dc-ml-emea-ar/playground.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from utils.biz_utils import add_slash_to_text_as_regex\n",
    "import json\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "regex = r\"Turnover \\n\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Turnover\\\\s+\\\\n'"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "add_slash_to_text_as_regex(regex)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"What was the share of investments made in transitional and enabling activities? \\nTaxonomy-aligned\\nactivities are expressed \\nas a share of\\n\\u2022\\t Turnover \\nreflects the\\n\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<re.Match object; span=(141, 151), match='Turnover \\n'>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "re.search(regex, text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "datapoint_keywords_config_file = r\"./configuration/datapoint_keyword.json\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TOR no match\n",
      "Turnover\\*\\s+ no match\n",
      "Turnover\\s+ match Turnover \n",
      "Turnover\\s+Ratio no match\n",
      "Turnover\\s+Rate no match\n",
      "Portfolio\\s+Turnover no match\n",
      "Portfolio\\s+turnover\\s+ratio no match\n",
      "Portfolio\\s+turnover\\s+rate no match\n",
      "PTR no match\n",
      "Annual\\s+Portfolio\\s+Turnover\\s+Ratio no match\n"
     ]
    }
   ],
   "source": [
    "with open(datapoint_keywords_config_file, \"r\", encoding=\"utf-8\") as file:\n",
    "    datapoint_keywords_config = json.load(file)\n",
    "\n",
    "tor_regex_list = datapoint_keywords_config.get(\"tor\", {}).get(\"english\", [])\n",
    "\n",
    "for tor_regex in tor_regex_list:\n",
    "    regex = add_slash_to_text_as_regex(tor_regex)\n",
    "    search = re.search(regex, text)\n",
    "    if search:\n",
    "        print(f\"{regex} match {search.group()}\")\n",
    "    else:\n",
    "        print(f\"{regex} no match\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "torch2_real",
   "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}