{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['bollywood_full_1950-2019.csv',\n",
       " 'common_words.csv',\n",
       " 'MovieGenre.csv',\n",
       " 'Top_10000_Movies.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dirc = 'data'\n",
    "os.listdir(dirc)"
   ]
  },
  {
   "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>title_x</th>\n",
       "      <th>imdb_id</th>\n",
       "      <th>poster_path</th>\n",
       "      <th>wiki_link</th>\n",
       "      <th>title_y</th>\n",
       "      <th>original_title</th>\n",
       "      <th>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>tagline</th>\n",
       "      <th>actors</th>\n",
       "      <th>wins_nominations</th>\n",
       "      <th>release_date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2559</th>\n",
       "      <td>Waaris (1988 film)</td>\n",
       "      <td>tt0367214</td>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Waaris_(1988_film)</td>\n",
       "      <td>Waaris</td>\n",
       "      <td>Waaris</td>\n",
       "      <td>0</td>\n",
       "      <td>1988</td>\n",
       "      <td>150</td>\n",
       "      <td>Drama</td>\n",
       "      <td>6.7</td>\n",
       "      <td>121.0</td>\n",
       "      <td>Multi-millionaire widower Kishan Singh prepare...</td>\n",
       "      <td>Multi-millionaire widower Kishan Singh prepare...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Smita Patil|Amrita Singh|Raj Babbar|Kulbhushan...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6 May 1988 (India)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 title_x    imdb_id  \\\n",
       "2559  Waaris (1988 film)  tt0367214   \n",
       "\n",
       "                                            poster_path  \\\n",
       "2559  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "                                             wiki_link title_y original_title  \\\n",
       "2559  https://en.wikipedia.org/wiki/Waaris_(1988_film)  Waaris         Waaris   \n",
       "\n",
       "      is_adult year_of_release runtime genres  imdb_rating  imdb_votes  \\\n",
       "2559         0            1988     150  Drama          6.7       121.0   \n",
       "\n",
       "                                                  story  \\\n",
       "2559  Multi-millionaire widower Kishan Singh prepare...   \n",
       "\n",
       "                                                summary tagline  \\\n",
       "2559  Multi-millionaire widower Kishan Singh prepare...     NaN   \n",
       "\n",
       "                                                 actors wins_nominations  \\\n",
       "2559  Smita Patil|Amrita Singh|Raj Babbar|Kulbhushan...              NaN   \n",
       "\n",
       "            release_date  \n",
       "2559  6 May 1988 (India)  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data/bollywood_full_1950-2019.csv')\n",
    "df.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4330, 18)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4330 entries, 0 to 4329\n",
      "Data columns (total 18 columns):\n",
      " #   Column            Non-Null Count  Dtype  \n",
      "---  ------            --------------  -----  \n",
      " 0   title_x           4330 non-null   object \n",
      " 1   imdb_id           4330 non-null   object \n",
      " 2   poster_path       3580 non-null   object \n",
      " 3   wiki_link         4330 non-null   object \n",
      " 4   title_y           4330 non-null   object \n",
      " 5   original_title    4330 non-null   object \n",
      " 6   is_adult          4330 non-null   int64  \n",
      " 7   year_of_release   4330 non-null   object \n",
      " 8   runtime           4330 non-null   object \n",
      " 9   genres            4330 non-null   object \n",
      " 10  imdb_rating       4317 non-null   float64\n",
      " 11  imdb_votes        4317 non-null   float64\n",
      " 12  story             4065 non-null   object \n",
      " 13  summary           4329 non-null   object \n",
      " 14  tagline           685 non-null    object \n",
      " 15  actors            4320 non-null   object \n",
      " 16  wins_nominations  1344 non-null   object \n",
      " 17  release_date      3049 non-null   object \n",
      "dtypes: float64(2), int64(1), object(15)\n",
      "memory usage: 609.0+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "l = []\n",
    "def year(df) : \n",
    "    try : \n",
    "        if int(df['year_of_release']) > 1999 : \n",
    "            l.append(df.name)\n",
    "    except : \n",
    "        pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       None\n",
       "1       None\n",
       "2       None\n",
       "3       None\n",
       "4       None\n",
       "        ... \n",
       "4325    None\n",
       "4326    None\n",
       "4327    None\n",
       "4328    None\n",
       "4329    None\n",
       "Length: 4330, dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.apply(year, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1687"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(l)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_df = df.iloc[l,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1687, 18)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_df.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>title_x</th>\n",
       "      <th>imdb_id</th>\n",
       "      <th>poster_path</th>\n",
       "      <th>wiki_link</th>\n",
       "      <th>title_y</th>\n",
       "      <th>original_title</th>\n",
       "      <th>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>tagline</th>\n",
       "      <th>actors</th>\n",
       "      <th>wins_nominations</th>\n",
       "      <th>release_date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1145</th>\n",
       "      <td>1151</td>\n",
       "      <td>Adharm (2006 film)</td>\n",
       "      <td>tt2435680</td>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Adharm_(2006_film)</td>\n",
       "      <td>Adharm</td>\n",
       "      <td>Adharm</td>\n",
       "      <td>0</td>\n",
       "      <td>2006</td>\n",
       "      <td>\\N</td>\n",
       "      <td>Action</td>\n",
       "      <td>5.1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>This story is inspired by true incident that h...</td>\n",
       "      <td>This story is inspired by true incident that h...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Rahul Dev|Mayuri Kango|Rocky Khanna|Anupam Khe...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      index             title_x    imdb_id  \\\n",
       "1145   1151  Adharm (2006 film)  tt2435680   \n",
       "\n",
       "                                            poster_path  \\\n",
       "1145  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "                                             wiki_link title_y original_title  \\\n",
       "1145  https://en.wikipedia.org/wiki/Adharm_(2006_film)  Adharm         Adharm   \n",
       "\n",
       "      is_adult year_of_release runtime  genres  imdb_rating  imdb_votes  \\\n",
       "1145         0            2006      \\N  Action          5.1         7.0   \n",
       "\n",
       "                                                  story  \\\n",
       "1145  This story is inspired by true incident that h...   \n",
       "\n",
       "                                                summary tagline  \\\n",
       "1145  This story is inspired by true incident that h...     NaN   \n",
       "\n",
       "                                                 actors wins_nominations  \\\n",
       "1145  Rahul Dev|Mayuri Kango|Rocky Khanna|Anupam Khe...              NaN   \n",
       "\n",
       "     release_date  \n",
       "1145          NaN  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://en.wikipedia.org/wiki/Uri:_The_Surgical_Strike'"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df[\"wiki_link\"][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "index                  0\n",
       "title_x                0\n",
       "imdb_id                0\n",
       "poster_path          111\n",
       "wiki_link              0\n",
       "title_y                0\n",
       "original_title         0\n",
       "is_adult               0\n",
       "year_of_release        0\n",
       "runtime                0\n",
       "genres                 0\n",
       "imdb_rating           12\n",
       "imdb_votes            12\n",
       "story                 20\n",
       "summary                0\n",
       "tagline             1106\n",
       "actors                 5\n",
       "wins_nominations     954\n",
       "release_date         113\n",
       "dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.isnull().sum()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Considering Only Important features :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['index', 'title_x', 'imdb_id', 'poster_path', 'wiki_link', 'title_y',\n",
       "       'original_title', 'is_adult', 'year_of_release', 'runtime', 'genres',\n",
       "       'imdb_rating', 'imdb_votes', 'story', 'summary', 'tagline', 'actors',\n",
       "       'wins_nominations', 'release_date'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# poster_path (required to show poster in the end (GUI))\n",
    "# original_title\n",
    "# is_adult \n",
    "# genres\n",
    "# imdb_rating\n",
    "# imdb_votes\n",
    "# story\n",
    "# summary\n",
    "# actors"
   ]
  },
  {
   "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>poster_path</th>\n",
       "      <th>original_title</th>\n",
       "      <th>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1017</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Chamku</td>\n",
       "      <td>0</td>\n",
       "      <td>2008</td>\n",
       "      <td>Action|Crime|Thriller</td>\n",
       "      <td>4.0</td>\n",
       "      <td>474.0</td>\n",
       "      <td>After witnessing his entire Bhagpur  Bihar-bas...</td>\n",
       "      <td>A traumatized child becomes a Naxalite  and up...</td>\n",
       "      <td>Bobby Deol|Priyanka Chopra|Irrfan Khan|Akhilen...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            poster_path original_title  \\\n",
       "1017  https://upload.wikimedia.org/wikipedia/en/thum...         Chamku   \n",
       "\n",
       "      is_adult year_of_release                 genres  imdb_rating  \\\n",
       "1017         0            2008  Action|Crime|Thriller          4.0   \n",
       "\n",
       "      imdb_votes                                              story  \\\n",
       "1017       474.0  After witnessing his entire Bhagpur  Bihar-bas...   \n",
       "\n",
       "                                                summary  \\\n",
       "1017  A traumatized child becomes a Naxalite  and up...   \n",
       "\n",
       "                                                 actors  \n",
