{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Checking for available files in the folder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['bollywood_full_1950-2019.csv', 'MovieGenre.csv', 'Top_10000_Movies.csv']"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dirc = 'data'\n",
    "os.listdir(dirc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "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>imdbId</th>\n",
       "      <th>Imdb Link</th>\n",
       "      <th>Title</th>\n",
       "      <th>IMDB Score</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10164</th>\n",
       "      <td>437407</td>\n",
       "      <td>http://www.imdb.com/title/tt437407</td>\n",
       "      <td>Parineeta (2005)</td>\n",
       "      <td>7.3</td>\n",
       "      <td>Drama|Musical|Romance</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       imdbId                           Imdb Link             Title  \\\n",
       "10164  437407  http://www.imdb.com/title/tt437407  Parineeta (2005)   \n",
       "\n",
       "       IMDB Score                  Genre  \\\n",
       "10164         7.3  Drama|Musical|Romance   \n",
       "\n",
       "                                                  Poster  \n",
       "10164  https://images-na.ssl-images-amazon.com/images...  "
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data/MovieGenre.csv', encoding='latin-1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(40108, 6)"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 40108 entries, 0 to 40107\n",
      "Data columns (total 6 columns):\n",
      " #   Column      Non-Null Count  Dtype  \n",
      "---  ------      --------------  -----  \n",
      " 0   imdbId      40108 non-null  int64  \n",
      " 1   Imdb Link   40108 non-null  object \n",
      " 2   Title       40108 non-null  object \n",
      " 3   IMDB Score  40060 non-null  float64\n",
      " 4   Genre       39963 non-null  object \n",
      " 5   Poster      39383 non-null  object \n",
      "dtypes: float64(1), int64(1), object(4)\n",
      "memory usage: 1.8+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### DATA CLEANING :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "593"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop_duplicates(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "imdbId          0\n",
       "Imdb Link       0\n",
       "Title           0\n",
       "IMDB Score     48\n",
       "Genre         145\n",
       "Poster        724\n",
       "dtype: int64"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(38654, 6)"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "pop = df[df[\"IMDB Score\"] > 7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://images-na.ssl-images-amazon.com/images/M/MV5BMDU2ZWJlMjktMTRhMy00ZTA5LWEzNDgtYmNmZTEwZTViZWJkXkEyXkFqcGdeQXVyNDQ2OTk4MzI@._V1_UX182_CR0,0,182,268_AL_.jpg'"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[0,\"Poster\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(12345, 6)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "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>imdbId</th>\n",
       "      <th>Imdb Link</th>\n",
       "      <th>Title</th>\n",
       "      <th>IMDB Score</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>114709</td>\n",
       "      <td>http://www.imdb.com/title/tt114709</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "      <td>8.3</td>\n",
       "      <td>Animation|Adventure|Comedy</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   imdbId                           Imdb Link             Title  IMDB Score  \\\n",
       "0  114709  http://www.imdb.com/title/tt114709  Toy Story (1995)         8.3   \n",
       "\n",
       "                        Genre  \\\n",
       "0  Animation|Adventure|Comedy   \n",
       "\n",
       "                                              Poster  \n",
       "0  https://images-na.ssl-images-amazon.com/images...  "
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "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>imdbId</th>\n",
       "      <th>Imdb Link</th>\n",
       "      <th>Title</th>\n",
       "      <th>IMDB Score</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>114709</td>\n",
       "      <td>http://www.imdb.com/title/tt114709</td>\n",
       "      <td>Toy Story (1995)</td>\n",
       "      <td>8.3</td>\n",
       "      <td>Animation|Adventure|Comedy</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "      <td>1995</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   imdbId                           Imdb Link             Title  IMDB Score  \\\n",
       "0  114709  http://www.imdb.com/title/tt114709  Toy Story (1995)         8.3   \n",
       "\n",
       "                        Genre  \\\n",
       "0  Animation|Adventure|Comedy   \n",
       "\n",
       "                                              Poster  year  \n",
       "0  https://images-na.ssl-images-amazon.com/images...  1995  "
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop[\"year\"] = pop[\"Title\"].apply(lambda x: x[-5:-1])\n",
    "pop.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(11987, 7)"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "for i in pop[\"year\"]:\n",
    "    if not str(i).isdigit():\n",
    "        pop.drop(index = pop[pop[\"year\"]==i].index[0], inplace=True)\n",
    "pop.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [],
   "source": [
    "pop.reset_index(drop=True, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        1995\n",
