Movies_ETL.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import re\n",
    "from sqlalchemy import create_engine \n",
    "import psycopg2\n",
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define a variable for the directory that's holding the data\n",
    "file_dir = \"C:/Users/krumb/Classwork/Movies_ETL\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies_metadata = pd.read_csv(\"Data/movies_metadata.csv\", low_memory=False)\n",
    "ratings = pd.read_csv(\"Data/ratings.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>adult</th>\n",
       "      <th>belongs_to_collection</th>\n",
       "      <th>budget</th>\n",
       "      <th>genres</th>\n",
       "      <th>homepage</th>\n",
       "      <th>id</th>\n",
       "      <th>imdb_id</th>\n",
       "      <th>original_language</th>\n",
       "      <th>original_title</th>\n",
       "      <th>overview</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>{'id': 10194, 'name': 'Toy Story Collection', ...</td>\n",
       "      <td>30000000</td>\n",
       "      <td>[{'id': 16, 'name': 'Animation'}, {'id': 35, '...</td>\n",
       "      <td>http://toystory.disney.com/toy-story</td>\n",
       "      <td>862</td>\n",
       "      <td>tt0114709</td>\n",
       "      <td>en</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>Led by Woody, Andy's toys live happily in his ...</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-10-30</td>\n",
       "      <td>373554033.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Toy Story</td>\n",
       "      <td>False</td>\n",
       "      <td>7.7</td>\n",
       "      <td>5415.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>65000000</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8844</td>\n",
       "      <td>tt0113497</td>\n",
       "      <td>en</td>\n",
       "      <td>Jumanji</td>\n",
       "      <td>When siblings Judy and Peter discover an encha...</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-12-15</td>\n",
       "      <td>262797249.0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}, {'iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>Roll the dice and unleash the excitement!</td>\n",
       "      <td>Jumanji</td>\n",
       "      <td>False</td>\n",
       "      <td>6.9</td>\n",
       "      <td>2413.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>{'id': 119050, 'name': 'Grumpy Old Men Collect...</td>\n",
       "      <td>0</td>\n",
       "      <td>[{'id': 10749, 'name': 'Romance'}, {'id': 35, ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15602</td>\n",
       "      <td>tt0113228</td>\n",
       "      <td>en</td>\n",
       "      <td>Grumpier Old Men</td>\n",
       "      <td>A family wedding reignites the ancient feud be...</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>0.0</td>\n",
       "      <td>101.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Still Yelling. Still Fighting. Still Ready for...</td>\n",
       "      <td>Grumpier Old Men</td>\n",
       "      <td>False</td>\n",
       "      <td>6.5</td>\n",
       "      <td>92.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16000000</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}, {'id': 18, 'nam...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>31357</td>\n",
       "      <td>tt0114885</td>\n",
       "      <td>en</td>\n",
       "      <td>Waiting to Exhale</td>\n",
       "      <td>Cheated on, mistreated and stepped on, the wom...</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>81452156.0</td>\n",
       "      <td>127.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Friends are the people who let you be yourself...</td>\n",
       "      <td>Waiting to Exhale</td>\n",
       "      <td>False</td>\n",
       "      <td>6.1</td>\n",
       "      <td>34.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>{'id': 96871, 'name': 'Father of the Bride Col...</td>\n",
       "      <td>0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11862</td>\n",
       "      <td>tt0113041</td>\n",
       "      <td>en</td>\n",
       "      <td>Father of the Bride Part II</td>\n",
       "      <td>Just when George Banks has recovered from his ...</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-02-10</td>\n",
       "      <td>76578911.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Just When His World Is Back To Normal... He's ...</td>\n",
       "      <td>Father of the Bride Part II</td>\n",
       "      <td>False</td>\n",
       "      <td>5.7</td>\n",
       "      <td>173.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   adult                              belongs_to_collection    budget  \\\n",
       "0  False  {'id': 10194, 'name': 'Toy Story Collection', ...  30000000   \n",
       "1  False                                                NaN  65000000   \n",
       "2  False  {'id': 119050, 'name': 'Grumpy Old Men Collect...         0   \n",
       "3  False                                                NaN  16000000   \n",
       "4  False  {'id': 96871, 'name': 'Father of the Bride Col...         0   \n",
       "\n",
       "                                              genres  \\\n",
       "0  [{'id': 16, 'name': 'Animation'}, {'id': 35, '...   \n",
       "1  [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...   \n",
       "2  [{'id': 10749, 'name': 'Romance'}, {'id': 35, ...   \n",
       "3  [{'id': 35, 'name': 'Comedy'}, {'id': 18, 'nam...   \n",
       "4                     [{'id': 35, 'name': 'Comedy'}]   \n",
       "\n",
       "                               homepage     id    imdb_id original_language  \\\n",
       "0  http://toystory.disney.com/toy-story    862  tt0114709                en   \n",
       "1                                   NaN   8844  tt0113497                en   \n",
       "2                                   NaN  15602  tt0113228                en   \n",
       "3                                   NaN  31357  tt0114885                en   \n",
       "4                                   NaN  11862  tt0113041                en   \n",
       "\n",
       "                original_title  \\\n",
       "0                    Toy Story   \n",
       "1                      Jumanji   \n",
       "2             Grumpier Old Men   \n",
       "3            Waiting to Exhale   \n",
       "4  Father of the Bride Part II   \n",
       "\n",
       "                                            overview  ... release_date  \\\n",
       "0  Led by Woody, Andy's toys live happily in his ...  ...   1995-10-30   \n",
       "1  When siblings Judy and Peter discover an encha...  ...   1995-12-15   \n",
       "2  A family wedding reignites the ancient feud be...  ...   1995-12-22   \n",
       "3  Cheated on, mistreated and stepped on, the wom...  ...   1995-12-22   \n",
       "4  Just when George Banks has recovered from his ...  ...   1995-02-10   \n",
       "\n",
       "       revenue runtime                                   spoken_languages  \\\n",
       "0  373554033.0    81.0           [{'iso_639_1': 'en', 'name': 'English'}]   \n",
       "1  262797249.0   104.0  [{'iso_639_1': 'en', 'name': 'English'}, {'iso...   \n",
       "2          0.0   101.0           [{'iso_639_1': 'en', 'name': 'English'}]   \n",
       "3   81452156.0   127.0           [{'iso_639_1': 'en', 'name': 'English'}]   \n",
       "4   76578911.0   106.0           [{'iso_639_1': 'en', 'name': 'English'}]   \n",
       "\n",
       "     status                                            tagline  \\\n",
       "0  Released                                                NaN   \n",
       "1  Released          Roll the dice and unleash the excitement!   \n",
       "2  Released  Still Yelling. Still Fighting. Still Ready for...   \n",
       "3  Released  Friends are the people who let you be yourself...   \n",
       "4  Released  Just When His World Is Back To Normal... He's ...   \n",
       "\n",
       "                         title  video vote_average vote_count  \n",
       "0                    Toy Story  False          7.7     5415.0  \n",
       "1                      Jumanji  False          6.9     2413.0  \n",
       "2             Grumpier Old Men  False          6.5       92.0  \n",
       "3            Waiting to Exhale  False          6.1       34.0  \n",
