{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie title</th>\n",
       "      <th>Run Time</th>\n",
       "      <th>Rating</th>\n",
       "      <th>User Rating</th>\n",
       "      <th>Generes</th>\n",
       "      <th>Overview</th>\n",
       "      <th>Plot Kyeword</th>\n",
       "      <th>Director</th>\n",
       "      <th>Top 5 Casts</th>\n",
       "      <th>Writer</th>\n",
       "      <th>year</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Top Gun: Maverick</td>\n",
       "      <td>$170,000,000 (estimated)</td>\n",
       "      <td>8.6</td>\n",
       "      <td>187K</td>\n",
       "      <td>['Action', 'Drama']</td>\n",
       "      <td>After more than thirty years of service as one...</td>\n",
       "      <td>['fighter jet', 'sequel', 'u.s. navy', 'fighte...</td>\n",
       "      <td>Joseph Kosinski</td>\n",
       "      <td>['Jack Epps Jr.', 'Peter Craig', 'Tom Cruise',...</td>\n",
       "      <td>Jim Cash</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt1745960/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jurassic World Dominion</td>\n",
       "      <td>2 hours 27 minutes</td>\n",
       "      <td>6</td>\n",
       "      <td>56K</td>\n",
       "      <td>['Action', 'Adventure', 'Sci-Fi']</td>\n",
       "      <td>Four years after the destruction of Isla Nubla...</td>\n",
       "      <td>['dinosaur', 'jurassic park', 'tyrannosaurus r...</td>\n",
       "      <td>Colin Trevorrow</td>\n",
       "      <td>['Colin Trevorrow', 'Derek Connolly', 'Chris P...</td>\n",
       "      <td>Emily Carmichael</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt8041270/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Top Gun</td>\n",
       "      <td>$15,000,000 (estimated)</td>\n",
       "      <td>6.9</td>\n",
       "      <td>380K</td>\n",
       "      <td>['Action', 'Drama']</td>\n",
       "      <td>As students at the United States Navy's elite ...</td>\n",
       "      <td>['pilot', 'male camaraderie', 'u.s. navy', 'gr...</td>\n",
       "      <td>Tony Scott</td>\n",
       "      <td>['Jack Epps Jr.', 'Ehud Yonay', 'Tom Cruise', ...</td>\n",
       "      <td>Jim Cash</td>\n",
       "      <td>-1986</td>\n",
       "      <td>/title/tt0092099/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Lightyear</td>\n",
       "      <td>$71,101,257</td>\n",
       "      <td>5.2</td>\n",
       "      <td>32K</td>\n",
       "      <td>['Animation', 'Action', 'Adventure']</td>\n",
       "      <td>While spending years attempting to return home...</td>\n",
       "      <td>['galaxy', 'spaceship', 'robot', 'rocket', 'sp...</td>\n",
       "      <td>Angus MacLane</td>\n",
       "      <td>['Jason Headley', 'Matthew Aldrich', 'Chris Ev...</td>\n",
       "      <td>Angus MacLane</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt10298810/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Spiderhead</td>\n",
       "      <td>not-released</td>\n",
       "      <td>5.4</td>\n",
       "      <td>23K</td>\n",
       "      <td>['Action', 'Crime', 'Drama']</td>\n",
       "      <td>In the near future, convicts are offered the c...</td>\n",
       "      <td>['discover', 'medical', 'test', 'reality', 'fi...</td>\n",
       "      <td>Joseph Kosinski</td>\n",
       "      <td>['Rhett Reese', 'Paul Wernick', 'Chris Hemswor...</td>\n",
       "      <td>George Saunders</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt9783600/</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24397</th>\n",
       "      <td>Delicatessen</td>\n",
       "      <td>FRF 24,000,000 (estimated)</td>\n",
       "      <td>7.6</td>\n",
       "      <td>85K</td>\n",
       "      <td>['Comedy', 'Crime']</td>\n",
       "      <td>Post-apocalyptic surrealist black comedy about...</td>\n",
       "      <td>['surrealist', 'black comedy', 'human meat', '...</td>\n",
       "      <td>Marc Caro</td>\n",
       "      <td>['Jean-Pierre Jeunet', 'Marc Caro', 'Gilles Ad...</td>\n",
       "      <td>Jean-Pierre Jeunet</td>\n",
       "      <td>-1991</td>\n",
       "      <td>/title/tt0101700/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24398</th>\n",
       "      <td>Bitch Ass</td>\n",
       "      <td>not-released</td>\n",
       "      <td>5.5</td>\n",
       "      <td>52</td>\n",
       "      <td>['Crime', 'Horror']</td>\n",
       "      <td>A gang initiation goes wrong when a group of f...</td>\n",
       "      <td>[]</td>\n",
       "      <td>Bill Posley</td>\n",
       "      <td>['Bill Posley', 'Teon Kelley', 'Tunde Laleye',...</td>\n",
       "      <td>Jonathan Colomb</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt13991504/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24399</th>\n",
       "      <td>Bullwhip</td>\n",
       "      <td>not-released</td>\n",
       "      <td>5.1</td>\n",
       "      <td>398</td>\n",
       "      <td>['Crime', 'Romance', 'Western']</td>\n",
       "      <td>In order to avoid the hangman's noose, a cowbo...</td>\n",
       "      <td>['taming of the shrew', 'fur trader', 'busines...</td>\n",
       "      <td>Harmon Jones</td>\n",
       "      <td>['Guy Madison', 'Rhonda Fleming', 'James Griff...</td>\n",
       "      <td>Adele Buffington</td>\n",
       "      <td>-1958</td>\n",
       "      <td>/title/tt0051438/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24400</th>\n",
       "      <td>The Freshman</td>\n",
       "      <td>1 hour 42 minutes</td>\n",
       "      <td>6.4</td>\n",
       "      <td>20K</td>\n",
       "      <td>['Comedy', 'Crime']</td>\n",
       "      <td>An N.Y.C. film school student accepts a job wi...</td>\n",
       "      <td>['endangered species', 'fish out of water', 'g...</td>\n",
       "      <td>Andrew Bergman</td>\n",
       "      <td>['Marlon Brando', 'Matthew Broderick', 'Bruno ...</td>\n",
       "      <td>Andrew Bergman</td>\n",
       "      <td>-1990</td>\n",
       "      <td>/title/tt0099615/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24401</th>\n",
       "      <td>Guys and Dolls</td>\n",
       "      <td>$5,500,000 (estimated)</td>\n",
       "      <td>7.1</td>\n",
       "      <td>18K</td>\n",
       "      <td>['Comedy', 'Crime', 'Musical']</td>\n",
       "      <td>In New York, a gambler is challenged to take a...</td>\n",
       "      <td>['mission', 'gambler', 'new york city', 'based...</td>\n",
       "      <td>Joseph L. Mankiewicz</td>\n",
       "      <td>['Abe Burrows', 'Damon Runyon', 'Marlon Brando...</td>\n",
       "      <td>Jo Swerling</td>\n",
       "      <td>-1955</td>\n",
       "      <td>/title/tt0048140/</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>24402 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                   movie title                    Run Time Rating User Rating  \\\n",
       "0            Top Gun: Maverick    $170,000,000 (estimated)    8.6        187K   \n",
       "1      Jurassic World Dominion          2 hours 27 minutes      6         56K   \n",
       "2                      Top Gun     $15,000,000 (estimated)    6.9        380K   \n",
       "3                    Lightyear                 $71,101,257    5.2         32K   \n",
       "4                   Spiderhead                not-released    5.4         23K   \n",
