{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sklearn\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "import numpy as np\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.preprocessing import LabelEncoder "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "def getInput(path):\n",
    "    with open(path,encoding='utf-8') as f:\n",
    "          return f.readlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/c/Users/mkoci/Desktop/naiwny_bayes\n"
     ]
    }
   ],
   "source": [
    "!pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_in=getInput('./train/in.tsv')\n",
    "train_expected=getInput('./train/expected.tsv')\n",
    "test_in=getInput('./test-A/in.tsv')\n",
    "dev_in=getInput('./dev-0/in.tsv')\n",
    "dev_expected=getInput('./dev-0/expected.tsv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())\n",
    "encTransform = LabelEncoder().fit_transform(train_expected)\n",
    "model = pipeline.fit(train_in, encTransform)\n",
    "dev_predicted = model.predict(dev_in)\n",
    "test_predicted = model.predict(test_in)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('./dev-0/out.tsv', \"w\") as result:\n",
    "            for out in dev_predicted:\n",
    "                result.write(str(out) + '\\n')\n",
    "with open('./test-A/out.tsv', \"w\") as result:\n",
    "            for out in test_predicted:\n",
    "                result.write(str(out) + '\\n')                "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[NbConvertApp] Converting notebook Naiwny_bayes.ipynb to script\n",
      "[NbConvertApp] Writing 1337 bytes to Naiwny_bayes.py\n"
     ]
    }
   ],
   "source": [
    "!jupyter nbconvert --to script Naiwny_bayes.ipynb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}