       "1        1995\n",
       "2        1995\n",
       "3        1995\n",
       "4        1995\n",
       "         ... \n",
       "11982    2016\n",
       "11983    2009\n",
       "11984    1967\n",
       "11985    2014\n",
       "11986    2015\n",
       "Name: year, Length: 11987, dtype: int64"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.to_numeric(pop[\"year\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2017'"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max(pop[\"year\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [],
   "source": [
    "l = []\n",
    "def year(df) : \n",
    "    try : \n",
    "        if int(df['year']) > 1999 : \n",
    "            l.append(df.name)\n",
    "    except : \n",
    "        pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        None\n",
       "1        None\n",
       "2        None\n",
       "3        None\n",
       "4        None\n",
       "         ... \n",
       "11982    None\n",
       "11983    None\n",
       "11984    None\n",
       "11985    None\n",
       "11986    None\n",
       "Length: 11987, dtype: object"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop.apply(year, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = pop.iloc[l,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5431, 7)"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "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>index</th>\n",
       "      <th>imdbId</th>\n",
       "      <th>Imdb Link</th>\n",
       "      <th>Title</th>\n",
       "      <th>IMDB Score</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>1455</td>\n",
       "      <td>221073</td>\n",
       "      <td>http://www.imdb.com/title/tt221073</td>\n",
       "      <td>Chopper (2000)</td>\n",
       "      <td>7.2</td>\n",
       "      <td>Biography|Crime|Drama</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "      <td>2000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    index  imdbId                           Imdb Link           Title  \\\n",
       "61   1455  221073  http://www.imdb.com/title/tt221073  Chopper (2000)   \n",
       "\n",
       "    IMDB Score                  Genre  \\\n",
       "61         7.2  Biography|Crime|Drama   \n",
       "\n",
       "                                               Poster  year  \n",
       "61  https://images-na.ssl-images-amazon.com/images...  2000  "
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "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>Title</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3687</th>\n",
       "      <td>The Amazing Screw-On Head (2006)</td>\n",
       "      <td>Animation|Short|Action</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "      <td>2006</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 Title                   Genre  \\\n",
       "3687  The Amazing Screw-On Head (2006)  Animation|Short|Action   \n",
       "\n",
       "                                                 Poster  year  \n",
       "3687  https://images-na.ssl-images-amazon.com/images...  2006  "
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.drop(columns=[\"index\", \"imdbId\", \"Imdb Link\", \"IMDB Score\"], inplace=True)\n",
    "movies.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Title     0\n",
       "Genre     0\n",
       "Poster    0\n",
       "year      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "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>Title</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2165</th>\n",
       "      <td>War Horse (2011)</td>\n",
       "      <td>[Drama, War]</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "      <td>2011</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Title         Genre  \\\n",
       "2165  War Horse (2011)  [Drama, War]   \n",
       "\n",
       "                                                 Poster  year  \n",
       "2165  https://images-na.ssl-images-amazon.com/images...  2011  "
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"Genre\"] = movies[\"Genre\"].apply(lambda row: str(row).split(\"|\"))\n",
    "movies.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies[\"tags\"] = movies[\"Title\"].apply(lambda x: str(x)[:-6].split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies[\"tags\"] = movies[\"tags\"] + movies[\"Genre\"]\n",
    "movies[\"tags\"] = movies[\"tags\"].apply(lambda x: (\" \".join(x)).lower())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "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>Title</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "      <th>year</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>312</th>\n",
       "      <td>Revolution OS (2001)</td>\n",
       "      <td>[Documentary, Comedy]</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "      <td>2001</td>\n",
       "      <td>revolution os documentary comedy</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Title                  Genre  \\\n",
       "312  Revolution OS (2001)  [Documentary, Comedy]   \n",
       "\n",
       "                                                Poster  year  \\\n",
       "312  https://images-na.ssl-images-amazon.com/images...  2001   \n",
       "\n",
       "                                 tags  \n",
       "312  revolution os documentary comedy  "
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pickle import load\n",
