{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from nltk.tokenize import RegexpTokenizer\n",
    "from stop_words import get_stop_words\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "data=pd.read_csv('dev-0/in.tsv', sep='\\t', header=None)\n",
    "expected_data=pd.read_csv('dev-0/expected.tsv', sep='\\t', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "data[0] = data[0].str.lower()\n",
    "filtered_words = [word for word in data[0] if word not in get_stop_words('polish')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "token = RegexpTokenizer(r'[a-zA-Z0-9]+')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(lowercase=True,ngram_range = (1,1),tokenizer = token.tokenize)\n",
    "text_counts= cv.fit_transform(data[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1x5048 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 234 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    text_counts, expected_data[0], test_size=0.3, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MultinomialNB Accuracy: 0.6296296296296297\n"
     ]
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn import metrics\n",
    "clf = MultinomialNB().fit(X_train, y_train)\n",
    "predicted= clf.predict(X_test)\n",
    "print(\"MultinomialNB Accuracy:\",metrics.accuracy_score(y_test, predicted))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "tf=TfidfVectorizer()\n",
    "text_tf= tf.fit_transform(filtered_words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    text_tf, expected_data[0], test_size=0.3, random_state=123)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MultinomialNB Accuracy: 0.2222222222222222\n"
     ]
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn import metrics\n",
    "clf = MultinomialNB().fit(X_train, y_train)\n",
    "predicted= clf.predict(X_test)\n",
    "print(\"MultinomialNB Accuracy:\",metrics.accuracy_score(y_test, predicted))"
   ]
  },
  {
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}