{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "30b23d26",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package punkt to\n",
      "[nltk_data]     C:\\Users\\HITES\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n",
      "[nltk_data] Downloading package wordnet to\n",
      "[nltk_data]     C:\\Users\\HITES\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package wordnet is already up-to-date!\n",
      "[nltk_data] Downloading package averaged_perceptron_tagger to\n",
      "[nltk_data]     C:\\Users\\HITES\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package averaged_perceptron_tagger is already up-to-\n",
      "[nltk_data]       date!\n",
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\HITES\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    }
   ],
   "source": [
    "import nltk\n",
    "nltk.download('punkt')\n",
    "nltk.download('wordnet')\n",
    "nltk.download('averaged_perceptron_tagger')\n",
    "nltk.download('stopwords')\n",
    "from nltk import sent_tokenize\n",
    "from nltk import word_tokenize\n",
    "from nltk.corpus import stopwords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2d11b152",
   "metadata": {},
   "outputs": [],
   "source": [
    "text='Real madrid is set to win the UCL for the season . Benzema might win Balon dor . Salah might be the runner up'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "41208d27",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Real madrid is set to win the UCL for the season .', 'Benzema might win Balon dor .', 'Salah might be the runner up']\n"
     ]
    }
   ],
   "source": [
    "tokens_sents = nltk.sent_tokenize(text)\n",
    "print(tokens_sents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c3cbaeb1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Real', 'madrid', 'is', 'set', 'to', 'win', 'the', 'UCL', 'for', 'the', 'season', '.', 'Benzema', 'might', 'win', 'Balon', 'dor', '.', 'Salah', 'might', 'be', 'the', 'runner', 'up']\n"
     ]
    }
   ],
   "source": [
    "tokens_words = nltk.word_tokenize(text)\n",
    "print(tokens_words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a57dfc78",
   "metadata": {},
   "outputs": [],
   "source": [
    "from nltk.stem import PorterStemmer\n",
    "from nltk.stem.snowball import SnowballStemmer\n",
    "from nltk.stem import LancasterStemmer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d4f73a83",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['real', 'madrid', 'is', 'set', 'to', 'win', 'the', 'ucl', 'for', 'the', 'season', '.', 'benzema', 'might', 'win', 'balon', 'dor', '.', 'salah', 'might', 'be', 'the', 'runner', 'up']\n"
     ]
    }
   ],
   "source": [
    "stem=[]\n",
    "for i in tokens_words:\n",
    "  ps = PorterStemmer()\n",
    "  stem_word= ps.stem(i)\n",
    "  stem.append(stem_word)\n",
    "print(stem)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "45d506b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "from nltk.stem import WordNetLemmatizer \n",
    "lemmatizer = WordNetLemmatizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a9138128",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "real madrid is set to win the ucl for the season . benzema might win balon dor . salah might be the runner up\n"
     ]
    }
   ],
   "source": [
    "lemmatized_output = ' '.join([lemmatizer.lemmatize(w) for w in stem])\n",
    "print(lemmatized_output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "8997a909",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['real', 'madrid', 'is', 'set', 'to', 'win', 'the', 'ucl', 'for', 'the', 'season', '.', 'benzema', 'might', 'win', 'balon', 'dor', '.', 'salah', 'might', 'be', 'the', 'runner', 'up']\n"
     ]
    }
   ],
   "source": [
    "leme=[]\n",
    "for i in stem:\n",
    "  lemetized_word=lemmatizer.lemmatize(i)\n",
    "  leme.append(lemetized_word)\n",
    "print(leme)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "cbf2072c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parts of Speech:  [('real', 'JJ'), ('madrid', 'NN'), ('is', 'VBZ'), ('set', 'VBN'), ('to', 'TO'), ('win', 'VB'), ('the', 'DT'), ('ucl', 'NN'), ('for', 'IN'), ('the', 'DT'), ('season', 'NN'), ('.', '.'), ('benzema', 'NN'), ('might', 'MD'), ('win', 'VB'), ('balon', 'NN'), ('dor', 'NN'), ('.', '.'), ('salah', 'NN'), ('might', 'MD'), ('be', 'VB'), ('the', 'DT'), ('runner', 'NN'), ('up', 'RP')]\n"
     ]
    }
   ],
   "source": [
    "print(\"Parts of Speech: \",nltk.pos_tag(leme))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "72cb06fd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', \"you're\", \"you've\", \"you'll\", \"you'd\", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', \"she's\", 'her', 'hers', 'herself', 'it', \"it's\", 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', \"that'll\", 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don', \"don't\", 'should', \"should've\", 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren', \"aren't\", 'couldn', \"couldn't\", 'didn', \"didn't\", 'doesn', \"doesn't\", 'hadn', \"hadn't\", 'hasn', \"hasn't\", 'haven', \"haven't\", 'isn', \"isn't\", 'ma', 'mightn', \"mightn't\", 'mustn', \"mustn't\", 'needn', \"needn't\", 'shan', \"shan't\", 'shouldn', \"shouldn't\", 'wasn', \"wasn't\", 'weren', \"weren't\", 'won', \"won't\", 'wouldn', \"wouldn't\"]\n"
     ]
    }
   ],
   "source": [
    "sw_nltk = stopwords.words('english')\n",
    "print(sw_nltk)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "62eb4c23",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Real madrid set win UCL season . Benzema might win Balon dor . Salah might runner\n"
     ]
    }
   ],
   "source": [
    "words = [word for word in text.split() if word.lower() not in sw_nltk]\n",
    "new_text = \" \".join(words)\n",
    "print(new_text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e5ed22ef",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}