       "1017  Bobby Deol|Priyanka Chopra|Irrfan Khan|Akhilen...  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = new_df.drop(columns=[\"index\",\"title_x\",\"imdb_id\",\"title_y\",\"runtime\",\"tagline\",'wins_nominations', 'release_date', \"wiki_link\"])\n",
    "data.sample()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ______________________________________________________________________________"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Dealing with NULL values :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "poster_path        111\n",
       "original_title       0\n",
       "is_adult             0\n",
       "year_of_release      0\n",
       "genres               0\n",
       "imdb_rating         12\n",
       "imdb_votes          12\n",
       "story               20\n",
       "summary              0\n",
       "actors               5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://upload.wikimedia.org/wikipedia/en/thumb/3/3b/URI_-_New_poster.jpg/220px-URI_-_New_poster.jpg'"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"poster_path\"][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Replacing the NULL poster links with 'image not available link' :\n",
    "\n",
    "data[\"poster_path\"].fillna(\"https://indianbankseauction.com/PropertyImages/nopreview.jpeg\", inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "data['imdb_rating'].fillna(0, inplace=True)\n",
    "data['imdb_votes'].fillna(0, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.fillna(\"\", inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "poster_path        0\n",
       "original_title     0\n",
       "is_adult           0\n",
       "year_of_release    0\n",
       "genres             0\n",
       "imdb_rating        0\n",
       "imdb_votes         0\n",
       "story              0\n",
       "summary            0\n",
       "actors             0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1687, 10)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.reset_index(drop = True, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>poster_path</th>\n",
       "      <th>original_title</th>\n",
       "      <th>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Uri: The Surgical Strike</td>\n",
       "      <td>0</td>\n",
       "      <td>2019</td>\n",
       "      <td>Action|Drama|War</td>\n",
       "      <td>8.4</td>\n",
       "      <td>35112.0</td>\n",
       "      <td>Divided over five chapters  the film chronicle...</td>\n",
       "      <td>Indian army special forces execute a covert op...</td>\n",
       "      <td>Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                         poster_path  \\\n",
       "0  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "             original_title  is_adult year_of_release            genres  \\\n",
       "0  Uri: The Surgical Strike         0            2019  Action|Drama|War   \n",
       "\n",
       "   imdb_rating  imdb_votes                                              story  \\\n",
       "0          8.4     35112.0  Divided over five chapters  the film chronicle...   \n",
       "\n",
       "                                             summary  \\\n",
       "0  Indian army special forces execute a covert op...   \n",
       "\n",
       "                                              actors  \n",
       "0  Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga...  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "def splitter(row):\n",
    "    return (str(row).split(\"|\"))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "data[\"genres\"] = data[\"genres\"].apply(splitter)\n",
    "data[\"actors\"] = data[\"actors\"].apply(splitter)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "data[\"num_actors\"] = data[\"actors\"].apply(lambda x: len(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "15"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max(data[\"num_actors\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# so as we can see no. of actors in a movie can be unto 15 that's why we will \n",
    "# create a func. to take only upto 4 actors into the consideration. \n",
    "\n",
    "data[\"actors\"] = data[\"actors\"].apply(lambda x: x[:4])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "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>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Uri: The Surgical Strike</td>\n",
       "      <td>0</td>\n",
       "      <td>2019</td>\n",
       "      <td>[Action, Drama, War]</td>\n",
       "      <td>8.4</td>\n",
       "      <td>35112.0</td>\n",
       "      <td>Divided over five chapters  the film chronicle...</td>\n",
       "      <td>Indian army special forces execute a covert op...</td>\n",
       "      <td>[Vicky Kaushal, Paresh Rawal, Mohit Raina, Yam...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                         poster_path  \\\n",
       "0  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "             original_title  is_adult year_of_release                genres  \\\n",
       "0  Uri: The Surgical Strike         0            2019  [Action, Drama, War]   \n",
       "\n",
       "   imdb_rating  imdb_votes                                              story  \\\n",
       "0          8.4     35112.0  Divided over five chapters  the film chronicle...   \n",
       "\n",
       "                                             summary  \\\n",
       "0  Indian army special forces execute a covert op...   \n",
       "\n",
       "                                              actors  \n",
       "0  [Vicky Kaushal, Paresh Rawal, Mohit Raina, Yam...  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.drop(columns=\"num_actors\", inplace=True)\n",
    "data.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "data[\"story\"] = data[\"story\"].apply(lambda x: str(x).split())\n",
    "data[\"summary\"] = data[\"summary\"].apply(lambda x: str(x).split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Uri: The Surgical Strike</td>\n",
       "      <td>0</td>\n",
       "      <td>2019</td>\n",
       "      <td>[Action, Drama, War]</td>\n",
       "      <td>8.4</td>\n",
       "      <td>35112.0</td>\n",
       "      <td>[Divided, over, five, chapters, the, film, chr...</td>\n",
       "      <td>[Indian, army, special, forces, execute, a, co...</td>\n",
       "      <td>[Vicky Kaushal, Paresh Rawal, Mohit Raina, Yam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>https://indianbankseauction.com/PropertyImages...</td>\n",
       "      <td>Battalion 609</td>\n",
       "      <td>0</td>\n",
       "      <td>2019</td>\n",
       "      <td>[War]</td>\n",
       "      <td>4.1</td>\n",
       "      <td>73.0</td>\n",
       "      <td>[The, story, revolves, around, a, cricket, mat...</td>\n",
       "      <td>[The, story, of, Battalion, 609, revolves, aro...</td>\n",
       "      <td>[Vicky Ahuja, Shoaib Ibrahim, Shrikant Kamat, ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                         poster_path  \\\n",
       "0  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "1  https://indianbankseauction.com/PropertyImages...   \n",
       "\n",
       "             original_title  is_adult year_of_release                genres  \\\n",
       "0  Uri: The Surgical Strike         0            2019  [Action, Drama, War]   \n",
       "1             Battalion 609         0            2019                 [War]   \n",
       "\n",
       "   imdb_rating  imdb_votes                                              story  \\\n",
       "0          8.4     35112.0  [Divided, over, five, chapters, the, film, chr...   \n",
       "1          4.1        73.0  [The, story, revolves, around, a, cricket, mat...   \n",
       "\n",
       "                                             summary  \\\n",
       "0  [Indian, army, special, forces, execute, a, co...   \n",
       "1  [The, story, of, Battalion, 609, revolves, aro...   \n",
       "\n",
       "                                              actors  \n",
       "0  [Vicky Kaushal, Paresh Rawal, Mohit Raina, Yam...  \n",
       "1  [Vicky Ahuja, Shoaib Ibrahim, Shrikant Kamat, ...  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1189</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Naksha</td>\n",
       "      <td>0</td>\n",
       "      <td>2006</td>\n",
       "      <td>[Action, Adventure, Fantasy]</td>\n",
       "      <td>3.1</td>\n",
       "      <td>916.0</td>\n",
       "      <td>[Bhagwan, Shri, Kishan, had, predicted, that, ...</td>\n",
       "      <td>[Bhagwan, Shri, Kishan, had, predicted, that, ...</td>\n",
       "      <td>[SunnyDeol, VivekOberoi, SameeraReddy, JackieS...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            poster_path original_title  \\\n",
       "1189  https://upload.wikimedia.org/wikipedia/en/thum...         Naksha   \n",
       "\n",
       "      is_adult year_of_release                        genres  imdb_rating  \\\n",
       "1189         0            2006  [Action, Adventure, Fantasy]          3.1   \n",
       "\n",
       "      imdb_votes                                              story  \\\n",
       "1189       916.0  [Bhagwan, Shri, Kishan, had, predicted, that, ...   \n",
       "\n",
       "                                                summary  \\\n",
       "1189  [Bhagwan, Shri, Kishan, had, predicted, that, ...   \n",
       "\n",
       "                                                 actors  \n",
       "1189  [SunnyDeol, VivekOberoi, SameeraReddy, JackieS...  "
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"genres\"] = data[\"genres\"].apply(lambda x: [i.replace(\" \",\"\") for i in x])\n",
    "data[\"story\"] = data[\"story\"].apply(lambda x: [i.replace(\" \",\"\") for i in x])\n",
    "data[\"summary\"] = data[\"summary\"].apply(lambda x: [i.replace(\" \",\"\") for i in x])\n",
    "data[\"actors\"] = data[\"actors\"].apply(lambda x: [i.replace(\" \",\"\") for i in x])\n",
    "data.sample()"
   ]
  },
  {
   "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>poster_path</th>\n",
       "      <th>original_title</th>\n",
       "      <th>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "      <th>title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Uri: The Surgical Strike</td>\n",
       "      <td>0</td>\n",
       "      <td>2019</td>\n",
       "      <td>[Action, Drama, War]</td>\n",
       "      <td>8.4</td>\n",
       "      <td>35112.0</td>\n",
       "      <td>[Divided, over, five, chapters, the, film, chr...</td>\n",
       "      <td>[Indian, army, special, forces, execute, a, co...</td>\n",
       "      <td>[VickyKaushal, PareshRawal, MohitRaina, YamiGa...</td>\n",
       "      <td>[Uri:, The, Surgical, Strike]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                         poster_path  \\\n",
       "0  https://upload.wikimedia.org/wikipedia/en/thum...   \n",
       "\n",
       "             original_title  is_adult year_of_release                genres  \\\n",
       "0  Uri: The Surgical Strike         0            2019  [Action, Drama, War]   \n",