       "4  Father of the Bride Part II  False          5.7      173.0  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_metadata.head()"
   ]
  },
  {
   "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>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>110</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1425941529</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>147</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1425942435</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>858</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1425941523</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1221</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1425941546</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1246</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1425941556</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   userId  movieId  rating   timestamp\n",
       "0       1      110     1.0  1425941529\n",
       "1       1      147     4.5  1425942435\n",
       "2       1      858     5.0  1425941523\n",
       "3       1     1221     5.0  1425941546\n",
       "4       1     1246     5.0  1425941556"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\krumb\\Anaconda3\\envs\\PythonData\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3051: DtypeWarning: Columns (10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    }
   ],
   "source": [
    "kaggle_metadata = pd.read_csv(f\"{file_dir}/Data/movies_metadata.csv\")\n",
    "ratings = pd.read_csv(f\"{file_dir}/Data/ratings.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>adult</th>\n",
       "      <th>belongs_to_collection</th>\n",
       "      <th>budget</th>\n",
       "      <th>genres</th>\n",
       "      <th>homepage</th>\n",
       "      <th>id</th>\n",
       "      <th>imdb_id</th>\n",
       "      <th>original_language</th>\n",
       "      <th>original_title</th>\n",
       "      <th>overview</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>45461</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>[{'id': 18, 'name': 'Drama'}, {'id': 10751, 'n...</td>\n",
       "      <td>http://www.imdb.com/title/tt6209470/</td>\n",
       "      <td>439050</td>\n",
       "      <td>tt6209470</td>\n",
       "      <td>fa</td>\n",
       "      <td>رگ خواب</td>\n",
       "      <td>Rising and falling between a man and woman.</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>90.0</td>\n",
       "      <td>[{'iso_639_1': 'fa', 'name': 'فارسی'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Rising and falling between a man and woman</td>\n",
       "      <td>Subdue</td>\n",
       "      <td>False</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45462</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>[{'id': 18, 'name': 'Drama'}]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>111109</td>\n",
       "      <td>tt2028550</td>\n",
       "      <td>tl</td>\n",
       "      <td>Siglo ng Pagluluwal</td>\n",
       "      <td>An artist struggles to finish his work while a...</td>\n",
       "      <td>...</td>\n",
       "      <td>2011-11-17</td>\n",
       "      <td>0.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>[{'iso_639_1': 'tl', 'name': ''}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Century of Birthing</td>\n",
       "      <td>False</td>\n",
       "      <td>9.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45463</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 18, 'nam...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>67758</td>\n",
       "      <td>tt0303758</td>\n",
       "      <td>en</td>\n",
       "      <td>Betrayal</td>\n",
       "      <td>When one of her hits goes wrong, a professiona...</td>\n",
       "      <td>...</td>\n",
       "      <td>2003-08-01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>90.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>A deadly game of wits.</td>\n",
       "      <td>Betrayal</td>\n",
       "      <td>False</td>\n",
       "      <td>3.8</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45464</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>[]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>227506</td>\n",
       "      <td>tt0008536</td>\n",
       "      <td>en</td>\n",
       "      <td>Satana likuyushchiy</td>\n",
       "      <td>In a small town live two brothers, one a minis...</td>\n",
       "      <td>...</td>\n",
       "      <td>1917-10-21</td>\n",
       "      <td>0.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>[]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Satan Triumphant</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45465</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>[]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>461257</td>\n",
       "      <td>tt6980792</td>\n",
       "      <td>en</td>\n",
       "      <td>Queerama</td>\n",
       "      <td>50 years after decriminalisation of homosexual...</td>\n",
       "      <td>...</td>\n",
       "      <td>2017-06-09</td>\n",
       "      <td>0.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Queerama</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       adult belongs_to_collection budget  \\\n",
       "45461  False                   NaN      0   \n",
       "45462  False                   NaN      0   \n",
       "45463  False                   NaN      0   \n",
       "45464  False                   NaN      0   \n",
       "45465  False                   NaN      0   \n",
       "\n",
       "                                                  genres  \\\n",
       "45461  [{'id': 18, 'name': 'Drama'}, {'id': 10751, 'n...   \n",
       "45462                      [{'id': 18, 'name': 'Drama'}]   \n",
       "45463  [{'id': 28, 'name': 'Action'}, {'id': 18, 'nam...   \n",
       "45464                                                 []   \n",
       "45465                                                 []   \n",
       "\n",
       "                                   homepage      id    imdb_id  \\\n",
       "45461  http://www.imdb.com/title/tt6209470/  439050  tt6209470   \n",
       "45462                                   NaN  111109  tt2028550   \n",
       "45463                                   NaN   67758  tt0303758   \n",
       "45464                                   NaN  227506  tt0008536   \n",
       "45465                                   NaN  461257  tt6980792   \n",
       "\n",
       "      original_language       original_title  \\\n",
       "45461                fa              رگ خواب   \n",
       "45462                tl  Siglo ng Pagluluwal   \n",
       "45463                en             Betrayal   \n",
       "45464                en  Satana likuyushchiy   \n",
       "45465                en             Queerama   \n",
       "\n",
       "                                                overview  ... release_date  \\\n",
       "45461        Rising and falling between a man and woman.  ...          NaN   \n",
       "45462  An artist struggles to finish his work while a...  ...   2011-11-17   \n",
       "45463  When one of her hits goes wrong, a professiona...  ...   2003-08-01   \n",
       "45464  In a small town live two brothers, one a minis...  ...   1917-10-21   \n",
       "45465  50 years after decriminalisation of homosexual...  ...   2017-06-09   \n",
       "\n",
       "      revenue runtime                          spoken_languages    status  \\\n",
       "45461     0.0    90.0    [{'iso_639_1': 'fa', 'name': 'فارسی'}]  Released   \n",
       "45462     0.0   360.0         [{'iso_639_1': 'tl', 'name': ''}]  Released   \n",
       "45463     0.0    90.0  [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "45464     0.0    87.0                                        []  Released   \n",
       "45465     0.0    75.0  [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "\n",
       "                                          tagline                title  video  \\\n",
       "45461  Rising and falling between a man and woman               Subdue  False   \n",
       "45462                                         NaN  Century of Birthing  False   \n",
       "45463                      A deadly game of wits.             Betrayal  False   \n",
