{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import ast\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from nltk.stem.porter import PorterStemmer\n",
    "from sklearn.metrics.pairwise import cosine_similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = pd.read_csv('tmdb_5000_movies.csv')\n",
    "credits = pd.read_csv('tmdb_5000_credits.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>budget</th>\n",
       "      <th>genres</th>\n",
       "      <th>homepage</th>\n",
       "      <th>id</th>\n",
       "      <th>keywords</th>\n",
       "      <th>original_language</th>\n",
       "      <th>original_title</th>\n",
       "      <th>overview</th>\n",
       "      <th>popularity</th>\n",
       "      <th>production_companies</th>\n",
       "      <th>production_countries</th>\n",
       "      <th>release_date</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>237000000</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>http://www.avatarmovie.com/</td>\n",
       "      <td>19995</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>en</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>150.437577</td>\n",
       "      <td>[{\"name\": \"Ingenious Film Partners\", \"id\": 289...</td>\n",
       "      <td>[{\"iso_3166_1\": \"US\", \"name\": \"United States o...</td>\n",
       "      <td>2009-12-10</td>\n",
       "      <td>2787965087</td>\n",
       "      <td>162.0</td>\n",
       "      <td>[{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>Enter the World of Pandora.</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>7.2</td>\n",
       "      <td>11800</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      budget                                             genres   \n",
       "0  237000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...  \\\n",
       "\n",
       "                      homepage     id   \n",
       "0  http://www.avatarmovie.com/  19995  \\\n",
       "\n",
       "                                            keywords original_language   \n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...                en  \\\n",
       "\n",
       "  original_title                                           overview   \n",
       "0         Avatar  In the 22nd century, a paraplegic Marine is di...  \\\n",
       "\n",
       "   popularity                               production_companies   \n",
       "0  150.437577  [{\"name\": \"Ingenious Film Partners\", \"id\": 289...  \\\n",
       "\n",
       "                                production_countries release_date     revenue   \n",
       "0  [{\"iso_3166_1\": \"US\", \"name\": \"United States o...   2009-12-10  2787965087  \\\n",
       "\n",
       "   runtime                                   spoken_languages    status   \n",
       "0    162.0  [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...  Released  \\\n",
       "\n",
       "                       tagline   title  vote_average  vote_count  \n",
       "0  Enter the World of Pandora.  Avatar           7.2       11800  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id   title                                               cast   \n",
       "0     19995  Avatar  [{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...  \\\n",
       "\n",
       "                                                crew  \n",
       "0  [{\"credit_id\": \"52fe48009251416c750aca23\", \"de...  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "credits.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = movies.merge(credits,on='title')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>budget</th>\n",
       "      <th>genres</th>\n",
       "      <th>homepage</th>\n",
       "      <th>id</th>\n",
       "      <th>keywords</th>\n",
       "      <th>original_language</th>\n",
       "      <th>original_title</th>\n",
       "      <th>overview</th>\n",
       "      <th>popularity</th>\n",
       "      <th>production_companies</th>\n",
       "      <th>...</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>237000000</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>http://www.avatarmovie.com/</td>\n",
       "      <td>19995</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>en</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>150.437577</td>\n",
       "      <td>[{\"name\": \"Ingenious Film Partners\", \"id\": 289...</td>\n",
       "      <td>...</td>\n",
       "      <td>162.0</td>\n",
       "      <td>[{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>Enter the World of Pandora.</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>7.2</td>\n",
       "      <td>11800</td>\n",
       "      <td>19995</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      budget                                             genres   \n",
       "0  237000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...  \\\n",
       "\n",
       "                      homepage     id   \n",
       "0  http://www.avatarmovie.com/  19995  \\\n",
       "\n",
       "                                            keywords original_language   \n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...                en  \\\n",
       "\n",
       "  original_title                                           overview   \n",
       "0         Avatar  In the 22nd century, a paraplegic Marine is di...  \\\n",
       "\n",
       "   popularity                               production_companies  ... runtime   \n",
       "0  150.437577  [{\"name\": \"Ingenious Film Partners\", \"id\": 289...  ...   162.0  \\\n",
       "\n",
       "                                    spoken_languages    status   \n",
       "0  [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...  Released  \\\n",
       "\n",
       "                       tagline   title vote_average vote_count movie_id   \n",
       "0  Enter the World of Pandora.  Avatar          7.2      11800    19995  \\\n",
       "\n",
       "                                                cast   \n",
       "0  [{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...  \\\n",
       "\n",
       "                                                crew  \n",
       "0  [{\"credit_id\": \"52fe48009251416c750aca23\", \"de...  \n",
       "\n",
       "[1 rows x 23 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['budget', 'genres', 'homepage', 'id', 'keywords', 'original_language',\n",
       "       'original_title', 'overview', 'popularity', 'production_companies',\n",
       "       'production_countries', 'release_date', 'revenue', 'runtime',\n",
       "       'spoken_languages', 'status', 'tagline', 'title', 'vote_average',\n",