       "...                        ...                         ...    ...         ...   \n",
       "24397             Delicatessen  FRF 24,000,000 (estimated)    7.6         85K   \n",
       "24398                Bitch Ass                not-released    5.5          52   \n",
       "24399                 Bullwhip                not-released    5.1         398   \n",
       "24400             The Freshman           1 hour 42 minutes    6.4         20K   \n",
       "24401           Guys and Dolls      $5,500,000 (estimated)    7.1         18K   \n",
       "\n",
       "                                    Generes  \\\n",
       "0                       ['Action', 'Drama']   \n",
       "1         ['Action', 'Adventure', 'Sci-Fi']   \n",
       "2                       ['Action', 'Drama']   \n",
       "3      ['Animation', 'Action', 'Adventure']   \n",
       "4              ['Action', 'Crime', 'Drama']   \n",
       "...                                     ...   \n",
       "24397                   ['Comedy', 'Crime']   \n",
       "24398                   ['Crime', 'Horror']   \n",
       "24399       ['Crime', 'Romance', 'Western']   \n",
       "24400                   ['Comedy', 'Crime']   \n",
       "24401        ['Comedy', 'Crime', 'Musical']   \n",
       "\n",
       "                                                Overview  \\\n",
       "0      After more than thirty years of service as one...   \n",
       "1      Four years after the destruction of Isla Nubla...   \n",
       "2      As students at the United States Navy's elite ...   \n",
       "3      While spending years attempting to return home...   \n",
       "4      In the near future, convicts are offered the c...   \n",
       "...                                                  ...   \n",
       "24397  Post-apocalyptic surrealist black comedy about...   \n",
       "24398  A gang initiation goes wrong when a group of f...   \n",
       "24399  In order to avoid the hangman's noose, a cowbo...   \n",
       "24400  An N.Y.C. film school student accepts a job wi...   \n",
       "24401  In New York, a gambler is challenged to take a...   \n",
       "\n",
       "                                            Plot Kyeword  \\\n",
       "0      ['fighter jet', 'sequel', 'u.s. navy', 'fighte...   \n",
       "1      ['dinosaur', 'jurassic park', 'tyrannosaurus r...   \n",
       "2      ['pilot', 'male camaraderie', 'u.s. navy', 'gr...   \n",
       "3      ['galaxy', 'spaceship', 'robot', 'rocket', 'sp...   \n",
       "4      ['discover', 'medical', 'test', 'reality', 'fi...   \n",
       "...                                                  ...   \n",
       "24397  ['surrealist', 'black comedy', 'human meat', '...   \n",
       "24398                                                 []   \n",
       "24399  ['taming of the shrew', 'fur trader', 'busines...   \n",
       "24400  ['endangered species', 'fish out of water', 'g...   \n",
       "24401  ['mission', 'gambler', 'new york city', 'based...   \n",
       "\n",
       "                   Director  \\\n",
       "0           Joseph Kosinski   \n",
       "1           Colin Trevorrow   \n",
       "2                Tony Scott   \n",
       "3             Angus MacLane   \n",
       "4           Joseph Kosinski   \n",
       "...                     ...   \n",
       "24397             Marc Caro   \n",
       "24398           Bill Posley   \n",
       "24399          Harmon Jones   \n",
       "24400        Andrew Bergman   \n",
       "24401  Joseph L. Mankiewicz   \n",
       "\n",
       "                                             Top 5 Casts              Writer  \\\n",
       "0      ['Jack Epps Jr.', 'Peter Craig', 'Tom Cruise',...            Jim Cash   \n",
       "1      ['Colin Trevorrow', 'Derek Connolly', 'Chris P...    Emily Carmichael   \n",
       "2      ['Jack Epps Jr.', 'Ehud Yonay', 'Tom Cruise', ...            Jim Cash   \n",
       "3      ['Jason Headley', 'Matthew Aldrich', 'Chris Ev...       Angus MacLane   \n",
       "4      ['Rhett Reese', 'Paul Wernick', 'Chris Hemswor...     George Saunders   \n",
       "...                                                  ...                 ...   \n",
       "24397  ['Jean-Pierre Jeunet', 'Marc Caro', 'Gilles Ad...  Jean-Pierre Jeunet   \n",
       "24398  ['Bill Posley', 'Teon Kelley', 'Tunde Laleye',...     Jonathan Colomb   \n",
       "24399  ['Guy Madison', 'Rhonda Fleming', 'James Griff...    Adele Buffington   \n",
       "24400  ['Marlon Brando', 'Matthew Broderick', 'Bruno ...      Andrew Bergman   \n",
       "24401  ['Abe Burrows', 'Damon Runyon', 'Marlon Brando...         Jo Swerling   \n",
       "\n",
       "        year                path  \n",
       "0      -2022   /title/tt1745960/  \n",
       "1      -2022   /title/tt8041270/  \n",
       "2      -1986   /title/tt0092099/  \n",
       "3      -2022  /title/tt10298810/  \n",
       "4      -2022   /title/tt9783600/  \n",
       "...      ...                 ...  \n",
       "24397  -1991   /title/tt0101700/  \n",
       "24398  -2022  /title/tt13991504/  \n",
       "24399  -1958   /title/tt0051438/  \n",
       "24400  -1990   /title/tt0099615/  \n",
       "24401  -1955   /title/tt0048140/  \n",
       "\n",
       "[24402 rows x 12 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "movies = pd.read_csv(\"25k_IMDb_movie_Dataset.csv\")\n",
    "movies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "train, dev, test = np.split(movies.sample(frac=1, random_state=69), [int(.6*len(movies)), int(.8*len(movies))])\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie title</th>\n",
       "      <th>Run Time</th>\n",
       "      <th>Rating</th>\n",
       "      <th>User Rating</th>\n",
       "      <th>Generes</th>\n",
       "      <th>Overview</th>\n",
       "      <th>Plot Kyeword</th>\n",
       "      <th>Director</th>\n",
       "      <th>Top 5 Casts</th>\n",
       "      <th>Writer</th>\n",
       "      <th>year</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4782</th>\n",
       "      <td>Golmaal: Fun Unlimited</td>\n",
       "      <td>2 hours 30 minutes</td>\n",
       "      <td>7.4</td>\n",
       "      <td>17K</td>\n",
       "      <td>['Action', 'Comedy', 'Drama']</td>\n",
       "      <td>Four runaway crooks take shelter in a bungalow...</td>\n",
       "      <td>['blind couple', 'friend', 'mute', 'slacker', ...</td>\n",
       "      <td>Rohit Shetty</td>\n",
       "      <td>['Ajay Devgn', 'Arshad Warsi', 'Sharman Joshi'...</td>\n",
       "      <td>Neeraj Vora</td>\n",
       "      <td>-2006</td>\n",
       "      <td>/title/tt0495034/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9291</th>\n",
       "      <td>The Remains of the Day</td>\n",
       "      <td>2 hours 14 minutes</td>\n",
       "      <td>7.8</td>\n",
       "      <td>74K</td>\n",
       "      <td>['Drama', 'Romance']</td>\n",
       "      <td>A butler who sacrificed body and soul to servi...</td>\n",
       "      <td>['class differences', 'butler', 'housekeeper',...</td>\n",
       "      <td>James Ivory</td>\n",
       "      <td>['Ruth Prawer Jhabvala', 'Anthony Hopkins', 'E...</td>\n",
       "      <td>Kazuo Ishiguro</td>\n",
       "      <td>-1993</td>\n",
