{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "8f5480f9-fa82-4150-acff-9309fdc43690",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "107463\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Pipeline(steps=[('tfidfvectorizer', TfidfVectorizer()),\n",
       "                ('linearregression', LinearRegression())])"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "with open('train/train.tsv', 'r', encoding='utf8') as file:\n",
    "    train_data = pd.read_csv(file, sep='\\t', names=['Begin', 'End', 'Title', 'Publisher', 'Text'])\n",
    "\n",
    "print(len(train_data))    \n",
    "train_data = train_data[:10000]\n",
    "    \n",
    "X = train_data['Text']\n",
    "Y = train_data['Begin']\n",
    "\n",
    "\n",
    "model = make_pipeline(TfidfVectorizer(), LinearRegression())\n",
    "model.fit(X, Y)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "02e89f1c-a2d0-4d41-94a2-aa86b257069d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def readFile(filename):\n",
    "    result = []\n",
    "    with open(filename, 'r', encoding=\"utf-8\") as file:\n",
    "        for line in file:\n",
    "            text = line.split(\"\\t\")[0].strip()\n",
    "            result.append(text)\n",
    "    return result\n",
    "\n",
    "def write_pred(filename, predictions):\n",
    "    with open(filename, \"w\") as file:\n",
    "        for pred in predictions:\n",
    "            file.write(str(pred) + \"\\n\")\n",
    "        \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "b85f5e22-eafb-41ee-aa2c-20c338d42701",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "dev_0 = readFile('dev-0/in.tsv')\n",
    "predict_dev_0 = model.predict(dev_0)\n",
    "write_pred('dev-0/out.tsv', predict_dev_0)\n",
    "\n",
    "dev_1 = readFile('dev-1/in.tsv')\n",
    "predict_dev_1 = model.predict(dev_1)\n",
    "write_pred('dev-1/out.tsv', predict_dev_1)\n",
    "\n",
    "test_A = readFile('test-A/in.tsv')\n",
    "predict_test_A = model.predict(test_A)\n",
    "write_pred('test-A/out.tsv', predict_test_A)\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
}