{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Movie Recommendor Sysytem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import ast\n",
    "import nltk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies=pd.read_csv(\"C://Users//ARYA SHARMA//Downloads//archive//tmdb_5000_movies.csv\")\n",
    "credits=pd.read_csv(\"C://Users//ARYA SHARMA//Downloads//archive//tmdb_5000_credits.csv\")"
   ]
  },
  {
   "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>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",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>300000000</td>\n",
       "      <td>[{\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"...</td>\n",
       "      <td>http://disney.go.com/disneypictures/pirates/</td>\n",
       "      <td>285</td>\n",
       "      <td>[{\"id\": 270, \"name\": \"ocean\"}, {\"id\": 726, \"na...</td>\n",
       "      <td>en</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>139.082615</td>\n",
       "      <td>[{\"name\": \"Walt Disney Pictures\", \"id\": 2}, {\"...</td>\n",
       "      <td>[{\"iso_3166_1\": \"US\", \"name\": \"United States o...</td>\n",
       "      <td>2007-05-19</td>\n",
       "      <td>961000000</td>\n",
       "      <td>169.0</td>\n",
       "      <td>[{\"iso_639_1\": \"en\", \"name\": \"English\"}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>At the end of the world, the adventure begins.</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>6.9</td>\n",
       "      <td>4500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>245000000</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>http://www.sonypictures.com/movies/spectre/</td>\n",
       "      <td>206647</td>\n",
       "      <td>[{\"id\": 470, \"name\": \"spy\"}, {\"id\": 818, \"name...</td>\n",
       "      <td>en</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>107.376788</td>\n",
       "      <td>[{\"name\": \"Columbia Pictures\", \"id\": 5}, {\"nam...</td>\n",
       "      <td>[{\"iso_3166_1\": \"GB\", \"name\": \"United Kingdom\"...</td>\n",
       "      <td>2015-10-26</td>\n",
       "      <td>880674609</td>\n",
       "      <td>148.0</td>\n",
       "      <td>[{\"iso_639_1\": \"fr\", \"name\": \"Fran\\u00e7ais\"},...</td>\n",
       "      <td>Released</td>\n",
       "      <td>A Plan No One Escapes</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>6.3</td>\n",
       "      <td>4466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>250000000</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 80, \"nam...</td>\n",
       "      <td>http://www.thedarkknightrises.com/</td>\n",
       "      <td>49026</td>\n",
       "      <td>[{\"id\": 849, \"name\": \"dc comics\"}, {\"id\": 853,...</td>\n",
       "      <td>en</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>112.312950</td>\n",
       "      <td>[{\"name\": \"Legendary Pictures\", \"id\": 923}, {\"...</td>\n",
       "      <td>[{\"iso_3166_1\": \"US\", \"name\": \"United States o...</td>\n",
       "      <td>2012-07-16</td>\n",
       "      <td>1084939099</td>\n",
       "      <td>165.0</td>\n",
       "      <td>[{\"iso_639_1\": \"en\", \"name\": \"English\"}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>The Legend Ends</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>7.6</td>\n",
       "      <td>9106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>260000000</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>http://movies.disney.com/john-carter</td>\n",
       "      <td>49529</td>\n",
       "      <td>[{\"id\": 818, \"name\": \"based on novel\"}, {\"id\":...</td>\n",
       "      <td>en</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>43.926995</td>\n",
       "      <td>[{\"name\": \"Walt Disney Pictures\", \"id\": 2}]</td>\n",
       "      <td>[{\"iso_3166_1\": \"US\", \"name\": \"United States o...</td>\n",
       "      <td>2012-03-07</td>\n",
       "      <td>284139100</td>\n",
       "      <td>132.0</td>\n",
       "      <td>[{\"iso_639_1\": \"en\", \"name\": \"English\"}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Lost in our world, found in another.</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>6.1</td>\n",
       "      <td>2124</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      budget                                             genres  \\\n",
       "0  237000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "1  300000000  [{\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"...   \n",
       "2  245000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "3  250000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 80, \"nam...   \n",
       "4  260000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "\n",
       "                                       homepage      id  \\\n",
       "0                   http://www.avatarmovie.com/   19995   \n",
       "1  http://disney.go.com/disneypictures/pirates/     285   \n",
       "2   http://www.sonypictures.com/movies/spectre/  206647   \n",
       "3            http://www.thedarkknightrises.com/   49026   \n",
       "4          http://movies.disney.com/john-carter   49529   \n",
       "\n",
       "                                            keywords original_language  \\\n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...                en   \n",
       "1  [{\"id\": 270, \"name\": \"ocean\"}, {\"id\": 726, \"na...                en   \n",
       "2  [{\"id\": 470, \"name\": \"spy\"}, {\"id\": 818, \"name...                en   \n",
       "3  [{\"id\": 849, \"name\": \"dc comics\"}, {\"id\": 853,...                en   \n",
       "4  [{\"id\": 818, \"name\": \"based on novel\"}, {\"id\":...                en   \n",
       "\n",
       "                             original_title  \\\n",
       "0                                    Avatar   \n",
       "1  Pirates of the Caribbean: At World's End   \n",
       "2                                   Spectre   \n",
       "3                     The Dark Knight Rises   \n",
       "4                               John Carter   \n",
       "\n",
       "                                            overview  popularity  \\\n",
       "0  In the 22nd century, a paraplegic Marine is di...  150.437577   \n",
       "1  Captain Barbossa, long believed to be dead, ha...  139.082615   \n",
       "2  A cryptic message from Bond’s past sends him o...  107.376788   \n",
       "3  Following the death of District Attorney Harve...  112.312950   \n",
       "4  John Carter is a war-weary, former military ca...   43.926995   \n",
       "\n",
       "                                production_companies  \\\n",
       "0  [{\"name\": \"Ingenious Film Partners\", \"id\": 289...   \n",
       "1  [{\"name\": \"Walt Disney Pictures\", \"id\": 2}, {\"...   \n",
       "2  [{\"name\": \"Columbia Pictures\", \"id\": 5}, {\"nam...   \n",
       "3  [{\"name\": \"Legendary Pictures\", \"id\": 923}, {\"...   \n",
       "4        [{\"name\": \"Walt Disney Pictures\", \"id\": 2}]   \n",
       "\n",
       "                                production_countries release_date     revenue  \\\n",
       "0  [{\"iso_3166_1\": \"US\", \"name\": \"United States o...   2009-12-10  2787965087   \n",
       "1  [{\"iso_3166_1\": \"US\", \"name\": \"United States o...   2007-05-19   961000000   \n",
       "2  [{\"iso_3166_1\": \"GB\", \"name\": \"United Kingdom\"...   2015-10-26   880674609   \n",
       "3  [{\"iso_3166_1\": \"US\", \"name\": \"United States o...   2012-07-16  1084939099   \n",