       "       'vote_count', 'movie_id', 'cast', 'crew'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = movies[['movie_id','title','overview','genres','keywords','cast','crew']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>[{\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"...</td>\n",
       "      <td>[{\"id\": 270, \"name\": \"ocean\"}, {\"id\": 726, \"na...</td>\n",
       "      <td>[{\"cast_id\": 4, \"character\": \"Captain Jack Spa...</td>\n",
       "      <td>[{\"credit_id\": \"52fe4232c3a36847f800b579\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 470, \"name\": \"spy\"}, {\"id\": 818, \"name...</td>\n",
       "      <td>[{\"cast_id\": 1, \"character\": \"James Bond\", \"cr...</td>\n",
       "      <td>[{\"credit_id\": \"54805967c3a36829b5002c41\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 80, \"nam...</td>\n",
       "      <td>[{\"id\": 849, \"name\": \"dc comics\"}, {\"id\": 853,...</td>\n",
       "      <td>[{\"cast_id\": 2, \"character\": \"Bruce Wayne / Ba...</td>\n",
       "      <td>[{\"credit_id\": \"52fe4781c3a36847f81398c3\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 818, \"name\": \"based on novel\"}, {\"id\":...</td>\n",
       "      <td>[{\"cast_id\": 5, \"character\": \"John Carter\", \"c...</td>\n",
       "      <td>[{\"credit_id\": \"52fe479ac3a36847f813eaa3\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title   \n",
       "0     19995                                    Avatar  \\\n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                            overview   \n",
       "0  In the 22nd century, a paraplegic Marine is di...  \\\n",
       "1  Captain Barbossa, long believed to be dead, ha...   \n",
       "2  A cryptic message from Bond’s past sends him o...   \n",
       "3  Following the death of District Attorney Harve...   \n",
       "4  John Carter is a war-weary, former military ca...   \n",
       "\n",
       "                                              genres   \n",
       "0  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...  \\\n",
       "1  [{\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"...   \n",
       "2  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "3  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 80, \"nam...   \n",
       "4  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "\n",
       "                                            keywords   \n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...  \\\n",
       "1  [{\"id\": 270, \"name\": \"ocean\"}, {\"id\": 726, \"na...   \n",
       "2  [{\"id\": 470, \"name\": \"spy\"}, {\"id\": 818, \"name...   \n",
       "3  [{\"id\": 849, \"name\": \"dc comics\"}, {\"id\": 853,...   \n",
       "4  [{\"id\": 818, \"name\": \"based on novel\"}, {\"id\":...   \n",
       "\n",
       "                                                cast   \n",
       "0  [{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...  \\\n",
       "1  [{\"cast_id\": 4, \"character\": \"Captain Jack Spa...   \n",
       "2  [{\"cast_id\": 1, \"character\": \"James Bond\", \"cr...   \n",
       "3  [{\"cast_id\": 2, \"character\": \"Bruce Wayne / Ba...   \n",
       "4  [{\"cast_id\": 5, \"character\": \"John Carter\", \"c...   \n",
       "\n",
       "                                                crew  \n",
       "0  [{\"credit_id\": \"52fe48009251416c750aca23\", \"de...  \n",
       "1  [{\"credit_id\": \"52fe4232c3a36847f800b579\", \"de...  \n",
       "2  [{\"credit_id\": \"54805967c3a36829b5002c41\", \"de...  \n",
       "3  [{\"credit_id\": \"52fe4781c3a36847f81398c3\", \"de...  \n",
       "4  [{\"credit_id\": \"52fe479ac3a36847f813eaa3\", \"de...  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "movie_id    0\n",
       "title       0\n",
       "overview    3\n",
       "genres      0\n",
       "keywords    0\n",
       "cast        0\n",
       "crew        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"name\": \"Fantasy\"}, {\"id\": 878, \"name\": \"Science Fiction\"}]'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.iloc[0].genres"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert(obj):\n",
    "    l = []\n",
    "    for i in ast.literal_eval(obj):\n",
    "        l.append(i['name'])   \n",
    "    return l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['genres'] = movies['genres'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id   title                                           overview   \n",
       "0     19995  Avatar  In the 22nd century, a paraplegic Marine is di...  \\\n",
       "\n",
       "                                          genres   \n",
       "0  [Action, Adventure, Fantasy, Science Fiction]  \\\n",
       "\n",
       "                                            keywords   \n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...  \\\n",
       "\n",
       "                                                cast   \n",
       "0  [{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...  \\\n",
       "\n",
       "                                                crew  \n",
       "0  [{\"credit_id\": \"52fe48009251416c750aca23\", \"de...  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['keywords'] = movies['keywords'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert3(obj):\n",
    "    l = []\n",
    "    c = 0\n",
    "    for i in ast.literal_eval(obj):\n",
    "        if c!=3:\n",
    "            l.append(i['name'])   \n",
    "            c+=1\n",
    "        else:\n",
    "            break\n",
    "    return l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['cast'] = movies['cast'].apply(convert3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fetch(obj):\n",
    "    l = []\n",
    "    for i in ast.literal_eval(obj):\n",
    "        if i['job']=='Director':\n",
    "            l.append(i['name'])   \n",
    "            break\n",
    "    return l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['crew'] = movies['crew'].apply(fetch)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[culture clash, future, space war, space colon...</td>\n",
       "      <td>[Sam Worthington, Zoe Saldana, Sigourney Weaver]</td>\n",
       "      <td>[James Cameron]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drug abuse, exotic island, east india ...</td>\n",
       "      <td>[Johnny Depp, Orlando Bloom, Keira Knightley]</td>\n",
       "      <td>[Gore Verbinski]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, based on novel, secret agent, sequel, mi...</td>\n",
       "      <td>[Daniel Craig, Christoph Waltz, Léa Seydoux]</td>\n",
       "      <td>[Sam Mendes]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dc comics, crime fighter, terrorist, secret i...</td>\n",
       "      <td>[Christian Bale, Michael Caine, Gary Oldman]</td>\n",
       "      <td>[Christopher Nolan]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[based on novel, mars, medallion, space travel...</td>\n",