       "\n",
       "   imdb_rating  imdb_votes                                              story  \\\n",
       "0          8.4     35112.0  [Divided, over, five, chapters, the, film, chr...   \n",
       "\n",
       "                                             summary  \\\n",
       "0  [Indian, army, special, forces, execute, a, co...   \n",
       "\n",
       "                                              actors  \\\n",
       "0  [VickyKaushal, PareshRawal, MohitRaina, YamiGa...   \n",
       "\n",
       "                           title  \n",
       "0  [Uri:, The, Surgical, Strike]  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"title\"] = data[\"original_title\"].apply(lambda x: str(x).split())\n",
    "data.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "data[\"tags\"] = data[\"genres\"] + data[\"story\"] + data[\"summary\"]+ data[\"actors\"]  + data[\"title\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies = data.drop(columns=[ \"story\",\"actors\", \"title\", \"is_adult\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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>197</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Raabta</td>\n",
       "      <td>2017</td>\n",
       "      <td>[Action, Adventure, Drama]</td>\n",
       "      <td>4.1</td>\n",
       "      <td>2667.0</td>\n",
       "      <td>[In, 2017, Shiv, and, Saira, fall, for, each, ...</td>\n",
       "      <td>action adventure drama in 2017 shiv and saira ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                           poster_path original_title  \\\n",
       "197  https://upload.wikimedia.org/wikipedia/en/thum...         Raabta   \n",
       "\n",
       "    year_of_release                      genres  imdb_rating  imdb_votes  \\\n",
       "197            2017  [Action, Adventure, Drama]          4.1      2667.0   \n",
       "\n",
       "                                               summary  \\\n",
       "197  [In, 2017, Shiv, and, Saira, fall, for, each, ...   \n",
       "\n",
       "                                                  tags  \n",
       "197  action adventure drama in 2017 shiv and saira ...  "
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"tags\"] = movies[\"tags\"].apply(lambda x: (\" \".join(x)).lower())\n",
    "movies.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"crime thriller akash a blind pianist is preparing for a london concert.sophie's scooter bumps into akash and upon finding he a pianist she takes him to her restaurant franco's run by her father and offers him a job.akash meets 70s actor pramod sinha at the restaurant who asks him to do a private concert of his songs at his residence to surprise his wife simi. next day upon reaching his house a shocking surprise is waiting for akash. a series of mysterious events changes the life of a blind pianist who must now report a crime that he should technically know nothing of. ayushmannkhurrana tabu radhikaapte anildhawan andhadhun\""
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"tags\"][145]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "from nltk.stem.porter import PorterStemmer\n",
    "ps = PorterStemmer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stem(text):\n",
    "    word=[]\n",
    "\n",
    "    for i in text.split():\n",
    "        word.append(ps.stem(i))\n",
    "\n",
    "    return \" \".join(word)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies[\"tags\"] = movies[\"tags\"].apply(stem)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"crime thriller akash a blind pianist is prepar for a london concert.sophie' scooter bump into akash and upon find he a pianist she take him to her restaur franco' run by her father and offer him a job.akash meet 70 actor pramod sinha at the restaur who ask him to do a privat concert of hi song at hi resid to surpris hi wife simi. next day upon reach hi hous a shock surpris is wait for akash. a seri of mysteri event chang the life of a blind pianist who must now report a crime that he should technic know noth of. ayushmannkhurrana tabu radhikaapt anildhawan andhadhun\""
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"tags\"][145]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "cv = CountVectorizer(max_features=5000, stop_words='english')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectors = cv.fit_transform(movies[\"tags\"]).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1687, 5000)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectors.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       ...,\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0]], dtype=int64)"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "frozenset({'a',\n",
       "           'about',\n",
       "           'above',\n",
       "           'across',\n",
       "           'after',\n",
       "           'afterwards',\n",
       "           'again',\n",
       "           'against',\n",
       "           'all',\n",
       "           'almost',\n",
       "           'alone',\n",
       "           'along',\n",
       "           'already',\n",
       "           'also',\n",
       "           'although',\n",
       "           'always',\n",
       "           'am',\n",
       "           'among',\n",
       "           'amongst',\n",
       "           'amoungst',\n",
       "           'amount',\n",
       "           'an',\n",
       "           'and',\n",
       "           'another',\n",
       "           'any',\n",
       "           'anyhow',\n",
       "           'anyone',\n",
       "           'anything',\n",
       "           'anyway',\n",
       "           'anywhere',\n",
       "           'are',\n",
       "           'around',\n",
       "           'as',\n",
       "           'at',\n",
       "           'back',\n",
       "           'be',\n",
       "           'became',\n",
       "           'because',\n",
       "           'become',\n",
       "           'becomes',\n",
       "           'becoming',\n",
       "           'been',\n",
       "           'before',\n",
       "           'beforehand',\n",
       "           'behind',\n",
       "           'being',\n",
       "           'below',\n",
       "           'beside',\n",
       "           'besides',\n",
       "           'between',\n",
       "           'beyond',\n",
       "           'bill',\n",
       "           'both',\n",
       "           'bottom',\n",
       "           'but',\n",
       "           'by',\n",
       "           'call',\n",
       "           'can',\n",
       "           'cannot',\n",
       "           'cant',\n",
       "           'co',\n",
       "           'con',\n",
       "           'could',\n",
       "           'couldnt',\n",
       "           'cry',\n",
       "           'de',\n",
       "           'describe',\n",
       "           'detail',\n",
       "           'do',\n",
       "           'done',\n",
       "           'down',\n",
       "           'due',\n",
       "           'during',\n",
       "           'each',\n",
       "           'eg',\n",
       "           'eight',\n",
       "           'either',\n",
       "           'eleven',\n",
       "           'else',\n",
       "           'elsewhere',\n",
       "           'empty',\n",
       "           'enough',\n",
       "           'etc',\n",
       "           'even',\n",
       "           'ever',\n",
       "           'every',\n",
       "           'everyone',\n",
       "           'everything',\n",
       "           'everywhere',\n",
       "           'except',\n",
       "           'few',\n",
       "           'fifteen',\n",
       "           'fifty',\n",
       "           'fill',\n",
       "           'find',\n",
       "           'fire',\n",
       "           'first',\n",
       "           'five',\n",
       "           'for',\n",
       "           'former',\n",
       "           'formerly',\n",
       "           'forty',\n",
       "           'found',\n",
       "           'four',\n",
       "           'from',\n",
       "           'front',\n",
       "           'full',\n",
       "           'further',\n",
       "           'get',\n",
       "           'give',\n",
       "           'go',\n",
       "           'had',\n",
       "           'has',\n",
       "           'hasnt',\n",
       "           'have',\n",
       "           'he',\n",
       "           'hence',\n",
       "           'her',\n",
       "           'here',\n",
       "           'hereafter',\n",
       "           'hereby',\n",
       "           'herein',\n",
       "           'hereupon',\n",
       "           'hers',\n",
       "           'herself',\n",
       "           'him',\n",
       "           'himself',\n",
       "           'his',\n",
       "           'how',\n",
       "           'however',\n",
       "           'hundred',\n",
       "           'i',\n",
       "           'ie',\n",
       "           'if',\n",
       "           'in',\n",
       "           'inc',\n",
       "           'indeed',\n",
       "           'interest',\n",
       "           'into',\n",
       "           'is',\n",
       "           'it',\n",
       "           'its',\n",
       "           'itself',\n",
       "           'keep',\n",
       "           'last',\n",
       "           'latter',\n",
       "           'latterly',\n",
       "           'least',\n",
       "           'less',\n",
       "           'ltd',\n",
       "           'made',\n",
       "           'many',\n",
       "           'may',\n",
       "           'me',\n",
       "           'meanwhile',\n",
       "           'might',\n",
       "           'mill',\n",
       "           'mine',\n",
       "           'more',\n",
       "           'moreover',\n",
       "           'most',\n",
       "           'mostly',\n",
       "           'move',\n",
       "           'much',\n",
       "           'must',\n",
       "           'my',\n",
       "           'myself',\n",
       "           'name',\n",
       "           'namely',\n",
       "           'neither',\n",
       "           'never',\n",
       "           'nevertheless',\n",
       "           'next',\n",
       "           'nine',\n",
       "           'no',\n",
       "           'nobody',\n",
       "           'none',\n",
       "           'noone',\n",
       "           'nor',\n",
       "           'not',\n",
       "           'nothing',\n",
       "           'now',\n",
       "           'nowhere',\n",
       "           'of',\n",
       "           'off',\n",
       "           'often',\n",
       "           'on',\n",
       "           'once',\n",
       "           'one',\n",
       "           'only',\n",
       "           'onto',\n",
       "           'or',\n",
       "           'other',\n",
       "           'others',\n",
       "           'otherwise',\n",
       "           'our',\n",
       "           'ours',\n",