       "4  [{\"iso_3166_1\": \"US\", \"name\": \"United States o...   2012-03-07   284139100   \n",
       "\n",
       "   runtime                                   spoken_languages    status  \\\n",
       "0    162.0  [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...  Released   \n",
       "1    169.0           [{\"iso_639_1\": \"en\", \"name\": \"English\"}]  Released   \n",
       "2    148.0  [{\"iso_639_1\": \"fr\", \"name\": \"Fran\\u00e7ais\"},...  Released   \n",
       "3    165.0           [{\"iso_639_1\": \"en\", \"name\": \"English\"}]  Released   \n",
       "4    132.0           [{\"iso_639_1\": \"en\", \"name\": \"English\"}]  Released   \n",
       "\n",
       "                                          tagline  \\\n",
       "0                     Enter the World of Pandora.   \n",
       "1  At the end of the world, the adventure begins.   \n",
       "2                           A Plan No One Escapes   \n",
       "3                                 The Legend Ends   \n",
       "4            Lost in our world, found in another.   \n",
       "\n",
       "                                      title  vote_average  vote_count  \n",
       "0                                    Avatar           7.2       11800  \n",
       "1  Pirates of the Caribbean: At World's End           6.9        4500  \n",
       "2                                   Spectre           6.3        4466  \n",
       "3                     The Dark Knight Rises           7.6        9106  \n",
       "4                               John Carter           6.1        2124  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4803, 20)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4803, 4)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "credits.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies=movies.merge(credits,on='title')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4809, 23)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 4809 entries, 0 to 4808\n",
      "Data columns (total 23 columns):\n",
      " #   Column                Non-Null Count  Dtype  \n",
      "---  ------                --------------  -----  \n",
      " 0   budget                4809 non-null   int64  \n",
      " 1   genres                4809 non-null   object \n",
      " 2   homepage              1713 non-null   object \n",
      " 3   id                    4809 non-null   int64  \n",
      " 4   keywords              4809 non-null   object \n",
      " 5   original_language     4809 non-null   object \n",
      " 6   original_title        4809 non-null   object \n",
      " 7   overview              4806 non-null   object \n",
      " 8   popularity            4809 non-null   float64\n",
      " 9   production_companies  4809 non-null   object \n",
      " 10  production_countries  4809 non-null   object \n",
      " 11  release_date          4808 non-null   object \n",
      " 12  revenue               4809 non-null   int64  \n",
      " 13  runtime               4807 non-null   float64\n",
      " 14  spoken_languages      4809 non-null   object \n",
      " 15  status                4809 non-null   object \n",
      " 16  tagline               3965 non-null   object \n",
      " 17  title                 4809 non-null   object \n",
      " 18  vote_average          4809 non-null   float64\n",
      " 19  vote_count            4809 non-null   int64  \n",
      " 20  movie_id              4809 non-null   int64  \n",
      " 21  cast                  4809 non-null   object \n",
      " 22  crew                  4809 non-null   object \n",
      "dtypes: float64(3), int64(5), object(15)\n",
      "memory usage: 901.7+ KB\n"
     ]
    }
   ],
   "source": [
    "movies.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies=movies.drop(['budget','homepage','original_language','original_title','popularity','production_countries','release_date','tagline','vote_count','production_companies','id','revenue','runtime','spoken_languages','status','vote_average'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</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>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>19995</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>[{\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"...</td>\n",
       "      <td>[{\"id\": 270, \"name\": \"ocean\"}, {\"id\": 726, \"na...</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>285</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>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 470, \"name\": \"spy\"}, {\"id\": 818, \"name...</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>206647</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>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 80, \"nam...</td>\n",
       "      <td>[{\"id\": 849, \"name\": \"dc comics\"}, {\"id\": 853,...</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>49026</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>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 818, \"name\": \"based on novel\"}, {\"id\":...</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>49529</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": [
       "                                              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",
       "                                            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",
       "                                      title  movie_id  \\\n",
       "0                                    Avatar     19995   \n",
       "1  Pirates of the Caribbean: At World's End       285   \n",
       "2                                   Spectre    206647   \n",
       "3                     The Dark Knight Rises     49026   \n",
       "4                               John Carter     49529   \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": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "genres      0\n",
       "keywords    0\n",
       "overview    3\n",
       "title       0\n",
       "movie_id    0\n",
       "cast        0\n",
       "crew        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "genres      0\n",
       "keywords    0\n",
       "overview    0\n",
       "title       0\n",
       "movie_id    0\n",
       "cast        0\n",
       "crew        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"name\": \"Fantasy\"}, {\"id\": 878, \"name\": \"Science Fiction\"}]'"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.iloc[0].genres"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert(obj):\n",
    "    L=[]\n",
    "    for i in ast.literal_eval(obj):\n",
    "        L.append(i['name'])\n",
    "    return L    \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['genres']=movies['genres'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</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>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>19995</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>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[{\"id\": 270, \"name\": \"ocean\"}, {\"id\": 726, \"na...</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>285</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>[Action, Adventure, Crime]</td>\n",
       "      <td>[{\"id\": 470, \"name\": \"spy\"}, {\"id\": 818, \"name...</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>206647</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>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[{\"id\": 849, \"name\": \"dc comics\"}, {\"id\": 853,...</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>49026</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>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[{\"id\": 818, \"name\": \"based on novel\"}, {\"id\":...</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>49529</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": [