    "bolly = load(open(\"movie_info.pkl\",\"rb\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "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>poster_path</th>\n",
       "      <th>original_title</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>summary</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1572</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Yaadein...</td>\n",
       "      <td>2001</td>\n",
       "      <td>[Drama, Musical, Romance]</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3034.0</td>\n",
       "      <td>[Raj, Singh, Puri, is, best, friends, with, L....</td>\n",
       "      <td>drama music romanc raj singh puri is best frie...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            poster_path original_title  \\\n",
       "1572  https://upload.wikimedia.org/wikipedia/en/thum...     Yaadein...   \n",
       "\n",
       "     year_of_release                     genres  imdb_rating  imdb_votes  \\\n",
       "1572            2001  [Drama, Musical, Romance]          4.4      3034.0   \n",
       "\n",
       "                                                summary  \\\n",
       "1572  [Raj, Singh, Puri, is, best, friends, with, L....   \n",
       "\n",
       "                                                   tags  \n",
       "1572  drama music romanc raj singh puri is best frie...  "
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bolly = pd.DataFrame(bolly)\n",
    "bolly.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "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>Title</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Poster</th>\n",
       "      <th>year</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1512</th>\n",
       "      <td>Ai no mukidashi (2008)</td>\n",
       "      <td>[Action, Comedy, Drama]</td>\n",
       "      <td>https://images-na.ssl-images-amazon.com/images...</td>\n",
       "      <td>2008</td>\n",
       "      <td>ai no mukidashi action comedy drama</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       Title                    Genre  \\\n",
       "1512  Ai no mukidashi (2008)  [Action, Comedy, Drama]   \n",
       "\n",
       "                                                 Poster  year  \\\n",
       "1512  https://images-na.ssl-images-amazon.com/images...  2008   \n",
       "\n",
       "                                     tags  \n",
       "1512  ai no mukidashi action comedy drama  "
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "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>Poster</th>\n",
       "      <th>Title</th>\n",
       "      <th>year</th>\n",
       "      <th>Genre</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>summary</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1490</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/commons...</td>\n",
       "      <td>Kaante</td>\n",
       "      <td>2002</td>\n",
       "      <td>[Action, Crime, Drama]</td>\n",
       "      <td>6.6</td>\n",
       "      <td>4267.0</td>\n",
       "      <td>[Six, bank, robbers, trying, to, pull, off, th...</td>\n",
       "      <td>action crime drama on or about 12may00 a truck...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Poster   Title  year  \\\n",
       "1490  https://upload.wikimedia.org/wikipedia/commons...  Kaante  2002   \n",
       "\n",
       "                       Genre  imdb_rating  imdb_votes  \\\n",
       "1490  [Action, Crime, Drama]          6.6      4267.0   \n",
       "\n",
       "                                                summary  \\\n",
       "1490  [Six, bank, robbers, trying, to, pull, off, th...   \n",
       "\n",
       "                                                   tags  \n",
       "1490  action crime drama on or about 12may00 a truck...  "
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bolly.rename(columns={\"poster_path\" : \"Poster\", \"original_title\" : \"Title\", \n",
    "                \"year_of_release\" : \"year\", \"genres\" : \"Genre\"}, inplace=True)\n",
    "\n",
    "bolly.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "bolly.shape \n",
    "bolly.reset_index(inplace=True)\n",
    "movies.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [],
   "source": [
    "new = pd.concat([bolly, movies]).drop(columns=[\"imdb_rating\",\"imdb_votes\",\"summary\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [],
   "source": [
    "new.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5431, 6)"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "level_0    0\n",
       "index      0\n",
       "Poster     0\n",
       "Title      0\n",
       "year       0\n",
       "Genre      0\n",
       "tags       0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7118 entries, 0 to 7117\n",
      "Data columns (total 7 columns):\n",
      " #   Column   Non-Null Count  Dtype \n",
      "---  ------   --------------  ----- \n",
      " 0   level_0  7118 non-null   int64 \n",
      " 1   index    7118 non-null   int64 \n",
      " 2   Poster   7118 non-null   object\n",
      " 3   Title    7118 non-null   object\n",
      " 4   year     7118 non-null   object\n",
      " 5   Genre    7118 non-null   object\n",
      " 6   tags     7118 non-null   object\n",
      "dtypes: int64(2), object(5)\n",
      "memory usage: 389.4+ KB\n"
     ]
    }
   ],
   "source": [
    "new.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "new[\"year\"] = pd.to_numeric(new[\"year\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7118 entries, 0 to 7117\n",
      "Data columns (total 7 columns):\n",
      " #   Column   Non-Null Count  Dtype \n",
      "---  ------   --------------  ----- \n",
      " 0   level_0  7118 non-null   int64 \n",
      " 1   index    7118 non-null   int64 \n",
      " 2   Poster   7118 non-null   object\n",
      " 3   Title    7118 non-null   object\n",
      " 4   year     7118 non-null   int64 \n",
      " 5   Genre    7118 non-null   object\n",
      " 6   tags     7118 non-null   object\n",
      "dtypes: int64(3), object(4)\n",
      "memory usage: 389.4+ KB\n"
     ]
    }
   ],
   "source": [
    "new.info()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ENCODING :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "cv = CountVectorizer(max_features=5000, stop_words='english')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectors = cv.fit_transform(new[\"tags\"]).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7118, 5000)"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectors.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "most_common_words = cv.get_feature_names_out()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "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>000</th>\n",
       "      <th>10</th>\n",
       "      <th>100</th>\n",
       "      <th>10th</th>\n",
       "      <th>11</th>\n",
       "      <th>11th</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>13th</th>\n",
       "      <th>14</th>\n",
       "      <th>...</th>\n",
       "      <th>zero</th>\n",
       "      <th>zinda</th>\n",
       "      <th>zindagi</th>\n",
       "      <th>zinta</th>\n",
       "      <th>zone</th>\n",
       "      <th>zooni</th>\n",
       "      <th>zoya</th>\n",
       "      <th>zubeida</th>\n",
       "      <th>zulfi</th>\n",
       "      <th>ìê</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7113</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7114</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7115</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7116</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7117</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7118 rows × 5000 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      000  10  100  10th  11  11th  12  13  13th  14  ...  zero  zinda  \\\n",
       "0       0   0    0     0   1     0   0   0     0   0  ...     0      0   \n",
       "1       0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "2       0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "3       0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "4       0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "...   ...  ..  ...   ...  ..   ...  ..  ..   ...  ..  ...   ...    ...   \n",
       "7113    0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "7114    0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "7115    0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "7116    0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "7117    0   0    0     0   0     0   0   0     0   0  ...     0      0   \n",
       "\n",
       "      zindagi  zinta  zone  zooni  zoya  zubeida  zulfi  ìê  \n",
       "0           0      0     0      0     0        0      0   0  \n",
       "1           0      0     0      0     0        0      0   0  \n",
       "2           0      0     0      0     0        0      0   0  \n",
       "3           0      0     0      0     0        0      0   0  \n",
       "4           0      0     0      0     0        0      0   0  \n",
       "...       ...    ...   ...    ...   ...      ...    ...  ..  \n",
       "7113        0      0     0      0     0        0      0   0  \n",
       "7114        0      0     0      0     0        0      0   0  \n",
       "7115        0      0     0      0     0        0      0   0  \n",
       "7116        0      0     0      0     0        0      0   0  \n",
       "7117        0      0     0      0     0        0      0   0  \n",
       "\n",
       "[7118 rows x 5000 columns]"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cs = pd.DataFrame(vectors, columns=most_common_words)\n",
    "# cs.to_csv(\"data\\common_words.csv\")\n",
    "cs"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### RECOMMENDATION ON THE BASIS OF DISTANCE BETWEEN VECTORS :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics.pairwise import cosine_similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [],
   "source": [
    "similarity = cosine_similarity(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [],
   "source": [
    "def recommended_movies(mov):\n",
    "    idx = new[new[\"Title\"] == mov].index[0]\n",
    "    corr = similarity[idx]\n",
    "    rec = sorted(list(enumerate(corr)), reverse=True, key=lambda x: x[1])[1:6]\n",
    "\n",
    "    for i in rec:\n",
    "        print(new.iloc[i[0]].Title)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Melancholian 3 huonetta (2004)\n",
      "The War on Democracy (2007)\n",
      "My First War (2008)\n",
      "Shooting War (2000)\n",
      "Armadillo (2010)\n"
     ]
    }
   ],
   "source": [
    "recommended_movies(\"Armadillo (2010)\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pickle import dump,load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dump(new, open(\"hollywood.pkl\", 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dump(similarity, open(\"sim_hollywood.pkl\", 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [],