       "           'ourselves',\n",
       "           'out',\n",
       "           'over',\n",
       "           'own',\n",
       "           'part',\n",
       "           'per',\n",
       "           'perhaps',\n",
       "           'please',\n",
       "           'put',\n",
       "           'rather',\n",
       "           're',\n",
       "           'same',\n",
       "           'see',\n",
       "           'seem',\n",
       "           'seemed',\n",
       "           'seeming',\n",
       "           'seems',\n",
       "           'serious',\n",
       "           'several',\n",
       "           'she',\n",
       "           'should',\n",
       "           'show',\n",
       "           'side',\n",
       "           'since',\n",
       "           'sincere',\n",
       "           'six',\n",
       "           'sixty',\n",
       "           'so',\n",
       "           'some',\n",
       "           'somehow',\n",
       "           'someone',\n",
       "           'something',\n",
       "           'sometime',\n",
       "           'sometimes',\n",
       "           'somewhere',\n",
       "           'still',\n",
       "           'such',\n",
       "           'system',\n",
       "           'take',\n",
       "           'ten',\n",
       "           'than',\n",
       "           'that',\n",
       "           'the',\n",
       "           'their',\n",
       "           'them',\n",
       "           'themselves',\n",
       "           'then',\n",
       "           'thence',\n",
       "           'there',\n",
       "           'thereafter',\n",
       "           'thereby',\n",
       "           'therefore',\n",
       "           'therein',\n",
       "           'thereupon',\n",
       "           'these',\n",
       "           'they',\n",
       "           'thick',\n",
       "           'thin',\n",
       "           'third',\n",
       "           'this',\n",
       "           'those',\n",
       "           'though',\n",
       "           'three',\n",
       "           'through',\n",
       "           'throughout',\n",
       "           'thru',\n",
       "           'thus',\n",
       "           'to',\n",
       "           'together',\n",
       "           'too',\n",
       "           'top',\n",
       "           'toward',\n",
       "           'towards',\n",
       "           'twelve',\n",
       "           'twenty',\n",
       "           'two',\n",
       "           'un',\n",
       "           'under',\n",
       "           'until',\n",
       "           'up',\n",
       "           'upon',\n",
       "           'us',\n",
       "           'very',\n",
       "           'via',\n",
       "           'was',\n",
       "           'we',\n",
       "           'well',\n",
       "           'were',\n",
       "           'what',\n",
       "           'whatever',\n",
       "           'when',\n",
       "           'whence',\n",
       "           'whenever',\n",
       "           'where',\n",
       "           'whereafter',\n",
       "           'whereas',\n",
       "           'whereby',\n",
       "           'wherein',\n",
       "           'whereupon',\n",
       "           'wherever',\n",
       "           'whether',\n",
       "           'which',\n",
       "           'while',\n",
       "           'whither',\n",
       "           'who',\n",
       "           'whoever',\n",
       "           'whole',\n",
       "           'whom',\n",
       "           'whose',\n",
       "           'why',\n",
       "           'will',\n",
       "           'with',\n",
       "           'within',\n",
       "           'without',\n",
       "           'would',\n",
       "           'yet',\n",
       "           'you',\n",
       "           'your',\n",
       "           'yours',\n",
       "           'yourself',\n",
       "           'yourselves'})"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv.get_stop_words()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "most_common_words = cv.get_feature_names_out()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "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>125</th>\n",
       "      <th>13</th>\n",
       "      <th>13th</th>\n",
       "      <th>...</th>\n",
       "      <th>zeenat</th>\n",
       "      <th>zeenataman</th>\n",
       "      <th>zero</th>\n",
       "      <th>zinda</th>\n",
       "      <th>zindagi</th>\n",
       "      <th>zinta</th>\n",
       "      <th>zooni</th>\n",
       "      <th>zoya</th>\n",
       "      <th>zubeida</th>\n",
       "      <th>zulfi</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>1682</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>1683</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>1684</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>1685</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>1686</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>1687 rows × 5000 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      000  10  100  10th  11  11th  12  125  13  13th  ...  zeenat  \\\n",
       "0       0   0    0     0   1     0   0    0   0     0  ...       0   \n",
       "1       0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "2       0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "3       0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "4       0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "...   ...  ..  ...   ...  ..   ...  ..  ...  ..   ...  ...     ...   \n",
       "1682    0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "1683    0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "1684    0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "1685    0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "1686    0   0    0     0   0     0   0    0   0     0  ...       0   \n",
       "\n",
       "      zeenataman  zero  zinda  zindagi  zinta  zooni  zoya  zubeida  zulfi  \n",
       "0              0     0      0        0      0      0     0        0      0  \n",
       "1              0     0      0        0      0      0     0        0      0  \n",
       "2              0     0      0        0      0      0     0        0      0  \n",
       "3              0     0      0        0      0      0     0        0      0  \n",
       "4              0     0      0        0      0      0     0        0      0  \n",
       "...          ...   ...    ...      ...    ...    ...   ...      ...    ...  \n",
       "1682           0     0      0        0      0      0     0        0      0  \n",
       "1683           0     0      0        0      0      0     0        0      0  \n",
       "1684           0     0      0        0      0      0     0        0      0  \n",
       "1685           0     0      0        0      0      0     0        0      0  \n",
       "1686           0     0      0        0      0      0     0        0      0  \n",
       "\n",
       "[1687 rows x 5000 columns]"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cs = pd.DataFrame(vectors, columns=most_common_words)\n",
    "cs.to_csv(\"data\\common_words.csv\")\n",
    "cs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Euclidian distance is not a good method for high-demensions, so we'll use Cosine Similarity.\n",
    "from sklearn.metrics.pairwise import cosine_similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "similarity = cosine_similarity(vectors)             # Relation of a movie with other movies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1.        , 0.30833492, 0.06123412, ..., 0.02261078, 0.01049901,\n",
       "       0.06855751])"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# As, correlation of movie 1 with movie 1 will always be equal to 1, so all the diagonal elements would be 1.as_integer_ratio\n",
    "\n",
    "similarity[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1687, 1687)"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "similarity.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(0, 1.0),\n",
       " (218, 0.34341479757995447),\n",
       " (1, 0.3083349194223892),\n",
       " (166, 0.30604692017553103),\n",
       " (1487, 0.3031960178847318),\n",
       " (1535, 0.2721655269759087),\n",
       " (1426, 0.22416986876995007),\n",
       " (127, 0.22371868507134143),\n",
       " (22, 0.21667041532219725),\n",
       " (667, 0.21650635094610968),\n",
       " (1497, 0.21103396143486278),\n",
       " (269, 0.20775007961358385),\n",
       " (1444, 0.20659326226697075),\n",
       " (1038, 0.2056971041128498),\n",
       " (1313, 0.1965021149155211),\n",
       " (255, 0.19444444444444448),\n",
       " (1301, 0.18371173070873836),\n",
       " (715, 0.18219813149998287),\n",
       " (835, 0.17891501337389773),\n",
       " (1331, 0.17757784879581398),\n",
       " (287, 0.17690759253434063),\n",
       " (373, 0.17391639824998362),\n",
       " (335, 0.17213259316477408),\n",
       " (924, 0.1700204568168902),\n",
       " (105, 0.1683064344266991),\n",
       " (865, 0.16601941503058407),\n",
       " (894, 0.1653060996890293),\n",
       " (158, 0.16453801395794543),\n",
       " (50, 0.16239245061540775),\n",
       " (58, 0.16139400871168066),\n",
       " (1360, 0.16118270179676272),\n",
       " (950, 0.15811388300841894),\n",
       " (497, 0.15555555555555556),\n",
       " (168, 0.1547461151475432),\n",
       " (364, 0.15408338784034142),\n",
       " (1483, 0.1534255013186446),\n",
       " (41, 0.1529438225803745),\n",
       " (595, 0.1527777777777778),\n",
       " (624, 0.15097027121927947),\n",
       " (440, 0.15059374348566512),\n",
       " (1145, 0.1484575537959652),\n",
       " (1009, 0.14638501094227996),\n",
       " (1328, 0.14483345242495155),\n",
       " (42, 0.14349100534871306),\n",
       " (1369, 0.14285714285714285),\n",
       " (483, 0.1396930126874916),\n",
       " (1353, 0.1388888888888889),\n",
       " (1241, 0.13882112167876096),\n",
       " (1634, 0.13636480060602701),\n",
       " (909, 0.1357813616483921),\n",
       " (577, 0.13552389967500503),\n",
       " (1238, 0.135381903394124),\n",
       " (659, 0.13489077471234956),\n",
       " (68, 0.13471506281091267),\n",
       " (1671, 0.13295400586957762),\n",
       " (574, 0.13230943668928924),\n",
       " (496, 0.1312159702703695),\n",
       " (493, 0.13105951658213078),\n",
       " (968, 0.13074409009212268),\n",
       " (1390, 0.13013931011614385),\n",
       " (1569, 0.12803687993289598),\n",
       " (1236, 0.1267916223003882),\n",
       " (416, 0.1252448582170299),\n",
       " (760, 0.12487810821089254),\n",
       " (779, 0.12487810821089254),\n",
       " (351, 0.1242259987499883),\n",
       " (1553, 0.12376844287208426),\n",
       " (122, 0.1200137166371826),\n",
       " (1070, 0.11952286093343938),\n",
       " (443, 0.11909826683508273),\n",
       " (438, 0.11873260194275806),\n",
       " (525, 0.11844484241978356),\n",
       " (457, 0.11755760264309971),\n",
       " (98, 0.11688906406161201),\n",