       "                                          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  [{\"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",
       "                                            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",
       "                                      title  movie_id  \\\n",
       "0                                    Avatar     19995   \n",
       "1  Pirates of the Caribbean: At World's End       285   \n",
       "2                                   Spectre    206647   \n",
       "3                     The Dark Knight Rises     49026   \n",
       "4                               John Carter     49529   \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": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['keywords']=movies['keywords'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert3(obj):\n",
    "    L=[]\n",
    "    counter=0\n",
    "    for i in ast.literal_eval(obj):\n",
    "        if counter!=3:\n",
    "            L.append(i['name'])\n",
    "            counter+=1\n",
    "        else:\n",
    "            break\n",
    "            \n",
    "    return L    \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['cast']=movies['cast'].apply(convert3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</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>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[culture clash, future, space war, space colon...</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>19995</td>\n",
       "      <td>[Sam Worthington, Zoe Saldana, Sigourney Weaver]</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drug abuse, exotic island, east india ...</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>285</td>\n",
       "      <td>[Johnny Depp, Orlando Bloom, Keira Knightley]</td>\n",
       "      <td>[{\"credit_id\": \"52fe4232c3a36847f800b579\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, based on novel, secret agent, sequel, mi...</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>206647</td>\n",
       "      <td>[Daniel Craig, Christoph Waltz, Léa Seydoux]</td>\n",
       "      <td>[{\"credit_id\": \"54805967c3a36829b5002c41\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dc comics, crime fighter, terrorist, secret i...</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>49026</td>\n",
       "      <td>[Christian Bale, Michael Caine, Gary Oldman]</td>\n",
       "      <td>[{\"credit_id\": \"52fe4781c3a36847f81398c3\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[based on novel, mars, medallion, space travel...</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>49529</td>\n",
       "      <td>[Taylor Kitsch, Lynn Collins, Samantha Morton]</td>\n",
       "      <td>[{\"credit_id\": \"52fe479ac3a36847f813eaa3\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          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",
       "                                            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",
       "                                      title  movie_id  \\\n",
       "0                                    Avatar     19995   \n",
       "1  Pirates of the Caribbean: At World's End       285   \n",
       "2                                   Spectre    206647   \n",
       "3                     The Dark Knight Rises     49026   \n",
       "4                               John Carter     49529   \n",
       "\n",
       "                                               cast  \\\n",
       "0  [Sam Worthington, Zoe Saldana, Sigourney Weaver]   \n",
       "1     [Johnny Depp, Orlando Bloom, Keira Knightley]   \n",
       "2      [Daniel Craig, Christoph Waltz, Léa Seydoux]   \n",
       "3      [Christian Bale, Michael Caine, Gary Oldman]   \n",
       "4    [Taylor Kitsch, Lynn Collins, Samantha Morton]   \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": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fetch_director(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": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['crew']=movies['crew'].apply(fetch_director)"
   ]
  },
  {
   "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>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</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>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[culture clash, future, space war, space colon...</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>19995</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>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drug abuse, exotic island, east india ...</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>285</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>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, based on novel, secret agent, sequel, mi...</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>206647</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>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dc comics, crime fighter, terrorist, secret i...</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>49026</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>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[based on novel, mars, medallion, space travel...</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>49529</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": [
       "                                          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",
       "                                            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",
       "                                      title  movie_id  \\\n",
       "0                                    Avatar     19995   \n",
       "1  Pirates of the Caribbean: At World's End       285   \n",
       "2                                   Spectre    206647   \n",
       "3                     The Dark Knight Rises     49026   \n",
       "4                               John Carter     49529   \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": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['overview']=movies['overview'].apply(lambda x:x.split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['genre']=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": 29,
   "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>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "      <th>genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[cultureclash, future, spacewar, spacecolony, ...</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>19995</td>\n",
       "      <td>[SamWorthington, ZoeSaldana, SigourneyWeaver]</td>\n",
       "      <td>[JamesCameron]</td>\n",
       "      <td>[Action, Adventure, Fantasy, ScienceFiction]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drugabuse, exoticisland, eastindiatrad...</td>\n",
       "      <td>[Captain, Barbossa,, long, believed, to, be, d...</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>285</td>\n",
       "      <td>[JohnnyDepp, OrlandoBloom, KeiraKnightley]</td>\n",
       "      <td>[GoreVerbinski]</td>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, basedonnovel, secretagent, sequel, mi6, ...</td>\n",
