{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import patoolib\n",
    "import os\n",
    "import patoolib\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.naive_bayes import GaussianNB, MultinomialNB\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## TRENING"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### ROZPAKOWANIE I WCZYTANIE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "patool: Extracting train/in.tsv.xz ...\n",
      "patool: running \"\"C:\\Program Files\\Git\\mingw64\\bin\\xz.EXE\"\" -c -d -- train/in.tsv.xz > train/in.tsv\n",
      "patool:     with shell=True\n",
      "patool: ... train/in.tsv.xz extracted to `train/'.\n"
     ]
    }
   ],
   "source": [
    "EXPECTED_FILE = open('train/expected.tsv', 'r', encoding=\"utf-8\")\n",
    "\n",
    "patoolib.extract_archive(\"train/in.tsv.xz\", outdir=\"train/\")\n",
    "TRAIN = open('train/in.tsv', 'r', encoding=\"utf-8\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### WRZUCENIE DO ZMIENNYCH"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "EXPECTED = []\n",
    "for line in EXPECTED_FILE:\n",
    "    EXPECTED.append(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "TRAIN_DATA = []\n",
    "for line in TRAIN:\n",
    "    TRAIN_DATA.append(line)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### ZAMKNIECIE ZMIENNYCH PLIKOW I USUNIECIE ROZPAKOWANIA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "EXPECTED_FILE.close()\n",
    "TRAIN.close()\n",
    "#os.remove(\"train/in.tsv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### MODEL TRENINGOWY"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "EXPECTED_ENCODER = LabelEncoder().fit_transform(EXPECTED)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "PIPE = Pipeline(steps=[(\"TF-IDF\",TfidfVectorizer()), (\"BAYES\", MultinomialNB())])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "TRAIN_MODEL = PIPE.fit(TRAIN_DATA, EXPECTED_ENCODER)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## FUNKCJE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def BayesFit(MODEL, DOC):\n",
    "    PREDICTION =  MODEL.predict(DOC)\n",
    "    return PREDICTION"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PLIK DEV-0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "patool: Extracting dev-0/in.tsv.xz ...\n",
      "patool: running \"\"C:\\Program Files\\Git\\mingw64\\bin\\xz.EXE\"\" -c -d -- dev-0/in.tsv.xz > dev-0/in.tsv\n",
      "patool:     with shell=True\n",
      "patool: ... dev-0/in.tsv.xz extracted to `dev-0/'.\n"
     ]
    }
   ],
   "source": [
    "patoolib.extract_archive(\"dev-0/in.tsv.xz\", outdir=\"dev-0/\")\n",
    "INFILE = open('dev-0/in.tsv', 'r', encoding=\"utf-8\")\n",
    "\n",
    "OUTFILE = open(\"dev-0/out.tsv\", \"w\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "ALL_DOC = INFILE.readlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "RESULT = BayesFit(TRAIN_MODEL, ALL_DOC)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "for x in RESULT:\n",
    "    OUTFILE.write(str(x) + '\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "INFILE.close()\n",
    "OUTFILE.close()\n",
    "#os.remove(\"dev-0/in.tsv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PLIK TEST-A"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "patool: Extracting test-A/in.tsv.xz ...\n",
      "patool: running \"\"C:\\Program Files\\Git\\mingw64\\bin\\xz.EXE\"\" -c -d -- test-A/in.tsv.xz > test-A/in.tsv\n",
      "patool:     with shell=True\n",
      "patool: ... test-A/in.tsv.xz extracted to `test-A/'.\n"
     ]
    }
   ],
   "source": [
    "patoolib.extract_archive(\"test-A/in.tsv.xz\", outdir=\"test-A/\")\n",
    "INFILE = open('test-A/in.tsv', 'r', encoding=\"utf-8\")\n",
    "\n",
    "OUTFILE = open(\"test-A/out.tsv\", \"w\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "ALL_DOC = INFILE.readlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "RESULT = BayesFit(TRAIN_MODEL, ALL_DOC)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "for x in RESULT:\n",
    "    OUTFILE.write(str(x) + '\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "INFILE.close()\n",
    "OUTFILE.close()\n",
    "#os.remove(\"test-A/in.tsv\")"
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}