       "45464                                         NaN     Satan Triumphant  False   \n",
       "45465                                         NaN             Queerama  False   \n",
       "\n",
       "      vote_average vote_count  \n",
       "45461          4.0        1.0  \n",
       "45462          9.0        3.0  \n",
       "45463          3.8        6.0  \n",
       "45464          0.0        0.0  \n",
       "45465          0.0        0.0  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kaggle_metadata.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'C:/Users/krumb/Classwork/Movies_ETLwikipedia.movies.json'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# To open the file in the directory instead of needing to type out entire directory every time\n",
    "# If I move files, I only need to update the file_dir rather than \n",
    "f\"{file_dir}wikipedia.movies.json\""
   ]
  },
  {
   "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>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>timestamp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>26024284</th>\n",
       "      <td>270896</td>\n",
       "      <td>58559</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1257031564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26024285</th>\n",
       "      <td>270896</td>\n",
       "      <td>60069</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1257032032</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26024286</th>\n",
       "      <td>270896</td>\n",
       "      <td>63082</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1257031764</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26024287</th>\n",
       "      <td>270896</td>\n",
       "      <td>64957</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1257033990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26024288</th>\n",
       "      <td>270896</td>\n",
       "      <td>71878</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1257031858</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          userId  movieId  rating   timestamp\n",
       "26024284  270896    58559     5.0  1257031564\n",
       "26024285  270896    60069     5.0  1257032032\n",
       "26024286  270896    63082     4.5  1257031764\n",
       "26024287  270896    64957     4.5  1257033990\n",
       "26024288  270896    71878     2.0  1257031858"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratings.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the JSON file into a list of dictionaries\n",
    "with open(f\"{file_dir}/Data/wikipedia.movies.json\", mode=\"r\") as file:\n",
    "    wiki_movies_raw = json.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7311"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(wiki_movies_raw)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'url': 'https://en.wikipedia.org/wiki/The_Adventures_of_Ford_Fairlane',\n",
       "  'year': 1990,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0098987/',\n",
       "  'title': 'The Adventures of Ford Fairlane',\n",
       "  'Directed by': 'Renny Harlin',\n",
       "  'Produced by': ['Steve Perry', 'Joel Silver'],\n",
       "  'Screenplay by': ['David Arnott', 'James Cappe', 'Daniel Waters'],\n",
       "  'Story by': ['David Arnott', 'James Cappe'],\n",
       "  'Based on': ['Characters', 'by Rex Weiner'],\n",
       "  'Starring': ['Andrew Dice Clay',\n",
       "   'Wayne Newton',\n",
       "   'Priscilla Presley',\n",
       "   'Lauren Holly',\n",
       "   'Morris Day',\n",
       "   'Robert Englund',\n",
       "   \"Ed O'Neill\"],\n",
       "  'Narrated by': 'Andrew \"Dice\" Clay',\n",
       "  'Music by': ['Cliff Eidelman', 'Yello'],\n",
       "  'Cinematography': 'Oliver Wood',\n",
       "  'Edited by': 'Michael Tronick',\n",
       "  'Productioncompany ': 'Silver Pictures',\n",
       "  'Distributed by': '20th Century Fox',\n",
       "  'Release date': ['July 11, 1990', '(', '1990-07-11', ')'],\n",
       "  'Running time': '102 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$20 million',\n",
       "  'Box office': '$21.4 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/After_Dark,_My_Sweet',\n",
       "  'year': 1990,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0098994/',\n",
       "  'title': 'After Dark, My Sweet',\n",
       "  'Directed by': 'James Foley',\n",
       "  'Produced by': ['Ric Kidney', 'Robert Redlin'],\n",
       "  'Screenplay by': ['James Foley', 'Robert Redlin'],\n",
       "  'Based on': ['the novel', 'After Dark, My Sweet', 'by', 'Jim Thompson'],\n",
       "  'Starring': ['Jason Patric',\n",
       "   'Rachel Ward',\n",
       "   'Bruce Dern',\n",
       "   'George Dickerson'],\n",
       "  'Music by': 'Maurice Jarre',\n",
       "  'Cinematography': 'Mark Plummer',\n",
       "  'Edited by': 'Howard E. Smith',\n",
       "  'Productioncompany ': 'Avenue Pictures',\n",
       "  'Distributed by': 'Avenue Pictures',\n",
       "  'Release date': ['May 17, 1990',\n",
       "   '(',\n",
       "   '1990-05-17',\n",
       "   ')',\n",
       "   '(Cannes Film Market)',\n",
       "   'August 24, 1990',\n",
       "   '(',\n",
       "   '1990-08-24',\n",
       "   ')',\n",
       "   '(United States)'],\n",
       "  'Running time': '114 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$6 million',\n",
       "  'Box office': '$2.7 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Air_America_(film)',\n",
       "  'year': 1990,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0099005/',\n",
       "  'title': 'Air America',\n",
       "  'Directed by': 'Roger Spottiswoode',\n",
       "  'Produced by': 'Daniel Melnick',\n",
       "  'Screenplay by': ['John Eskow', 'Richard Rush'],\n",
       "  'Based on': ['Air America', 'by', 'Christopher Robbins'],\n",
       "  'Starring': ['Mel Gibson',\n",
       "   'Robert Downey Jr.',\n",
       "   'Nancy Travis',\n",
       "   'David Marshall Grant',\n",
       "   'Lane Smith'],\n",
       "  'Music by': 'Charles Gross',\n",
       "  'Cinematography': 'Roger Deakins',\n",
       "  'Edited by': ['John Bloom', 'Lois Freeman-Fox'],\n",
       "  'Productioncompany ': ['Carolco Pictures', 'IndieProd Company'],\n",
       "  'Distributed by': 'TriStar Pictures',\n",
       "  'Release date': ['August 10, 1990', '(', '1990-08-10', ')'],\n",
       "  'Running time': '113 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': ['English', 'Lao'],\n",
       "  'Budget': '$35 million',\n",
       "  'Box office': '$57,718,089'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Alice_(1990_film)',\n",
       "  'year': 1990,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0099012/',\n",
       "  'title': 'Alice',\n",
       "  'Directed by': 'Woody Allen',\n",
       "  'Produced by': 'Robert Greenhut',\n",
       "  'Written by': 'Woody Allen',\n",
       "  'Starring': ['Alec Baldwin',\n",
       "   'Blythe Danner',\n",
       "   'Judy Davis',\n",
       "   'Mia Farrow',\n",
       "   'William Hurt',\n",
       "   'Keye Luke',\n",
       "   'Joe Mantegna',\n",
       "   'Bernadette Peters'],\n",
       "  'Cinematography': 'Carlo Di Palma',\n",
       "  'Edited by': 'Susan E. Morse',\n",
       "  'Distributed by': 'Orion Pictures',\n",
       "  'Release date': ['December 25, 1990', '(', '1990-12-25', ')'],\n",
       "  'Running time': '106 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$12 million',\n",
       "  'Box office': '$7,331,647'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Almost_an_Angel',\n",
       "  'year': 1990,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0099018/',\n",
       "  'title': 'Almost an Angel',\n",
       "  'Directed by': 'John Cornell',\n",
       "  'Produced by': 'John Cornell',\n",
       "  'Written by': 'Paul Hogan',\n",
       "  'Starring': ['Paul Hogan', 'Elias Koteas', 'Linda Kozlowski'],\n",
       "  'Music by': 'Maurice Jarre',\n",
       "  'Cinematography': 'Russell Boyd',\n",
       "  'Edited by': 'David Stiven',\n",
       "  'Distributed by': 'Paramount Pictures',\n",
       "  'Release date': 'December 19, 1990',\n",
       "  'Running time': '95 minutes',\n",
       "  'Country': 'US',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$25 million',\n",
       "  'Box office': '$6,939,946 (USA)'}]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# First 5 records\n",
