>6</td>\n <td>52</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n </tr>\n <tr>\n <th>14016</th>\n <td>A61B8/52</td>\n <td>{Devices using data or image processing specia...</td>\n <td>A</td>\n <td>61</td>\n <td>B</td>\n <td>8</td>\n <td>52</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n </tr>\n <tr>\n <th>15252</th>\n <td>A61B2018/0069</td>\n <td>{using fuzzy logic}</td>\n <td>A</td>\n <td>61</td>\n <td>B</td>\n <td>2018</td>\n <td>0069</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</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 </tr>\n <tr>\n <th>250685</th>\n <td>Y10S707/99946</td>\n <td>Object-oriented database structure network</td>\n <td>Y</td>\n <td>10</td>\n <td>S</td>\n <td>707</td>\n <td>99946</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n </tr>\n <tr>\n <th>250686</th>\n <td>Y10S707/99947</td>\n <td>Object-oriented database structure reference</td>\n <td>Y</td>\n <td>10</td>\n <td>S</td>\n <td>707</td>\n <td>99947</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n </tr>\n <tr>\n <th>250687</th>\n <td>Y10S707/99948</td>\n <td>Application of database or data structure, e.g...</td>\n <td>Y</td>\n <td>10</td>\n <td>S</td>\n <td>707</td>\n <td>99948</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n </tr>\n <tr>\n <th>250688</th>\n <td>Y10S707/99951</td>\n <td>File or database maintenance</td>\n <td>Y</td>\n <td>10</td>\n <td>S</td>\n <td>707</td>\n <td>99951</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n </tr>\n <tr>\n <th>250703</th>\n <td>Y10S715/968</td>\n <td>interface for database querying and retrieval</td>\n <td>Y</td>\n <td>10</td>\n <td>S</td>\n <td>715</td>\n <td>968</td>\n <td>2023</td>\n <td>NaN</td>\n <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n </tr>\n </tbody>\n</table>\n<p>317 rows × 10 columns</p>\n</div>"
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cpc_ids[cpc_ids[\"cpc_name\"].str.lower().str.contains(\"machine learn|neural network|deep learn|deep network|artificial intel*| big data|database|recommender system|computer vision|image processing|language model|language processing|fuzzy logic|principal component|image classification|video classification\", regex=True, na=False)]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"outputs": [],
"source": [
"cpc_ids.to_csv(f\"{outdir}/cpc_defs.csv\", index=False)"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 13,
"id": "2e8368b4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": " appln_id appln_auth appln_nr appln_kind appln_filing_date \n0 340657036 EP 12000117 A 2012-01-09 \\\n1 340982410 EP 12151915 A 2012-01-20 \n2 341078960 EP 12700310 A 2012-01-11 \n3 341078962 EP 12700311 A 2012-01-11 \n4 341127772 EP 12700372 A 2012-01-02 \n\n appln_filing_year appln_nr_original ipr_type receiving_office \n0 2012 12000117 PI \\\n1 2012 12151915 PI \n2 2012 12700310 PI \n3 2012 12700311 PI \n4 2012 12700372 PI \n\n internat_appln_id ... earliest_pat_publn_id granted docdb_family_id \n0 0 ... 407623142 Y 45507394 \\\n1 0 ... 365158710 Y 45531220 \n2 340778427 ... 413564969 Y 45491582 \n3 340778431 ... 413564970 Y 45491583 \n4 340460188 ... 421840120 Y 45495923 \n\n inpadoc_family_id docdb_family_size nb_citing_docdb_fam nb_applicants \n0 340657036 3 6 1 \\\n1 340982410 2 16 2 \n2 340778427 3 2 1 \n3 340778431 3 3 1 \n4 340460188 4 8 1 \n\n nb_inventors appln_title_lg \n0 2 en \\\n1 6 en \n2 1 en \n3 1 en \n4 2 en \n\n appln_title \n0 Rotating membrane filter disc apparatus \n1 Heating-Cooling-Capacity measurement controlli... \n2 TRANSMISSION DEVICE \n3 TRANSMISSION DEVICE \n4 POWER CONTROL IN A WIRELESS COMMUNICATION SYST... \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>340657036</td>\n <td>EP</td>\n <td>12000117</td>\n <td>A</td>\n <td>2012-01-09</td>\n <td>2012</td>\n <td>12000117</td>\n <td>PI</td>\n <td></td>\n <td>0</td>\n <td>...</td>\n <td>407623142</td>\n <td>Y</td>\n <td>45507394</td>\n <td>340657036</td>\n <td>3</td>\n <td>6</td>\n <td>1</td>\n <td>2</td>\n <td>en</td>\n <td>Rotating membrane filter disc apparatus</td>\n </tr>\n <tr>\n <th>1</th>\n <td>340982410</td>\n <td>EP</td>\n <td>12151915</td>\n <td>A</td>\n <td>2012-01-20</td>\n <td>2012</td>\n <td>12151915</td>\n <td>PI</td>\n <td></td>\n <td>0</td>\n <td>...</td>\n <td>365158710</td>\n <td>Y</td>\n <td>45531220</td>\n <td>340982410</td>\n <td>2</td>\n <td>16</td>\n <td>2</td>\n <td>6</td>\n <td>en</td>\n <td>Heating-Cooling-Capacity measurement controlli...</td>\n </tr>\n <tr>\n <th>2</th>\n <td>341078960</td>\n <td>EP</td>\n <td>12700310</td>\n <td>A</td>\n <td>2012-01-11</td>\n <td>2012</td>\n <td>12700310</td>\n <td>PI</td>\n <td></td>\n <td>340778427</td>\n <td>...</td>\n <td>413564969</td>\n <td>Y</td>\n <td>45491582</td>\n <td>340778427</td>\n <td>3</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>en</td>\n <td>TRANSMISSION DEVICE</td>\n </tr>\n <tr>\n <th>3</th>\n <td>341078962</td>\n <td>EP</td>\n <td>12700311</td>\n <td>A</td>\n <td>2012-01-11</td>\n <td>2012</td>\n <td>12700311</td>\n <td>PI</td>\n <td></td>\n <td>340778431</td>\n <td>...</td>\n <td>413564970</td>\n <td>Y</td>\n <td>45491583</td>\n <td>340778431</td>\n <td>3</td>\n <td>3</td>\n <td>1</td>\n <td>1</td>\n <td>en</td>\n <td>TRANSMISSION DEVICE</td>\n </tr>\n <tr>\n <th>4</th>\n <td>341127772</td>\n <td>EP</td>\n <td>12700372</td>\n <td>A</td>\n <td>2012-01-02</td>\n <td>2012</td>\n <td>12700372</td>\n <td>PI</td>\n <td></td>\n <td>340460188</td>\n <td>...</td>\n <td>421840120</td>\n <td>Y</td>\n <td>45495923</td>\n <td>340460188</td>\n <td>4</td>\n <td>8</td>\n <td>1</td>\n <td>2</td>\n <td>en</td>\n <td>POWER CONTROL IN A WIRELESS COMMUNICATION SYST...</td>\n </tr>\n </tbody>\n</table>\n<p>5 rows × 28 columns</p>\n</div>"
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"appln_data = appln.merge(appln_title, on=\"appln_id\")\n",
"appln_data.head()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink