{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import ast\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "credits = pd.read_csv('tmdb_5000_credits.csv')\n",
    "movies = pd.read_csv('tmdb_5000_movies.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>[{\"cast_id\": 4, \"character\": \"Captain Jack Spa...</td>\n",
       "      <td>[{\"credit_id\": \"52fe4232c3a36847f800b579\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>[{\"cast_id\": 1, \"character\": \"James Bond\", \"cr...</td>\n",
       "      <td>[{\"credit_id\": \"54805967c3a36829b5002c41\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>[{\"cast_id\": 2, \"character\": \"Bruce Wayne / Ba...</td>\n",
       "      <td>[{\"credit_id\": \"52fe4781c3a36847f81398c3\", \"de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>[{\"cast_id\": 5, \"character\": \"John Carter\", \"c...</td>\n",
       "      <td>[{\"credit_id\": \"52fe479ac3a36847f813eaa3\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title  \\\n",
       "0     19995                                    Avatar   \n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                                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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "credits.head()"
   ]
  },
  {
   "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",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      budget                                             genres  \\\n",
       "0  237000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "\n",
       "                      homepage     id  \\\n",
       "0  http://www.avatarmovie.com/  19995   \n",
       "\n",
       "                                            keywords original_language  \\\n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...                en   \n",
       "\n",
       "  original_title                                           overview  \\\n",
       "0         Avatar  In the 22nd century, a paraplegic Marine is di...   \n",
       "\n",
       "   popularity                               production_companies  \\\n",
       "0  150.437577  [{\"name\": \"Ingenious Film Partners\", \"id\": 289...   \n",
       "\n",
       "                                production_countries release_date     revenue  \\\n",
       "0  [{\"iso_3166_1\": \"US\", \"name\": \"United States o...   2009-12-10  2787965087   \n",
       "\n",
       "   runtime                                   spoken_languages    status  \\\n",
       "0    162.0  [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...  Released   \n",
       "\n",
       "                       tagline   title  vote_average  vote_count  \n",
       "0  Enter the World of Pandora.  Avatar           7.2       11800  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = movies.merge(credits, left_on='title', right_on='title')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>budget</th>\n",
       "      <th>genres</th>\n",
       "      <th>homepage</th>\n",
       "      <th>id</th>\n",
       "      <th>keywords</th>\n",
       "      <th>original_language</th>\n",
       "      <th>original_title</th>\n",
       "      <th>overview</th>\n",
       "      <th>popularity</th>\n",
       "      <th>production_companies</th>\n",
       "      <th>...</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "      <th>movie_id</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>237000000</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>http://www.avatarmovie.com/</td>\n",
       "      <td>19995</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>en</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>150.437577</td>\n",
       "      <td>[{\"name\": \"Ingenious Film Partners\", \"id\": 289...</td>\n",
       "      <td>...</td>\n",
       "      <td>162.0</td>\n",
       "      <td>[{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>Enter the World of Pandora.</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>7.2</td>\n",
       "      <td>11800</td>\n",
       "      <td>19995</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      budget                                             genres  \\\n",
       "0  237000000  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "\n",
       "                      homepage     id  \\\n",
       "0  http://www.avatarmovie.com/  19995   \n",
       "\n",
       "                                            keywords original_language  \\\n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...                en   \n",
       "\n",
       "  original_title                                           overview  \\\n",
       "0         Avatar  In the 22nd century, a paraplegic Marine is di...   \n",
       "\n",
       "   popularity                               production_companies  ... runtime  \\\n",
       "0  150.437577  [{\"name\": \"Ingenious Film Partners\", \"id\": 289...  ...   162.0   \n",
       "\n",
       "                                    spoken_languages    status  \\\n",
       "0  [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...  Released   \n",
       "\n",