       "      <td>/title/tt0107943/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3137</th>\n",
       "      <td>Blue Iguana</td>\n",
       "      <td>1 hour 40 minutes</td>\n",
       "      <td>5.6</td>\n",
       "      <td>5.2K</td>\n",
       "      <td>['Action', 'Comedy', 'Crime']</td>\n",
       "      <td>Ex-jailbirds Eddie and Paul are on parole and ...</td>\n",
       "      <td>['singing in a car', 'reference to the world c...</td>\n",
       "      <td>Hadi Hajaig</td>\n",
       "      <td>['Sam Rockwell', 'Phoebe Fox', 'Ben Schwartz',...</td>\n",
       "      <td>Hadi Hajaig</td>\n",
       "      <td>-2018</td>\n",
       "      <td>/title/tt2316479/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17052</th>\n",
       "      <td>Nocturna</td>\n",
       "      <td>1 hour 20 minutes</td>\n",
       "      <td>7.2</td>\n",
       "      <td>2.4K</td>\n",
       "      <td>['Animation', 'Adventure', 'Family']</td>\n",
       "      <td>An orphan boy named Tim is afraid of the dark....</td>\n",
       "      <td>['orphan', 'night', 'cat', 'one word title', '...</td>\n",
       "      <td>Adrià García</td>\n",
       "      <td>['Adrià García', 'Víctor Maldonado', 'Teresa V...</td>\n",
       "      <td>Víctor Maldonado</td>\n",
       "      <td>-2007</td>\n",
       "      <td>/title/tt0836682/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>Alexander</td>\n",
       "      <td>$155,000,000 (estimated)</td>\n",
       "      <td>5.6</td>\n",
       "      <td>169K</td>\n",
       "      <td>['Action', 'Biography', 'Drama']</td>\n",
       "      <td>Alexander, the King of Macedonia and one of th...</td>\n",
       "      <td>['ancient greece', 'greek', 'macedonia', 'sex ...</td>\n",
       "      <td>Oliver Stone</td>\n",
       "      <td>['Christopher Kyle', 'Laeta Kalogridis', 'Coli...</td>\n",
       "      <td>Oliver Stone</td>\n",
       "      <td>-2004</td>\n",
       "      <td>/title/tt0346491/</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6365</th>\n",
       "      <td>Yalghaar</td>\n",
       "      <td>2 hours 38 minutes</td>\n",
       "      <td>6.4</td>\n",
       "      <td>1K</td>\n",
       "      <td>['Action', 'Romance', 'War']</td>\n",
       "      <td>The film \"explores what happens in the lives o...</td>\n",
       "      <td>['live']</td>\n",
       "      <td>Hassan Rana</td>\n",
       "      <td>['Shaan Shahid', 'Humayun Saeed', 'Adnan Siddi...</td>\n",
       "      <td>Hassan Rana</td>\n",
       "      <td>-2017</td>\n",
       "      <td>/title/tt3945864/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7172</th>\n",
       "      <td>Brown of Harvard</td>\n",
       "      <td>not-released</td>\n",
       "      <td>6.2</td>\n",
       "      <td>1.5K</td>\n",
       "      <td>['Action', 'Drama', 'Romance']</td>\n",
       "      <td>Tom Brown shows up at Harvard, confident and a...</td>\n",
       "      <td>['harvard', 'no homoeroticism', 'pre code film...</td>\n",
       "      <td>Jack Conway</td>\n",
       "      <td>['Donald Ogden Stewart', 'Andrew Percival Youn...</td>\n",
       "      <td>Rida Johnson Young</td>\n",
       "      <td>-1926</td>\n",
       "      <td>/title/tt0016690/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12644</th>\n",
       "      <td>Deseo</td>\n",
       "      <td>1 hour 37 minutes</td>\n",
       "      <td>4.6</td>\n",
       "      <td>417</td>\n",
       "      <td>['Comedy', 'Drama', 'Romance']</td>\n",
       "      <td>A succession of erotic encounters weaved into ...</td>\n",
       "      <td>['smoking marijuana', 'female full frontal nud...</td>\n",
       "      <td>Antonio Zavala Kugler</td>\n",
       "      <td>['Antonio Zavala Kugler', 'Christian Bach', 'A...</td>\n",
       "      <td>Arthur Schnitzler</td>\n",
       "      <td>-2013</td>\n",
       "      <td>/title/tt1236434/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23970</th>\n",
       "      <td>Saezuru Tori Wa Habatakanai: The Clouds Gather</td>\n",
       "      <td>1 hour 25 minutes</td>\n",
       "      <td>6.9</td>\n",
       "      <td>681</td>\n",
       "      <td>['Animation', 'Crime', 'Drama']</td>\n",
       "      <td>Yashiro is the president of the Shinseikai Ent...</td>\n",
       "      <td>['yaoi', 'boys love', 'gay', 'anime', 'yakuza'...</td>\n",
       "      <td>Kaori Makita</td>\n",
       "      <td>['Kou Yoneda', 'Tarusuke Shingaki', 'Wataru Ha...</td>\n",
       "      <td>Hiroshi Seko</td>\n",
       "      <td>-2020</td>\n",
       "      <td>/title/tt10675392/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13423</th>\n",
       "      <td>99</td>\n",
       "      <td>2 hours 15 minutes</td>\n",
       "      <td>7.3</td>\n",
       "      <td>2.9K</td>\n",
       "      <td>['Comedy', 'Crime', 'Drama']</td>\n",
       "      <td>A gangster deputes two of his men to recover m...</td>\n",
       "      <td>['cricket the sport', 'briefcase', 'caper', 'e...</td>\n",
       "      <td>Krishna D.K.</td>\n",
       "      <td>['Raj Nidimoru', 'Krishna D.K.', 'Sita Menon',...</td>\n",
       "      <td>Raj Nidimoru</td>\n",
       "      <td>(I) (2009)</td>\n",
       "      <td>/title/tt1370429/</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>14641 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          movie title  \\\n",
       "4782                           Golmaal: Fun Unlimited   \n",
       "9291                           The Remains of the Day   \n",
       "3137                                      Blue Iguana   \n",
       "17052                                        Nocturna   \n",
       "675                                         Alexander   \n",
       "...                                               ...   \n",
       "6365                                         Yalghaar   \n",
       "7172                                 Brown of Harvard   \n",
       "12644                                           Deseo   \n",
       "23970  Saezuru Tori Wa Habatakanai: The Clouds Gather   \n",
       "13423                                              99   \n",
       "\n",
       "                       Run Time Rating User Rating  \\\n",
       "4782         2 hours 30 minutes    7.4         17K   \n",
       "9291         2 hours 14 minutes    7.8         74K   \n",
       "3137          1 hour 40 minutes    5.6        5.2K   \n",
       "17052         1 hour 20 minutes    7.2        2.4K   \n",
       "675    $155,000,000 (estimated)    5.6        169K   \n",
       "...                         ...    ...         ...   \n",
       "6365         2 hours 38 minutes    6.4          1K   \n",
       "7172               not-released    6.2        1.5K   \n",
       "12644         1 hour 37 minutes    4.6         417   \n",
       "23970         1 hour 25 minutes    6.9         681   \n",
       "13423        2 hours 15 minutes    7.3        2.9K   \n",
       "\n",
       "                                    Generes  \\\n",
       "4782          ['Action', 'Comedy', 'Drama']   \n",
       "9291                   ['Drama', 'Romance']   \n",
       "3137          ['Action', 'Comedy', 'Crime']   \n",
       "17052  ['Animation', 'Adventure', 'Family']   \n",
       "675        ['Action', 'Biography', 'Drama']   \n",
       "...                                     ...   \n",
       "6365           ['Action', 'Romance', 'War']   \n",
       "7172         ['Action', 'Drama', 'Romance']   \n",
       "12644        ['Comedy', 'Drama', 'Romance']   \n",
       "23970       ['Animation', 'Crime', 'Drama']   \n",
       "13423          ['Comedy', 'Crime', 'Drama']   \n",
       "\n",
       "                                                Overview  \\\n",
       "4782   Four runaway crooks take shelter in a bungalow...   \n",
       "9291   A butler who sacrificed body and soul to servi...   \n",
       "3137   Ex-jailbirds Eddie and Paul are on parole and ...   \n",
       "17052  An orphan boy named Tim is afraid of the dark....   \n",
       "675    Alexander, the King of Macedonia and one of th...   \n",
       "...                                                  ...   \n",
       "6365   The film \"explores what happens in the lives o...   \n",
       "7172   Tom Brown shows up at Harvard, confident and a...   \n",
       "12644  A succession of erotic encounters weaved into ...   \n",
       "23970  Yashiro is the president of the Shinseikai Ent...   \n",
       "13423  A gangster deputes two of his men to recover m...   \n",
       "\n",
       "                                            Plot Kyeword  \\\n",
       "4782   ['blind couple', 'friend', 'mute', 'slacker', ...   \n",
       "9291   ['class differences', 'butler', 'housekeeper',...   \n",
       "3137   ['singing in a car', 'reference to the world c...   \n",
       "17052  ['orphan', 'night', 'cat', 'one word title', '...   \n",
       "675    ['ancient greece', 'greek', 'macedonia', 'sex ...   \n",
       "...                                                  ...   \n",
       "6365                                            ['live']   \n",
       "7172   ['harvard', 'no homoeroticism', 'pre code film...   \n",
       "12644  ['smoking marijuana', 'female full frontal nud...   \n",
       "23970  ['yaoi', 'boys love', 'gay', 'anime', 'yakuza'...   \n",
       "13423  ['cricket the sport', 'briefcase', 'caper', 'e...   \n",
       "\n",
       "                    Director  \\\n",
       "4782            Rohit Shetty   \n",
       "9291             James Ivory   \n",
       "3137             Hadi Hajaig   \n",
       "17052           Adrià García   \n",
       "675             Oliver Stone   \n",
       "...                      ...   \n",
       "6365             Hassan Rana   \n",
       "7172             Jack Conway   \n",
       "12644  Antonio Zavala Kugler   \n",
       "23970           Kaori Makita   \n",
       "13423           Krishna D.K.   \n",
       "\n",
       "                                             Top 5 Casts              Writer  \\\n",
       "4782   ['Ajay Devgn', 'Arshad Warsi', 'Sharman Joshi'...         Neeraj Vora   \n",
       "9291   ['Ruth Prawer Jhabvala', 'Anthony Hopkins', 'E...      Kazuo Ishiguro   \n",
       "3137   ['Sam Rockwell', 'Phoebe Fox', 'Ben Schwartz',...         Hadi Hajaig   \n",
       "17052  ['Adrià García', 'Víctor Maldonado', 'Teresa V...    Víctor Maldonado   \n",
       "675    ['Christopher Kyle', 'Laeta Kalogridis', 'Coli...        Oliver Stone   \n",
       "...                                                  ...                 ...   \n",
       "6365   ['Shaan Shahid', 'Humayun Saeed', 'Adnan Siddi...         Hassan Rana   \n",
       "7172   ['Donald Ogden Stewart', 'Andrew Percival Youn...  Rida Johnson Young   \n",
       "12644  ['Antonio Zavala Kugler', 'Christian Bach', 'A...   Arthur Schnitzler   \n",
       "23970  ['Kou Yoneda', 'Tarusuke Shingaki', 'Wataru Ha...        Hiroshi Seko   \n",
       "13423  ['Raj Nidimoru', 'Krishna D.K.', 'Sita Menon',...        Raj Nidimoru   \n",
       "\n",
       "             year                path  \n",
       "4782        -2006   /title/tt0495034/  \n",
       "9291        -1993   /title/tt0107943/  \n",
       "3137        -2018   /title/tt2316479/  \n",
       "17052       -2007   /title/tt0836682/  \n",
       "675         -2004   /title/tt0346491/  \n",
       "...           ...                 ...  \n",
       "6365        -2017   /title/tt3945864/  \n",
       "7172        -1926   /title/tt0016690/  \n",
       "12644       -2013   /title/tt1236434/  \n",
       "23970       -2020  /title/tt10675392/  \n",
       "13423  (I) (2009)   /title/tt1370429/  \n",
       "\n",
       "[14641 rows x 12 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie title</th>\n",
       "      <th>Run Time</th>\n",
       "      <th>Rating</th>\n",
       "      <th>User Rating</th>\n",
       "      <th>Generes</th>\n",
       "      <th>Overview</th>\n",
       "      <th>Plot Kyeword</th>\n",
       "      <th>Director</th>\n",
       "      <th>Top 5 Casts</th>\n",
       "      <th>Writer</th>\n",
       "      <th>year</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20683</th>\n",
       "      <td>The Animals</td>\n",
       "      <td>not-released</td>\n",
       "      <td>4.2</td>\n",
       "      <td>398</td>\n",
       "      <td>['Western']</td>\n",
       "      <td>A woman tracks down the five men who raped her...</td>\n",
       "      <td>['rape and revenge', 'arizona territory', 'ari...</td>\n",
       "      <td>Ron Joy</td>\n",
       "      <td>['Michele Carey', 'Henry Silva', 'Keenan Wynn'...</td>\n",
       "      <td>Richard Bakalyan</td>\n",
       "      <td>-1970</td>\n",
       "      <td>/title/tt0065407/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8040</th>\n",
       "      <td>The Lincoln Lawyer</td>\n",
       "      <td>$40,000,000 (estimated)</td>\n",
       "      <td>7.3</td>\n",
       "      <td>236K</td>\n",
       "      <td>['Crime', 'Drama', 'Mystery']</td>\n",
       "      <td>A lawyer defending a wealthy man begins to bel...</td>\n",
       "      <td>['defense lawyer', 'plot twist', 'drug rehabil...</td>\n",
       "      <td>Brad Furman</td>\n",
       "      <td>['Michael Connelly', 'Matthew McConaughey', 'M...</td>\n",
       "      <td>John Romano</td>\n",
       "      <td>-2011</td>\n",
       "      <td>/title/tt1189340/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23664</th>\n",
       "      <td>What's the Worst That Could Happen?</td>\n",
       "      <td>1 hour 34 minutes</td>\n",
       "      <td>5.4</td>\n",
       "      <td>16K</td>\n",
       "      <td>['Comedy', 'Crime']</td>\n",
       "      <td>A rich man catches a thief burglarizing his ho...</td>\n",
       "      <td>['breaking and entering', 'bankruptcy', 'quest...</td>\n",
       "      <td>Sam Weisman</td>\n",
       "      <td>['Matthew Chapman', 'Martin Lawrence', 'Danny ...</td>\n",
       "      <td>Donald E. Westlake</td>\n",
       "      <td>-2001</td>\n",
       "      <td>/title/tt0161083/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9078</th>\n",
       "      <td>Cleopatra</td>\n",
       "      <td>not-released</td>\n",
       "      <td>6.2</td>\n",
       "      <td>652</td>\n",
       "      <td>['Animation', 'History', 'Romance']</td>\n",
       "      <td>In order to foil the enemy aliens' \"Cleopatra ...</td>\n",
       "      <td>['adult anime', 'adult animation', 'anime', 'd...</td>\n",
       "      <td>Osamu Tezuka</td>\n",
       "      <td>['Osamu Tezuka', 'Shigemi Satoyoshi', 'Chinats...</td>\n",
       "      <td>Eiichi Yamamoto</td>\n",
       "      <td>-1963</td>\n",
       "      <td>/title/tt0056937/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17118</th>\n",
       "      <td>Seven Cities of Gold</td>\n",
       "      <td>1 hour 43 minutes</td>\n",
       "      <td>5.9</td>\n",
       "      <td>479</td>\n",
       "      <td>['Adventure', 'Biography', 'History']</td>\n",
       "      <td>In 1769, a Spanish expedition to California se...</td>\n",
       "      <td>['limping man', 'prologue', 'voice over narrat...</td>\n",
       "      <td>Robert D. Webb</td>\n",
       "      <td>['John C. Higgins', 'Joseph Petracca', 'Richar...</td>\n",
       "      <td>Richard L. Breen</td>\n",
       "      <td>-1955</td>\n",
       "      <td>/title/tt0048603/</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1248</th>\n",
       "      <td>The Wall</td>\n",
       "      <td>1 hour 28 minutes</td>\n",
       "      <td>6.2</td>\n",
       "      <td>27K</td>\n",
       "      <td>['Action', 'Drama', 'Thriller']</td>\n",
       "      <td>Two American Soldiers are trapped by a lethal ...</td>\n",
       "      <td>['sniper', 'soldier', 'deception', 'wound', 'd...</td>\n",
       "      <td>Doug Liman</td>\n",
       "      <td>['Aaron Taylor-Johnson', 'John Cena', 'Laith N...</td>\n",
       "      <td>Dwain Worrell</td>\n",
       "      <td>(II) (2017)</td>\n",
       "      <td>/title/tt4218696/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7091</th>\n",
       "      <td>Commando 3</td>\n",
       "      <td>2 hours 13 minutes</td>\n",
       "      <td>5.7</td>\n",
       "      <td>3K</td>\n",
       "      <td>['Action', 'Adventure', 'Thriller']</td>\n",
       "      <td>Karan goes to London to stop a terrorist attac...</td>\n",
       "      <td>['chase']</td>\n",
       "      <td>Aditya Datt</td>\n",
       "      <td>['Junaid Wasi', 'Gulshan Devaiah', 'Robin Chau...</td>\n",
       "      <td>Darius Yarmil</td>\n",
       "      <td>-2019</td>\n",
       "      <td>/title/tt8983168/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15635</th>\n",
       "      <td>Adam Resurrected</td>\n",
       "      <td>1 hour 46 minutes</td>\n",
       "      <td>6.2</td>\n",
       "      <td>4.2K</td>\n",
       "      <td>['Drama', 'War']</td>\n",
       "      <td>In the aftermath of World War II, a former cir...</td>\n",
       "      <td>['man wears a white suit', 'desert hotel', 'ti...</td>\n",
       "      <td>Paul Schrader</td>\n",
       "      <td>['Noah Stollman', 'Jeff Goldblum', 'Willem Daf...</td>\n",
       "      <td>Yoram Kaniuk</td>\n",
       "      <td>-2008</td>\n",
       "      <td>/title/tt0479341/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12914</th>\n",
       "      <td>Main Street</td>\n",
       "      <td>1 hour 32 minutes</td>\n",
       "      <td>4.7</td>\n",
       "      <td>2.9K</td>\n",
       "      <td>['Drama']</td>\n",
       "      <td>Durham is slowly dying like the tobacco busine...</td>\n",
       "      <td>['economic depression', 'reference to lucky st...</td>\n",
       "      <td>John Doyle</td>\n",
       "      <td>['Colin Firth', 'Ellen Burstyn', 'Patricia Cla...</td>\n",
       "      <td>Horton Foote</td>\n",
       "      <td>-2010</td>\n",
       "      <td>/title/tt1365483/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2825</th>\n",
       "      <td>The Outrage</td>\n",
       "      <td>1 hour 36 minutes</td>\n",
       "      <td>6.2</td>\n",
       "      <td>2.2K</td>\n",
       "      <td>['Crime', 'Drama', 'Western']</td>\n",
       "      <td>Travelers in the 1870s Southwest discuss a rec...</td>\n",
       "      <td>['highwayman', 'man bound and gagged', 'gun du...</td>\n",
       "      <td>Martin Ritt</td>\n",
       "      <td>['Akira Kurosawa', 'Ryûnosuke Akutagawa', 'Pau...</td>\n",
       "      <td>Michael Kanin</td>\n",
       "      <td>-1964</td>\n",
       "      <td>/title/tt0058437/</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4880 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                               movie title                 Run Time Rating  \\\n",
       "20683                          The Animals             not-released    4.2   \n",
       "8040                    The Lincoln Lawyer  $40,000,000 (estimated)    7.3   \n",
       "23664  What's the Worst That Could Happen?        1 hour 34 minutes    5.4   \n",
       "9078                             Cleopatra             not-released    6.2   \n",
       "17118                 Seven Cities of Gold        1 hour 43 minutes    5.9   \n",
       "...                                    ...                      ...    ...   \n",
       "1248                              The Wall        1 hour 28 minutes    6.2   \n",
       "7091                            Commando 3       2 hours 13 minutes    5.7   \n",
       "15635                     Adam Resurrected        1 hour 46 minutes    6.2   \n",
       "12914                          Main Street        1 hour 32 minutes    4.7   \n",
       "2825                           The Outrage        1 hour 36 minutes    6.2   \n",
       "\n",
       "      User Rating                                Generes  \\\n",
       "20683         398                            ['Western']   \n",
       "8040         236K          ['Crime', 'Drama', 'Mystery']   \n",
       "23664         16K                    ['Comedy', 'Crime']   \n",
       "9078          652    ['Animation', 'History', 'Romance']   \n",
       "17118         479  ['Adventure', 'Biography', 'History']   \n",
       "...           ...                                    ...   \n",
       "1248          27K        ['Action', 'Drama', 'Thriller']   \n",
       "7091           3K    ['Action', 'Adventure', 'Thriller']   \n",
       "15635        4.2K                       ['Drama', 'War']   \n",
       "12914        2.9K                              ['Drama']   \n",
       "2825         2.2K          ['Crime', 'Drama', 'Western']   \n",
       "\n",
       "                                                Overview  \\\n",
       "20683  A woman tracks down the five men who raped her...   \n",
       "8040   A lawyer defending a wealthy man begins to bel...   \n",
       "23664  A rich man catches a thief burglarizing his ho...   \n",
       "9078   In order to foil the enemy aliens' \"Cleopatra ...   \n",
       "17118  In 1769, a Spanish expedition to California se...   \n",
       "...                                                  ...   \n",
       "1248   Two American Soldiers are trapped by a lethal ...   \n",
       "7091   Karan goes to London to stop a terrorist attac...   \n",
       "15635  In the aftermath of World War II, a former cir...   \n",
       "12914  Durham is slowly dying like the tobacco busine...   \n",
       "2825   Travelers in the 1870s Southwest discuss a rec...   \n",
       "\n",
       "                                            Plot Kyeword        Director  \\\n",
       "20683  ['rape and revenge', 'arizona territory', 'ari...         Ron Joy   \n",
       "8040   ['defense lawyer', 'plot twist', 'drug rehabil...     Brad Furman   \n",
       "23664  ['breaking and entering', 'bankruptcy', 'quest...     Sam Weisman   \n",
       "9078   ['adult anime', 'adult animation', 'anime', 'd...    Osamu Tezuka   \n",