   "source": [
    "data2 = load(open(\"hollywood.pkl\", 'rb'))\n",
    "holly = pd.DataFrame(data2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "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>level_0</th>\n",
       "      <th>index</th>\n",
       "      <th>Poster</th>\n",
       "      <th>Title</th>\n",
       "      <th>year</th>\n",
       "      <th>Genre</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>551</th>\n",
       "      <td>551</td>\n",
       "      <td>551</td>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>ROAR: Tigers of the Sundarbans</td>\n",
       "      <td>2014</td>\n",
       "      <td>[Action, Adventure, Sci-Fi]</td>\n",
       "      <td>action adventur sci-fi after hi photojournalis...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     level_0  index                                             Poster  \\\n",
       "551      551    551  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "                              Title  year                        Genre  \\\n",
       "551  ROAR: Tigers of the Sundarbans  2014  [Action, Adventure, Sci-Fi]   \n",
       "\n",
       "                                                  tags  \n",
       "551  action adventur sci-fi after hi photojournalis...  "
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holly.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7118, 7)"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holly.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "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>level_0</th>\n",
       "      <th>index</th>\n",
       "      <th>Poster</th>\n",
       "      <th>Title</th>\n",
       "      <th>year</th>\n",
       "      <th>Genre</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4913</th>\n",
       "      <td>3226</td>\n",
       "      <td>3226</td>\n",
       "      <td>http://ia.media-imdb.com/images/G/01/imdb/imag...</td>\n",
       "      <td>Slow Southern Steel (2010)</td>\n",
       "      <td>2010</td>\n",
       "      <td>[Documentary, History, Music]</td>\n",
       "      <td>slow southern steel documentary history music</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      level_0  index                                             Poster  \\\n",
       "4913     3226   3226  http://ia.media-imdb.com/images/G/01/imdb/imag...   \n",
       "\n",
       "                           Title  year                          Genre  \\\n",
       "4913  Slow Southern Steel (2010)  2010  [Documentary, History, Music]   \n",
       "\n",
       "                                               tags  \n",
       "4913  slow southern steel documentary history music  "
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holly.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Int64Index([0], dtype='int64')"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holly[holly[\"Title\"] == \"Uri: The Surgical Strike\"].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('Avatar (2009)',\n",
       " 'https://images-na.ssl-images-amazon.com/images/M/MV5BMTYwOTEwNjAzMl5BMl5BanBnXkFtZTcwODc5MTUwMw@@._V1_UX182_CR0,0,182,268_AL_.jpg',\n",
       " 'Action Adventure Fantasy',\n",
       " 2009,\n",
       " ' ',\n",
       " 3235)"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idx = holly[holly[\"Title\"] == \"Avatar (2009)\"].index[0]\n",
    "p = holly.iloc[idx].Poster\n",
    "l = holly.iloc[idx].Title\n",
    "c = \" \".join([holly.iloc[idx].Genre][0])\n",
    "y = holly.iloc[idx].year\n",
    "s = \" \"\n",
    "l,p,c,y,s,idx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "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>level_0</th>\n",
       "      <th>index</th>\n",
       "      <th>Poster</th>\n",
       "      <th>Title</th>\n",
       "      <th>year</th>\n",
       "      <th>Genre</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Uri: The Surgical Strike</td>\n",
       "      <td>2019</td>\n",
       "      <td>[Action, Drama, War]</td>\n",
       "      <td>action drama war divid over five chapter the f...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   level_0  index                                             Poster  \\\n",
       "0        0      0  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "                      Title  year                 Genre  \\\n",
       "0  Uri: The Surgical Strike  2019  [Action, Drama, War]   \n",
       "\n",
       "                                                tags  \n",
       "0  action drama war divid over five chapter the f...  "
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holly[holly[\"Title\"] == \"Uri: The Surgical Strike\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "level_0                                                 1548\n",
       "index                                                   1548\n",
       "Poster     https://upload.wikimedia.org/wikipedia/en/thum...\n",
       "Title                                                 Pyaasa\n",
       "year                                                    2002\n",
       "Genre                                                [Drama]\n",
       "tags       drama suraj thakur (aftab shivdasani) is one o...\n",
       "Name: 1548, dtype: object"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "holly.iloc[1548]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "706654849fe4d07e215a38f448ee8e5d780794e2be3793e11d37ab3169b306ae"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}