       " (293, 0.11669000700233415),\n",
       " (411, 0.11669000700233415),\n",
       " (1018, 0.11637608921255717),\n",
       " (1326, 0.11586227443356203),\n",
       " (1357, 0.11509484552229768),\n",
       " (1400, 0.11494271803476605),\n",
       " (1401, 0.11494271803476605),\n",
       " (219, 0.11480778669894409),\n",
       " (663, 0.1147550621098494),\n",
       " (470, 0.11419811830458859),\n",
       " (331, 0.11396057645963795),\n",
       " (144, 0.11385500851066219),\n",
       " (805, 0.1137539387983225),\n",
       " (285, 0.11274690420042435),\n",
       " (176, 0.11270870433342904),\n",
       " (131, 0.11262289639991432),\n",
       " (1324, 0.11106914279569094),\n",
       " (796, 0.11013785635132559),\n",
       " (833, 0.1097134314340639),\n",
       " (899, 0.10929387566615228),\n",
       " (7, 0.10926834468453098),\n",
       " (1397, 0.10910894511799618),\n",
       " (621, 0.10786315658047482),\n",
       " (1233, 0.10691671651659736),\n",
       " (915, 0.10650160840378228),\n",
       " (1194, 0.10611908999450222),\n",
       " (1159, 0.10610212315611824),\n",
       " (1191, 0.10580184237878974),\n",
       " (1329, 0.10549170295056474),\n",
       " (292, 0.10532224809726146),\n",
       " (1293, 0.10524493839518115),\n",
       " (366, 0.10499013139145202),\n",
       " (367, 0.10499013139145202),\n",
       " (332, 0.10497277621629561),\n",
       " (931, 0.1049727762162956),\n",
       " (491, 0.10497277621629558),\n",
       " (359, 0.10480469092042208),\n",
       " (432, 0.1047565601757848),\n",
       " (531, 0.10437071518085826),\n",
       " (1203, 0.10429644129291062),\n",
       " (1106, 0.10277830647412974),\n",
       " (78, 0.10206207261596575),\n",
       " (1456, 0.10125804187397412),\n",
       " (552, 0.10041067934611822),\n",
       " (1660, 0.10041067934611822),\n",
       " (33, 0.1002194704003772),\n",
       " (318, 0.1002194704003772),\n",
       " (474, 0.10015420209622192),\n",
       " (934, 0.09999999999999998),\n",
       " (1262, 0.09960238411119947),\n",
       " (1466, 0.09951829597116882),\n",
       " (879, 0.09938079899999067),\n",
       " (115, 0.09913531291324379),\n",
       " (1274, 0.09829463743659808),\n",
       " (532, 0.09820927516479827),\n",
       " (782, 0.09798005352332918),\n",
       " (1057, 0.0975900072948533),\n",
       " (456, 0.09743547036924464),\n",
       " (408, 0.09698572899377438),\n",
       " (687, 0.09698572899377436),\n",
       " (1017, 0.09622504486493763),\n",
       " (883, 0.09566067023247539),\n",
       " (1340, 0.0951061109496652),\n",
       " (14, 0.09496714704969829),\n",
       " (1373, 0.09483242373202184),\n",
       " (1661, 0.09476225544736291),\n",
       " (23, 0.09459675396808044),\n",
       " (1256, 0.09455143815519593),\n",
       " (582, 0.09435641951204965),\n",
       " (1252, 0.09365858115816941),\n",
       " (537, 0.0935568998979686),\n",
       " (187, 0.09340808971963417),\n",
       " (1623, 0.09304842103984709),\n",
       " (1317, 0.09296222517045284),\n",
       " (1399, 0.09296222517045283),\n",
       " (473, 0.09247943325597503),\n",
       " (279, 0.09245003270420485),\n",
       " (654, 0.09212846639876111),\n",
       " (1601, 0.09200874124564723),\n",
       " (82, 0.09179850920431568),\n",
       " (890, 0.09143835580986637),\n",
       " (268, 0.09128709291752768),\n",
       " (1421, 0.09128709291752768),\n",
       " (513, 0.09016696346674324),\n",
       " (507, 0.09012301173931253),\n",
       " (481, 0.09001028747788695),\n",
       " (551, 0.08980265101338746),\n",
       " (1524, 0.08961112680829966),\n",
       " (111, 0.08948747402853659),\n",
       " (651, 0.08948747402853657),\n",
       " (1298, 0.08934271123648291),\n",
       " (1639, 0.08921722983855179),\n",
       " (606, 0.08913971702649112),\n",
       " (477, 0.0890870806374748),\n",
       " (798, 0.08908708063747478),\n",
       " (892, 0.08882529023711003),\n",
       " (1120, 0.08882529023711003),\n",
       " (1185, 0.08867576348258963),\n",
       " (124, 0.08793155726408239),\n",
       " (1657, 0.08779776400125336),\n",
       " (1383, 0.08748177652797064),\n",
       " (1065, 0.08744344477119373),\n",
       " (152, 0.08716272672808179),\n",
       " (157, 0.08703882797784893),\n",
       " (183, 0.08703882797784893),\n",
       " (611, 0.08703882797784893),\n",
       " (940, 0.0868810058571145),\n",
       " (1342, 0.08671369113740707),\n",
       " (699, 0.08632206622970622),\n",
       " (1163, 0.08632206622970622),\n",
       " (1512, 0.0863220662297062),\n",
       " (1428, 0.08613751405140559),\n",
       " (1380, 0.08554415042912275),\n",
       " (435, 0.08486251286955257),\n",
       " (1549, 0.08451542547285168),\n",
       " (426, 0.08399210511316162),\n",
       " (797, 0.0839921051131616),\n",
       " (216, 0.08394256685753218),\n",
       " (674, 0.08341955511876983),\n",
       " (560, 0.08333333333333334),\n",
       " (199, 0.08312577800896942),\n",
       " (855, 0.08300970751529203),\n",
       " (1559, 0.08240220541217404),\n",
       " (670, 0.08206099398622184),\n",
       " (1031, 0.08190729279494122),\n",
       " (104, 0.08168300490163391),\n",
       " (215, 0.08168300490163391),\n",
       " (1438, 0.08164965809277261),\n",
       " (789, 0.08161701781239863),\n",
       " (70, 0.08146881698903526),\n",
       " (110, 0.08144629623753681),\n",
       " (1584, 0.08108546209455464),\n",
       " (1166, 0.0807502638519182),\n",
       " (378, 0.08058638469539994),\n",
       " (1602, 0.08040844011283461),\n",
       " (908, 0.08018753738744802),\n",
       " (77, 0.08006407690254358),\n",
       " (1044, 0.08006407690254357),\n",
       " (545, 0.08001322641986387),\n",
       " (1625, 0.07911417286705225),\n",
       " (361, 0.07830153977496952),\n",
       " (419, 0.07772873369453565),\n",
       " (424, 0.07754035086653924),\n",
       " (181, 0.07745966692414834),\n",
       " (517, 0.07745966692414832),\n",
       " (579, 0.07736784709142126),\n",
       " (133, 0.07726438749546088),\n",
       " (1155, 0.076847327936784),\n",
       " (99, 0.07684732793678399),\n",
       " (921, 0.07654655446197431),\n",
       " (1679, 0.07613869876268811),\n",
       " (1577, 0.07613869876268808),\n",
       " (1076, 0.07607257743127308),\n",
       " (881, 0.07580980435789034),\n",
       " (1500, 0.07580980435789032),\n",
       " (809, 0.07566499084579775),\n",
       " (1218, 0.07522257782070334),\n",
       " (386, 0.07516460280028289),\n",
       " (1332, 0.07491109582924912),\n",
       " (1321, 0.0747696205456059),\n",
       " (1505, 0.07453559924999298),\n",
       " (12, 0.07423923386456233),\n",
       " (917, 0.07423923386456233),\n",
       " (1673, 0.07410810764999062),\n",
       " (555, 0.07407407407407407),\n",
       " (709, 0.07372097807744857),\n",
       " (1268, 0.07358513094805799),\n",
       " (681, 0.0734930919740164),\n",
       " (225, 0.07345531603115878),\n",
       " (1557, 0.07333055637076138),\n",
       " (1307, 0.07302967433402215),\n",
       " (1183, 0.07294801825540143),\n",
       " (1598, 0.07273929674533079),\n",
       " (1498, 0.07267523746672638),\n",
       " (148, 0.07241672621247579),\n",
       " (1344, 0.07241672621247579),\n",
       " (1654, 0.07241672621247579),\n",
       " (138, 0.07216878364870322),\n",
       " (689, 0.0721021519443032),\n",
       " (1210, 0.07202013512085205),\n",
       " (347, 0.07180336973794409),\n",
       " (1096, 0.07178425360775541),\n",
       " (1117, 0.07178425360775541),\n",
       " (795, 0.07152351257047909),\n",
       " (162, 0.07147416898918632),\n",
       " (620, 0.07147416898918632),\n",
       " (1107, 0.07136240321480627),\n",
       " (165, 0.07106690545187014),\n",
       " (596, 0.07093804422989572),\n",
       " (1035, 0.07086586712703119),\n",
       " (169, 0.07017932675554325),\n",
       " (893, 0.07009925201600498),\n",
       " (479, 0.0700140042014005),\n",
       " (1423, 0.06999342092763468),\n",
       " (1306, 0.06978631577988531),\n",
       " (1085, 0.06969444979857556),\n",
       " (454, 0.06944444444444446),\n",
       " (1543, 0.06944444444444445),\n",
       " (718, 0.06900655593423542),\n",
       " (725, 0.06875537172325702),\n",
       " (961, 0.06874649261535878),\n",
       " (1618, 0.06865346047348511),\n",
       " (1686, 0.0685575058158106),\n",
       " (800, 0.068308735943808),\n",
       " (1534, 0.0682523632789935),\n",
       " (427, 0.06804138174397717),\n",
       " (436, 0.06804138174397717),\n",
       " (1099, 0.06804138174397717),\n",
       " (744, 0.06804138174397716),\n",
       " (1597, 0.06787191353128069),\n",
       " (1384, 0.0676115519099702),\n",
       " (390, 0.0675737378399486),\n",
       " (71, 0.06737100695453693),\n",
       " (874, 0.06737100695453693),\n",
       " (128, 0.06735753140545635),\n",
       " (929, 0.06735753140545635),\n",
       " (888, 0.0672577696407091),\n",
       " (535, 0.06721326105145359),\n",
       " (178, 0.06720648654545931),\n",
       " (75, 0.06672006408545297),\n",
       " (175, 0.06672006408545297),\n",
       " (1105, 0.06672006408545297),\n",
       " (121, 0.06666666666666665),\n",
       " (1627, 0.06641465930020336),\n",
       " (170, 0.06600983619844494),\n",
       " (1325, 0.06584269219592206),\n",
       " (678, 0.0657951694959769),\n",
       " (1646, 0.06577808649698821),\n",
       " (623, 0.06573421981221797),\n",
       " (1614, 0.06573421981221797),\n",
       " (296, 0.06542341797740515),\n",
       " (751, 0.06537204504606134),\n",
       " (1053, 0.06502285955340587),\n",
       " (567, 0.0649569802461631),\n",
       " (1352, 0.06487491201346025),\n",
       " (460, 0.06481481481481483),\n",
       " (73, 0.06454972243679027),\n",
       " (1350, 0.0643711613134312),\n",
       " (1664, 0.06429306248420497),\n",
       " (1403, 0.06401843996644799),\n",
       " (1028, 0.06393293950763894),\n",
       " (38, 0.06372659274182271),\n",
       " (109, 0.06364688465216445),\n",
       " (49, 0.06337242505244779),\n",
       " (1455, 0.06337242505244779),\n",
       " (134, 0.06336463543591632),\n",
       " (978, 0.06327719971683327),\n",
       " (164, 0.06317483696490861),\n",
       " (1337, 0.06314335411250997),\n",
       " (864, 0.06308610821751877),\n",
       " (799, 0.06306450264538696),\n",
       " (1272, 0.0627702980962258),\n",
       " (254, 0.06264546476465861),\n",
       " (538, 0.06262242910851495),\n",
       " (519, 0.06250000000000001),\n",
       " (948, 0.06250000000000001),\n",
       " (1405, 0.062257280636469035),\n",
       " (767, 0.06203228069323139),\n",
       " (974, 0.06189844605901729),\n",
       " (1244, 0.06189844605901729),\n",
       " (588, 0.06163335513613657),\n",
       " (849, 0.06163335513613656),\n",
       " (1672, 0.06160177257954774),\n",
       " (949, 0.061545745489666376),\n",
       " (1496, 0.061545745489666376),\n",
       " (975, 0.06154574548966636),\n",
       " (1636, 0.061475926130276456),\n",
       " (383, 0.06143675701121218),\n",
       " (944, 0.06123724356957945),\n",