       "17118  ['limping man', 'prologue', 'voice over narrat...  Robert D. Webb   \n",
       "...                                                  ...             ...   \n",
       "1248   ['sniper', 'soldier', 'deception', 'wound', 'd...      Doug Liman   \n",
       "7091                                           ['chase']     Aditya Datt   \n",
       "15635  ['man wears a white suit', 'desert hotel', 'ti...   Paul Schrader   \n",
       "12914  ['economic depression', 'reference to lucky st...      John Doyle   \n",
       "2825   ['highwayman', 'man bound and gagged', 'gun du...     Martin Ritt   \n",
       "\n",
       "                                             Top 5 Casts              Writer  \\\n",
       "20683  ['Michele Carey', 'Henry Silva', 'Keenan Wynn'...    Richard Bakalyan   \n",
       "8040   ['Michael Connelly', 'Matthew McConaughey', 'M...         John Romano   \n",
       "23664  ['Matthew Chapman', 'Martin Lawrence', 'Danny ...  Donald E. Westlake   \n",
       "9078   ['Osamu Tezuka', 'Shigemi Satoyoshi', 'Chinats...     Eiichi Yamamoto   \n",
       "17118  ['John C. Higgins', 'Joseph Petracca', 'Richar...    Richard L. Breen   \n",
       "...                                                  ...                 ...   \n",
       "1248   ['Aaron Taylor-Johnson', 'John Cena', 'Laith N...       Dwain Worrell   \n",
       "7091   ['Junaid Wasi', 'Gulshan Devaiah', 'Robin Chau...       Darius Yarmil   \n",
       "15635  ['Noah Stollman', 'Jeff Goldblum', 'Willem Daf...        Yoram Kaniuk   \n",
       "12914  ['Colin Firth', 'Ellen Burstyn', 'Patricia Cla...        Horton Foote   \n",
       "2825   ['Akira Kurosawa', 'Ryûnosuke Akutagawa', 'Pau...       Michael Kanin   \n",
       "\n",
       "              year               path  \n",
       "20683        -1970  /title/tt0065407/  \n",
       "8040         -2011  /title/tt1189340/  \n",
       "23664        -2001  /title/tt0161083/  \n",
       "9078         -1963  /title/tt0056937/  \n",
       "17118        -1955  /title/tt0048603/  \n",
       "...            ...                ...  \n",
       "1248   (II) (2017)  /title/tt4218696/  \n",
       "7091         -2019  /title/tt8983168/  \n",
       "15635        -2008  /title/tt0479341/  \n",
       "12914        -2010  /title/tt1365483/  \n",
       "2825         -1964  /title/tt0058437/  \n",
       "\n",
       "[4880 rows x 12 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dev"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>movie title</th>\n",
       "      <th>Run Time</th>\n",
       "      <th>Rating</th>\n",
       "      <th>User Rating</th>\n",
       "      <th>Generes</th>\n",
       "      <th>Overview</th>\n",
       "      <th>Plot Kyeword</th>\n",
       "      <th>Director</th>\n",
       "      <th>Top 5 Casts</th>\n",
       "      <th>Writer</th>\n",
       "      <th>year</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>16788</th>\n",
       "      <td>High in the Clouds</td>\n",
       "      <td>not-released</td>\n",
       "      <td>no-rating</td>\n",
       "      <td>0</td>\n",
       "      <td>['Animation', 'Adventure', 'Comedy']</td>\n",
       "      <td>A squirrel embarks on a journey to find an ani...</td>\n",
       "      <td>['journey', 'cloud', 'animal', 'friend', 'trag...</td>\n",
       "      <td>Timothy Reckart</td>\n",
       "      <td>['Jon Croker', 'Geoff Dunbar', 'Timothy Reckar...</td>\n",
       "      <td>Philip Ardagh</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt1458167/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17155</th>\n",
       "      <td>Curious George 3: Back to the Jungle</td>\n",
       "      <td>1 hour 21 minutes</td>\n",
       "      <td>5.4</td>\n",
       "      <td>598</td>\n",
       "      <td>['Animation', 'Adventure', 'Comedy']</td>\n",
       "      <td>Curious George goes on an epic adventure to sp...</td>\n",
       "      <td>['sequel', 'third part', 'jungle', 'curious ge...</td>\n",
       "      <td>Phil Weinstein</td>\n",
       "      <td>['H.A. Rey', 'Chuck Tately', 'Frank Welker', '...</td>\n",
       "      <td>Margret Rey</td>\n",
       "      <td>-2015</td>\n",
       "      <td>/title/tt4622340/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5985</th>\n",
       "      <td>Tarkan: Altin Madalyon</td>\n",
       "      <td>not-released</td>\n",
       "      <td>6.2</td>\n",
       "      <td>1.6K</td>\n",
       "      <td>['Action', 'Adventure', 'History']</td>\n",
       "      <td>The story of Tarkan and his friends efforts to...</td>\n",
       "      <td>['black magic', 'blood', 'axe', 'snake', 'pros...</td>\n",
       "      <td>Mehmet Aslan</td>\n",
       "      <td>['Sadik Sendil', 'Kartal Tibet', 'Eva Bender',...</td>\n",
       "      <td>Sezgin Burak</td>\n",
       "      <td>-1973</td>\n",
       "      <td>/title/tt0274933/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1640</th>\n",
       "      <td>Harley Davidson and the Marlboro Man</td>\n",
       "      <td>$23,000,000 (estimated)</td>\n",
       "      <td>6.1</td>\n",
       "      <td>20K</td>\n",
       "      <td>['Action', 'Crime', 'Drama']</td>\n",
       "      <td>Forced by the imminent foreclosure of their fr...</td>\n",
       "      <td>['swimming pool', 'night club', 'voyeurism', '...</td>\n",
       "      <td>Simon Wincer</td>\n",
       "      <td>['Mickey Rourke', 'Don Johnson', 'Chelsea Fiel...</td>\n",
       "      <td>Don Michael Paul</td>\n",
       "      <td>-1991</td>\n",
       "      <td>/title/tt0102005/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9826</th>\n",
       "      <td>I Am All Girls</td>\n",
       "      <td>not-released</td>\n",
       "      <td>5.9</td>\n",
       "      <td>5.8K</td>\n",
       "      <td>['Crime', 'Drama', 'Mystery']</td>\n",
       "      <td>A special crimes investigator forms an unlikel...</td>\n",
       "      <td>['child', 'bond', 'investigator', 'murder', 'c...</td>\n",
       "      <td>Donovan Marsh</td>\n",
       "      <td>['Marcell Greeff', 'Emile Leuvennink', 'Erica ...</td>\n",
       "      <td>Wayne Fitzjohn</td>\n",
       "      <td>-2021</td>\n",
       "      <td>/title/tt9013182/</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11825</th>\n",
       "      <td>The Apostle</td>\n",
       "      <td>2 hours 14 minutes</td>\n",
       "      <td>7.2</td>\n",
       "      <td>14K</td>\n",
       "      <td>['Drama']</td>\n",
       "      <td>After his happy life spins out of control, a p...</td>\n",
       "      <td>['southern gothic', 'timeframe 1930s', 'preach...</td>\n",
       "      <td>Robert Duvall</td>\n",
       "      <td>['Robert Duvall', 'Todd Allen', 'Paul Bagget',...</td>\n",
       "      <td>Robert Duvall</td>\n",
       "      <td>-1997</td>\n",
       "      <td>/title/tt0118632/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14740</th>\n",
       "      <td>My Normal</td>\n",
       "      <td>not-released</td>\n",
       "      <td>4.1</td>\n",
       "      <td>756</td>\n",
       "      <td>['Drama', 'Romance']</td>\n",
       "      <td>A lesbian dominatrix finds a way to use her un...</td>\n",
       "      <td>['dominatrix', 'lesbian', 'lesbian kiss', 'blo...</td>\n",
       "      <td>Irving Schwartz</td>\n",