       "      <td>[Taylor Kitsch, Lynn Collins, Samantha Morton]</td>\n",
       "      <td>[Andrew Stanton]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title   \n",
       "0     19995                                    Avatar  \\\n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                            overview   \n",
       "0  In the 22nd century, a paraplegic Marine is di...  \\\n",
       "1  Captain Barbossa, long believed to be dead, ha...   \n",
       "2  A cryptic message from Bond’s past sends him o...   \n",
       "3  Following the death of District Attorney Harve...   \n",
       "4  John Carter is a war-weary, former military ca...   \n",
       "\n",
       "                                          genres   \n",
       "0  [Action, Adventure, Fantasy, Science Fiction]  \\\n",
       "1                   [Adventure, Fantasy, Action]   \n",
       "2                     [Action, Adventure, Crime]   \n",
       "3               [Action, Crime, Drama, Thriller]   \n",
       "4           [Action, Adventure, Science Fiction]   \n",
       "\n",
       "                                            keywords   \n",
       "0  [culture clash, future, space war, space colon...  \\\n",
       "1  [ocean, drug abuse, exotic island, east india ...   \n",
       "2  [spy, based on novel, secret agent, sequel, mi...   \n",
       "3  [dc comics, crime fighter, terrorist, secret i...   \n",
       "4  [based on novel, mars, medallion, space travel...   \n",
       "\n",
       "                                               cast                 crew  \n",
       "0  [Sam Worthington, Zoe Saldana, Sigourney Weaver]      [James Cameron]  \n",
       "1     [Johnny Depp, Orlando Bloom, Keira Knightley]     [Gore Verbinski]  \n",
       "2      [Daniel Craig, Christoph Waltz, Léa Seydoux]         [Sam Mendes]  \n",
       "3      [Christian Bale, Michael Caine, Gary Oldman]  [Christopher Nolan]  \n",
       "4    [Taylor Kitsch, Lynn Collins, Samantha Morton]     [Andrew Stanton]  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['overview'] = movies['overview'].apply(lambda x:x.split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "      <td>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[culture clash, future, space war, space colon...</td>\n",
       "      <td>[Sam Worthington, Zoe Saldana, Sigourney Weaver]</td>\n",
       "      <td>[James Cameron]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>[Captain, Barbossa,, long, believed, to, be, d...</td>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drug abuse, exotic island, east india ...</td>\n",
       "      <td>[Johnny Depp, Orlando Bloom, Keira Knightley]</td>\n",
       "      <td>[Gore Verbinski]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>[A, cryptic, message, from, Bond’s, past, send...</td>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, based on novel, secret agent, sequel, mi...</td>\n",
       "      <td>[Daniel Craig, Christoph Waltz, Léa Seydoux]</td>\n",
       "      <td>[Sam Mendes]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>[Following, the, death, of, District, Attorney...</td>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dc comics, crime fighter, terrorist, secret i...</td>\n",
       "      <td>[Christian Bale, Michael Caine, Gary Oldman]</td>\n",
       "      <td>[Christopher Nolan]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>[John, Carter, is, a, war-weary,, former, mili...</td>\n",
       "      <td>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[based on novel, mars, medallion, space travel...</td>\n",
       "      <td>[Taylor Kitsch, Lynn Collins, Samantha Morton]</td>\n",
       "      <td>[Andrew Stanton]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title   \n",
       "0     19995                                    Avatar  \\\n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                            overview   \n",
       "0  [In, the, 22nd, century,, a, paraplegic, Marin...  \\\n",
       "1  [Captain, Barbossa,, long, believed, to, be, d...   \n",
       "2  [A, cryptic, message, from, Bond’s, past, send...   \n",
       "3  [Following, the, death, of, District, Attorney...   \n",
       "4  [John, Carter, is, a, war-weary,, former, mili...   \n",
       "\n",
       "                                          genres   \n",
       "0  [Action, Adventure, Fantasy, Science Fiction]  \\\n",
       "1                   [Adventure, Fantasy, Action]   \n",
       "2                     [Action, Adventure, Crime]   \n",
       "3               [Action, Crime, Drama, Thriller]   \n",
       "4           [Action, Adventure, Science Fiction]   \n",
       "\n",
       "                                            keywords   \n",
       "0  [culture clash, future, space war, space colon...  \\\n",
       "1  [ocean, drug abuse, exotic island, east india ...   \n",
       "2  [spy, based on novel, secret agent, sequel, mi...   \n",
       "3  [dc comics, crime fighter, terrorist, secret i...   \n",
       "4  [based on novel, mars, medallion, space travel...   \n",
       "\n",
       "                                               cast                 crew  \n",
       "0  [Sam Worthington, Zoe Saldana, Sigourney Weaver]      [James Cameron]  \n",
       "1     [Johnny Depp, Orlando Bloom, Keira Knightley]     [Gore Verbinski]  \n",
       "2      [Daniel Craig, Christoph Waltz, Léa Seydoux]         [Sam Mendes]  \n",
       "3      [Christian Bale, Michael Caine, Gary Oldman]  [Christopher Nolan]  \n",
       "4    [Taylor Kitsch, Lynn Collins, Samantha Morton]     [Andrew Stanton]  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['genres'] = movies['genres'].apply(lambda x:[i.replace(\" \",\"\") for i in x])\n",
    "movies['keywords'] = movies['keywords'].apply(lambda x:[i.replace(\" \",\"\") for i in x])\n",
    "movies['cast'] = movies['cast'].apply(lambda x:[i.replace(\" \",\"\") for i in x])\n",
    "movies['crew'] = movies['crew'].apply(lambda x:[i.replace(\" \",\"\") for i in x])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "      <td>[Action, Adventure, Fantasy, ScienceFiction]</td>\n",
       "      <td>[cultureclash, future, spacewar, spacecolony, ...</td>\n",
       "      <td>[SamWorthington, ZoeSaldana, SigourneyWeaver]</td>\n",
       "      <td>[JamesCameron]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id   title                                           overview   \n",
       "0     19995  Avatar  [In, the, 22nd, century,, a, paraplegic, Marin...  \\\n",
       "\n",
       "                                         genres   \n",
       "0  [Action, Adventure, Fantasy, ScienceFiction]  \\\n",
       "\n",
       "                                            keywords   \n",