       "      <td>[A, cryptic, message, from, Bond’s, past, send...</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>206647</td>\n",
       "      <td>[DanielCraig, ChristophWaltz, LéaSeydoux]</td>\n",
       "      <td>[SamMendes]</td>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dccomics, crimefighter, terrorist, secretiden...</td>\n",
       "      <td>[Following, the, death, of, District, Attorney...</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>49026</td>\n",
       "      <td>[ChristianBale, MichaelCaine, GaryOldman]</td>\n",
       "      <td>[ChristopherNolan]</td>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[basedonnovel, mars, medallion, spacetravel, p...</td>\n",
       "      <td>[John, Carter, is, a, war-weary,, former, mili...</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>49529</td>\n",
       "      <td>[TaylorKitsch, LynnCollins, SamanthaMorton]</td>\n",
       "      <td>[AndrewStanton]</td>\n",
       "      <td>[Action, Adventure, ScienceFiction]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          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  [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",
       "                                            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",
       "                                      title  movie_id  \\\n",
       "0                                    Avatar     19995   \n",
       "1  Pirates of the Caribbean: At World's End       285   \n",
       "2                                   Spectre    206647   \n",
       "3                     The Dark Knight Rises     49026   \n",
       "4                               John Carter     49529   \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",
       "                                          genre  \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]  "
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['tags']=movies['overview']+movies['genres']+movies['keywords']+movies['cast']+movies['crew']"
   ]
  },
  {
   "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>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>overview</th>\n",
       "      <th>title</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "      <th>genre</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[Action, Adventure, Fantasy, Science Fiction]</td>\n",
       "      <td>[cultureclash, future, spacewar, spacecolony, ...</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>19995</td>\n",
       "      <td>[SamWorthington, ZoeSaldana, SigourneyWeaver]</td>\n",
       "      <td>[JamesCameron]</td>\n",
       "      <td>[Action, Adventure, Fantasy, ScienceFiction]</td>\n",
       "      <td>[In, the, 22nd, century,, a, paraplegic, Marin...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[ocean, drugabuse, exoticisland, eastindiatrad...</td>\n",
       "      <td>[Captain, Barbossa,, long, believed, to, be, d...</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>285</td>\n",
       "      <td>[JohnnyDepp, OrlandoBloom, KeiraKnightley]</td>\n",
       "      <td>[GoreVerbinski]</td>\n",
       "      <td>[Adventure, Fantasy, Action]</td>\n",
       "      <td>[Captain, Barbossa,, long, believed, to, be, d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[spy, basedonnovel, secretagent, sequel, mi6, ...</td>\n",
       "      <td>[A, cryptic, message, from, Bond’s, past, send...</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>206647</td>\n",
       "      <td>[DanielCraig, ChristophWaltz, LéaSeydoux]</td>\n",
       "      <td>[SamMendes]</td>\n",
       "      <td>[Action, Adventure, Crime]</td>\n",
       "      <td>[A, cryptic, message, from, Bond’s, past, send...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[dccomics, crimefighter, terrorist, secretiden...</td>\n",
       "      <td>[Following, the, death, of, District, Attorney...</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>49026</td>\n",
       "      <td>[ChristianBale, MichaelCaine, GaryOldman]</td>\n",
       "      <td>[ChristopherNolan]</td>\n",
       "      <td>[Action, Crime, Drama, Thriller]</td>\n",
       "      <td>[Following, the, death, of, District, Attorney...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[Action, Adventure, Science Fiction]</td>\n",
       "      <td>[basedonnovel, mars, medallion, spacetravel, p...</td>\n",
       "      <td>[John, Carter, is, a, war-weary,, former, mili...</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>49529</td>\n",
       "      <td>[TaylorKitsch, LynnCollins, SamanthaMorton]</td>\n",
       "      <td>[AndrewStanton]</td>\n",
       "      <td>[Action, Adventure, ScienceFiction]</td>\n",
       "      <td>[John, Carter, is, a, war-weary,, former, mili...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          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  [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",
       "                                            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",
       "                                      title  movie_id  \\\n",
       "0                                    Avatar     19995   \n",
       "1  Pirates of the Caribbean: At World's End       285   \n",
       "2                                   Spectre    206647   \n",
       "3                     The Dark Knight Rises     49026   \n",
       "4                               John Carter     49529   \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",
       "                                          genre  \\\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",
       "                                                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": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_df=movies[['movie_id','title','tags']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "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, 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",
       "    </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",
       "    </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",
       "    </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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4804</th>\n",
       "      <td>9367</td>\n",
       "      <td>El Mariachi</td>\n",
       "      <td>[El, Mariachi, just, wants, to, play, his, gui...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4805</th>\n",
       "      <td>72766</td>\n",
       "      <td>Newlyweds</td>\n",
       "      <td>[A, newlywed, couple's, honeymoon, is, upended...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4806</th>\n",
       "      <td>231617</td>\n",
       "      <td>Signed, Sealed, Delivered</td>\n",
       "      <td>[\"Signed,, Sealed,, Delivered\", introduces, a,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4807</th>\n",
       "      <td>126186</td>\n",
       "      <td>Shanghai Calling</td>\n",
       "      <td>[When, ambitious, New, York, attorney, Sam, is...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4808</th>\n",
       "      <td>25975</td>\n",
       "      <td>My Date with Drew</td>\n",
       "      <td>[Ever, since, the, second, grade, when, he, fi...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4806 rows × 3 columns</p>\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",
       "4804      9367                               El Mariachi   \n",
       "4805     72766                                 Newlyweds   \n",
       "4806    231617                 Signed, Sealed, Delivered   \n",