       "      <td>['Renee Garzon', 'Keith Planit', 'Nicole LaLib...</td>\n",
       "      <td>Abdul Malik Abbott</td>\n",
       "      <td>-2009</td>\n",
       "      <td>/title/tt1117983/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9818</th>\n",
       "      <td>Lust och fägring stor</td>\n",
       "      <td>2 hours 10 minutes</td>\n",
       "      <td>6.9</td>\n",
       "      <td>6.5K</td>\n",
       "      <td>['Drama', 'Romance', 'War']</td>\n",
       "      <td>Malmö, Sweden during the Second World War. Sti...</td>\n",
       "      <td>['extramarital affair', 'teacher student sex',...</td>\n",
       "      <td>Bo Widerberg</td>\n",
       "      <td>['Johan Widerberg', 'Marika Lagercrantz', 'Tom...</td>\n",
       "      <td>Bo Widerberg</td>\n",
       "      <td>-1995</td>\n",
       "      <td>/title/tt0113720/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4041</th>\n",
       "      <td>RoboCop Returns</td>\n",
       "      <td>not-released</td>\n",
       "      <td>no-rating</td>\n",
       "      <td>0</td>\n",
       "      <td>['Action', 'Adventure', 'Crime']</td>\n",
       "      <td>RoboCop returns to fight crime in Detroit.</td>\n",
       "      <td>['sequel', 'reboot', 'non comic book superhero...</td>\n",
       "      <td>Abe Forsythe</td>\n",
       "      <td>['Edward Neumeier', 'Justin Rhodes', 'Abe Fors...</td>\n",
       "      <td>Michael Miner</td>\n",
       "      <td>NaN</td>\n",
       "      <td>/title/tt8688550/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23755</th>\n",
       "      <td>The Maiden Heist</td>\n",
       "      <td>1 hour 30 minutes</td>\n",
       "      <td>6</td>\n",
       "      <td>17K</td>\n",
       "      <td>['Comedy', 'Crime']</td>\n",
       "      <td>A comedy centered on three museum security gua...</td>\n",
       "      <td>['heist crime', 'caper crime', 'forgery', 'hei...</td>\n",
       "      <td>Peter Hewitt</td>\n",
       "      <td>['Christopher Walken', 'Joseph McKenna', 'Wynn...</td>\n",
       "      <td>Michael LeSieur</td>\n",
       "      <td>-2009</td>\n",
       "      <td>/title/tt1107860/</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4881 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                movie title                 Run Time  \\\n",
       "16788                    High in the Clouds             not-released   \n",
       "17155  Curious George 3: Back to the Jungle        1 hour 21 minutes   \n",
       "5985                 Tarkan: Altin Madalyon             not-released   \n",
       "1640   Harley Davidson and the Marlboro Man  $23,000,000 (estimated)   \n",
       "9826                         I Am All Girls             not-released   \n",
       "...                                     ...                      ...   \n",
       "11825                           The Apostle       2 hours 14 minutes   \n",
       "14740                             My Normal             not-released   \n",
       "9818                  Lust och fägring stor       2 hours 10 minutes   \n",
       "4041                        RoboCop Returns             not-released   \n",
       "23755                      The Maiden Heist        1 hour 30 minutes   \n",
       "\n",
       "          Rating User Rating                               Generes  \\\n",
       "16788  no-rating           0  ['Animation', 'Adventure', 'Comedy']   \n",
       "17155        5.4         598  ['Animation', 'Adventure', 'Comedy']   \n",
       "5985         6.2        1.6K    ['Action', 'Adventure', 'History']   \n",
       "1640         6.1         20K          ['Action', 'Crime', 'Drama']   \n",
       "9826         5.9        5.8K         ['Crime', 'Drama', 'Mystery']   \n",
       "...          ...         ...                                   ...   \n",
       "11825        7.2         14K                             ['Drama']   \n",
       "14740        4.1         756                  ['Drama', 'Romance']   \n",
       "9818         6.9        6.5K           ['Drama', 'Romance', 'War']   \n",
       "4041   no-rating           0      ['Action', 'Adventure', 'Crime']   \n",
       "23755          6         17K                   ['Comedy', 'Crime']   \n",
       "\n",
       "                                                Overview  \\\n",
       "16788  A squirrel embarks on a journey to find an ani...   \n",
       "17155  Curious George goes on an epic adventure to sp...   \n",
       "5985   The story of Tarkan and his friends efforts to...   \n",
       "1640   Forced by the imminent foreclosure of their fr...   \n",
       "9826   A special crimes investigator forms an unlikel...   \n",
       "...                                                  ...   \n",
       "11825  After his happy life spins out of control, a p...   \n",
       "14740  A lesbian dominatrix finds a way to use her un...   \n",
       "9818   Malmö, Sweden during the Second World War. Sti...   \n",
       "4041          RoboCop returns to fight crime in Detroit.   \n",
       "23755  A comedy centered on three museum security gua...   \n",
       "\n",
       "                                            Plot Kyeword         Director  \\\n",
       "16788  ['journey', 'cloud', 'animal', 'friend', 'trag...  Timothy Reckart   \n",
       "17155  ['sequel', 'third part', 'jungle', 'curious ge...   Phil Weinstein   \n",
       "5985   ['black magic', 'blood', 'axe', 'snake', 'pros...     Mehmet Aslan   \n",
       "1640   ['swimming pool', 'night club', 'voyeurism', '...     Simon Wincer   \n",
       "9826   ['child', 'bond', 'investigator', 'murder', 'c...    Donovan Marsh   \n",
       "...                                                  ...              ...   \n",
       "11825  ['southern gothic', 'timeframe 1930s', 'preach...    Robert Duvall   \n",
       "14740  ['dominatrix', 'lesbian', 'lesbian kiss', 'blo...  Irving Schwartz   \n",
       "9818   ['extramarital affair', 'teacher student sex',...     Bo Widerberg   \n",
       "4041   ['sequel', 'reboot', 'non comic book superhero...     Abe Forsythe   \n",
       "23755  ['heist crime', 'caper crime', 'forgery', 'hei...     Peter Hewitt   \n",
       "\n",
       "                                             Top 5 Casts              Writer  \\\n",
       "16788  ['Jon Croker', 'Geoff Dunbar', 'Timothy Reckar...       Philip Ardagh   \n",
       "17155  ['H.A. Rey', 'Chuck Tately', 'Frank Welker', '...         Margret Rey   \n",
       "5985   ['Sadik Sendil', 'Kartal Tibet', 'Eva Bender',...        Sezgin Burak   \n",
       "1640   ['Mickey Rourke', 'Don Johnson', 'Chelsea Fiel...    Don Michael Paul   \n",
       "9826   ['Marcell Greeff', 'Emile Leuvennink', 'Erica ...      Wayne Fitzjohn   \n",
       "...                                                  ...                 ...   \n",
       "11825  ['Robert Duvall', 'Todd Allen', 'Paul Bagget',...       Robert Duvall   \n",
       "14740  ['Renee Garzon', 'Keith Planit', 'Nicole LaLib...  Abdul Malik Abbott   \n",
       "9818   ['Johan Widerberg', 'Marika Lagercrantz', 'Tom...        Bo Widerberg   \n",
       "4041   ['Edward Neumeier', 'Justin Rhodes', 'Abe Fors...       Michael Miner   \n",
       "23755  ['Christopher Walken', 'Joseph McKenna', 'Wynn...     Michael LeSieur   \n",
       "\n",
