{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f1acd866",
   "metadata": {},
   "outputs": [],
   "source": [
    "pos= open('positive.txt','r').read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "08fa198d",
   "metadata": {},
   "outputs": [],
   "source": [
    "neg= open('negative.txt','r').read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0b9e046f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6827e073",
   "metadata": {},
   "outputs": [],
   "source": [
    "test= open('test.srt','r').read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f0cabfe3",
   "metadata": {},
   "outputs": [],
   "source": [
    "characters_to_remove = \"]!()-@0123456789:->,'[\"\n",
    "pattern = \"[\" + characters_to_remove + \"]\"\n",
    "test= re.sub(pattern, \"\", test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1924d6b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "sent = nltk.tokenize.PunktSentenceTokenizer().tokenize(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1b4c6b1e",
   "metadata": {},
   "outputs": [],
   "source": [
    "words= nltk.tokenize.wordpunct_tokenize(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "74115f66",
   "metadata": {},
   "outputs": [],
   "source": [
    "words2=nltk.tokenize.word_tokenize(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "b3cd7edd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9864"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2023d52e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9770"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(words2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1817a2f7",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4e88b559",
   "metadata": {},
   "outputs": [],
   "source": [
    "sent= nltk.tokenize.LineTokenizer().tokenize(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cbfac454",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40e42062",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "207ba393",
   "metadata": {},
   "outputs": [],
   "source": [
    "word_frq= nltk.FreqDist(words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "93742ea7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2005"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(word_frq)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e458c57",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a98c9a0a",
   "metadata": {},
   "outputs": [],
   "source": [
    "words_frq= nltk.FreqDist(words2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c1fe9ad2",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "5f5b4662",
   "metadata": {},
   "outputs": [],
   "source": [
    "import spacy\n",
    "nlp= spacy.load('en_core_web_sm')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "3125cf03",
   "metadata": {},
   "outputs": [],
   "source": [
    "w= nlp(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ca3fe86d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "180a4353",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}