       "                       tagline   title vote_average vote_count movie_id  \\\n",
       "0  Enter the World of Pandora.  Avatar          7.2      11800    19995   \n",
       "\n",
       "                                                cast  \\\n",
       "0  [{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...   \n",
       "\n",
       "                                                crew  \n",
       "0  [{\"credit_id\": \"52fe48009251416c750aca23\", \"de...  \n",
       "\n",
       "[1 rows x 23 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = movies[['movie_id', 'title', 'overview', 'genres', 'keywords', 'cast', 'crew']]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>genres</th>\n",
       "      <th>keywords</th>\n",
       "      <th>cast</th>\n",
       "      <th>crew</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19995</td>\n",
       "      <td>Avatar</td>\n",
       "      <td>In the 22nd century, a paraplegic Marine is di...</td>\n",
       "      <td>[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...</td>\n",
       "      <td>[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...</td>\n",
       "      <td>[{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...</td>\n",
       "      <td>[{\"credit_id\": \"52fe48009251416c750aca23\", \"de...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id   title                                           overview  \\\n",
       "0     19995  Avatar  In the 22nd century, a paraplegic Marine is di...   \n",
       "\n",
       "                                              genres  \\\n",
       "0  [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...   \n",
       "\n",
       "                                            keywords  \\\n",
       "0  [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...   \n",
       "\n",
       "                                                cast  \\\n",
       "0  [{\"cast_id\": 242, \"character\": \"Jake Sully\", \"...   \n",
       "\n",
       "                                                crew  \n",
       "0  [{\"credit_id\": \"52fe48009251416c750aca23\", \"de...  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert(obj):\n",
    "    L = []\n",
    "    for i in ast.literal_eval(obj):\n",
    "        L.append(i['name'])\n",
    "    return L"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['genres'] = movies['genres'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "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",
       "4804                        [Action, Crime, Thriller]\n",
       "4805                                [Comedy, Romance]\n",
       "4806               [Comedy, Drama, Romance, TV Movie]\n",
       "4807                                               []\n",
       "4808                                    [Documentary]\n",
       "Name: genres, Length: 4809, dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies['genres']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['keywords'] = movies['keywords'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "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",
       "4804    [united states–mexico barrier, legs, arms, pap...\n",
       "4805                                                   []\n",
       "4806    [date, love at first sight, narration, investi...\n",
       "4807                                                   []\n",
       "4808            [obsession, camcorder, crush, dream girl]\n",
       "Name: keywords, Length: 4809, dtype: object"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies['keywords']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['cast'] = movies['cast'].apply(lambda x: [i['name'] for i in ast.literal_eval(x)[:3]])  # Only top 3 actors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['crew'] = movies['crew'].apply(lambda x: [i['name'] for i in ast.literal_eval(x) if i['job'] == 'Director'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['tags'] = movies['genres'] + movies['keywords'] + movies['cast'] + movies['crew']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       [Action, Adventure, Fantasy, Science Fiction, ...\n",
       "1       [Adventure, Fantasy, Action, ocean, drug abuse...\n",
       "2       [Action, Adventure, Crime, spy, based on novel...\n",
       "3       [Action, Crime, Drama, Thriller, dc comics, cr...\n",
       "4       [Action, Adventure, Science Fiction, based on ...\n",
       "                              ...                        \n",
       "4804    [Action, Crime, Thriller, united states–mexico...\n",
       "4805    [Comedy, Romance, Edward Burns, Kerry Bishé, M...\n",
       "4806    [Comedy, Drama, Romance, TV Movie, date, love ...\n",
       "4807    [Daniel Henney, Eliza Coupe, Bill Paxton, Dani...\n",
       "4808    [Documentary, obsession, camcorder, crush, dre...\n",
       "Name: tags, Length: 4809, dtype: object"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies['tags']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['tags'] = movies['tags'].apply(lambda x: \" \".join(x))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       Action Adventure Fantasy Science Fiction cultu...\n",