       "        year               path  \n",
       "16788  -2022  /title/tt1458167/  \n",
       "17155  -2015  /title/tt4622340/  \n",
       "5985   -1973  /title/tt0274933/  \n",
       "1640   -1991  /title/tt0102005/  \n",
       "9826   -2021  /title/tt9013182/  \n",
       "...      ...                ...  \n",
       "11825  -1997  /title/tt0118632/  \n",
       "14740  -2009  /title/tt1117983/  \n",
       "9818   -1995  /title/tt0113720/  \n",
       "4041     NaN  /title/tt8688550/  \n",
       "23755  -2009  /title/tt1107860/  \n",
       "\n",
       "[4881 rows x 12 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test"
   ]
  },
  {
   "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>movie title</th>\n",
       "      <th>Run Time</th>\n",
       "      <th>Rating</th>\n",
       "      <th>User Rating</th>\n",
       "      <th>Generes</th>\n",
       "      <th>Overview</th>\n",
       "      <th>Plot Kyeword</th>\n",
       "      <th>Director</th>\n",
       "      <th>Top 5 Casts</th>\n",
       "      <th>Writer</th>\n",
       "      <th>year</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>24158</td>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>24402</td>\n",
       "      <td>23624</td>\n",
       "      <td>24402</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>23922</td>\n",
       "      <td>1556</td>\n",
       "      <td>91</td>\n",
       "      <td>1684</td>\n",
       "      <td>746</td>\n",
       "      <td>23957</td>\n",
       "      <td>21546</td>\n",
       "      <td>11604</td>\n",
       "      <td>24211</td>\n",
       "      <td>15562</td>\n",
       "      <td>250</td>\n",
       "      <td>23922</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>Rage</td>\n",
       "      <td>not-released</td>\n",
       "      <td>no-rating</td>\n",
       "      <td>0</td>\n",
       "      <td>['Drama']</td>\n",
       "      <td>none</td>\n",
       "      <td>[]</td>\n",
       "      <td>See company contact information</td>\n",
       "      <td>['See producer', 'See preliminary cast']</td>\n",
       "      <td>See writer</td>\n",
       "      <td>-2022</td>\n",
       "      <td>/title/tt0114224/</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>4</td>\n",
       "      <td>8475</td>\n",
       "      <td>1740</td>\n",
       "      <td>1740</td>\n",
       "      <td>943</td>\n",
       "      <td>142</td>\n",
       "      <td>1696</td>\n",
       "      <td>142</td>\n",
       "      <td>142</td>\n",
       "      <td>142</td>\n",
       "      <td>1201</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       movie title      Run Time     Rating User Rating    Generes Overview  \\\n",
       "count        24402         24402      24402       24402      24402    24158   \n",
       "unique       23922          1556         91        1684        746    23957   \n",
       "top           Rage  not-released  no-rating           0  ['Drama']     none   \n",
       "freq             4          8475       1740        1740        943      142   \n",
       "\n",
       "       Plot Kyeword                         Director  \\\n",
       "count         24402                            24402   \n",
       "unique        21546                            11604   \n",
       "top              []  See company contact information   \n",
       "freq           1696                              142   \n",
       "\n",
       "                                     Top 5 Casts      Writer   year  \\\n",
       "count                                      24402       24402  23624   \n",
       "unique                                     24211       15562    250   \n",
       "top     ['See producer', 'See preliminary cast']  See writer  -2022   \n",
       "freq                                         142         142   1201   \n",
       "\n",
       "                     path  \n",
       "count               24402  \n",
       "unique              23922  \n",
       "top     /title/tt0114224/  \n",
       "freq                    4  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Rage                                         4\n",
       "The Killer                                   4\n",
       "The Beast                                    4\n",
       "Spiral                                       4\n",
       "The Silence                                  3\n",
       "                                            ..\n",
       "The Mule                                     1\n",
       "Donnie Brasco                                1\n",
       "Little Miss Sunshine                         1\n",
       "Three Billboards Outside Ebbing, Missouri    1\n",
       "Guys and Dolls                               1\n",
       "Name: movie title, Length: 23922, dtype: int64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"movie title\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "not-released                  8475\n",
       "1 hour 30 minutes              503\n",
       "1 hour 35 minutes              376\n",
       "1 hour 38 minutes              350\n",
       "1 hour 31 minutes              338\n",
       "                              ... \n",
       "$14,492                          1\n",
       "$181,415                         1\n",
       "$11,060,485                      1\n",
       "$1,043,910                       1\n",
       "FRF 24,000,000 (estimated)       1\n",
       "Name: Run Time, Length: 1556, dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"Run Time\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "no-rating    1740\n",
       "6.4           852\n",
       "6.2           847\n",
       "6.1           819\n",
       "6.3           809\n",
       "             ... \n",
       "9.9             2\n",
       "9.8             2\n",
       "9.4             2\n",
       "1               2\n",
       "9.5             2\n",
       "Name: Rating, Length: 91, dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"Rating\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       1740\n",
       "11K      325\n",
       "1.2K     323\n",
       "1.1K     315\n",
       "1.3K     295\n",
       "        ... \n",
       "501K       1\n",
       "769K       1\n",
       "321K       1\n",
       "991K       1\n",
       "347K       1\n",
       "Name: User Rating, Length: 1684, dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"User Rating\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Drama']                            943\n",
       "['Action', 'Crime', 'Drama']         867\n",
       "['Crime', 'Drama', 'Thriller']       609\n",
       "['Comedy', 'Drama', 'Romance']       608\n",
       "['Crime', 'Drama']                   550\n",
       "                                    ... \n",
       "['Drama', 'Romance', 'Crime']          1\n",
       "['Drama', 'Crime', 'Mystery']          1\n",
       "['Family', 'Adventure', 'Comedy']      1\n",
       "['Crime', 'Mystery', 'Horror']         1\n",
       "['Crime', 'Romance', 'Western']        1\n",
       "Name: Generes, Length: 746, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies[\"Generes\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  }
 ],
 "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
 },
 "nbformat": 4,
 "nbformat_minor": 2
}