sport-text-classification-ball-ISI-public/bayes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ce420679-f5aa-4c83-a912-3c4afa982d7e",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\Users\\Adrian\\anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3444: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version.\n",
      "\n",
      "\n",
      "  exec(code_obj, self.user_global_ns, self.user_ns)\n",
      "b'Skipping line 25706: expected 2 fields, saw 3\\nSkipping line 58881: expected 2 fields, saw 3\\nSkipping line 73761: expected 2 fields, saw 3\\n'\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "\n",
    "\n",
    "df = pd.read_csv(\"train/train.tsv\", sep=\"\\t\", header=None, error_bad_lines=False)\n",
    "\n",
    "\n",
    "\n",
    "dev_x = pd.read_csv(\"dev-0/in.tsv\", sep=\"\\t\", header=None, error_bad_lines=False)\n",
    "\n",
    "\n",
    "with open('test-A/in.tsv', 'r', encoding='utf8') as file:\n",
    "    test = file.readlines()\n",
    "test = pd.Series(test)\n",
    "\n",
    "\n",
    "x = df[1]\n",
    "y = df[0]\n",
    "\n",
    "model = make_pipeline(TfidfVectorizer(), MultinomialNB())\n",
    "model.fit(x,y)\n",
    "\n",
    "pred_dev = model.predict(dev_x[0])\n",
    "pred_dev = pd.Series(pred_dev)\n",
    "\n",
    "with open('dev-0/out.tsv', 'wt') as file:\n",
    "    for pred in pred_dev:\n",
    "        file.write(str(pred)+'\\n')\n",
    "\n",
    "\n",
    "pred_test = model.predict(test)\n",
    "pred_test = pd.Series(pred_test)\n",
    "pred_test = pred_test.astype('int')\n",
    "\n",
    "\n",
    "        \n",
    "with open('test-A/out.tsv', 'wt') as file:\n",
    "    for pred in pred_test:\n",
    "        file.write(str(pred)+'\\n')\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "        \n"
   ]
  }
 ],
 "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}