    "wiki_movies_raw[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'url': 'https://en.wikipedia.org/wiki/Holmes_%26_Watson',\n",
       "  'year': 2018,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt1255919/',\n",
       "  'title': 'Holmes & Watson',\n",
       "  'Directed by': 'Etan Cohen',\n",
       "  'Produced by': ['Will Ferrell',\n",
       "   'Adam McKay',\n",
       "   'Jimmy Miller',\n",
       "   'Clayton Townsend'],\n",
       "  'Screenplay by': 'Etan Cohen',\n",
       "  'Based on': ['Sherlock Holmes',\n",
       "   'and',\n",
       "   'Dr. Watson',\n",
       "   'by',\n",
       "   'Sir Arthur Conan Doyle'],\n",
       "  'Starring': ['Will Ferrell',\n",
       "   'John C. Reilly',\n",
       "   'Rebecca Hall',\n",
       "   'Rob Brydon',\n",
       "   'Steve Coogan',\n",
       "   'Ralph Fiennes'],\n",
       "  'Music by': 'Mark Mothersbaugh',\n",
       "  'Cinematography': 'Oliver Wood',\n",
       "  'Edited by': 'Dean Zimmerman',\n",
       "  'Productioncompanies ': ['Columbia Pictures',\n",
       "   'Gary Sanchez Productions',\n",
       "   'Mosaic Media Group',\n",
       "   'Mimran Schur Pictures'],\n",
       "  'Distributed by': 'Sony Pictures Releasing',\n",
       "  'Release date': ['December 25, 2018',\n",
       "   '(',\n",
       "   '2018-12-25',\n",
       "   ')',\n",
       "   '(United States)'],\n",
       "  'Running time': '90 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$42 million',\n",
       "  'Box office': '$41.9 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Vice_(2018_film)',\n",
       "  'year': 2018,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt6266538/',\n",
       "  'title': 'Vice',\n",
       "  'Directed by': 'Adam McKay',\n",
       "  'Produced by': ['Brad Pitt',\n",
       "   'Dede Gardner',\n",
       "   'Jeremy Kleiner',\n",
       "   'Kevin J. Messick',\n",
       "   'Will Ferrell',\n",
       "   'Adam McKay'],\n",
       "  'Written by': 'Adam McKay',\n",
       "  'Starring': ['Christian Bale',\n",
       "   'Amy Adams',\n",
       "   'Steve Carell',\n",
       "   'Sam Rockwell',\n",
       "   'Tyler Perry',\n",
       "   'Alison Pill',\n",
       "   'Lily Rabe',\n",
       "   'Jesse Plemons'],\n",
       "  'Music by': 'Nicholas Britell',\n",
       "  'Cinematography': 'Greig Fraser',\n",
       "  'Edited by': 'Hank Corwin',\n",
       "  'Productioncompany ': ['Plan B Entertainment',\n",
       "   'Gary Sanchez Productions',\n",
       "   'Annapurna Pictures'],\n",
       "  'Distributed by': 'Mirror Releasing',\n",
       "  'Release date': ['December 11, 2018',\n",
       "   '(',\n",
       "   '2018-12-11',\n",
       "   ')',\n",
       "   '(',\n",
       "   'Samuel Goldwyn Theater',\n",
       "   ')',\n",
       "   'December 25, 2018',\n",
       "   '(',\n",
       "   '2018-12-25',\n",
       "   ')',\n",
       "   '(United States)'],\n",
       "  'Running time': '132 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$60 million',\n",
       "  'Box office': '$76.1 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/On_the_Basis_of_Sex',\n",
       "  'year': 2018,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt4669788/',\n",
       "  'title': 'On the Basis of Sex',\n",
       "  'Directed by': 'Mimi Leder',\n",
       "  'Produced by': 'Robert W. Cort',\n",
       "  'Written by': 'Daniel Stiepleman',\n",
       "  'Starring': ['Felicity Jones',\n",
       "   'Armie Hammer',\n",
       "   'Justin Theroux',\n",
       "   'Sam Waterston',\n",
       "   'Kathy Bates'],\n",
       "  'Music by': 'Mychael Danna',\n",
       "  'Cinematography': 'Michael Grady',\n",
       "  'Edited by': 'Michelle Tesoro',\n",
       "  'Productioncompanies ': ['Focus Features',\n",
       "   '[1]',\n",
       "   'Participant Media',\n",
       "   '[1]',\n",
       "   'Robert Cort Productions',\n",
       "   '[1]',\n",
       "   'Alibaba Pictures',\n",
       "   '[2]'],\n",
       "  'Distributed by': 'Focus Features',\n",
       "  'Release date': ['November 8, 2018',\n",
       "   '(',\n",
       "   '2018-11-08',\n",
       "   ')',\n",
       "   '(',\n",
       "   'AFI Fest',\n",
       "   ')',\n",
       "   'December 25, 2018',\n",
       "   '(',\n",
       "   '2018-12-25',\n",
       "   ')',\n",
       "   '(United States)'],\n",
       "  'Running time': '120 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$20 million',\n",
       "  'Box office': '$38.4 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Destroyer_(2018_film)',\n",
       "  'year': 2018,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt7137380/',\n",
       "  'title': 'Destroyer',\n",
       "  'Directed by': 'Karyn Kusama',\n",
       "  'Produced by': ['Fred Berger', 'Phil Hay', 'Matt Manfredi'],\n",
       "  'Written by': ['Phil Hay', 'Matt Manfredi'],\n",
       "  'Starring': ['Nicole Kidman',\n",
       "   'Sebastian Stan',\n",
       "   'Toby Kebbell',\n",
       "   'Tatiana Maslany',\n",
       "   'Bradley Whitford',\n",
       "   'Jade Pettyjohn',\n",
       "   'Scoot McNairy'],\n",
       "  'Music by': 'Theodore Shapiro',\n",
       "  'Cinematography': 'Julie Kirkwood',\n",
       "  'Edited by': 'Plummy Tucker',\n",
       "  'Productioncompany ': ['30West',\n",
       "   'Automatik Entertainment',\n",
       "   'Annapurna Pictures'],\n",
       "  'Distributed by': 'Mirror Releasing',\n",
       "  'Release date': ['August 31, 2018',\n",
       "   '(',\n",
       "   '2018-08-31',\n",
       "   ')',\n",
       "   '(',\n",
       "   'Telluride',\n",
       "   ')',\n",
       "   'December 25, 2018',\n",
       "   '(',\n",
       "   '2018-12-25',\n",
       "   ')',\n",
       "   '(United States)'],\n",
       "  'Running time': '123 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$9 million',\n",
       "  'Box office': '$5.5 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Black_Mirror:_Bandersnatch',\n",
       "  'year': 2018,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt9495224/',\n",
       "  'title': 'Bandersnatch',\n",
       "  'Directed by': 'David Slade',\n",
       "  'Produced by': 'Russell McLean',\n",
       "  'Written by': 'Charlie Brooker',\n",
       "  'Starring': ['Fionn Whitehead',\n",
       "   'Will Poulter',\n",
       "   'Craig Parkinson',\n",
       "   'Alice Lowe',\n",
       "   'Asim Chaudhry'],\n",
       "  'Music by': 'Brian Reitzell',\n",
       "  'Cinematography': ['Aaron Morton', 'Jake Polonsky'],\n",
       "  'Edited by': 'Tony Kearns',\n",
       "  'Productioncompany ': ['House of Tomorrow', 'Netflix'],\n",
       "  'Distributed by': 'Netflix',\n",
       "  'Release date': ['28 December 2018', '(', '2018-12-28', ')'],\n",
       "  'Running time': 'Variable; 90 minutes for default path',\n",
       "  'Country': 'United Kingdom',\n",
       "  'Language': 'English'}]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Last 5 records\n",
    "wiki_movies_raw[-5:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'url': 'https://en.wikipedia.org/wiki/Benji:_Off_the_Leash!',\n",
       "  'year': 2004,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0315273/',\n",
       "  'title': 'Benji: Off the Leash!',\n",
       "  'Directed by': 'Joe Camp',\n",
       "  'Written by': 'Joe Camp',\n",
       "  'Starring': ['Benji', 'Nick Whitaker', 'Shaggy', 'Gypsy the Cockatoo'],\n",
       "  'Music by': 'Antonio di Lorenzo',\n",
       "  'Productioncompany ': 'Mulberry Square Productions',\n",
       "  'Distributed by': 'Mulberry Square Productions',\n",
       "  'Release date': ['March 26, 2004', '(', '2004-03-26', ')'],\n",
       "  'Running time': '97 min',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Box office': '$3,817,362'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/The_Best_Thief_in_the_World',\n",
       "  'year': 2004,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0389796/',\n",
       "  'title': 'The Best Thief in the World',\n",
       "  'Directed by': 'Jacob Kornbluth',\n",
       "  'Produced by': ['Tim Perrell', 'Nicola Usborne'],\n",
       "  'Written by': 'Jacob Kornbluth',\n",
       "  'Starring': ['Marc Rozendaal',\n",
       "   'Michael Silverman',\n",
       "   'David Warshofsky',\n",