       "0  [cultureclash, future, spacewar, spacecolony, ...  \\\n",
       "\n",
       "                                            cast            crew  \n",
       "0  [SamWorthington, ZoeSaldana, SigourneyWeaver]  [JamesCameron]  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['tags'] = movies['overview']+movies['keywords']+movies['cast']+movies['crew']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "      <td>[Action, Adventure, Fantasy, ScienceFiction]</td>\n",
       "      <td>[cultureclash, future, spacewar, spacecolony, ...</td>\n",
       "      <td>[SamWorthington, ZoeSaldana, SigourneyWeaver]</td>\n",
       "      <td>[JamesCameron]</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>[Captain, Barbossa,, long, believed, to, be, d...</td>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drugabuse, exoticisland, eastindiatrad...</td>\n",
       "      <td>[JohnnyDepp, OrlandoBloom, KeiraKnightley]</td>\n",
       "      <td>[GoreVerbinski]</td>\n",
       "      <td>[Captain, Barbossa,, long, believed, to, be, d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>[A, cryptic, message, from, Bond’s, past, send...</td>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, basedonnovel, secretagent, sequel, mi6, ...</td>\n",
       "      <td>[DanielCraig, ChristophWaltz, LéaSeydoux]</td>\n",
       "      <td>[SamMendes]</td>\n",
       "      <td>[A, cryptic, message, from, Bond’s, past, send...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>[Following, the, death, of, District, Attorney...</td>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dccomics, crimefighter, terrorist, secretiden...</td>\n",
       "      <td>[ChristianBale, MichaelCaine, GaryOldman]</td>\n",
       "      <td>[ChristopherNolan]</td>\n",
       "      <td>[Following, the, death, of, District, Attorney...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>[John, Carter, is, a, war-weary,, former, mili...</td>\n",
       "      <td>[Action, Adventure, ScienceFiction]</td>\n",
       "      <td>[basedonnovel, mars, medallion, spacetravel, p...</td>\n",
       "      <td>[TaylorKitsch, LynnCollins, SamanthaMorton]</td>\n",
       "      <td>[AndrewStanton]</td>\n",
       "      <td>[John, Carter, is, a, war-weary,, former, mili...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title   \n",
       "0     19995                                    Avatar  \\\n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                            overview   \n",
       "0  [In, the, 22nd, century,, a, paraplegic, Marin...  \\\n",
       "1  [Captain, Barbossa,, long, believed, to, be, d...   \n",
       "2  [A, cryptic, message, from, Bond’s, past, send...   \n",
       "3  [Following, the, death, of, District, Attorney...   \n",
       "4  [John, Carter, is, a, war-weary,, former, mili...   \n",
       "\n",
       "                                         genres   \n",
       "0  [Action, Adventure, Fantasy, ScienceFiction]  \\\n",
       "1                  [Adventure, Fantasy, Action]   \n",
       "2                    [Action, Adventure, Crime]   \n",
       "3              [Action, Crime, Drama, Thriller]   \n",
       "4           [Action, Adventure, ScienceFiction]   \n",
       "\n",
       "                                            keywords   \n",
       "0  [cultureclash, future, spacewar, spacecolony, ...  \\\n",
       "1  [ocean, drugabuse, exoticisland, eastindiatrad...   \n",
       "2  [spy, basedonnovel, secretagent, sequel, mi6, ...   \n",
       "3  [dccomics, crimefighter, terrorist, secretiden...   \n",
       "4  [basedonnovel, mars, medallion, spacetravel, p...   \n",
       "\n",
       "                                            cast                crew   \n",
       "0  [SamWorthington, ZoeSaldana, SigourneyWeaver]      [JamesCameron]  \\\n",
       "1     [JohnnyDepp, OrlandoBloom, KeiraKnightley]     [GoreVerbinski]   \n",
       "2      [DanielCraig, ChristophWaltz, LéaSeydoux]         [SamMendes]   \n",
       "3      [ChristianBale, MichaelCaine, GaryOldman]  [ChristopherNolan]   \n",
       "4    [TaylorKitsch, LynnCollins, SamanthaMorton]     [AndrewStanton]   \n",
       "\n",
       "                                                tags  \n",
       "0  [In, the, 22nd, century,, a, paraplegic, Marin...  \n",
       "1  [Captain, Barbossa,, long, believed, to, be, d...  \n",
       "2  [A, cryptic, message, from, Bond’s, past, send...  \n",
       "3  [Following, the, death, of, District, Attorney...  \n",
       "4  [John, Carter, is, a, war-weary,, former, mili...  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_df = movies[['movie_id','title','tags']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\user\\AppData\\Local\\Temp\\ipykernel_11184\\3089450492.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  new_df['tags'] = new_df['tags'].apply(lambda x:\" \".join(x))\n"
     ]
    }
   ],
   "source": [
    "new_df['tags'] = new_df['tags'].apply(lambda x:\" \".join(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title   \n",
       "0     19995                                    Avatar  \\\n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                                tags  \n",
       "0  In the 22nd century, a paraplegic Marine is di...  \n",
       "1  Captain Barbossa, long believed to be dead, ha...  \n",
       "2  A cryptic message from Bond’s past sends him o...  \n",
       "3  Following the death of District Attorney Harve...  \n",
       "4  John Carter is a war-weary, former military ca...  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\user\\AppData\\Local\\Temp\\ipykernel_11184\\3214958533.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  new_df['tags'] = new_df['tags'].apply(lambda x:x.lower())\n"
     ]
    }
   ],
   "source": [
    "new_df['tags'] = new_df['tags'].apply(lambda x:x.lower())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(max_features=5000,stop_words='english')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectors = cv.fit_transform(new_df['tags']).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       ...,\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0]], dtype=int64)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\utils\\deprecation.py:87: FutureWarning: Function get_feature_names is deprecated; get_feature_names is deprecated in 1.0 and will be removed in 1.2. Please use get_feature_names_out instead.\n",
      "  warnings.warn(msg, category=FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "5000"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(cv.get_feature_names())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "ps = PorterStemmer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stem(text):\n",
    "    y = []\n",