       "1       Adventure Fantasy Action ocean drug abuse exot...\n",
       "2       Action Adventure Crime spy based on novel secr...\n",
       "3       Action Crime Drama Thriller dc comics crime fi...\n",
       "4       Action Adventure Science Fiction based on nove...\n",
       "                              ...                        \n",
       "4804    Action Crime Thriller united states–mexico bar...\n",
       "4805    Comedy Romance Edward Burns Kerry Bishé Marsha...\n",
       "4806    Comedy Drama Romance TV Movie date love at fir...\n",
       "4807    Daniel Henney Eliza Coupe Bill Paxton Daniel Hsia\n",
       "4808    Documentary obsession camcorder crush dream gi...\n",
       "Name: tags, Length: 4809, dtype: object"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies['tags']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = movies[['movie_id', 'title', 'overview', 'tags']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies['tags'] = movies['tags'].apply(lambda x: x.lower())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie_id</th>\n",
       "      <th>title</th>\n",
       "      <th>overview</th>\n",
       "      <th>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",
       "      <td>action adventure fantasy science fiction cultu...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>285</td>\n",
       "      <td>Pirates of the Caribbean: At World's End</td>\n",
       "      <td>Captain Barbossa, long believed to be dead, ha...</td>\n",
       "      <td>adventure fantasy action ocean drug abuse exot...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>206647</td>\n",
       "      <td>Spectre</td>\n",
       "      <td>A cryptic message from Bond’s past sends him o...</td>\n",
       "      <td>action adventure crime spy based on novel secr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>49026</td>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>Following the death of District Attorney Harve...</td>\n",
       "      <td>action crime drama thriller dc comics crime fi...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>49529</td>\n",
       "      <td>John Carter</td>\n",
       "      <td>John Carter is a war-weary, former military ca...</td>\n",
       "      <td>action adventure science fiction based on nove...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   movie_id                                     title  \\\n",
       "0     19995                                    Avatar   \n",
       "1       285  Pirates of the Caribbean: At World's End   \n",
       "2    206647                                   Spectre   \n",
       "3     49026                     The Dark Knight Rises   \n",
       "4     49529                               John Carter   \n",
       "\n",
       "                                            overview  \\\n",
       "0  In the 22nd century, a paraplegic Marine is di...   \n",
       "1  Captain Barbossa, long believed to be dead, ha...   \n",
       "2  A cryptic message from Bond’s past sends him o...   \n",
       "3  Following the death of District Attorney Harve...   \n",
       "4  John Carter is a war-weary, former military ca...   \n",
       "\n",
       "                                                tags  \n",
       "0  action adventure fantasy science fiction cultu...  \n",
       "1  adventure fantasy action ocean drug abuse exot...  \n",
       "2  action adventure crime spy based on novel secr...  \n",
       "3  action crime drama thriller dc comics crime fi...  \n",
       "4  action adventure science fiction based on nove...  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "tfidf = TfidfVectorizer(stop_words='english')\n",
    "tfidf_matrix = tfidf.fit_transform(movies['tags'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_recommendations(title, cosine_sim=cosine_sim):\n",
    "    idx = movies[movies['title'] == title].index[0]\n",
    "    sim_scores = list(enumerate(cosine_sim[idx]))\n",
    "    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)\n",
    "    sim_scores = sim_scores[1:11]  # Get top 10 similar movies\n",
    "    movie_indices = [i[0] for i in sim_scores]\n",
    "    return movies['title'].iloc[movie_indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "65               The Dark Knight\n",
      "119                Batman Begins\n",
      "1360                      Batman\n",
      "210               Batman & Robin\n",
      "428               Batman Returns\n",
      "1361                      Batman\n",
      "1197                The Prestige\n",
      "303                     Catwoman\n",
      "4644    Amidst the Devil's Wings\n",
      "72                 Suicide Squad\n",
      "Name: title, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(get_recommendations('The Dark Knight Rises'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "with open('movie_data.pkl', 'wb') as file:\n",
    "    pickle.dump((movies, cosine_sim), file)"
   ]
  }
 ],
 "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}