       "4807    126186                          Shanghai Calling   \n",
       "4808     25975                         My Date with Drew   \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...  \n",
       "...                                                 ...  \n",
       "4804  [El, Mariachi, just, wants, to, play, his, gui...  \n",
       "4805  [A, newlywed, couple's, honeymoon, is, upended...  \n",
       "4806  [\"Signed,, Sealed,, Delivered\", introduces, a,...  \n",
       "4807  [When, ambitious, New, York, attorney, Sam, is...  \n",
       "4808  [Ever, since, the, second, grade, when, he, fi...  \n",
       "\n",
       "[4806 rows x 3 columns]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ARYA SHARMA\\AppData\\Local\\Temp\\ipykernel_19872\\487797088.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": 35,
   "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": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes torn between following orders and protecting an alien civilization. Action Adventure Fantasy Science Fiction cultureclash future spacewar spacecolony society spacetravel futuristic romance space alien tribe alienplanet cgi marine soldier battle loveaffair antiwar powerrelations mindandsoul 3d SamWorthington ZoeSaldana SigourneyWeaver JamesCameron'"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df['tags'][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ARYA SHARMA\\AppData\\Local\\Temp\\ipykernel_19872\\3923394162.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": 38,
   "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": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "from nltk.stem.porter import PorterStemmer\n",
    "ps=PorterStemmer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stem(text):\n",
    "    y=[]\n",
    "    for i in text.split():\n",
    "        y.append(ps.stem(i))\n",
    "    return \" \".join(y)    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ARYA SHARMA\\AppData\\Local\\Temp\\ipykernel_19872\\3514595201.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": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "cv=CountVectorizer(max_features=7000,stop_words='english')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectors= cv.fit_transform(new_df['tags']).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\ARYA SHARMA\\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",
       " '10th',\n",
       " '11',\n",
       " '12',\n",
       " '12th',\n",
       " '13',\n",
       " '14',\n",
       " '15',\n",
       " '150',\n",
       " '16',\n",
       " '16th',\n",
       " '17',\n",
       " '17th',\n",
       " '18',\n",
       " '1890',\n",
       " '18th',\n",
       " '18thcenturi',\n",
       " '19',\n",
       " '1910',\n",
       " '1920',\n",
       " '1930',\n",
       " '1930s',\n",
       " '1937',\n",
       " '1940',\n",
       " '1941',\n",
       " '1944',\n",
       " '1945',\n",
       " '1950',\n",
       " '1950s',\n",
       " '1955',\n",
       " '1959',\n",
       " '1960',\n",
       " '1960s',\n",
       " '1962',\n",
       " '1964',\n",
       " '1965',\n",
       " '1967',\n",
       " '1970',\n",
       " '1970s',\n",
       " '1971',\n",
       " '1972',\n",
       " '1973',\n",
       " '1974',\n",
       " '1976',\n",
       " '1977',\n",
       " '1979',\n",
       " '1980',\n",
       " '1980s',\n",
       " '1984',\n",
       " '1985',\n",
       " '1990',\n",
       " '1994',\n",
       " '1995',\n",
       " '1997',\n",
       " '1999',\n",
       " '19th',\n",
       " '19thcenturi',\n",
       " '20',\n",
       " '200',\n",
       " '2000',\n",
       " '2001',\n",
       " '2002',\n",
       " '2003',\n",
       " '2008',\n",
       " '2009',\n",
       " '20th',\n",
       " '21st',\n",
       " '21stcenturi',\n",
       " '23',\n",
       " '24',\n",
       " '25',\n",
       " '27',\n",
       " '30',\n",
       " '300',\n",
       " '35',\n",
       " '3d',\n",
       " '40',\n",
       " '47',\n",
       " '50',\n",
       " '500',\n",
       " '51',\n",
       " '60',\n",
       " '60s',\n",
       " '70',\n",
       " '7th',\n",
       " '80',\n",
       " 'aaron',\n",
       " 'aaroneckhart',\n",
       " 'aarontaylor',\n",
       " 'abandon',\n",
       " 'abbi',\n",
       " 'abduct',\n",
       " 'abigailbreslin',\n",
       " 'abil',\n",
       " 'abl',\n",
       " 'aboard',\n",
       " 'aborigin',\n",
       " 'abov',\n",
       " 'abroad',\n",
       " 'absolut',\n",
       " 'absurd',\n",
       " 'abus',\n",
       " 'abuse',\n",
       " 'academ',\n",
       " 'academi',\n",
       " 'academy',\n",
       " 'accept',\n",
       " 'access',\n",
       " 'accid',\n",
       " 'accident',\n",
       " 'acclaim',\n",
       " 'accompani',\n",
       " 'accomplish',\n",
       " 'account',\n",
       " 'accus',\n",
       " 'ace',\n",
       " 'achiev',\n",
       " 'acquaint',\n",
       " 'acquir',\n",
       " 'act',\n",
       " 'action',\n",
       " 'actionhero',\n",
       " 'activ',\n",
       " 'activist',\n",
       " 'activities',\n",
       " 'actor',\n",
       " 'actress',\n",
       " 'actual',\n",
       " 'ad',\n",
       " 'ada',\n",
       " 'adam',\n",
       " 'adammckay',\n",
       " 'adamsandl',\n",
       " 'adamshankman',\n",
       " 'adapt',\n",
       " 'add',\n",
       " 'addict',\n",
       " 'addiction',\n",
       " 'addit',\n",
       " 'addl',\n",
       " 'adjust',\n",
       " 'admir',\n",
       " 'admit',\n",
       " 'adolesc',\n",
       " 'adopt',\n",
       " 'ador',\n",
       " 'adrienbrodi',\n",
       " 'adrift',\n",
       " 'adult',\n",
       " 'adultanim',\n",
       " 'adulteri',\n",
       " 'adulthood',\n",
       " 'adults',\n",
       " 'advanc',\n",
       " 'advantag',\n",
       " 'advantage',\n",
       " 'adventur',\n",
       " 'adventure',\n",
       " 'adventures',\n",
       " 'advertis',\n",
       " 'advic',\n",
       " 'advice',\n",
       " 'advis',\n",
       " 'affair',\n",
       " 'affect',\n",
       " 'affection',\n",
       " 'afflict',\n",
       " 'affluent',\n",
       " 'afford',\n",
       " 'afghanistan',\n",
       " 'afraid',\n",
       " 'africa',\n",
       " 'african',\n",
       " 'africanamerican',\n",
       " 'aftercreditssting',\n",
       " 'afterlif',\n",
       " 'aftermath',\n",
       " 'afternoon',\n",
       " 'ag',\n",
       " 'age',\n",
       " 'agediffer',\n",
       " 'agenc',\n",
       " 'agency',\n",
       " 'agenda',\n",
       " 'agent',\n",
       " 'agents',\n",
       " 'aggress',\n",
       " 'aggressionbyanim',\n",
       " 'ago',\n",
       " 'agre',\n",
       " 'ahead',\n",
       " 'aid',\n",
       " 'aidanquinn',\n",
       " 'ail',\n",
       " 'aim',\n",
       " 'air',\n",
       " 'airborn',\n",
       " 'aircraft',\n",
       " 'airplan',\n",
       " 'airplanecrash',\n",
       " 'airport',\n",
       " 'aka',\n",
       " 'al',\n",
       " 'alabama',\n",
       " 'alan',\n",
       " 'alanarkin',\n",
       " 'alaska',\n",
       " 'alaskan',\n",
       " 'albert',\n",
       " 'albertbrook',\n",
       " 'albertfinney',\n",
       " 'alcatraz',\n",
       " 'alcohol',\n",
       " 'alcoholabus',\n",
       " 'alecbaldwin',\n",
       " 'alejandrogonzáleziñárritu',\n",
       " 'alex',\n",
       " 'alexanderpayn',\n",
       " 'alexanderskarsgård',\n",
       " 'alexapenavega',\n",
       " 'alexia',\n",
       " 'alexisbledel',\n",
       " 'alexkendrick',\n",
       " 'alexpettyf',\n",
       " 'alexproya',\n",
       " 'alfi',\n",