       "   'Audra McDonald',\n",
       "   'Lois Smith'],\n",
       "  'Music by': ['Prince Paul', 'and', 'Don Newkirk'],\n",
       "  'Cinematography': 'Ben Kutchins',\n",
       "  'Edited by': 'Stephanie Sterner',\n",
       "  'Distributed by': 'Showtime Networks',\n",
       "  'Release date': ['January 16, 2004', '(', '2004-01-16', ')'],\n",
       "  'Running time': '93 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Beyond_the_Sea_(2004_film)',\n",
       "  'year': 2004,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0363473/',\n",
       "  'title': 'Beyond the Sea',\n",
       "  'Directed by': 'Kevin Spacey',\n",
       "  'Produced by': ['Kevin Spacey',\n",
       "   'Phillip Barry',\n",
       "   'Dana Brunetti',\n",
       "   'Arthur Friedman',\n",
       "   'Jan Fantl',\n",
       "   'Andy Paterson'],\n",
       "  'Written by': ['Lewis Colick', 'Kevin Spacey'],\n",
       "  'Starring': ['Kevin Spacey', 'Kate Bosworth', 'Bob Hoskins', 'John Goodman'],\n",
       "  'Music by': 'Bobby Darin',\n",
       "  'Cinematography': 'Eduardo Serra',\n",
       "  'Edited by': 'Trevor Waite',\n",
       "  'Productioncompany ': 'Trigger Street Productions',\n",
       "  'Distributed by': ['Lionsgate Films',\n",
       "   '(USA)',\n",
       "   'Entertainment Film Distributors',\n",
       "   '(UK)',\n",
       "   'GAGA',\n",
       "   '(Japan)',\n",
       "   'Maple Pictures',\n",
       "   '(Canada)'],\n",
       "  'Release date': ['December 17, 2004', '(', '2004-12-17', ')'],\n",
       "  'Running time': '118 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$25 million',\n",
       "  'Box office': '$8.4 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/The_Big_Bounce_(2004_film)',\n",
       "  'year': 2004,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0315824/',\n",
       "  'title': 'The Big Bounce',\n",
       "  'Directed by': 'George Armitage',\n",
       "  'Produced by': ['George Armitage', 'Steve Bing'],\n",
       "  'Screenplay by': 'Sebastian Gutierrez',\n",
       "  'Based on': ['The Big Bounce', 'by', 'Elmore Leonard'],\n",
       "  'Starring': ['Owen Wilson',\n",
       "   'Charlie Sheen',\n",
       "   'Morgan Freeman',\n",
       "   'Sara Foster',\n",
       "   'Gary Sinise'],\n",
       "  'Music by': 'George S. Clinton',\n",
       "  'Cinematography': 'Jeffrey L. Kimball',\n",
       "  'Edited by': 'Barry Malkin',\n",
       "  'Productioncompany ': 'Shangri-La Entertainment',\n",
       "  'Distributed by': 'Warner Bros. Pictures',\n",
       "  'Release date': ['January 30, 2004', '(', '2004-01-30', ')'],\n",
       "  'Running time': '88 minutes',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$50 million',\n",
       "  'Box office': '$6.8 million'},\n",
       " {'url': 'https://en.wikipedia.org/wiki/Birth_(film)',\n",
       "  'year': 2004,\n",
       "  'imdb_link': 'https://www.imdb.com/title/tt0337876/',\n",
       "  'title': 'Birth',\n",
       "  'Directed by': 'Jonathan Glazer',\n",
       "  'Produced by': ['Lizie Gower', 'Nick Morris', 'Jean-Louis Piel'],\n",
       "  'Written by': ['Jean-Claude Carrière', 'Milo Addica', 'Jonathan Glazer'],\n",
       "  'Starring': ['Nicole Kidman',\n",
       "   'Cameron Bright',\n",
       "   'Danny Huston',\n",
       "   'Lauren Bacall'],\n",
       "  'Music by': 'Alexandre Desplat',\n",
       "  'Cinematography': 'Harris Savides',\n",
       "  'Edited by': ['Sam Sneade', 'Claus Wehlisch'],\n",
       "  'Distributed by': 'New Line Cinema',\n",
       "  'Release date': ['November 8, 2004', '(', '2004-11-08', ')'],\n",
       "  'Running time': '96 minutes',\n",
       "  'Country': 'United States',\n",
       "  'Language': 'English',\n",
       "  'Budget': '$20 million',\n",
       "  'Box office': '$23.9 million'}]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Some records in the middle\n",
    "wiki_movies_raw[3600:3605]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "wiki_movies_df = pd.DataFrame(wiki_movies_raw)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title</th>\n",
       "      <th>Directed by</th>\n",
       "      <th>Produced by</th>\n",
       "      <th>Screenplay by</th>\n",
       "      <th>Story by</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>...</th>\n",
       "      <th>Predecessor</th>\n",
       "      <th>Founders</th>\n",
       "      <th>Area served</th>\n",
       "      <th>Products</th>\n",
       "      <th>Services</th>\n",
       "      <th>Russian</th>\n",
       "      <th>Hebrew</th>\n",
       "      <th>Revenue</th>\n",
       "      <th>Operating income</th>\n",
       "      <th>Polish</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>1990.0</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>Renny Harlin</td>\n",
       "      <td>[Steve Perry, Joel Silver]</td>\n",
       "      <td>[David Arnott, James Cappe, Daniel Waters]</td>\n",
       "      <td>[David Arnott, James Cappe]</td>\n",
       "      <td>[Characters, by Rex Weiner]</td>\n",
       "      <td>[Andrew Dice Clay, Wayne Newton, Priscilla Pre...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>1990.0</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>James Foley</td>\n",
       "      <td>[Ric Kidney, Robert Redlin]</td>\n",
       "      <td>[James Foley, Robert Redlin]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[the novel, After Dark, My Sweet, by, Jim Thom...</td>\n",
       "      <td>[Jason Patric, Rachel Ward, Bruce Dern, George...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>1990.0</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>Air America</td>\n",
       "      <td>Roger Spottiswoode</td>\n",
       "      <td>Daniel Melnick</td>\n",
       "      <td>[John Eskow, Richard Rush]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Air America, by, Christopher Robbins]</td>\n",
       "      <td>[Mel Gibson, Robert Downey Jr., Nancy Travis, ...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>1990.0</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Woody Allen</td>\n",
       "      <td>Robert Greenhut</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Alec Baldwin, Blythe Danner, Judy Davis, Mia ...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>1990.0</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Paul Hogan, Elias Koteas, Linda Kozlowski]</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 193 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 url    year  \\\n",
       "0  https://en.wikipedia.org/wiki/The_Adventures_o...  1990.0   \n",
       "1  https://en.wikipedia.org/wiki/After_Dark,_My_S...  1990.0   \n",
       "2   https://en.wikipedia.org/wiki/Air_America_(film)  1990.0   \n",
       "3    https://en.wikipedia.org/wiki/Alice_(1990_film)  1990.0   \n",
       "4      https://en.wikipedia.org/wiki/Almost_an_Angel  1990.0   \n",
       "\n",
       "                               imdb_link                            title  \\\n",
       "0  https://www.imdb.com/title/tt0098987/  The Adventures of Ford Fairlane   \n",
       "1  https://www.imdb.com/title/tt0098994/             After Dark, My Sweet   \n",
       "2  https://www.imdb.com/title/tt0099005/                      Air America   \n",
       "3  https://www.imdb.com/title/tt0099012/                            Alice   \n",
       "4  https://www.imdb.com/title/tt0099018/                  Almost an Angel   \n",
       "\n",
       "          Directed by                  Produced by  \\\n",
       "0        Renny Harlin   [Steve Perry, Joel Silver]   \n",
       "1         James Foley  [Ric Kidney, Robert Redlin]   \n",
       "2  Roger Spottiswoode               Daniel Melnick   \n",
       "3         Woody Allen              Robert Greenhut   \n",
       "4        John Cornell                 John Cornell   \n",
       "\n",
       "                                Screenplay by                     Story by  \\\n",
       "0  [David Arnott, James Cappe, Daniel Waters]  [David Arnott, James Cappe]   \n",
       "1                [James Foley, Robert Redlin]                          NaN   \n",
       "2                  [John Eskow, Richard Rush]                          NaN   \n",
       "3                                         NaN                          NaN   \n",