       " (2, 0.06123411945950577),\n",
       " (203, 0.06119900613621046),\n",
       " (657, 0.06098264357375362),\n",
       " (791, 0.060858061945018464),\n",
       " (952, 0.060858061945018464),\n",
       " (295, 0.06085806194501846),\n",
       " (1566, 0.06085806194501846),\n",
       " (1567, 0.06085806194501846),\n",
       " (858, 0.06085806194501845),\n",
       " (1064, 0.06073424073445792),\n",
       " (252, 0.06063390625908324),\n",
       " (1254, 0.060633906259083235),\n",
       " (65, 0.060616080621108986),\n",
       " (349, 0.060616080621108986),\n",
       " (660, 0.06052275326688025),\n",
       " (1253, 0.06048884885927481),\n",
       " (379, 0.06033884900318473),\n",
       " (802, 0.060192926542884606),\n",
       " (1442, 0.05976143046671969),\n",
       " (401, 0.059676239503286085),\n",
       " (1667, 0.05954913341754137),\n",
       " (898, 0.05953620902598002),\n",
       " (1005, 0.059391387091649865),\n",
       " (1621, 0.059391387091649865),\n",
       " (1286, 0.05933490454240869),\n",
       " (756, 0.059304999573790707),\n",
       " (1149, 0.059062442321861836),\n",
       " (820, 0.05892556509887897),\n",
       " (852, 0.05892556509887897),\n",
       " (765, 0.05892556509887896),\n",
       " (1021, 0.05892556509887896),\n",
       " (824, 0.05885054843562047),\n",
       " (362, 0.05869672708837492),\n",
       " (711, 0.058696727088374916),\n",
       " (1345, 0.058627205890120715),\n",
       " (920, 0.05818804460627859),\n",
       " (126, 0.05802588531856595),\n",
       " (414, 0.05802588531856595),\n",
       " (492, 0.05802588531856595),\n",
       " (1246, 0.057993350477029436),\n",
       " (448, 0.05797890810338324),\n",
       " (11, 0.057972132749994555),\n",
       " (572, 0.05773502691896258),\n",
       " (1537, 0.05753758026694707),\n",
       " (288, 0.0573775310549247),\n",
       " (325, 0.0573775310549247),\n",
       " (992, 0.05737753105492469),\n",
       " (1551, 0.057338538504682214),\n",
       " (229, 0.05721881005638328),\n",
       " (1066, 0.057218810056383275),\n",
       " (728, 0.057099059152294296),\n",
       " (1378, 0.05706139900145506),\n",
       " (1243, 0.05673521058541754),\n",
       " (375, 0.05672527447140345),\n",
       " (816, 0.05661385170722979),\n",
       " (1261, 0.05659684799706785),\n",
       " (566, 0.056343616981901115),\n",
       " (34, 0.056131276171213614),\n",
       " (450, 0.05607721540920443),\n",
       " (1592, 0.05602046370727958),\n",
       " (1588, 0.05599473674210774),\n",
       " (1420, 0.05593738517329483),\n",
       " (542, 0.055929671267835365),\n",
       " (399, 0.05581455721859476),\n",
       " (253, 0.055555555555555566),\n",
       " (863, 0.055555555555555566),\n",
       " (1585, 0.05555555555555556),\n",
       " (719, 0.05555555555555555),\n",
       " (1016, 0.05555555555555555),\n",
       " (976, 0.055441595321592964),\n",
       " (1619, 0.05532833351724881),\n",
       " (392, 0.0553001263609331),\n",
       " (1479, 0.05499719409228703),\n",
       " (1137, 0.0549857399228215),\n",
       " (1362, 0.0549857399228215),\n",
       " (1019, 0.05482930791331408),\n",
       " (482, 0.05463417234226549),\n",
       " (163, 0.05443310539518174),\n",
       " (706, 0.05416296424682583),\n",
       " (1508, 0.05416296424682583),\n",
       " (778, 0.05392918574411949),\n",
       " (857, 0.053896805563629545),\n",
       " (712, 0.05383819020581655),\n",
       " (1467, 0.05362412100731557),\n",
       " (1407, 0.05360562674188975),\n",
       " (547, 0.05358677475370628),\n",
       " (639, 0.05345835825829868),\n",
       " (57, 0.05337605126836238),\n",
       " (1385, 0.053376051268362375),\n",
       " (770, 0.053250804201891155),\n",
       " (1104, 0.05324820425539145),\n",
       " (24, 0.05314940034527339),\n",
       " (265, 0.05313139275527819),\n",
       " (282, 0.05292561240249631),\n",
       " (312, 0.052870105714542946),\n",
       " (964, 0.052870105714542946),\n",
       " (36, 0.05281035421037316),\n",
       " (1503, 0.05274585147528237),\n",
       " (580, 0.05249506569572601),\n",
       " (625, 0.05249506569572601),\n",
       " (990, 0.05243776708047439),\n",
       " (1174, 0.05243776708047438),\n",
       " (1605, 0.05213745913371834),\n",
       " (672, 0.052057920629535355),\n",
       " (418, 0.05196746370519363),\n",
       " (1144, 0.05196746370519363),\n",
       " (745, 0.05184758473652127),\n",
       " (1015, 0.05184758473652126),\n",
       " (289, 0.05178237582537449),\n",
       " (376, 0.05175491695067656),\n",
       " (1574, 0.05166561721947523),\n",
       " (1431, 0.051434449987363975),\n",
       " (759, 0.05128812124138864),\n",
       " (44, 0.05103103630798288),\n",
       " (697, 0.05103103630798288),\n",
       " (463, 0.05099917178017538),\n",
       " (815, 0.05099917178017538),\n",
       " (1437, 0.05083285677753489),\n",
       " (1363, 0.05071505162084871),\n",
       " (870, 0.050486604280923476),\n",
       " (1223, 0.050486604280923476),\n",
       " (54, 0.050435627722400206),\n",
       " (149, 0.050435627722400206),\n",
       " (1025, 0.050435627722400206),\n",
       " (1568, 0.05034538273357869),\n",
       " (871, 0.0501097352001886),\n",
       " (907, 0.0501097352001886),\n",
       " (1146, 0.0501097352001886),\n",
       " (377, 0.05006645879933536),\n",
       " (723, 0.05006645879933536),\n",
       " (503, 0.05006261743217588),\n",
       " (1365, 0.05000390670782329),\n",
       " (1239, 0.04996877926639076),\n",
       " (1570, 0.04989036167410414),\n",
       " (1242, 0.04975185951049945),\n",
       " (943, 0.04969039949999533),\n",
       " (1119, 0.04969039949999533),\n",
       " (51, 0.049690399499995326),\n",
       " (59, 0.049690399499995326),\n",
       " (221, 0.049690399499995326),\n",
       " (705, 0.049669963389939134),\n",
       " (132, 0.049624277847951134),\n",
       " (1513, 0.04958847036804648),\n",
       " (698, 0.049587200220373454),\n",
       " (453, 0.04936240647992436),\n",
       " (549, 0.04936240647992436),\n",
       " (1138, 0.04928141806363819),\n",
       " (1474, 0.04928141806363819),\n",
       " (942, 0.04914731871829904),\n",
       " (622, 0.049104637582399135),\n",
       " (1258, 0.049104637582399135),\n",
       " (937, 0.04904082386137497),\n",
       " (780, 0.04899539464934427),\n",
       " (1579, 0.048970210687439175),\n",
       " (10, 0.04888237167378443),\n",
       " (828, 0.04835490443213829),\n",
       " (1356, 0.04794633014853843),\n",
       " (838, 0.04787374913511885),\n",
       " (1416, 0.04787374913511885),\n",
       " (1318, 0.0478689131586294),\n",
       " (1477, 0.0478689131586294),\n",
       " (1164, 0.04778184825674965),\n",
       " (1013, 0.04763849587291913),\n",
       " (1115, 0.04746792363392696),\n",
       " (142, 0.047467923633926955),\n",
       " (872, 0.04745789978762495),\n",
       " (914, 0.04740667699904787),\n",
       " (932, 0.04740667699904787),\n",
       " (274, 0.047178209756024825),\n",
       " (731, 0.04702304105723989),\n",
       " (1495, 0.04695301415158427),\n",
       " (120, 0.046829290579084706),\n",
       " (246, 0.046829290579084706),\n",
       " (1020, 0.046731012841003686),\n",
       " (1311, 0.04667600280093366),\n",
       " (1554, 0.046524210519923545),\n",
       " (691, 0.04633653645712773),\n",
       " (1153, 0.046225016352102424),\n",
       " (1514, 0.04608343863411092),\n",
       " (1372, 0.04607756775840914),\n",
       " (501, 0.046004370622823615),\n",
       " (772, 0.045873490213598364),\n",
       " (469, 0.04578685464956301),\n",
       " (55, 0.04567924732183544),\n",
       " (1169, 0.045643546458763846),\n",
       " (1222, 0.04564354645876384),\n",
       " (1092, 0.04562027674200355),\n",
       " (1139, 0.04562027674200354),\n",
       " (1677, 0.04546206046583175),\n",
       " (724, 0.04536092116265145),\n",
       " (561, 0.04504915855996573),\n",
       " (946, 0.04504915855996573),\n",
       " (459, 0.04486515850484713),\n",
       " (919, 0.04480556340414984),\n",
       " (911, 0.044743737014268294),\n",
       " (935, 0.044743737014268294),\n",
       " (345, 0.0445435403187374),\n",
       " (1628, 0.0445435403187374),\n",
       " (994, 0.044480042723635316),\n",
       " (1475, 0.044480042723635316),\n",
       " (753, 0.044291166954394494),\n",
       " (1026, 0.044291166954394494),\n",
       " (1054, 0.044291166954394494),\n",
       " (1069, 0.044151078568834795),\n",
       " (680, 0.04415107856883479),\n",
       " (433, 0.04410467700208026),\n",
       " (546, 0.04402254531628119),\n",
       " (1481, 0.04402254531628119),\n",
       " (783, 0.04392052305789416),\n",
       " (281, 0.043863446330651264),\n",
       " (1520, 0.043846018300165025),\n",
       " (1184, 0.04376881095324085),\n",
       " (1434, 0.04376881095324085),\n",
       " (1062, 0.04366140266629866),\n",
       " (372, 0.04358136336404089),\n",
       " (686, 0.04358136336404089),\n",
       " (1611, 0.04351941398892446),\n",
       " (1540, 0.0433816005246128),\n",
       " (1225, 0.043121240805683414),\n",
       " (205, 0.04303314829119352),\n",
       " (471, 0.04303314829119352),\n",
       " (637, 0.04303314829119352),\n",
       " (1001, 0.04303314829119352),\n",
       " (1170, 0.04303314829119352),\n",
       " (792, 0.04286204165613664),\n",
       " (1032, 0.042766686606638946),\n",
       " (452, 0.04269295996488),\n",
       " (1078, 0.042686101107101804),\n",
       " (409, 0.04256282653793743),\n",
       " (1263, 0.04252586358998573),\n",
       " (340, 0.04251569682960854),\n",
       " (63, 0.04250511420422255),\n",
       " (172, 0.04250511420422255),\n",
       " (258, 0.04250511420422255),\n",
       " (405, 0.04250511420422255),\n",
       " (1547, 0.04250511420422255),\n",
       " (977, 0.04244763599780089),\n",
       " (1051, 0.04236071398127907),\n",
       " (437, 0.04224828336829853),\n",
       " (1178, 0.04222003309207491),\n",
       " (884, 0.04219747362848612),\n",
       " (1289, 0.04219747362848612),\n",
       " (1312, 0.04209845712841021),\n",
       " (1071, 0.04187657563580051),\n",
       " (92, 0.04177559931443569),\n",
       " (321, 0.0417482860723433),\n",
       " (669, 0.0417482860723433),\n",
       " (1077, 0.04171884786014657),\n",
       " (1460, 0.04171884786014657),\n",
       " (114, 0.04166666666666667),\n",
       " (374, 0.04166666666666667),\n",
       " (563, 0.04166666666666667),\n",
       " (1527, 0.04156288900448471),\n",
       " (1255, 0.04129955231527935),\n",
       " (1180, 0.041256147624028086),\n",
       " (636, 0.041239304942116126),\n",
       " (518, 0.041030496993110906),\n",
       " (1682, 0.041030496993110906),\n",
       " (710, 0.040841502450816955),\n",
       " (922, 0.04080850890619932),\n",
       " (985, 0.04080850890619932),\n",
       " (1220, 0.040799337424140304),\n",
       " (1565, 0.040799337424140304),\n",
       " (650, 0.04051805319385961),\n",
       " (1355, 0.04039836272875922),\n",
       " (260, 0.040348502177920166),\n",