       " 'alfredhitchcock',\n",
       " 'alfredmolina',\n",
       " 'algeria',\n",
       " 'ali',\n",
       " 'alic',\n",
       " 'alice',\n",
       " 'alicebraga',\n",
       " 'alien',\n",
       " 'alieninvas',\n",
       " 'alienlife',\n",
       " 'alienplanet',\n",
       " 'aliens',\n",
       " 'alik',\n",
       " 'alike',\n",
       " 'alilart',\n",
       " 'aliv',\n",
       " 'alive',\n",
       " 'alleg',\n",
       " 'allegedli',\n",
       " 'allen',\n",
       " 'alli',\n",
       " 'allianc',\n",
       " 'allies',\n",
       " 'allow',\n",
       " 'alon',\n",
       " 'alongsid',\n",
       " 'alpacino',\n",
       " 'alpha',\n",
       " 'alreadi',\n",
       " 'alt',\n",
       " 'alter',\n",
       " 'altern',\n",
       " 'alternatehistori',\n",
       " 'alternater',\n",
       " 'alway',\n",
       " 'alyssa',\n",
       " 'alzheimer',\n",
       " 'amanda',\n",
       " 'amandabyn',\n",
       " 'amandapeet',\n",
       " 'amandaseyfri',\n",
       " 'amateur',\n",
       " 'amaz',\n",
       " 'amazon',\n",
       " 'ambassador',\n",
       " 'amberheard',\n",
       " 'ambit',\n",
       " 'ambiti',\n",
       " 'ambul',\n",
       " 'ambush',\n",
       " 'america',\n",
       " 'american',\n",
       " 'americanabroad',\n",
       " 'americancivilwar',\n",
       " 'americandream',\n",
       " 'americanfootbal',\n",
       " 'americanfootballplay',\n",
       " 'ami',\n",
       " 'amid',\n",
       " 'amidst',\n",
       " 'amnesia',\n",
       " 'amp',\n",
       " 'amsterdam',\n",
       " 'amus',\n",
       " 'amusementpark',\n",
       " 'amy',\n",
       " 'amyadam',\n",
       " 'amysmart',\n",
       " 'ana',\n",
       " 'anakin',\n",
       " 'analyst',\n",
       " 'anarchiccomedi',\n",
       " 'ancient',\n",
       " 'ancientgreec',\n",
       " 'ancientrom',\n",
       " 'ancientworld',\n",
       " 'anderson',\n",
       " 'andi',\n",
       " 'andiemacdowel',\n",
       " 'andrew',\n",
       " 'andrewadamson',\n",
       " 'andrewgarfield',\n",
       " 'andrewniccol',\n",
       " 'android',\n",
       " 'andrzejbartkowiak',\n",
       " 'andy',\n",
       " 'andyfickman',\n",
       " 'andygarcía',\n",
       " 'andyserki',\n",
       " 'andytenn',\n",
       " 'angel',\n",
       " 'angela',\n",
       " 'angelabassett',\n",
       " 'angeles',\n",
       " 'angelinajoli',\n",
       " 'anger',\n",
       " 'angle',\n",
       " 'angri',\n",
       " 'ani',\n",
       " 'anim',\n",
       " 'animal',\n",
       " 'animalattack',\n",
       " 'animalhorror',\n",
       " 'animals',\n",
       " 'anjelicahuston',\n",
       " 'ann',\n",
       " 'anna',\n",
       " 'annabel',\n",
       " 'annafari',\n",
       " 'annafriel',\n",
       " 'annakendrick',\n",
       " 'annasophiarobb',\n",
       " 'anne',\n",
       " 'annefletch',\n",
       " 'annehathaway',\n",
       " 'annehech',\n",
       " 'annemoss',\n",
       " 'annetteben',\n",
       " 'anni',\n",
       " 'annie',\n",
       " 'anniversari',\n",
       " 'announc',\n",
       " 'annual',\n",
       " 'anonym',\n",
       " 'anoth',\n",
       " 'answer',\n",
       " 'answers',\n",
       " 'ant',\n",
       " 'antarct',\n",
       " 'antarctica',\n",
       " 'antholog',\n",
       " 'anthoni',\n",
       " 'anthonyanderson',\n",
       " 'anthonyhopkin',\n",
       " 'anthonymacki',\n",
       " 'anthropomorph',\n",
       " 'anti',\n",
       " 'antic',\n",
       " 'antihero',\n",
       " 'antiqu',\n",
       " 'antisemit',\n",
       " 'antiterror',\n",
       " 'antoinefuqua',\n",
       " 'anton',\n",
       " 'antonio',\n",
       " 'antoniobandera',\n",
       " 'antonyelchin',\n",
       " 'anyon',\n",
       " 'anyth',\n",
       " 'apart',\n",
       " 'apartheid',\n",
       " 'apartment',\n",
       " 'ape',\n",
       " 'apes',\n",
       " 'apocalyps',\n",
       " 'apocalypse',\n",
       " 'apocalypt',\n",
       " 'apollo',\n",
       " 'appar',\n",
       " 'appear',\n",
       " 'appl',\n",
       " 'apple',\n",
       " 'appli',\n",
       " 'appoint',\n",
       " 'appreci',\n",
       " 'apprehend',\n",
       " 'apprentic',\n",
       " 'approach',\n",
       " 'approaches',\n",
       " 'april',\n",
       " 'aquarium',\n",
       " 'arab',\n",
       " 'arbitrarylaw',\n",
       " 'arch',\n",
       " 'archaeologist',\n",
       " 'archeolog',\n",
       " 'archer',\n",
       " 'archeri',\n",
       " 'architect',\n",
       " 'arctic',\n",
       " 'area',\n",
       " 'aren',\n",
       " 'arena',\n",
       " 'argument',\n",
       " 'aris',\n",
       " 'aristocrat',\n",
       " 'arizona',\n",
       " 'arm',\n",
       " 'armi',\n",
       " 'armiehamm',\n",
       " 'armor',\n",
       " 'armsdeal',\n",
       " 'army',\n",
       " 'arnold',\n",
       " 'arnoldschwarzenegg',\n",
       " 'arrang',\n",
       " 'arrangedmarriag',\n",
       " 'array',\n",
       " 'arrest',\n",
       " 'arrested',\n",
       " 'arriv',\n",
       " 'arrive',\n",
       " 'arrives',\n",
       " 'arrog',\n",
       " 'arson',\n",
       " 'art',\n",
       " 'artgalleri',\n",
       " 'arthur',\n",
       " 'articl',\n",
       " 'artifact',\n",
       " 'artifici',\n",
       " 'artificialintellig',\n",
       " 'artist',\n",
       " 'artists',\n",
       " 'ash',\n",
       " 'ashley',\n",
       " 'ashleyjudd',\n",
       " 'ashtonkutch',\n",
       " 'asia',\n",
       " 'asian',\n",
       " 'asid',\n",
       " 'ask',\n",
       " 'aspect',\n",
       " 'aspir',\n",
       " 'assassin',\n",
       " 'assassins',\n",
       " 'assault',\n",
       " 'assembl',\n",
       " 'assign',\n",
       " 'assignment',\n",
       " 'assist',\n",
       " 'assistant',\n",
       " 'associ',\n",
       " 'assort',\n",
       " 'assum',\n",
       " 'asteroid',\n",
       " 'astronaut',\n",
       " 'asylum',\n",
       " 'atheist',\n",
       " 'athlet',\n",
       " 'atlant',\n",
       " 'atlanta',\n",
       " 'atom',\n",
       " 'atomegoyan',\n",
       " 'atomicbomb',\n",
       " 'attach',\n",
       " 'attack',\n",
       " 'attacks',\n",
       " 'attempt',\n",
       " 'attemptedmurd',\n",
       " 'attempttoescap',\n",
       " 'attend',\n",
       " 'attent',\n",
       " 'attic',\n",
       " 'attitud',\n",
       " 'attorney',\n",
       " 'attract',\n",
       " 'auction',\n",
       " 'audienc',\n",
       " 'audit',\n",
       " 'audreytaut',\n",
       " 'august',\n",
       " 'aunt',\n",
       " 'austin',\n",
       " 'australia',\n",
       " 'australian',\n",
       " 'austria',\n",
       " 'austrian',\n",
       " 'author',\n",
       " 'authorities',\n",
       " 'authority',\n",
       " 'autism',\n",
       " 'auto',\n",
       " 'autobiograph',\n",
       " 'automobilerac',\n",
       " 'avail',\n",
       " 'aveng',\n",
       " 'averag',\n",
       " 'aviat',\n",
       " 'avoid',\n",
       " 'await',\n",
       " 'awak',\n",
       " 'awaken',\n",
       " 'awar',\n",
       " 'award',\n",
       " 'away',\n",
       " 'awe',\n",
       " 'awesom',\n",
       " 'awkward',\n",
       " 'awri',\n",
       " 'awry',\n",
       " 'ax',\n",
       " 'axe',\n",
       " 'axel',\n",
       " 'babe',\n",
       " 'babi',\n",
       " 'baby',\n",
       " 'babysitt',\n",
       " 'bachelor',\n",
       " 'backdrop',\n",
       " 'background',\n",
       " 'backpack',\n",
       " 'backstag',\n",
       " 'backwat',\n",
       " 'backyard',\n",
       " 'bad',\n",
       " 'badli',\n",
       " 'bag',\n",
       " 'bahama',\n",
       " 'bail',\n",
       " 'bailey',\n",
       " 'baker',\n",
       " 'balanc',\n",