       "4                                         NaN                          NaN   \n",
       "\n",
       "                                            Based on  \\\n",
       "0                        [Characters, by Rex Weiner]   \n",
       "1  [the novel, After Dark, My Sweet, by, Jim Thom...   \n",
       "2             [Air America, by, Christopher Robbins]   \n",
       "3                                                NaN   \n",
       "4                                                NaN   \n",
       "\n",
       "                                            Starring  ... Predecessor  \\\n",
       "0  [Andrew Dice Clay, Wayne Newton, Priscilla Pre...  ...         NaN   \n",
       "1  [Jason Patric, Rachel Ward, Bruce Dern, George...  ...         NaN   \n",
       "2  [Mel Gibson, Robert Downey Jr., Nancy Travis, ...  ...         NaN   \n",
       "3  [Alec Baldwin, Blythe Danner, Judy Davis, Mia ...  ...         NaN   \n",
       "4        [Paul Hogan, Elias Koteas, Linda Kozlowski]  ...         NaN   \n",
       "\n",
       "  Founders Area served Products Services Russian Hebrew Revenue  \\\n",
       "0      NaN         NaN      NaN      NaN     NaN    NaN     NaN   \n",
       "1      NaN         NaN      NaN      NaN     NaN    NaN     NaN   \n",
       "2      NaN         NaN      NaN      NaN     NaN    NaN     NaN   \n",
       "3      NaN         NaN      NaN      NaN     NaN    NaN     NaN   \n",
       "4      NaN         NaN      NaN      NaN     NaN    NaN     NaN   \n",
       "\n",
       "  Operating income Polish  \n",
       "0              NaN    NaN  \n",
       "1              NaN    NaN  \n",
       "2              NaN    NaN  \n",
       "3              NaN    NaN  \n",
       "4              NaN    NaN  \n",
       "\n",
       "[5 rows x 193 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wiki_movies_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['url',\n",
       " 'year',\n",
       " 'imdb_link',\n",
       " 'title',\n",
       " 'Directed by',\n",
       " 'Produced by',\n",
       " 'Screenplay by',\n",
       " 'Story by',\n",
       " 'Based on',\n",
       " 'Starring',\n",
       " 'Narrated by',\n",
       " 'Music by',\n",
       " 'Cinematography',\n",
       " 'Edited by',\n",
       " 'Productioncompany ',\n",
       " 'Distributed by',\n",
       " 'Release date',\n",
       " 'Running time',\n",
       " 'Country',\n",
       " 'Language',\n",
       " 'Budget',\n",
       " 'Box office',\n",
       " 'Written by',\n",
       " 'Genre',\n",
       " 'Theme music composer',\n",
       " 'Country of origin',\n",
       " 'Original language(s)',\n",
       " 'Producer(s)',\n",
       " 'Editor(s)',\n",
       " 'Production company(s)',\n",
       " 'Original network',\n",
       " 'Original release',\n",
       " 'Productioncompanies ',\n",
       " 'Executive producer(s)',\n",
       " 'Production location(s)',\n",
       " 'Distributor',\n",
       " 'Picture format',\n",
       " 'Audio format',\n",
       " 'Voices of',\n",
       " 'Followed by',\n",
       " 'Composer(s)',\n",
       " 'Created by',\n",
       " 'Also known as',\n",
       " 'Opening theme',\n",
       " 'No. of episodes',\n",
       " 'Preceded by',\n",
       " 'Author',\n",
       " 'Publisher',\n",
       " 'Publication date',\n",
       " 'Media type',\n",
       " 'Pages',\n",
       " 'ISBN',\n",
       " 'OCLC',\n",
       " 'LC Class',\n",
       " 'Cover artist',\n",
       " 'Series',\n",
       " 'Set in',\n",
       " 'Adaptation by',\n",
       " 'Suggested by',\n",
       " 'Biographical data',\n",
       " 'Born',\n",
       " 'Died',\n",
       " 'Resting place',\n",
       " 'Occupation',\n",
       " 'Years active',\n",
       " 'Spouse(s)',\n",
       " 'Children',\n",
       " 'Parent(s)',\n",
       " 'Genres',\n",
       " 'Instruments',\n",
       " 'Labels',\n",
       " 'Website',\n",
       " 'Traditional',\n",
       " 'Mandarin',\n",
       " 'Type',\n",
       " 'Industry',\n",
       " 'Fate',\n",
       " 'Founded',\n",
       " 'Founder',\n",
       " 'Headquarters',\n",
       " 'Parent',\n",
       " 'Released',\n",
       " 'Recorded',\n",
       " 'Venue',\n",
       " 'Length',\n",
       " 'Label',\n",
       " 'Director',\n",
       " 'Producer',\n",
       " 'Area',\n",
       " 'Coordinates',\n",
       " 'Status',\n",
       " 'Opening date',\n",
       " 'Closing date',\n",
       " 'Replaced',\n",
       " 'Replaced by',\n",
       " 'Name',\n",
       " 'Attraction type',\n",
       " 'Music',\n",
       " 'Duration',\n",
       " 'Simplified Chinese',\n",
       " 'Traditional Chinese',\n",
       " 'Hanyu Pinyin',\n",
       " 'Literal meaning',\n",
       " 'Transcriptions',\n",
       " 'Bopomofo',\n",
       " 'Gwoyeu Romatzyh',\n",
       " 'Wade–Giles',\n",
       " 'IPA',\n",
       " 'Yale Romanization',\n",
       " 'Jyutping',\n",
       " 'Hokkien POJ',\n",
       " 'Animation by',\n",
       " 'Color process',\n",
       " 'Engine(s)',\n",
       " 'Genre(s)',\n",
       " 'Actor control',\n",
       " 'Production company',\n",
       " 'Release(s)',\n",
       " 'Format(s)',\n",
       " 'Simplified',\n",
       " 'Characters',\n",
       " 'Date premiered',\n",
       " 'Place premiered',\n",
       " 'Setting',\n",
       " 'Original language',\n",
       " 'Subject',\n",
       " 'Published',\n",
       " 'Dewey Decimal',\n",
       " 'Text',\n",
       " 'Illustrator',\n",
       " 'Original title',\n",
       " 'Published in English',\n",
       " 'French',\n",
       " 'Developed by',\n",
       " 'Ending theme',\n",
       " 'No. of seasons',\n",
       " 'Nationality',\n",
       " 'Portrayed by',\n",
       " 'Alias',\n",
       " 'Species',\n",
       " 'Gender',\n",
       " 'Family',\n",
       " 'Alma mater',\n",
       " 'Camera setup',\n",
       " 'Novel(s)',\n",
       " 'Comics',\n",
       " 'Film(s)',\n",
       " 'Screen story by',\n",
       " 'Hangul',\n",
       " 'Revised Romanization',\n",
       " 'McCune–Reischauer',\n",
       " 'Developer(s)',\n",
       " 'Publisher(s)',\n",
       " 'Designer(s)',\n",
       " 'Programmer(s)',\n",
       " 'Artist(s)',\n",
       " 'Writer(s)',\n",
       " 'Engine',\n",
       " 'Platform(s)',\n",
       " 'Release',\n",
       " 'Mode(s)',\n",
       " 'Original work',\n",
       " 'Television series',\n",
       " 'Japanese',\n",
       " 'Hepburn',\n",
       " 'Literally',\n",
       " 'Cantonese',\n",
       " 'Full name',\n",
       " 'Height',\n",
       " 'Seasons',\n",
       " 'Chinese',\n",
       " 'Other names',\n",
       " 'Relatives',\n",
       " 'Yiddish',\n",
       " 'Formerly',\n",
       " 'Key people',\n",
       " 'Total assets',\n",
       " 'Owner',\n",
       " 'Number of employees',\n",
       " 'Divisions',\n",
       " 'Subsidiaries',\n",
       " 'Arabic',\n",
       " 'Romanized',\n",
       " 'Predecessor',\n",
       " 'Founders',\n",
       " 'Area served',\n",
       " 'Products',\n",
       " 'Services',\n",
       " 'Russian',\n",
       " 'Hebrew',\n",
       " 'Revenue',\n",
       " 'Operating income',\n",
       " 'Polish']"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Need to convert the wiki_movies_df.columns to a list to see them all\n",
    "wiki_movies_df.columns.tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7076"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create a fiter expression only for movies with a director and IMDb link\n",
    "wiki_movies = [movie for movie in wiki_movies_raw\n",
    "                if (\"Director\" in movie or \"Directed by\" in movie) \n",
    "                and \"imdb_link\" in movie\n",
    "                and \"No. of episodes\" not in movie]\n",
    "len(wiki_movies)"
   ]
  },
  {
   "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>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title</th>\n",
       "      <th>Directed by</th>\n",
       "      <th>Produced by</th>\n",
       "      <th>Screenplay by</th>\n",
       "      <th>Story by</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>...</th>\n",
       "      <th>Hepburn</th>\n",
       "      <th>Literally</th>\n",
       "      <th>Cantonese</th>\n",
       "      <th>Chinese</th>\n",
       "      <th>Yiddish</th>\n",
       "      <th>Arabic</th>\n",
       "      <th>Romanized</th>\n",