    "\n",
    "    for i in text.split():\n",
    "        y.append(ps.stem(i))\n",
    "\n",
    "    return \" \".join(y)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'danc'"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps.stem('danc')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\user\\AppData\\Local\\Temp\\ipykernel_11184\\3213734980.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  new_df['tags'] = new_df['tags'].apply(stem)\n"
     ]
    }
   ],
   "source": [
    "new_df['tags'] = new_df['tags'].apply(stem)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\user\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\utils\\deprecation.py:87: FutureWarning: Function get_feature_names is deprecated; get_feature_names is deprecated in 1.0 and will be removed in 1.2. Please use get_feature_names_out instead.\n",
      "  warnings.warn(msg, category=FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['000',\n",
       " '007',\n",
       " '10',\n",
       " '100',\n",
       " '11',\n",
       " '12',\n",
       " '13',\n",
       " '14',\n",
       " '15',\n",
       " '16',\n",
       " '17',\n",
       " '18',\n",
       " '18th',\n",
       " '19',\n",
       " '1930s',\n",
       " '1940s',\n",
       " '1944',\n",
       " '1950',\n",
       " '1950s',\n",
       " '1960s',\n",
       " '1970s',\n",
       " '1971',\n",
       " '1974',\n",
       " '1976',\n",
       " '1980',\n",
       " '1980s',\n",
       " '1985',\n",
       " '1990s',\n",
       " '19th',\n",
       " '19thcentury',\n",
       " '20',\n",
       " '200',\n",
       " '2009',\n",
       " '20th',\n",
       " '21st',\n",
       " '23',\n",
       " '24',\n",
       " '25',\n",
       " '30',\n",
       " '300',\n",
       " '3d',\n",
       " '40',\n",
       " '50',\n",
       " '500',\n",
       " '60',\n",
       " '60s',\n",
       " '70',\n",
       " '70s',\n",
       " 'aaron',\n",
       " 'aaroneckhart',\n",
       " 'abandoned',\n",
       " 'abducted',\n",
       " 'abigailbreslin',\n",
       " 'abilities',\n",
       " 'ability',\n",
       " 'able',\n",
       " 'aboard',\n",
       " 'abuse',\n",
       " 'abusive',\n",
       " 'academic',\n",
       " 'academy',\n",
       " 'accept',\n",
       " 'accepted',\n",
       " 'accepts',\n",
       " 'access',\n",
       " 'accident',\n",
       " 'accidental',\n",
       " 'accidentally',\n",
       " 'accompanied',\n",
       " 'accomplish',\n",
       " 'account',\n",
       " 'accountant',\n",
       " 'accused',\n",
       " 'ace',\n",
       " 'achieve',\n",
       " 'act',\n",
       " 'acting',\n",
       " 'action',\n",
       " 'actionhero',\n",
       " 'actions',\n",
       " 'activist',\n",
       " 'activities',\n",
       " 'activity',\n",
       " 'actor',\n",
       " 'actors',\n",
       " 'actress',\n",
       " 'acts',\n",
       " 'actual',\n",
       " 'actually',\n",
       " 'adam',\n",
       " 'adams',\n",
       " 'adamsandler',\n",
       " 'adamshankman',\n",
       " 'adaptation',\n",
       " 'adapted',\n",
       " 'addict',\n",
       " 'addicted',\n",
       " 'addiction',\n",
       " 'adolescence',\n",
       " 'adopt',\n",
       " 'adopted',\n",
       " 'adoption',\n",
       " 'adopts',\n",
       " 'adrienbrody',\n",
       " 'adult',\n",
       " 'adultery',\n",
       " 'adulthood',\n",
       " 'adults',\n",
       " 'advantage',\n",
       " 'adventure',\n",
       " 'adventures',\n",
       " 'advertising',\n",
       " 'advice',\n",
       " 'affair',\n",
       " 'affairs',\n",
       " 'affection',\n",
       " 'affections',\n",
       " 'afghanistan',\n",
       " 'africa',\n",
       " 'african',\n",
       " 'africanamerican',\n",
       " 'aftercreditsstinger',\n",
       " 'afterlife',\n",
       " 'aftermath',\n",
       " 'age',\n",
       " 'aged',\n",
       " 'agedifference',\n",
       " 'agency',\n",
       " 'agenda',\n",
       " 'agent',\n",
       " 'agents',\n",
       " 'aggressive',\n",
       " 'aging',\n",
       " 'ago',\n",
       " 'agree',\n",
       " 'agrees',\n",
       " 'ahead',\n",
       " 'aid',\n",
       " 'aided',\n",
       " 'aids',\n",
       " 'ailing',\n",
       " 'air',\n",
       " 'airplane',\n",
       " 'airplanecrash',\n",
       " 'airport',\n",
       " 'aka',\n",
       " 'al',\n",
       " 'alabama',\n",
       " 'alan',\n",
       " 'alaska',\n",
       " 'albert',\n",
       " 'alcohol',\n",
       " 'alcoholic',\n",
       " 'alcoholism',\n",
       " 'alecbaldwin',\n",
       " 'alex',\n",
       " 'alexkendrick',\n",
       " 'alfredhitchcock',\n",
       " 'ali',\n",
       " 'alice',\n",
       " 'alien',\n",
       " 'alieninvasion',\n",
       " 'alienlife',\n",
       " 'aliens',\n",
       " 'alike',\n",
       " 'alive',\n",
       " 'allen',\n",
       " 'alliance',\n",
       " 'allied',\n",
       " 'allies',\n",
       " 'allow',\n",
       " 'allowing',\n",
       " 'allows',\n",
       " 'ally',\n",
       " 'alongside',\n",
       " 'alpacino',\n",
       " 'alter',\n",
       " 'alternate',\n",
       " 'alternative',\n",
       " 'alzheimer',\n",
       " 'amanda',\n",
       " 'amandapeet',\n",
       " 'amandaseyfried',\n",
       " 'amateur',\n",
       " 'amazing',\n",
       " 'ambassador',\n",
       " 'ambition',\n",
       " 'ambitious',\n",
       " 'ambulance',\n",
       " 'ambush',\n",
       " 'america',\n",
       " 'american',\n",
       " 'americanabroad',\n",
       " 'americanfootball',\n",
       " 'americans',\n",
       " 'amid',\n",
       " 'amidst',\n",
       " 'amnesia',\n",
       " 'amp',\n",
       " 'amsterdam',\n",
       " 'amusement',\n",
       " 'amusementpark',\n",
       " 'amy',\n",
       " 'amyadams',\n",
       " 'amysmart',\n",
       " 'analyst',\n",
       " 'anarchiccomedy',\n",
       " 'ancient',\n",
       " 'ancientrome',\n",
       " 'ancientworld',\n",
       " 'anderson',\n",
       " 'andiemacdowell',\n",
       " 'andrew',\n",
       " 'android',\n",
       " 'andy',\n",
       " 'andygarcía',\n",
       " 'angel',\n",
       " 'angelabassett',\n",
       " 'angeles',\n",
       " 'angelinajolie',\n",
       " 'angels',\n",
       " 'anger',\n",
       " 'anglee',\n",
       " 'angry',\n",
       " 'animal',\n",
       " 'animalattack',\n",
       " 'animalhorror',\n",
       " 'animals',\n",
       " 'animated',\n",
       " 'animation',\n",
       " 'anna',\n",
       " 'annafaris',\n",
       " 'anne',\n",
       " 'annehathaway',\n",
       " 'annemoss',\n",
       " 'annettebening',\n",
       " 'annie',\n",
       " 'anniversary',\n",
       " 'annual',\n",
       " 'answer',\n",
       " 'answers',\n",
       " 'ant',\n",
       " 'anthology',\n",
       " 'anthony',\n",
       " 'anthonyanderson',\n",
       " 'anthonyhopkins',\n",
       " 'anthropomorphism',\n",
