persian_verbs/1.extract_verbs_from_PVC.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "this_dir_path = Path().resolve()\n",
    "data_path = this_dir_path / \"Data\"\n",
    "verb_path = data_path / \"PVC\" / \"Data\" / \"TXT\" / \"verb.txt\"\n",
    "processed_past_verb_path = data_path / \"verbs_past_PVC.json\"\n",
    "processed_present_verb_path = data_path / \"verbs_present_PVC.json\"\n",
    "\n",
    "# You can download the PVC data from https://www.peykaregan.ir/dataset/%D9%85%D8%AC%D9%85%D9%88%D8%B9%D9%87-%D8%A7%D9%81%D8%B9%D8%A7%D9%84-%D8%AA%D8%B5%D8%B1%DB%8C%D9%81%E2%80%8C%D8%B4%D8%AF%D9%87-%D9%81%D8%A7%D8%B1%D8%B3%DB%8C\n",
    "# After downloading, unzip the data and place it in a directory called Data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(verb_path, \"r\") as f:\n",
    "    lines = f.readlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "result: dict[str, list] = {}\n",
    "for line in lines:\n",
    "    verb = line.split(\"@\")[0]\n",
    "    idx = line.split(\"@\")[1]\n",
    "    if isinstance(result.get(idx), list):\n",
    "        result[idx].append(verb)\n",
    "    else:\n",
    "        result[idx] = [verb]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_simple_past: dict[str, str] = {}\n",
    "for line in lines:\n",
    "    if line.split(\"@\")[2:] == [\n",
    "        \"ACTIVE\",\n",
    "        \"SINGULAR\",\n",
    "        \"FIRST_PERSON\",\n",
    "        \"POSITIVE\",\n",
    "        \"م\",\n",
    "        \"PAST\",\n",
    "        \"INDICATIVE\",\n",
    "        \"SIMPLE\\n\",\n",
    "    ]:\n",
    "        result_simple_past[line.split(\"@\")[1]] = line.split(\"@\")[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_simple_past_list = {\n",
    "    key: value[:-1]\n",
    "    for key, value in sorted(result_simple_past.items(), key=lambda x: x[1])\n",
    "}\n",
    "with open(processed_past_verb_path, \"w\", encoding=\"utf-8\") as f:\n",
    "    json.dump(result_simple_past_list, f, ensure_ascii=False, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_simple_present: dict[str, str] = {}\n",
    "for line in lines:\n",
    "    if line.split(\"@\")[2:] == [\n",
    "        \"ACTIVE\",\n",
    "        \"SINGULAR\",\n",
    "        \"FIRST_PERSON\",\n",
    "        \"POSITIVE\",\n",
    "        \"م\",\n",
    "        \"PRESENT\",\n",
    "        \"INDICATIVE\",\n",
    "        \"SIMPLE\\n\",\n",
    "    ]:\n",
    "        result_simple_present[line.split(\"@\")[1]] = line.split(\"@\")[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_simple_present_list = {\n",
    "    key: value[:-1]\n",
    "    for key, value in sorted(result_simple_present.items(), key=lambda x: x[1])\n",
    "}\n",
    "with open(processed_present_verb_path, \"w\", encoding=\"utf-8\") as f:\n",
    "    json.dump(result_simple_present_list, f, ensure_ascii=False, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".env",
   "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": "3.10.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}