       " (360, 0.040348502177920166),\n",
       " (1036, 0.040348502177920166),\n",
       " (1669, 0.040348502177920166),\n",
       " (510, 0.04009376869372401),\n",
       " (1167, 0.04009376869372401),\n",
       " (241, 0.04003203845127179),\n",
       " (283, 0.04003203845127179),\n",
       " (790, 0.04003203845127178),\n",
       " (523, 0.03991228933928331),\n",
       " (873, 0.03991228933928331),\n",
       " (1284, 0.03991228933928331),\n",
       " (1182, 0.03981820688062471),\n",
       " (1257, 0.03969942227836091),\n",
       " (6, 0.03965257928590721),\n",
       " (353, 0.03965257928590721),\n",
       " (403, 0.03965257928590721),\n",
       " (902, 0.03965257928590721),\n",
       " (1499, 0.03955938860646178),\n",
       " (1179, 0.039553704377880604),\n",
       " (1388, 0.03946685189819293),\n",
       " (1111, 0.039415314153366854),\n",
       " (499, 0.03937496154790789),\n",
       " (343, 0.03928371006591931),\n",
       " (1168, 0.03928371006591931),\n",
       " (1539, 0.03928371006591931),\n",
       " (1635, 0.03928371006591931),\n",
       " (601, 0.03918180662561556),\n",
       " (1330, 0.03915341547791163),\n",
       " (1084, 0.039080692117369954),\n",
       " (618, 0.038924947208076155),\n",
       " (1411, 0.038924947208076155),\n",
       " (1412, 0.038924947208076155),\n",
       " (748, 0.03889666900077805),\n",
       " (1112, 0.03889666900077805),\n",
       " (1201, 0.03889666900077805),\n",
       " (1300, 0.038880789567986955),\n",
       " (95, 0.03877017543326962),\n",
       " (1192, 0.03877017543326962),\n",
       " (45, 0.03868392354571063),\n",
       " (1638, 0.03864490798001402),\n",
       " (853, 0.03829899930809508),\n",
       " (1128, 0.038152379685825785),\n",
       " (382, 0.037917979599440835),\n",
       " (302, 0.03774256780481986),\n",
       " (918, 0.03774256780481986),\n",
       " (1121, 0.037742567804819854),\n",
       " (1008, 0.03766217885773547),\n",
       " (1083, 0.03745554791462456),\n",
       " (1488, 0.03742405942825599),\n",
       " (1067, 0.03736323588785367),\n",
       " (1375, 0.037267799624996496),\n",
       " (1123, 0.037230587634064186),\n",
       " (1143, 0.03703703703703704),\n",
       " (1082, 0.037037037037037035),\n",
       " (13, 0.03696106354772864),\n",
       " (1010, 0.036866750907288734),\n",
       " (848, 0.03668545443023433),\n",
       " (1124, 0.036661778755338326),\n",
       " (244, 0.03657927344217893),\n",
       " (1264, 0.03657927344217892),\n",
       " (1616, 0.0365331082900794),\n",
       " (112, 0.03647400912770071),\n",
       " (235, 0.036369648372665396),\n",
       " (330, 0.036369648372665396),\n",
       " (478, 0.036369648372665396),\n",
       " (609, 0.036369648372665396),\n",
       " (773, 0.036369648372665396),\n",
       " (810, 0.036369648372665396),\n",
       " (607, 0.03636964837266539),\n",
       " (1295, 0.03636964837266539),\n",
       " (1415, 0.03636964837266539),\n",
       " (1319, 0.03626617832410372),\n",
       " (1354, 0.03608439182435161),\n",
       " (1600, 0.03608439182435161),\n",
       " (758, 0.036049204695725014),\n",
       " (8, 0.03594425773447947),\n",
       " (261, 0.035761756285239546),\n",
       " (1271, 0.035761756285239546),\n",
       " (156, 0.03573708449459316),\n",
       " (653, 0.03573708449459316),\n",
       " (722, 0.03558403417890825),\n",
       " (441, 0.03546902211494786),\n",
       " (1140, 0.03546902211494786),\n",
       " (1043, 0.03537302999816741),\n",
       " (1217, 0.03537302999816741),\n",
       " (1215, 0.03533326266687867),\n",
       " (1465, 0.03528374160166421),\n",
       " (694, 0.03520166719043814),\n",
       " (1630, 0.03513641844631533),\n",
       " (46, 0.03508966337777163),\n",
       " (231, 0.03500700210070025),\n",
       " (291, 0.03500700210070025),\n",
       " (272, 0.034904492357641294),\n",
       " (1622, 0.034904492357641294),\n",
       " (1093, 0.03487900532075779),\n",
       " (299, 0.03456505649101418),\n",
       " (341, 0.03456505649101418),\n",
       " (717, 0.03456505649101418),\n",
       " (1406, 0.03454277801206993),\n",
       " (257, 0.03450327796711771),\n",
       " (1472, 0.03450327796711771),\n",
       " (1648, 0.0344540929414468),\n",
       " (89, 0.03442651863295482),\n",
       " (430, 0.03442651863295482),\n",
       " (358, 0.034289633324909315),\n",
       " (250, 0.0342787529079053),\n",
       " (130, 0.03425943549137658),\n",
       " (565, 0.03425943549137658),\n",
       " (1410, 0.034192080827592425),\n",
       " (420, 0.034154367971904),\n",
       " (230, 0.034106062877919084),\n",
       " (1452, 0.03406416781097072),\n",
       " (388, 0.03402069087198859),\n",
       " (368, 0.034020690871988585),\n",
       " (1647, 0.034020690871988585),\n",
       " (509, 0.03388857118502326),\n",
       " (1419, 0.03385185265426614),\n",
       " (428, 0.0337868689199743),\n",
       " (1302, 0.03376837076971283),\n",
       " (837, 0.03375797890278889),\n",
       " (1533, 0.03361463227264072),\n",
       " (113, 0.033501260508640406),\n",
       " (851, 0.033501260508640406),\n",
       " (981, 0.033501260508640406),\n",
       " (1490, 0.033501260508640406),\n",
       " (732, 0.033333333333333326),\n",
       " (84, 0.03328012765961966),\n",
       " (1379, 0.03327791628198609),\n",
       " (129, 0.03312693299999689),\n",
       " (1613, 0.03312693299999689),\n",
       " (1377, 0.033122026396548515),\n",
       " (300, 0.03311330892662609),\n",
       " (1655, 0.03311330892662609),\n",
       " (1259, 0.03305898024536432),\n",
       " (16, 0.03289758474798845),\n",
       " (40, 0.03289758474798845),\n",
       " (342, 0.03289758474798845),\n",
       " (631, 0.03289758474798845),\n",
       " (1366, 0.03288904324849411),\n",
       " (1663, 0.0328124679565899),\n",
       " (556, 0.032660908402900854),\n",
       " (1676, 0.03264680712495945),\n",
       " (1109, 0.032585911958573965),\n",
       " (354, 0.03253000243161777),\n",
       " (94, 0.03247849012308155),\n",
       " (485, 0.032414442555087686),\n",
       " (303, 0.03229101076217202),\n",
       " (1339, 0.03222454963485546),\n",
       " (1234, 0.032186969972351175),\n",
       " (1275, 0.03214653124210248),\n",
       " (1059, 0.032075014954979206),\n",
       " (1189, 0.032075014954979206),\n",
       " (1030, 0.031863296370911356),\n",
       " (882, 0.03185456550449977),\n",
       " (1470, 0.03185456550449977),\n",
       " (1591, 0.03178208630818641),\n",
       " (544, 0.03172445781778671),\n",
       " (96, 0.031686212526223896),\n",
       " (671, 0.031686212526223896),\n",
       " (841, 0.031686212526223896),\n",
       " (1029, 0.03165571568323276),\n",
       " (150, 0.031497039417435604),\n",
       " (916, 0.031497039417435604),\n",
       " (19, 0.031322732382329306),\n",
       " (206, 0.031322732382329306),\n",
       " (684, 0.03131121455425748),\n",
       " (227, 0.031219527052723135),\n",
       " (823, 0.031219527052723135),\n",
       " (1464, 0.031219527052723135),\n",
       " (1433, 0.031128640318234518),\n",
       " (768, 0.03111733520062244),\n",
       " (905, 0.03111733520062244),\n",
       " (1607, 0.03111733520062244),\n",
       " (1586, 0.031056499687497078),\n",
       " (1304, 0.031056499687497074),\n",
       " (209, 0.03099200013773341),\n",
       " (160, 0.030949223029508643),\n",
       " (371, 0.030949223029508643),\n",
       " (239, 0.030816677568068284),\n",
       " (612, 0.030816677568068284),\n",
       " (15, 0.03077287274483318),\n",
       " (1335, 0.03077287274483318),\n",
       " (1270, 0.030718378505606093),\n",
       " (1260, 0.03061326493211021),\n",
       " (1530, 0.03061326493211021),\n",
       " (329, 0.03052456976637534),\n",
       " (1110, 0.030513909884867668),\n",
       " (39, 0.030429030972509232),\n",
       " (200, 0.030429030972509232),\n",
       " (1175, 0.03033438367955267),\n",
       " (822, 0.030261376633440126),\n",
       " (847, 0.030261376633440126),\n",
       " (1484, 0.030261376633440126),\n",
       " (599, 0.030147708776408974),\n",
       " (310, 0.03012923025259114),\n",
       " (1187, 0.03007032652029301),\n",
       " (136, 0.030055654488914414),\n",
       " (529, 0.030055654488914414),\n",
       " (581, 0.030055654488914414),\n",
       " (1046, 0.03001176691940082),\n",
       " (107, 0.02996443833169965),\n",
       " (413, 0.029934217004462485),\n",
       " (1292, 0.029895666805590637),\n",
       " (1417, 0.029895666805590634),\n",
       " (26, 0.02987404766321472),\n",
       " (1516, 0.029784470107251354),\n",
       " (530, 0.02978447010725135),\n",
       " (740, 0.029695693545824933),\n",
       " (613, 0.02961744388795462),\n",
       " (923, 0.02961744388795462),\n",
       " (1235, 0.029607706112288502),\n",
       " (1294, 0.029607706112288502),\n",
       " (1538, 0.029607706112288502),\n",
       " (1408, 0.029520496184669842),\n",
       " (1454, 0.029520496184669842),\n",
       " (926, 0.029462782549439483),\n",
       " (444, 0.029434052379223197),\n",
       " (1186, 0.029434052379223197),\n",
       " (154, 0.02934836354418746),\n",
       " (614, 0.02934836354418746),\n",
       " (1296, 0.02934836354418746),\n",
       " (20, 0.029310519088027467),\n",
       " (641, 0.02926341875374314),\n",
       " (885, 0.02926341875374314),\n",
       " (1521, 0.0292262759929956),\n",
       " (602, 0.029160592175990215),\n",
       " (951, 0.029160592175990215),\n",
       " (702, 0.029095718698132315),\n",
       " (1125, 0.029095718698132315),\n",
       " (541, 0.029012942659282975),\n",
       " (646, 0.029012942659282975),\n",
       " (1358, 0.029012942659282975),\n",
       " (1392, 0.029012942659282975),\n",
       " (1492, 0.029012942659282972),\n",
       " (1349, 0.028939954008661634),\n",
       " (598, 0.028930869106849753),\n",
       " (730, 0.02886751345948129),\n",
       " (1364, 0.0288494881605277),\n",
       " (1074, 0.02875273163926476),\n",
       " (324, 0.02868876552746235),\n",
       " (1063, 0.02868876552746235),\n",
       " (1091, 0.02868876552746235),\n",
       " (1522, 0.02868876552746235),\n",
       " (1656, 0.02868876552746235),\n",
       " (1594, 0.02859992596060751),\n",
       " (476, 0.028583097523751475),\n",
       " (901, 0.028583097523751475),\n",
       " (1023, 0.028583097523751475),\n",
       " (1422, 0.028452639985087996),\n",
       " (784, 0.028444006199428717),\n",
       " (1668, 0.028444006199428717),\n",
       " (679, 0.028375217691958287),\n",
       " (1432, 0.028375217691958287),\n",
       " (86, 0.028306925853614898),\n",
       " (1681, 0.02825264598420043),\n",
       " (1251, 0.02822225044448678),\n",
       " (814, 0.028171808490950558),\n",
       " (868, 0.028171808490950558),\n",
       " (204, 0.0280717307022173),\n",
       " (1219, 0.028038607704602213),\n",
       " (1172, 0.02799736837105387),\n",
       " (1022, 0.027923593886113034),\n",
       " (1632, 0.027923593886113034),\n",
       " (27, 0.02790727860929738),\n",