       "      <th>Russian</th>\n",
       "      <th>Hebrew</th>\n",
       "      <th>Polish</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>Renny Harlin</td>\n",
       "      <td>[Steve Perry, Joel Silver]</td>\n",
       "      <td>[David Arnott, James Cappe, Daniel Waters]</td>\n",
       "      <td>[David Arnott, James Cappe]</td>\n",
       "      <td>[Characters, by Rex Weiner]</td>\n",
       "      <td>[Andrew Dice Clay, Wayne Newton, Priscilla Pre...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>James Foley</td>\n",
       "      <td>[Ric Kidney, Robert Redlin]</td>\n",
       "      <td>[James Foley, Robert Redlin]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[the novel, After Dark, My Sweet, by, Jim Thom...</td>\n",
       "      <td>[Jason Patric, Rachel Ward, Bruce Dern, George...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>Air America</td>\n",
       "      <td>Roger Spottiswoode</td>\n",
       "      <td>Daniel Melnick</td>\n",
       "      <td>[John Eskow, Richard Rush]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Air America, by, Christopher Robbins]</td>\n",
       "      <td>[Mel Gibson, Robert Downey Jr., Nancy Travis, ...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Woody Allen</td>\n",
       "      <td>Robert Greenhut</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Alec Baldwin, Blythe Danner, Judy Davis, Mia ...</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Paul Hogan, Elias Koteas, Linda Kozlowski]</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 75 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 url  year  \\\n",
       "0  https://en.wikipedia.org/wiki/The_Adventures_o...  1990   \n",
       "1  https://en.wikipedia.org/wiki/After_Dark,_My_S...  1990   \n",
       "2   https://en.wikipedia.org/wiki/Air_America_(film)  1990   \n",
       "3    https://en.wikipedia.org/wiki/Alice_(1990_film)  1990   \n",
       "4      https://en.wikipedia.org/wiki/Almost_an_Angel  1990   \n",
       "\n",
       "                               imdb_link                            title  \\\n",
       "0  https://www.imdb.com/title/tt0098987/  The Adventures of Ford Fairlane   \n",
       "1  https://www.imdb.com/title/tt0098994/             After Dark, My Sweet   \n",
       "2  https://www.imdb.com/title/tt0099005/                      Air America   \n",
       "3  https://www.imdb.com/title/tt0099012/                            Alice   \n",
       "4  https://www.imdb.com/title/tt0099018/                  Almost an Angel   \n",
       "\n",
       "          Directed by                  Produced by  \\\n",
       "0        Renny Harlin   [Steve Perry, Joel Silver]   \n",
       "1         James Foley  [Ric Kidney, Robert Redlin]   \n",
       "2  Roger Spottiswoode               Daniel Melnick   \n",
       "3         Woody Allen              Robert Greenhut   \n",
       "4        John Cornell                 John Cornell   \n",
       "\n",
       "                                Screenplay by                     Story by  \\\n",
       "0  [David Arnott, James Cappe, Daniel Waters]  [David Arnott, James Cappe]   \n",
       "1                [James Foley, Robert Redlin]                          NaN   \n",
       "2                  [John Eskow, Richard Rush]                          NaN   \n",
       "3                                         NaN                          NaN   \n",
       "4                                         NaN                          NaN   \n",
       "\n",
       "                                            Based on  \\\n",
       "0                        [Characters, by Rex Weiner]   \n",
       "1  [the novel, After Dark, My Sweet, by, Jim Thom...   \n",
       "2             [Air America, by, Christopher Robbins]   \n",
       "3                                                NaN   \n",
       "4                                                NaN   \n",
       "\n",
       "                                            Starring  ... Hepburn Literally  \\\n",
       "0  [Andrew Dice Clay, Wayne Newton, Priscilla Pre...  ...     NaN       NaN   \n",
       "1  [Jason Patric, Rachel Ward, Bruce Dern, George...  ...     NaN       NaN   \n",
       "2  [Mel Gibson, Robert Downey Jr., Nancy Travis, ...  ...     NaN       NaN   \n",
       "3  [Alec Baldwin, Blythe Danner, Judy Davis, Mia ...  ...     NaN       NaN   \n",
       "4        [Paul Hogan, Elias Koteas, Linda Kozlowski]  ...     NaN       NaN   \n",
       "\n",
       "  Cantonese Chinese Yiddish Arabic Romanized Russian Hebrew Polish  \n",
       "0       NaN     NaN     NaN    NaN       NaN     NaN    NaN    NaN  \n",
       "1       NaN     NaN     NaN    NaN       NaN     NaN    NaN    NaN  \n",
       "2       NaN     NaN     NaN    NaN       NaN     NaN    NaN    NaN  \n",
       "3       NaN     NaN     NaN    NaN       NaN     NaN    NaN    NaN  \n",
       "4       NaN     NaN     NaN    NaN       NaN     NaN    NaN    NaN  \n",
       "\n",
       "[5 rows x 75 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wiki_movies_df = pd.DataFrame(wiki_movies)\n",
    "wiki_movies_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "def clean_movie(movie):\n",
    "    movie_copy = dict(movie) # Create a non-destructive copy\n",
    "    return movie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6834    https://en.wikipedia.org/wiki/The_Insult_(film)\n",
       "7058     https://en.wikipedia.org/wiki/Capernaum_(film)\n",
       "Name: url, dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Looking at all the languages\n",
    "wiki_movies_df[wiki_movies_df[\"Arabic\"].notnull()][\"url\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Based on              1\n",
       "Composer(s)           1\n",
       "Chinese               1\n",
       "Productioncompany     1\n",
       "Screenplay by         1\n",
       "                     ..\n",
       "Also known as         1\n",
       "Preceded by           1\n",
       "Simplified            1\n",
       "Cinematography        1\n",
       "Running time          1\n",
       "Length: 75, dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wiki_movies_df.columns.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Adaptation by',\n",
       " 'Also known as',\n",
       " 'Animation by',\n",
       " 'Arabic',\n",
       " 'Audio format',\n",
       " 'Based on',\n",
       " 'Box office',\n",
       " 'Budget',\n",
       " 'Cantonese',\n",
       " 'Chinese',\n",
       " 'Cinematography',\n",
       " 'Color process',\n",
       " 'Composer(s)',\n",
       " 'Country',\n",
       " 'Country of origin',\n",
       " 'Created by',\n",
       " 'Directed by',\n",
       " 'Director',\n",
       " 'Distributed by',\n",
       " 'Distributor',\n",
       " 'Edited by',\n",
       " 'Editor(s)',\n",
       " 'Executive producer(s)',\n",
       " 'Followed by',\n",
       " 'French',\n",
       " 'Genre',\n",
       " 'Hangul',\n",
       " 'Hebrew',\n",
       " 'Hepburn',\n",
       " 'Japanese',\n",
       " 'Label',\n",
       " 'Language',\n",
       " 'Length',\n",
       " 'Literally',\n",
       " 'Mandarin',\n",
       " 'McCune–Reischauer',\n",
       " 'Music by',\n",
       " 'Narrated by',\n",
       " 'Original language(s)',\n",
       " 'Original network',\n",
       " 'Original release',\n",
       " 'Original title',\n",
       " 'Picture format',\n",
       " 'Polish',\n",
       " 'Preceded by',\n",
       " 'Produced by',\n",
       " 'Producer',\n",
       " 'Producer(s)',\n",
       " 'Production company(s)',\n",
       " 'Production location(s)',\n",
       " 'Productioncompanies ',\n",
       " 'Productioncompany ',\n",
       " 'Recorded',\n",
       " 'Release date',\n",
       " 'Released',\n",
       " 'Revised Romanization',\n",
       " 'Romanized',\n",
       " 'Running time',\n",
       " 'Russian',\n",
       " 'Screen story by',\n",
       " 'Screenplay by',\n",
       " 'Simplified',\n",
       " 'Starring',\n",
       " 'Story by',\n",
       " 'Suggested by',\n",
       " 'Theme music composer',\n",
       " 'Traditional',\n",
       " 'Venue',\n",
       " 'Voices of',\n",
       " 'Written by',\n",
       " 'Yiddish',\n",
       " 'imdb_link',\n",
       " 'title',\n",
       " 'url',\n",