       " 'anti',\n",
       " 'antics',\n",
       " 'antihero',\n",
       " 'antoinefuqua',\n",
       " 'antoniobanderas',\n",
       " 'antonyelchin',\n",
       " 'apart',\n",
       " 'apartheid',\n",
       " 'apartment',\n",
       " 'ape',\n",
       " 'apes',\n",
       " 'apocalypse',\n",
       " 'apocalyptic',\n",
       " 'apparent',\n",
       " 'apparently',\n",
       " 'appear',\n",
       " 'appears',\n",
       " 'apple',\n",
       " 'appointed',\n",
       " 'apprentice',\n",
       " 'approach',\n",
       " 'approaches',\n",
       " 'approaching',\n",
       " 'april',\n",
       " 'aquarium',\n",
       " 'arab',\n",
       " 'arch',\n",
       " 'archaeologist',\n",
       " 'archeology',\n",
       " 'architect',\n",
       " 'arctic',\n",
       " 'area',\n",
       " 'aren',\n",
       " 'arena',\n",
       " 'argument',\n",
       " 'arise',\n",
       " 'aristocrat',\n",
       " 'armed',\n",
       " 'arms',\n",
       " 'army',\n",
       " 'arnold',\n",
       " 'arnoldschwarzenegger',\n",
       " 'arrangedmarriage',\n",
       " 'arrangement',\n",
       " 'arrest',\n",
       " 'arrested',\n",
       " 'arrival',\n",
       " 'arrive',\n",
       " 'arrives',\n",
       " 'arriving',\n",
       " 'arrogant',\n",
       " 'art',\n",
       " 'arthur',\n",
       " 'artificialintelligence',\n",
       " 'artist',\n",
       " 'artistic',\n",
       " 'artists',\n",
       " 'arts',\n",
       " 'ashley',\n",
       " 'ashleyjudd',\n",
       " 'ashtonkutcher',\n",
       " 'asia',\n",
       " 'aside',\n",
       " 'ask',\n",
       " 'asked',\n",
       " 'asking',\n",
       " 'asks',\n",
       " 'aspirations',\n",
       " 'aspiring',\n",
       " 'assassin',\n",
       " 'assassinate',\n",
       " 'assassination',\n",
       " 'assassins',\n",
       " 'assault',\n",
       " 'assigned',\n",
       " 'assignment',\n",
       " 'assistant',\n",
       " 'assumes',\n",
       " 'asteroid',\n",
       " 'astronaut',\n",
       " 'astronauts',\n",
       " 'asylum',\n",
       " 'athlete',\n",
       " 'atomicbomb',\n",
       " 'attack',\n",
       " 'attacked',\n",
       " 'attacks',\n",
       " 'attempt',\n",
       " 'attempting',\n",
       " 'attempts',\n",
       " 'attempttoescape',\n",
       " 'attending',\n",
       " 'attends',\n",
       " 'attention',\n",
       " 'attic',\n",
       " 'attitude',\n",
       " 'attorney',\n",
       " 'attracted',\n",
       " 'attraction',\n",
       " 'attractive',\n",
       " 'audience',\n",
       " 'audiences',\n",
       " 'audition',\n",
       " 'august',\n",
       " 'aunt',\n",
       " 'austin',\n",
       " 'australia',\n",
       " 'australian',\n",
       " 'author',\n",
       " 'authorities',\n",
       " 'authority',\n",
       " 'autism',\n",
       " 'auto',\n",
       " 'avenge',\n",
       " 'average',\n",
       " 'avoid',\n",
       " 'awaits',\n",
       " 'awakens',\n",
       " 'award',\n",
       " 'away',\n",
       " 'awry',\n",
       " 'ax',\n",
       " 'babe',\n",
       " 'baby',\n",
       " 'bachelor',\n",
       " 'backdrop',\n",
       " 'background',\n",
       " 'backgrounds',\n",
       " 'bad',\n",
       " 'bag',\n",
       " 'bahamas',\n",
       " 'bail',\n",
       " 'balance',\n",
       " 'ball',\n",
       " 'ballet',\n",
       " 'baltimore',\n",
       " 'band',\n",
       " 'bandits',\n",
       " 'bangkok',\n",
       " 'banished',\n",
       " 'bank',\n",
       " 'banker',\n",
       " 'bankrobber',\n",
       " 'bankrobbery',\n",
       " 'bar',\n",
       " 'barely',\n",
       " 'bargained',\n",
       " 'barn',\n",
       " 'barney',\n",
       " 'barry',\n",
       " 'barrylevinson',\n",
       " 'bars',\n",
       " 'base',\n",
       " 'baseball',\n",
       " 'based',\n",
       " 'basedoncomicbook',\n",
       " 'basedongraphicnovel',\n",
       " 'basedonnovel',\n",
       " 'basedonplay',\n",
       " 'basedonstagemusical',\n",
       " 'basedontrueevents',\n",
       " 'basedontruestory',\n",
       " 'basedontvseries',\n",
       " 'basedonvideogame',\n",
       " 'basedonyoungadultnovel',\n",
       " 'basement',\n",
       " 'basketball',\n",
       " 'batman',\n",
       " 'battle',\n",
       " 'battlefield',\n",
       " 'battles',\n",
       " 'battling',\n",
       " 'bay',\n",
       " 'beach',\n",
       " 'bear',\n",
       " 'bears',\n",
       " 'beast',\n",
       " 'beasts',\n",
       " 'beat',\n",
       " 'beating',\n",
       " 'beautiful',\n",
       " 'beautifulwoman',\n",
       " 'beauty',\n",
       " 'becky',\n",
       " 'becominganadult',\n",
       " 'bed',\n",
       " 'bedroom',\n",
       " 'bee',\n",
       " 'beer',\n",
       " 'befriends',\n",
       " 'began',\n",
       " 'begin',\n",
       " 'beginning',\n",
       " 'begins',\n",
       " 'behavior',\n",
       " 'beings',\n",
       " 'belief',\n",
       " 'beliefs',\n",
       " 'believe',\n",
       " 'believed',\n",
       " 'believes',\n",
       " 'believing',\n",
       " 'bell',\n",
       " 'belong',\n",
       " 'belongs',\n",
       " 'beloved',\n",
       " 'ben',\n",
       " 'benaffleck',\n",
       " 'beneath',\n",
       " 'benfoster',\n",
       " 'beniciodeltoro',\n",
       " 'benjamin',\n",
       " 'benjaminbratt',\n",
       " 'benkingsley',\n",
       " 'bennett',\n",
       " 'benstiller',\n",
       " 'bent',\n",
       " 'berlin',\n",
       " 'best',\n",
       " 'bestfriend',\n",
       " 'bet',\n",
       " 'beth',\n",
       " 'betrayal',\n",
       " 'betrayed',\n",
       " 'bettemidler',\n",
       " 'better',\n",
       " 'betty',\n",
       " 'beverly',\n",
       " 'bible',\n",
       " 'bid',\n",
       " 'big',\n",
       " 'bigger',\n",
       " 'biggest',\n",
       " 'biker',\n",
       " 'bikini',\n",
       " 'billhader',\n",
       " 'billionaire',\n",
       " 'billmurray',\n",
       " 'billnighy',\n",
       " 'billpaxton',\n",
       " 'billpullman',\n",
       " 'billy',\n",
       " 'billybobthornton',\n",
       " 'billycrudup',\n",
       " 'billycrystal',\n",
       " 'biography',\n",
       " 'bird',\n",
       " 'birth',\n",
       " 'birthday',\n",
       " 'bisexual',\n",
       " 'bishop',\n",
       " 'bit',\n",
       " 'bite',\n",
       " 'bitter',\n",
       " 'bizarre',\n",
       " 'black',\n",
       " 'blackmagic',\n",
       " 'blackmail',\n",
       " 'blackpeople',\n",
       " 'blacksmith',\n",
       " 'blade',\n",
       " 'blame',\n",
       " 'blind',\n",
       " 'bliss',\n",
       " 'block',\n",
       " 'blonde',\n",
       " 'blood',\n",
       " 'bloodsplatter',\n",
       " 'bloodthirsty',\n",
       " 'bloody',\n",
       " 'blow',\n",
       " 'blue',\n",
       " 'board',\n",
       " 'boarding',\n",
       " 'boardingschool',\n",
       " 'boat',\n",
       " 'bob',\n",