       " 'ball',\n",
       " 'ballet',\n",
       " 'balloon',\n",
       " 'baltimor',\n",
       " 'ban',\n",
       " 'band',\n",
       " 'bandit',\n",
       " 'bangkok',\n",
       " 'banish',\n",
       " 'bank',\n",
       " 'banker',\n",
       " 'bankrobb',\n",
       " 'bankrobberi',\n",
       " 'bar',\n",
       " 'barbara',\n",
       " 'barbarian',\n",
       " 'barbershop',\n",
       " 'barbrastreisand',\n",
       " 'bare',\n",
       " 'bargain',\n",
       " 'barn',\n",
       " 'barney',\n",
       " 'baron',\n",
       " 'barri',\n",
       " 'barrier',\n",
       " 'barry',\n",
       " 'barrylevinson',\n",
       " 'barrypepp',\n",
       " 'barrysonnenfeld',\n",
       " 'bars',\n",
       " 'bas',\n",
       " 'base',\n",
       " 'basebal',\n",
       " 'basedonchildren',\n",
       " 'basedoncomicbook',\n",
       " 'basedonfilm',\n",
       " 'basedongraphicnovel',\n",
       " 'basedonnovel',\n",
       " 'basedonplay',\n",
       " 'basedonstagemus',\n",
       " 'basedontrueev',\n",
       " 'basedontruestori',\n",
       " 'basedontvseri',\n",
       " 'basedonvideogam',\n",
       " 'basedonyoungadultnovel',\n",
       " 'basement',\n",
       " 'basketbal',\n",
       " 'basketball',\n",
       " 'bat',\n",
       " 'bathtub',\n",
       " 'batman',\n",
       " 'battalion',\n",
       " 'battl',\n",
       " 'battle',\n",
       " 'battlefield',\n",
       " 'bay',\n",
       " 'beach',\n",
       " 'beam',\n",
       " 'bear',\n",
       " 'beard',\n",
       " 'beast',\n",
       " 'beat',\n",
       " 'beaten',\n",
       " 'beau',\n",
       " 'beauti',\n",
       " 'beautiful',\n",
       " 'beautifulwoman',\n",
       " 'beauty',\n",
       " 'becam',\n",
       " 'becaus',\n",
       " 'becki',\n",
       " 'becom',\n",
       " 'becominganadult',\n",
       " 'bed',\n",
       " 'bedroom',\n",
       " 'bee',\n",
       " 'beer',\n",
       " 'befor',\n",
       " 'befriend',\n",
       " 'beg',\n",
       " 'began',\n",
       " 'begin',\n",
       " 'begins',\n",
       " 'beguil',\n",
       " 'behavior',\n",
       " 'behead',\n",
       " 'belgium',\n",
       " 'belief',\n",
       " 'beliefs',\n",
       " 'believ',\n",
       " 'bell',\n",
       " 'bella',\n",
       " 'belong',\n",
       " 'belov',\n",
       " 'ben',\n",
       " 'benaffleck',\n",
       " 'bend',\n",
       " 'beneath',\n",
       " 'benefit',\n",
       " 'benfost',\n",
       " 'beniciodeltoro',\n",
       " 'benjamin',\n",
       " 'benjaminbratt',\n",
       " 'benkingsley',\n",
       " 'bennett',\n",
       " 'benstil',\n",
       " 'bent',\n",
       " 'berlin',\n",
       " 'berniemac',\n",
       " 'best',\n",
       " 'bestfriend',\n",
       " 'bestfriendsinlov',\n",
       " 'bet',\n",
       " 'beth',\n",
       " 'betray',\n",
       " 'betrayal',\n",
       " 'bettemidl',\n",
       " 'better',\n",
       " 'betti',\n",
       " 'bettythoma',\n",
       " 'beverli',\n",
       " 'bibl',\n",
       " 'biblic',\n",
       " 'bicker',\n",
       " 'bicycl',\n",
       " 'bid',\n",
       " 'big',\n",
       " 'bigger',\n",
       " 'biggest',\n",
       " 'bike',\n",
       " 'biker',\n",
       " 'bikini',\n",
       " 'bilbo',\n",
       " 'billcondon',\n",
       " 'billhad',\n",
       " 'billi',\n",
       " 'billion',\n",
       " 'billionair',\n",
       " 'billmoseley',\n",
       " 'billmurray',\n",
       " 'billnighi',\n",
       " 'billpaxton',\n",
       " 'billpullman',\n",
       " 'billybobthornton',\n",
       " 'billyconnolli',\n",
       " 'billycrudup',\n",
       " 'billycryst',\n",
       " 'bind',\n",
       " 'biograph',\n",
       " 'biographi',\n",
       " 'biolog',\n",
       " 'biologist',\n",
       " 'biopic',\n",
       " 'bird',\n",
       " 'birth',\n",
       " 'birthday',\n",
       " 'bisexu',\n",
       " 'bishop',\n",
       " 'bit',\n",
       " 'bite',\n",
       " 'bitten',\n",
       " 'bitter',\n",
       " 'bittersweet',\n",
       " 'bizarr',\n",
       " 'black',\n",
       " 'blackandwhit',\n",
       " 'blackhol',\n",
       " 'blackmag',\n",
       " 'blackmail',\n",
       " 'blackpeopl',\n",
       " 'blacksmith',\n",
       " 'blade',\n",
       " 'blake',\n",
       " 'blame',\n",
       " 'blart',\n",
       " 'blast',\n",
       " 'blaxploit',\n",
       " 'blaze',\n",
       " 'blend',\n",
       " 'bless',\n",
       " 'blind',\n",
       " 'blinddat',\n",
       " 'blindnessandimpairedvis',\n",
       " 'bliss',\n",
       " 'blizzard',\n",
       " 'block',\n",
       " 'blofeld',\n",
       " 'blog',\n",
       " 'blond',\n",
       " 'blonde',\n",
       " 'blood',\n",
       " 'bloodi',\n",
       " 'bloodsplatt',\n",
       " 'bloodthirsti',\n",
       " 'bloom',\n",
       " 'blossom',\n",
       " 'blow',\n",
       " 'blu',\n",
       " 'blue',\n",
       " 'blunt',\n",
       " 'blur',\n",
       " 'board',\n",
       " 'boardingschool',\n",
       " 'boat',\n",
       " 'bob',\n",
       " 'bobbi',\n",
       " 'bobby',\n",
       " 'bobbyfarrelli',\n",
       " 'bobhoskin',\n",
       " 'bodi',\n",
       " 'body',\n",
       " 'bodyguard',\n",
       " 'bodyhorror',\n",
       " 'bohemian',\n",
       " 'bold',\n",
       " 'bollywood',\n",
       " 'bolt',\n",
       " 'bomb',\n",
       " 'bomber',\n",
       " 'bond',\n",
       " 'bone',\n",
       " 'bonniehunt',\n",
       " 'boo',\n",
       " 'book',\n",
       " 'books',\n",
       " 'boot',\n",
       " 'border',\n",
       " 'bore',\n",
       " 'boredom',\n",
       " 'boring',\n",
       " 'born',\n",
       " 'borrow',\n",
       " 'boss',\n",
       " 'boston',\n",
       " 'botch',\n",
       " 'bottl',\n",
       " 'bounc',\n",
       " 'bound',\n",
       " 'boundari',\n",
       " 'bounti',\n",
       " 'bountyhunt',\n",
       " 'bourn',\n",
       " 'bout',\n",
       " 'bowl',\n",
       " 'box',\n",
       " 'boxer',\n",
       " 'boxingmatch',\n",
       " 'boy',\n",
       " 'boyd',\n",
       " 'boyfriend',\n",
       " 'boys',\n",
       " 'brad',\n",
       " 'bradanderson',\n",
       " 'bradleycoop',\n",
       " 'bradpitt',\n",
       " 'brain',\n",
       " 'braintumor',\n",
       " 'brainwash',\n",
       " 'brand',\n",
       " 'brandon',\n",
       " 'brave',\n",
       " 'braveri',\n",
       " 'brazil',\n",
       " 'brazilian',\n",
       " 'break',\n",
       " 'breakdown',\n",
       " 'breakingthefourthwal',\n",
       " 'breakup',\n",
       " 'breast',\n",
       " 'breath',\n",
       " 'breed',\n",
       " 'brendan',\n",
       " 'brendanfras',\n",
       " 'brendangleeson',\n",
       " 'brent',\n",
       " 'brentspin',\n",
       " 'brettratn',\n",
       " 'brew',\n",
       " 'brian',\n",
       " 'briancox',\n",
       " 'briandepalma',\n",
       " 'brianhelgeland',\n",
       " 'brianlev',\n",
       " 'brianrobbin',\n",
       " 'brick',\n",
       " 'bride',\n",
       " 'bridesmaid',\n",
       " 'bridg',\n",
       " 'bridge',\n",
       " 'bridgetfonda',\n",
       " 'brief',\n",
       " 'brielarson',\n",
       " 'brien',\n",
       " 'bright',\n",
       " 'brilliant',\n",
       " 'bring',\n",
       " 'brink',\n",
       " 'britain',\n",
       " 'british',\n",
       " 'britisharmi',\n",
       " 'britishsecretservic',\n",
       " 'brittanymurphi',\n",
       " 'broadcast',\n",
       " 'broadway',\n",
       " 'broke',\n",
       " 'broken',\n",
       " 'broker',\n",
       " 'bronson',\n",
       " 'bronx',\n",
       " 'brood',\n",
       " 'brook',\n",
       " 'brooklyn',\n",
       " 'brooklynnewyorkc',\n",
       " 'broom',\n",
