{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "greenhouse-technician",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import sklearn\n",
    "import pandas as pd\n",
    "from gzip import open as open_gz\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"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "acoustic-dividend",
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict_year(x, path_out, model):\n",
    "    results = model.predict(x)\n",
    "    with open(path_out, 'wt') as file:\n",
    "        for r in results:\n",
    "            file.write(str(r) + '\\n')       "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78c79a98-8309-4c1c-b27d-faad2ee7a2af",
   "metadata": {},
   "outputs": [],
   "source": [
    "def read_file(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"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "senior-harassment",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('train/train.tsv', 'r', encoding='utf8') as file:\n",
    "    train = pd.read_csv(file, sep='\\t', names=['Begin', 'End', 'Title', 'Author', 'Text'])\n",
    "    \n",
    "train = train[0:12000]\n",
    "train_x = train['Text']\n",
    "#train['Date'] = (train['Date1'].astype(float) + train['Date2'].astype(float))/2\n",
    "train_y = train['Begin']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "polyphonic-coach",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pipeline(steps=[('tfidfvectorizer', TfidfVectorizer()),\n",
       "                ('linearregression', LinearRegression())])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = make_pipeline(TfidfVectorizer(), LinearRegression())\n",
    "model.fit(train_x, train_y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "varying-wright",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_dev_0 = read_file('dev-0/in.tsv')\n",
    "predict_year(x_dev_0, 'dev-0/out.tsv', model)\n",
    "x_dev_1 = read_file('dev-1/in.tsv')\n",
    "predict_year(x_dev_1,'dev-1/out.tsv', model)\n",
    "x_test = read_file('test-A/in.tsv')\n",
    "predict_year(x_test,'test-A/out.tsv', model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "traditional-amount",
   "metadata": {},
   "outputs": [],
   "source": [
    "#y_dev = pd.read_csv('dev-0/out.tsv',header = None, sep = '/t',engine = 'python')\n",
    "#y_dev = y_dev[0]\n",
    "#y_dev_exp = pd.read_csv('dev-0/expected.tsv',header = None, sep = '/t',engine = 'python')\n",
    "#y_dev_exp = y_dev_exp[0]\n",
    "#RMSE_dev = mean_squared_error(y_dev_exp, y_dev) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "close-clinton",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "official-sweet",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}