       " 'bobby',\n",
       " 'bobbyfarrelly',\n",
       " 'bobhoskins',\n",
       " 'bodies',\n",
       " 'body',\n",
       " 'bodyguard',\n",
       " 'bold',\n",
       " 'bollywood',\n",
       " 'bomb',\n",
       " 'bombing',\n",
       " 'bond',\n",
       " 'bonds',\n",
       " 'bone',\n",
       " 'book',\n",
       " 'books',\n",
       " 'border',\n",
       " 'bored',\n",
       " 'boredom',\n",
       " 'boring',\n",
       " 'born',\n",
       " 'boss',\n",
       " 'boston',\n",
       " 'botched',\n",
       " 'bound',\n",
       " 'boundaries',\n",
       " 'bounty',\n",
       " 'bountyhunter',\n",
       " 'bourne',\n",
       " 'box',\n",
       " 'boxer',\n",
       " 'boxing',\n",
       " 'boy',\n",
       " 'boyfriend',\n",
       " 'boys',\n",
       " 'bradleycooper',\n",
       " 'bradpitt',\n",
       " 'brain',\n",
       " 'brand',\n",
       " 'brave',\n",
       " 'bravery',\n",
       " 'brazil',\n",
       " 'brazilian',\n",
       " 'break',\n",
       " 'breakdown',\n",
       " 'breaking',\n",
       " 'breaks',\n",
       " 'brendanfraser',\n",
       " 'brendangleeson',\n",
       " 'brent',\n",
       " 'brettratner',\n",
       " 'brian',\n",
       " 'briandepalma',\n",
       " 'bride',\n",
       " 'bridge',\n",
       " 'brief',\n",
       " 'brien',\n",
       " 'bright',\n",
       " 'brilliant',\n",
       " 'bring',\n",
       " 'bringing',\n",
       " 'brings',\n",
       " 'brink',\n",
       " 'britain',\n",
       " 'british',\n",
       " 'britishsecretservice',\n",
       " 'brittanymurphy',\n",
       " 'broadway',\n",
       " 'broke',\n",
       " 'broken',\n",
       " 'broker',\n",
       " 'brooklyn',\n",
       " 'brooks',\n",
       " 'brothel',\n",
       " 'brother',\n",
       " 'brotherbrotherrelationship',\n",
       " 'brothers',\n",
       " 'brothersisterrelationship',\n",
       " 'brought',\n",
       " 'brown',\n",
       " 'bruce',\n",
       " 'brucewillis',\n",
       " 'brutal',\n",
       " 'brutality',\n",
       " 'brutally',\n",
       " 'bryansinger',\n",
       " 'buck',\n",
       " 'buddies',\n",
       " 'buddy',\n",
       " 'buddycomedy',\n",
       " 'budget',\n",
       " 'build',\n",
       " 'building',\n",
       " 'built',\n",
       " 'bully',\n",
       " 'bullying',\n",
       " 'bumbling',\n",
       " 'bunny',\n",
       " 'burglar',\n",
       " 'buried',\n",
       " 'burned',\n",
       " 'bus',\n",
       " 'bush',\n",
       " 'business',\n",
       " 'businessman',\n",
       " 'bust',\n",
       " 'busy',\n",
       " 'butler',\n",
       " 'buy',\n",
       " 'cabin',\n",
       " 'caesar',\n",
       " 'cage',\n",
       " 'cairo',\n",
       " 'cal',\n",
       " 'california',\n",
       " 'called',\n",
       " 'calls',\n",
       " 'calvin',\n",
       " 'camcorder',\n",
       " 'came',\n",
       " 'camera',\n",
       " 'cameraman',\n",
       " 'cameras',\n",
       " 'camerondiaz',\n",
       " 'camp',\n",
       " 'campaign',\n",
       " 'campbell',\n",
       " 'camping',\n",
       " 'campus',\n",
       " 'canada',\n",
       " 'canadian',\n",
       " 'cancer',\n",
       " 'candidate',\n",
       " 'candy',\n",
       " 'cannibal',\n",
       " 'capable',\n",
       " 'capital',\n",
       " 'capitalism',\n",
       " 'capt',\n",
       " 'captain',\n",
       " 'captive',\n",
       " 'capture',\n",
       " 'captured',\n",
       " 'captures',\n",
       " 'car',\n",
       " 'caraccident',\n",
       " 'carchase',\n",
       " 'carcrash',\n",
       " 'card',\n",
       " 'care',\n",
       " 'career',\n",
       " 'carefree',\n",
       " 'caretaker',\n",
       " 'caribbean',\n",
       " 'carjourney',\n",
       " 'carl',\n",
       " 'carlagugino',\n",
       " 'carmen',\n",
       " 'carol',\n",
       " 'carolina',\n",
       " 'carrace',\n",
       " 'carrie',\n",
       " 'carry',\n",
       " 'carrying',\n",
       " 'cars',\n",
       " 'cartel',\n",
       " 'carter',\n",
       " 'cartoon',\n",
       " 'caryelwes',\n",
       " 'case',\n",
       " 'caseyaffleck',\n",
       " 'cash',\n",
       " 'casino',\n",
       " 'cast',\n",
       " 'castle',\n",
       " 'cat',\n",
       " 'cataclysm',\n",
       " 'catastrophe',\n",
       " 'catch',\n",
       " 'catches',\n",
       " 'cateblanchett',\n",
       " 'catherinedeneuve',\n",
       " 'catherinekeener',\n",
       " 'catherinezeta',\n",
       " 'catholic',\n",
       " 'catholicism',\n",
       " 'cattle',\n",
       " 'caught',\n",
       " 'cause',\n",
       " 'caused',\n",
       " 'causes',\n",
       " 'causing',\n",
       " 'cavalry',\n",
       " 'cave',\n",
       " 'cavemen',\n",
       " 'celebrate',\n",
       " 'celebrated',\n",
       " 'celebration',\n",
       " 'celebrity',\n",
       " 'cell',\n",
       " 'cellphone',\n",
       " 'cemetery',\n",
       " 'center',\n",
       " 'centered',\n",
       " 'centers',\n",
       " 'central',\n",
       " 'centuries',\n",
       " 'century',\n",
       " 'ceo',\n",
       " 'ceremony',\n",
       " 'certain',\n",
       " 'chad',\n",
       " 'chain',\n",
       " 'chainsaw',\n",
       " 'challenge',\n",
       " 'challenged',\n",
       " 'challenges',\n",
       " 'champion',\n",
       " 'championship',\n",
       " 'chance',\n",
       " 'change',\n",
       " 'changed',\n",
       " 'changes',\n",
       " 'changing',\n",
       " 'channingtatum',\n",
       " 'chaos',\n",
       " 'chaotic',\n",
       " 'chapter',\n",
       " 'character',\n",
       " 'characters',\n",
       " 'charge',\n",
       " 'charged',\n",
       " 'charismatic',\n",
       " 'charles',\n",
       " 'charlie',\n",
       " 'charliesheen',\n",
       " 'charlizetheron',\n",
       " 'charlotte',\n",
       " 'charm',\n",
       " 'charming',\n",
       " 'chase',\n",
       " 'chased',\n",
       " 'chauffeur',\n",
       " 'cheating',\n",
       " 'cheerleader',\n",
       " 'chef',\n",
       " 'chemical',\n",
       " 'cher',\n",
       " 'chicago',\n",
       " 'chicken',\n",
       " 'chief',\n",
       " 'child',\n",
       " 'childabuse',\n",
       " 'childhero',\n",
       " 'childhood',\n",
       " 'childprodigy',\n",
       " 'children',\n",
       " 'chilling',\n",
       " 'china',\n",
       " 'chinese',\n",
       " 'chip',\n",
       " 'chiwetelejiofor',\n",
       " 'chloe',\n",
       " 'chloëgracemoretz',\n",
       " 'chloësevigny',\n",
       " 'chocolate',\n",
       " 'choice',\n",
       " 'choices',\n",
       " 'choose',\n",
       " 'chosen',\n",
       " 'chris',\n",
       " 'chriscolumbus',\n",
       " 'chriscooper',\n",
       " 'chrisevans',\n",
       " 'chrishemsworth',\n",
       " 'chrisklein',\n",
       " 'chrispine',\n",
       " 'chrisrock',\n",
       " 'christ',\n",
       " 'christian',\n",