       " 'brothel',\n",
       " 'brother',\n",
       " 'brotherbrotherrelationship',\n",
       " 'brotherhood',\n",
       " 'brothers',\n",
       " 'brothersisterrelationship',\n",
       " 'brought',\n",
       " 'brown',\n",
       " 'bruce',\n",
       " 'brucecampbel',\n",
       " 'brucedern',\n",
       " 'brucegreenwood',\n",
       " 'brucewilli',\n",
       " 'brutal',\n",
       " 'bryancranston',\n",
       " 'bryansing',\n",
       " 'brycedallashoward',\n",
       " 'bu',\n",
       " 'buck',\n",
       " 'bud',\n",
       " 'budapest',\n",
       " 'buddi',\n",
       " 'buddy',\n",
       " 'buddycomedi',\n",
       " 'buddycop',\n",
       " 'budget',\n",
       " 'buffalo',\n",
       " 'bug',\n",
       " 'build',\n",
       " 'building',\n",
       " 'built',\n",
       " 'bull',\n",
       " 'bullet',\n",
       " 'bulli',\n",
       " 'bum',\n",
       " 'bumbl',\n",
       " 'bump',\n",
       " 'bunch',\n",
       " 'bunker',\n",
       " 'bunni',\n",
       " 'bureaucraci',\n",
       " 'burglar',\n",
       " 'buri',\n",
       " 'burn',\n",
       " 'burnedal',\n",
       " 'burtlancast',\n",
       " 'burton',\n",
       " 'burtreynold',\n",
       " 'bush',\n",
       " 'busi',\n",
       " 'business',\n",
       " 'businessman',\n",
       " 'businesswoman',\n",
       " 'bust',\n",
       " 'butch',\n",
       " 'butcher',\n",
       " 'butler',\n",
       " 'butt',\n",
       " 'button',\n",
       " 'buy',\n",
       " 'buzz',\n",
       " 'cabin',\n",
       " 'cabl',\n",
       " 'caesar',\n",
       " 'cage',\n",
       " 'cain',\n",
       " 'cairo',\n",
       " 'cal',\n",
       " 'cale',\n",
       " 'caleb',\n",
       " 'california',\n",
       " 'calm',\n",
       " 'calvin',\n",
       " 'cambodia',\n",
       " 'camcord',\n",
       " 'came',\n",
       " 'camelot',\n",
       " 'camera',\n",
       " 'cameraman',\n",
       " 'cameron',\n",
       " 'cameroncrow',\n",
       " 'camerondiaz',\n",
       " 'camgigandet',\n",
       " 'camillabel',\n",
       " 'camp',\n",
       " 'campaign',\n",
       " 'campbel',\n",
       " 'campbell',\n",
       " 'campbellscott',\n",
       " 'campu',\n",
       " 'canada',\n",
       " 'canadian',\n",
       " 'cancer',\n",
       " 'candi',\n",
       " 'candid',\n",
       " 'candlelightvigil',\n",
       " 'canin',\n",
       " 'cannabi',\n",
       " 'cannib',\n",
       " 'canuxploit',\n",
       " 'canyon',\n",
       " 'capabl',\n",
       " 'cape',\n",
       " 'caper',\n",
       " 'capit',\n",
       " 'capt',\n",
       " 'captain',\n",
       " 'captiv',\n",
       " 'captur',\n",
       " 'capture',\n",
       " 'captured',\n",
       " 'car',\n",
       " 'caraccid',\n",
       " 'carbomb',\n",
       " 'carchas',\n",
       " 'carcrash',\n",
       " 'card',\n",
       " 'care',\n",
       " 'career',\n",
       " 'carefre',\n",
       " 'caretak',\n",
       " 'careymulligan',\n",
       " 'cargo',\n",
       " 'caribbean',\n",
       " 'carjourney',\n",
       " 'carl',\n",
       " 'carlagugino',\n",
       " 'carlo',\n",
       " 'carmen',\n",
       " 'carniv',\n",
       " 'carol',\n",
       " 'carolina',\n",
       " 'carrac',\n",
       " 'carri',\n",
       " 'carrie',\n",
       " 'carriefish',\n",
       " 'cartel',\n",
       " 'carter',\n",
       " 'cartoon',\n",
       " 'caryelw',\n",
       " 'case',\n",
       " 'casey',\n",
       " 'caseyaffleck',\n",
       " 'cash',\n",
       " ...]"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv.get_feature_names()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics.pairwise import cosine_similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "similarity=cosine_similarity(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4806, 4806)"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cosine_similarity(vectors).shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "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)\n",
    "        \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Dark Knight\n",
      "Batman\n",
      "Batman\n",
      "The Dark Knight Rises\n",
      "10th & Wolf\n"
     ]
    }
   ],
   "source": [
    "recommend('Batman Begins')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(new_df.to_dict(),open('movies_dict.pkl','wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "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 parapleg marin is dispa...</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 believ to be dead, ha c...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>a cryptic messag from bond’ past send him on a...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>follow the death of district attorney harvey d...</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 militari ca...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4804</th>\n",
       "      <td>9367</td>\n",
       "      <td>El Mariachi</td>\n",
       "      <td>el mariachi just want to play hi guitar and ca...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4805</th>\n",
       "      <td>72766</td>\n",
       "      <td>Newlyweds</td>\n",
       "      <td>a newlyw couple' honeymoon is upend by the arr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4806</th>\n",
       "      <td>231617</td>\n",
       "      <td>Signed, Sealed, Delivered</td>\n",
       "      <td>\"signed, sealed, delivered\" introduc a dedic q...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4807</th>\n",
       "      <td>126186</td>\n",
       "      <td>Shanghai Calling</td>\n",
       "      <td>when ambiti new york attorney sam is sent to s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4808</th>\n",
       "      <td>25975</td>\n",
       "      <td>My Date with Drew</td>\n",
       "      <td>ever sinc the second grade when he first saw h...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4806 rows × 3 columns</p>\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",
       "4804      9367                               El Mariachi   \n",
       "4805     72766                                 Newlyweds   \n",
       "4806    231617                 Signed, Sealed, Delivered   \n",
       "4807    126186                          Shanghai Calling   \n",
       "4808     25975                         My Date with Drew   \n",
       "\n",
       "                                                   tags  \n",
       "0     in the 22nd century, a parapleg marin is dispa...  \n",
       "1     captain barbossa, long believ to be dead, ha c...  \n",
       "2     a cryptic messag from bond’ past send him on a...  \n",
       "3     follow the death of district attorney harvey d...  \n",
       "4     john carter is a war-weary, former militari ca...  \n",
       "...                                                 ...  \n",
       "4804  el mariachi just want to play hi guitar and ca...  \n",
       "4805  a newlyw couple' honeymoon is upend by the arr...  \n",
       "4806  \"signed, sealed, delivered\" introduc a dedic q...  \n",
       "4807  when ambiti new york attorney sam is sent to s...  \n",
       "4808  ever sinc the second grade when he first saw h...  \n",
       "\n",
       "[4806 rows x 3 columns]"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(similarity,open('similarity.pkl','wb'))"
   ]
  }
 ],
 "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": "3.10.7"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "547e4bcef05e70932573b937d3cf0146e04e40231df58f37570a8721868a7605"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}