       " (47, 0.027777777777777783),\n",
       " (464, 0.027777777777777783),\n",
       " (586, 0.027777777777777783),\n",
       " (592, 0.027777777777777783),\n",
       " (957, 0.027777777777777783),\n",
       " (1683, 0.027777777777777783),\n",
       " (1666, 0.027705721164112757),\n",
       " (1088, 0.02756327435315744),\n",
       " (1171, 0.02756327435315744),\n",
       " (48, 0.02749286996141075),\n",
       " (1494, 0.02749286996141075),\n",
       " (306, 0.02742300232632424),\n",
       " (504, 0.02742300232632424),\n",
       " (887, 0.02742300232632424),\n",
       " (707, 0.02739983121755955),\n",
       " (913, 0.02739983121755955),\n",
       " (439, 0.02721655269759087),\n",
       " (1441, 0.027194805548534904),\n",
       " (1439, 0.02718636239135184),\n",
       " (4, 0.02715627232967842),\n",
       " (240, 0.02715627232967842),\n",
       " (190, 0.027081482123412916),\n",
       " (969, 0.027036903521793762),\n",
       " (1599, 0.027036903521793762),\n",
       " (264, 0.026948402781814772),\n",
       " (721, 0.026948402781814772),\n",
       " (1237, 0.026948402781814772),\n",
       " (1469, 0.026948402781814772),\n",
       " (391, 0.026919095102908276),\n",
       " (605, 0.026919095102908276),\n",
       " (412, 0.026882594618183726),\n",
       " (793, 0.026688025634181187),\n",
       " (1542, 0.026574700172636696),\n",
       " (839, 0.02646280620124816),\n",
       " (85, 0.026435052857271473),\n",
       " (271, 0.026372925737641186),\n",
       " (585, 0.026352313834736497),\n",
       " (1291, 0.026352313834736497),\n",
       " (1651, 0.026352313834736497),\n",
       " (234, 0.026243194054073903),\n",
       " (971, 0.026243194054073903),\n",
       " (387, 0.026189140043946204),\n",
       " (764, 0.02602896031476768),\n",
       " (1278, 0.02602896031476768),\n",
       " (1436, 0.025949964805384102),\n",
       " (494, 0.02592379236826063),\n",
       " (1309, 0.02592379236826063),\n",
       " (597, 0.025819888974716113),\n",
       " (1430, 0.025774822434235307),\n",
       " (1670, 0.025774822434235307),\n",
       " (278, 0.025717224993681988),\n",
       " (1081, 0.025615775978928),\n",
       " (1519, 0.02560317908808562),\n",
       " (754, 0.02551551815399144),\n",
       " (1228, 0.025490637096729087),\n",
       " (421, 0.025434919790550525),\n",
       " (1643, 0.025434919790550525),\n",
       " (998, 0.025392818139000215),\n",
       " (1620, 0.025342864042323523),\n",
       " (1640, 0.02532457254658621),\n",
       " (875, 0.025269934785963444),\n",
       " (1609, 0.02521564914907446),\n",
       " (690, 0.025125945381480302),\n",
       " (1346, 0.025108119238490316),\n",
       " (1348, 0.025108119238490316),\n",
       " (174, 0.0250548676000943),\n",
       " (381, 0.0250548676000943),\n",
       " (396, 0.0250548676000943),\n",
       " (266, 0.02503130871608794),\n",
       " (716, 0.02503130871608794),\n",
       " (67, 0.024845199749997667),\n",
       " (66, 0.024845199749997663),\n",
       " (495, 0.024845199749997663),\n",
       " (262, 0.024753688574416854),\n",
       " (1359, 0.024753688574416854),\n",
       " (933, 0.0246631811833495),\n",
       " (1515, 0.024640709031819096),\n",
       " (1526, 0.024540339127743675),\n",
       " (301, 0.024441185836892216),\n",
       " (1202, 0.024392057775486746),\n",
       " (81, 0.024246432248443594),\n",
       " (895, 0.02414022747926338),\n",
       " (904, 0.024056261216234408),\n",
       " (866, 0.024056261216234404),\n",
       " (750, 0.023973165074269213),\n",
       " (589, 0.023916533444472508),\n",
       " (806, 0.02389092412837483),\n",
       " (76, 0.023870495801314433),\n",
       " (313, 0.023870495801314433),\n",
       " (813, 0.023870495801314433),\n",
       " (831, 0.023870495801314433),\n",
       " (1154, 0.023733961816963477),\n",
       " (506, 0.023728949893812475),\n",
       " (989, 0.023728949893812475),\n",
       " (1157, 0.023688968483956713),\n",
       " (979, 0.02364918849202011),\n",
       " (947, 0.023570226039551584),\n",
       " (1343, 0.02349204928674698),\n",
       " (311, 0.023262105259961773),\n",
       " (451, 0.023262105259961773),\n",
       " (512, 0.023262105259961773),\n",
       " (1004, 0.023262105259961773),\n",
       " (980, 0.023168268228563865),\n",
       " (1162, 0.023112508176051212),\n",
       " (1049, 0.023084778702148128),\n",
       " (938, 0.02303878387920457),\n",
       " (1287, 0.02303878387920457),\n",
       " (1061, 0.023002185311411807),\n",
       " (1114, 0.023002185311411807),\n",
       " (1443, 0.023002185311411807),\n",
       " (1402, 0.022893427324781505),\n",
       " (267, 0.02283962366091772),\n",
       " (355, 0.02283962366091772),\n",
       " (214, 0.022821773229381923),\n",
       " (1113, 0.022799518935225645),\n",
       " (180, 0.022680460581325727),\n",
       " (97, 0.022680460581325723),\n",
       " (736, 0.022680460581325723),\n",
       " (840, 0.022680460581325723),\n",
       " (1173, 0.022680460581325723),\n",
       " (1281, 0.022680460581325723),\n",
       " (1684, 0.02261078158230673),\n",
       " (801, 0.02254174086668581),\n",
       " (1212, 0.02254174086668581),\n",
       " (514, 0.022524579279982866),\n",
       " (1132, 0.022524579279982866),\n",
       " (832, 0.02240553574741104),\n",
       " ...]"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted(list(enumerate(similarity[0])), reverse=True, key=lambda x: x[1])"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Creating Recommendations :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>145</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Andhadhun</td>\n",
       "      <td>2018</td>\n",
       "      <td>[Crime, Thriller]</td>\n",
       "      <td>8.4</td>\n",
       "      <td>51615.0</td>\n",
       "      <td>[A, series, of, mysterious, events, changes, t...</td>\n",
       "      <td>crime thriller akash a blind pianist is prepar...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                           poster_path original_title  \\\n",
       "145  https://upload.wikimedia.org/wikipedia/en/thum...      Andhadhun   \n",
       "\n",
       "    year_of_release             genres  imdb_rating  imdb_votes  \\\n",
       "145            2018  [Crime, Thriller]          8.4     51615.0   \n",
       "\n",
       "                                               summary  \\\n",
       "145  [A, series, of, mysterious, events, changes, t...   \n",
       "\n",
       "                                                  tags  \n",
       "145  crime thriller akash a blind pianist is prepar...  "
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[movies[\"original_title\"] == \"Andhadhun\"]         # Returns Row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "145"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[movies[\"original_title\"] == \"Andhadhun\"].index[0]       # Return Index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Raag Desh'"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.iloc[218].original_title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "def recommended_movies(mov):\n",
    "    idx = movies[movies[\"original_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(movies.iloc[i[0]].original_title)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://upload.wikimedia.org/wikipedia/en/thumb/3/3b/URI_-_New_poster.jpg/220px-URI_-_New_poster.jpg'"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.iloc[0].poster_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Armaan\n",
      "Haider\n",
      "Chehraa\n",
      "Rukh\n",
      "London Dreams\n"
     ]
    }
   ],
   "source": [
    "recommended_movies(\"Andhadhun\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "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>is_adult</th>\n",
       "      <th>year_of_release</th>\n",
       "      <th>genres</th>\n",
       "      <th>imdb_rating</th>\n",
       "      <th>imdb_votes</th>\n",
       "      <th>story</th>\n",
       "      <th>summary</th>\n",
       "      <th>actors</th>\n",
       "      <th>title</th>\n",
       "      <th>tags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>https://upload.wikimedia.org/wikipedia/en/thum...</td>\n",
       "      <td>Soni</td>\n",
       "      <td>0</td>\n",
       "      <td>2018</td>\n",
       "      <td>[Drama]</td>\n",
       "      <td>7.2</td>\n",
       "      <td>1595.0</td>\n",
       "      <td>[Soni, a, young, policewoman, in, Delhi, and, ...</td>\n",
       "      <td>[While, fighting, crimes, against, women, in, ...</td>\n",
       "      <td>[GeetikaVidyaOhlyan, SaloniBatra, VikasShukla,...</td>\n",
       "      <td>[Soni]</td>\n",
       "      <td>[Drama, Soni, a, young, policewoman, in, Delhi...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                         poster_path original_title  is_adult  \\\n",
       "5  https://upload.wikimedia.org/wikipedia/en/thum...           Soni         0   \n",
       "\n",
       "  year_of_release   genres  imdb_rating  imdb_votes  \\\n",
       "5            2018  [Drama]          7.2      1595.0   \n",
       "\n",
       "                                               story  \\\n",
       "5  [Soni, a, young, policewoman, in, Delhi, and, ...   \n",
       "\n",
       "                                             summary  \\\n",
       "5  [While, fighting, crimes, against, women, in, ...   \n",
       "\n",
       "                                              actors   title  \\\n",
       "5  [GeetikaVidyaOhlyan, SaloniBatra, VikasShukla,...  [Soni]   \n",
       "\n",
       "                                                tags  \n",
       "5  [Drama, Soni, a, young, policewoman, in, Delhi...  "
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[data[\"original_title\"]==\"Soni\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pickle import dump"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "dump(movies.to_dict(), open(\"movie_info.pkl\", 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Uri: The Surgical Strike', 'Battalion 609',\n",
       "       'The Accidental Prime Minister', ..., 'Sabse Bada Sukh', 'Daaka',\n",
       "       'Humsafar'], dtype=object)"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"original_title\"].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "dump(similarity, open(\"similarity.pkl\", 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Series([], Name: poster_path, dtype: object)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[data[\"original_title\"]==\"Smuggler\"].poster_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'A series of mysterious events changes the life of a blind pianist who must now report a crime that he should technically know nothing of.'"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idx = movies[movies[\"original_title\"] == \"Andhadhun\"].index[0]\n",
    "\" \".join(movies.iloc[idx].summary)\n"
   ]
  },
  {
   "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
}