       " 'christianbale',\n",
       " 'christianity',\n",
       " 'christianslater',\n",
       " 'christinaapplegate',\n",
       " 'christinaricci',\n",
       " 'christine',\n",
       " 'christmas',\n",
       " 'christmasparty',\n",
       " 'christmastree',\n",
       " 'christopher',\n",
       " 'christopherlloyd',\n",
       " 'christophernolan',\n",
       " 'christopherplummer',\n",
       " 'christopherwalken',\n",
       " 'christophwaltz',\n",
       " 'chrisweitz',\n",
       " 'chronicle',\n",
       " 'chronicles',\n",
       " 'chuck',\n",
       " 'church',\n",
       " 'cia',\n",
       " 'ciaránhinds',\n",
       " 'cigarettesmoking',\n",
       " 'cillianmurphy',\n",
       " 'cindy',\n",
       " 'cinema',\n",
       " 'circle',\n",
       " 'circuit',\n",
       " 'circumstances',\n",
       " 'circus',\n",
       " 'cities',\n",
       " 'citizens',\n",
       " 'city',\n",
       " 'civil',\n",
       " 'civilization',\n",
       " 'civilwar',\n",
       " 'claim',\n",
       " 'claims',\n",
       " 'claire',\n",
       " 'clairedanes',\n",
       " 'clan',\n",
       " 'clark',\n",
       " 'clash',\n",
       " 'class',\n",
       " 'classes',\n",
       " 'classic',\n",
       " 'classmate',\n",
       " 'classmates',\n",
       " 'classroom',\n",
       " 'claudevandamme',\n",
       " 'clay',\n",
       " 'clean',\n",
       " 'clear',\n",
       " 'clerk',\n",
       " 'client',\n",
       " 'clients',\n",
       " 'climate',\n",
       " 'climbing',\n",
       " 'clinteastwood',\n",
       " 'clique',\n",
       " 'cliveowen',\n",
       " 'clock',\n",
       " 'clone',\n",
       " 'cloning',\n",
       " 'close',\n",
       " 'closed',\n",
       " 'closer',\n",
       " 'club',\n",
       " 'clubs',\n",
       " 'clue',\n",
       " 'clueless',\n",
       " 'clues',\n",
       " 'clutches',\n",
       " 'coach',\n",
       " 'coast',\n",
       " 'cocaine',\n",
       " 'cocky',\n",
       " 'code',\n",
       " 'cody',\n",
       " 'coffin',\n",
       " 'cohen',\n",
       " 'col',\n",
       " 'cold',\n",
       " 'coldwar',\n",
       " 'cole',\n",
       " 'colin',\n",
       " 'colinfarrell',\n",
       " 'colinfirth',\n",
       " 'collapse',\n",
       " 'colleague',\n",
       " 'colleagues',\n",
       " 'collect',\n",
       " 'collection',\n",
       " 'collector',\n",
       " 'college',\n",
       " 'collide',\n",
       " 'collision',\n",
       " 'colonel',\n",
       " 'colony',\n",
       " 'color',\n",
       " 'colorado',\n",
       " 'colorful',\n",
       " 'coma',\n",
       " 'combat',\n",
       " 'combined',\n",
       " 'come',\n",
       " 'comeback',\n",
       " 'comedian',\n",
       " 'comedic',\n",
       " 'comedy',\n",
       " 'comes',\n",
       " 'comet',\n",
       " 'comfort',\n",
       " 'comic',\n",
       " 'comics',\n",
       " 'coming',\n",
       " 'comingofage',\n",
       " 'comingout',\n",
       " 'command',\n",
       " 'commander',\n",
       " 'commercial',\n",
       " 'commit',\n",
       " 'commitment',\n",
       " 'committed',\n",
       " 'common',\n",
       " 'communication',\n",
       " 'community',\n",
       " 'companion',\n",
       " 'company',\n",
       " 'compete',\n",
       " 'competing',\n",
       " 'competition',\n",
       " 'complete',\n",
       " 'completely',\n",
       " 'complex',\n",
       " 'complicated',\n",
       " 'complications',\n",
       " 'composer',\n",
       " 'computer',\n",
       " 'computervirus',\n",
       " 'conan',\n",
       " 'concert',\n",
       " 'conclusion',\n",
       " 'condition',\n",
       " 'confession',\n",
       " 'confidence',\n",
       " 'confident',\n",
       " 'conflict',\n",
       " 'confront',\n",
       " 'confronted',\n",
       " 'confused',\n",
       " 'congress',\n",
       " 'conman',\n",
       " 'connected',\n",
       " 'connection',\n",
       " 'connell',\n",
       " 'connor',\n",
       " 'conquer',\n",
       " 'conscience',\n",
       " 'consequences',\n",
       " 'conservative',\n",
       " 'considered',\n",
       " 'conspiracy',\n",
       " 'constant',\n",
       " 'constantly',\n",
       " 'construction',\n",
       " 'contact',\n",
       " 'contain',\n",
       " 'contemporary',\n",
       " 'contend',\n",
       " 'contest',\n",
       " 'continue',\n",
       " 'continues',\n",
       " 'continuing',\n",
       " 'contract',\n",
       " 'control',\n",
       " 'controlled',\n",
       " 'controlling',\n",
       " 'controversial',\n",
       " 'convention',\n",
       " 'converge',\n",
       " 'convict',\n",
       " 'convicted',\n",
       " 'convince',\n",
       " 'convinced',\n",
       " 'convinces',\n",
       " 'cook',\n",
       " 'cooking',\n",
       " 'cool',\n",
       " 'cooper',\n",
       " 'cop',\n",
       " 'cope',\n",
       " 'cops',\n",
       " 'core',\n",
       " 'corner',\n",
       " 'corners',\n",
       " 'corporate',\n",
       " ...]"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv.get_feature_names()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1.        , 0.        , 0.        , ..., 0.        , 0.02752409,\n",
       "        0.        ],\n",
       "       [0.        , 1.        , 0.        , ..., 0.02865341, 0.        ,\n",
       "        0.        ],\n",
       "       [0.        , 0.        , 1.        , ..., 0.02865341, 0.        ,\n",
       "        0.        ],\n",
       "       ...,\n",
       "       [0.        , 0.02865341, 0.02865341, ..., 1.        , 0.048795  ,\n",
       "        0.05006262],\n",
       "       [0.02752409, 0.        , 0.        , ..., 0.048795  , 1.        ,\n",
       "        0.05129892],\n",
       "       [0.        , 0.        , 0.        , ..., 0.05006262, 0.05129892,\n",
       "        1.        ]])"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cosine_similarity(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "similarity = cosine_similarity(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "def recommend(movie):\n",
    "    movie_index = new_df[new_df['title']== movie].index[0]\n",
    "    distances = similarity[movie_index]\n",
    "    movies_list = sorted(list(enumerate(distances)),reverse=True,key=lambda x:x[1])[1:6]\n",
    "\n",
    "    for i in movies_list:\n",
    "        print(new_df.iloc[i[0]].title)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Dark Knight\n",
      "The Dark Knight Rises\n",
      "Batman\n",
      "Batman v Superman: Dawn of Justice\n",
      "Batman\n"
     ]
    }
   ],
   "source": [
    "recommend('Batman Begins')"
   ]
  },
  {
   "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": "3.10.4"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "fb4569285eef3a3450cb62085a5b1e0da4bce0af555edc33dcf29baf3acc1368"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}