{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Define the symbol-tag mappings\n",
    "symbol_tags = {\n",
    "    \".\": \"PMP\",\n",
    "    \"!\": \"PME\",\n",
    "    \"?\": \"PMQ\",\n",
    "    \",\": \"PMC\",\n",
    "    \";\": \"PMSC\",\n",
    "    \"@\": \"PMS\",\n",
    "    \"/\": \"PMS\",\n",
    "    \"+\": \"PMS\",\n",
    "    \"*\": \"PMS\",\n",
    "    \"(\": \"PMS\",\n",
    "    \")\": \"PMS\",\n",
    "    \"\\\"\": \"PMS\",\n",
    "    \"'\": \"PMS\",\n",
    "    \"~\": \"PMS\",\n",
    "    \"&\": \"PMS\",\n",
    "    \"%\": \"PMS\",\n",
    "    \"$\": \"PMS\",\n",
    "    \"#\": \"PMS\",\n",
    "    \"=\": \"PMS\",\n",
    "    \"-\": \"PMS\",\n",
    "    \":\": \"PMS\"\n",
    "}\n",
    "\n",
    "# Read the dataset from CSV\n",
    "\n",
    "output_file = 'final_CRF.csv'\n",
    "\n",
    "# Read the dataset\n",
    "df = pd.read_csv(r'D:\\Thesis\\POS Tag Automation\\cleaned_output.csv')\n",
    "\n",
    "# Update tags based on symbols\n",
    "df['Tag'] = df.apply(lambda row: symbol_tags.get(row['Token'], row['Tag']), axis=1)\n",
    "\n",
    "# Save the updated dataset to CSV\n",
    "df.to_csv(output_file, index=False)\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}