{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import csv\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from stop_words import get_stop_words\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#trening\n",
    "\n",
    "#dane treningowe\n",
    "train_data = pd.read_csv('train/train.tsv.xz', compression='xz', header=None, sep='\\t')\n",
    "\n",
    "#regresja liniowa\n",
    "LR = LinearRegression()\n",
    "#vectorizer\n",
    "VEC = TfidfVectorizer(stop_words=get_stop_words('polish'))\n",
    "#wektoryzacja danych treningowych\n",
    "train_x = VEC.fit_transform(train_data[4])\n",
    "#średnia dat\n",
    "dm = (train_data[0] + train_data[1])/2\n",
    "#trening\n",
    "LR.fit(train_x, dm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "#dev-0 predict\n",
    "\n",
    "#dane treningowe\n",
    "dev0_data = pd.read_csv('dev-0/in.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t')\n",
    "\n",
    "#wektoryzacja danych treningowych\n",
    "dev0_x = VEC.transform(dev0_data[0])\n",
    "#predykcja\n",
    "dev0_y = LR.predict(dev0_x)\n",
    "#zapis wyników\n",
    "dev0_y.tofile('dev-0/out.tsv', sep='\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#dev-1 predict\n",
    "\n",
    "#dane treningowe\n",
    "dev1_data = pd.read_csv('dev-1/in.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t')\n",
    "\n",
    "#wektoryzacja danych treningowych\n",
    "dev1_x = VEC.transform(dev1_data[0])\n",
    "#predykcja\n",
    "dev1_y = LR.predict(dev1_x)\n",
    "#zapis wyników\n",
    "dev1_y.tofile('dev-1/out.tsv', sep='\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "#test-A predict\n",
    "\n",
    "#dane treningowe\n",
    "testA_data = pd.read_csv('test-A/in.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t')\n",
    "\n",
    "#wektoryzacja danych treningowych\n",
    "testA_x = VEC.transform(testA_data[0])\n",
    "#predykcja\n",
    "testA_y = LR.predict(testA_x)\n",
    "#zapis wyników\n",
    "testA_y.tofile('test-A/out.tsv', sep='\\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": "3.8.0"
  },
  "metadata": {
   "interpreter": {
    "hash": "d4bdc0d8028da516e3b937f3ab23da3f18f7264589053952c883afefa2219368"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}