       " 'year']"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorted(wiki_movies_df.columns.tolist())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Handle alternative titles by creating an empty dictionary\n",
    "# loop through all alt. title keys\n",
    "# if they exist, remove the key-value pair and add to alt. titles dict.\n",
    "def clean_movie(movie):\n",
    "    movie = dict(movie) # create a non-destructive copy\n",
    "    alt_titles = {}\n",
    "    # combine alternate titles into one list\n",
    "    for key in ['Also known as','Arabic','Cantonese','Chinese','French',\n",
    "                'Hangul','Hebrew','Hepburn','Japanese','Literally',\n",
    "                'Mandarin','McCune–Reischauer','Original title','Polish',\n",
    "                'Revised Romanization','Romanized','Russian',\n",
    "                'Simplified','Traditional','Yiddish']:\n",
    "        if key in movie:\n",
    "            alt_titles[key] = movie[key]\n",
    "            movie.pop(key)\n",
    "    if len(alt_titles) > 0:\n",
    "        movie['alt_titles'] = alt_titles \n",
    "\n",
    "    # merger column names that mean the same thing\n",
    "    def change_column_name(old_name, new_name):\n",
    "        if old_name in movie:\n",
    "            movie[new_name] = movie.pop(old_name)\n",
    "    change_column_name('Adaptation by', 'Writer(s)')\n",
    "    change_column_name('Country of origin', 'Country')\n",
    "    change_column_name('Directed by', 'Director')\n",
    "    change_column_name('Distributed by', 'Distributor')\n",
    "    change_column_name('Edited by', 'Editor(s)')\n",
    "    change_column_name('Length', 'Running time')\n",
    "    change_column_name('Original release', 'Release date')\n",
    "    change_column_name('Music by', 'Composer(s)')\n",
    "    change_column_name('Produced by', 'Producer(s)')\n",
    "    change_column_name('Producer', 'Producer(s)')\n",
    "    change_column_name('Productioncompanies ', 'Production company(s)')\n",
    "    change_column_name('Productioncompany ', 'Production company(s)')\n",
    "    change_column_name('Released', 'Release Date')\n",
    "    change_column_name('Release Date', 'Release date')\n",
    "    change_column_name('Screen story by', 'Writer(s)')\n",
    "    change_column_name('Screenplay by', 'Writer(s)')\n",
    "    change_column_name('Story by', 'Writer(s)')\n",
    "    change_column_name('Theme music composer', 'Composer(s)')\n",
    "    change_column_name('Written by', 'Writer(s)')\n",
    "\n",
    "    return movie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Make a list of cleanned movies with a list comprehension\n",
    "clean_movies = [clean_movie(movie) for movie in wiki_movies]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Animation by',\n",
       " 'Audio format',\n",
       " 'Based on',\n",
       " 'Box office',\n",
       " 'Budget',\n",
       " 'Cinematography',\n",
       " 'Color process',\n",
       " 'Composer(s)',\n",
       " 'Country',\n",
       " 'Created by',\n",
       " 'Director',\n",
       " 'Distributor',\n",
       " 'Editor(s)',\n",
       " 'Executive producer(s)',\n",
       " 'Followed by',\n",
       " 'Genre',\n",
       " 'Label',\n",
       " 'Language',\n",
       " 'Narrated by',\n",
       " 'Original language(s)',\n",
       " 'Original network',\n",
       " 'Picture format',\n",
       " 'Preceded by',\n",
       " 'Producer(s)',\n",
       " 'Production company(s)',\n",
       " 'Production location(s)',\n",
       " 'Recorded',\n",
       " 'Release date',\n",
       " 'Running time',\n",
       " 'Starring',\n",
       " 'Suggested by',\n",
       " 'Venue',\n",
       " 'Voices of',\n",
       " 'Writer(s)',\n",
       " 'alt_titles',\n",
       " 'imdb_link',\n",
       " 'title',\n",
       " 'url',\n",
       " 'year']"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wiki_movies_df = pd.DataFrame(clean_movies)\n",
    "sorted(wiki_movies_df.columns.tolist())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7076\n",
      "7033\n"
     ]
    },
    {
     "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>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>Narrated by</th>\n",
       "      <th>Cinematography</th>\n",
       "      <th>Release date</th>\n",
       "      <th>Running time</th>\n",
       "      <th>...</th>\n",
       "      <th>Created by</th>\n",
       "      <th>Preceded by</th>\n",
       "      <th>Suggested by</th>\n",
       "      <th>alt_titles</th>\n",
       "      <th>Recorded</th>\n",
       "      <th>Venue</th>\n",
       "      <th>Label</th>\n",
       "      <th>Animation by</th>\n",
       "      <th>Color process</th>\n",
       "      <th>imdb_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>[Characters, by Rex Weiner]</td>\n",
       "      <td>[Andrew Dice Clay, Wayne Newton, Priscilla Pre...</td>\n",
       "      <td>Andrew \"Dice\" Clay</td>\n",
       "      <td>Oliver Wood</td>\n",
       "      <td>[July 11, 1990, (, 1990-07-11, )]</td>\n",
       "      <td>102 minutes</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>tt0098987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>[the novel, After Dark, My Sweet, by, Jim Thom...</td>\n",
       "      <td>[Jason Patric, Rachel Ward, Bruce Dern, George...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mark Plummer</td>\n",
       "      <td>[May 17, 1990, (, 1990-05-17, ), (Cannes Film ...</td>\n",
       "      <td>114 minutes</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>tt0098994</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>Air America</td>\n",
       "      <td>[Air America, by, Christopher Robbins]</td>\n",
       "      <td>[Mel Gibson, Robert Downey Jr., Nancy Travis, ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Roger Deakins</td>\n",
       "      <td>[August 10, 1990, (, 1990-08-10, )]</td>\n",
       "      <td>113 minutes</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>tt0099005</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>Alice</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Alec Baldwin, Blythe Danner, Judy Davis, Mia ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Carlo Di Palma</td>\n",
       "      <td>[December 25, 1990, (, 1990-12-25, )]</td>\n",
       "      <td>106 minutes</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>tt0099012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Paul Hogan, Elias Koteas, Linda Kozlowski]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Russell Boyd</td>\n",
       "      <td>December 19, 1990</td>\n",
       "      <td>95 minutes</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>tt0099018</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 url  year  \\\n",
       "0  https://en.wikipedia.org/wiki/The_Adventures_o...  1990   \n",
       "1  https://en.wikipedia.org/wiki/After_Dark,_My_S...  1990   \n",
       "2   https://en.wikipedia.org/wiki/Air_America_(film)  1990   \n",
       "3    https://en.wikipedia.org/wiki/Alice_(1990_film)  1990   \n",
       "4      https://en.wikipedia.org/wiki/Almost_an_Angel  1990   \n",
       "\n",
       "                               imdb_link                            title  \\\n",
       "0  https://www.imdb.com/title/tt0098987/  The Adventures of Ford Fairlane   \n",
       "1  https://www.imdb.com/title/tt0098994/             After Dark, My Sweet   \n",
       "2  https://www.imdb.com/title/tt0099005/                      Air America   \n",
       "3  https://www.imdb.com/title/tt0099012/                            Alice   \n",
       "4  https://www.imdb.com/title/tt0099018/                  Almost an Angel   \n",
       "\n",
       "                                            Based on  \\\n",
       "0                        [Characters, by Rex Weiner]   \n",
       "1  [the novel, After Dark, My Sweet, by, Jim Thom...   \n",
       "2             [Air America, by, Christopher Robbins]   \n",
       "3                                                NaN   \n",
       "4                                                NaN   \n",
       "\n",
       "                                            Starring         Narrated by  \\\n",
       "0  [Andrew Dice Clay, Wayne Newton, Priscilla Pre...  Andrew \"Dice\" Clay   \n",
       "1  [Jason Patric, Rachel Ward, Bruce Dern, George...                 NaN   \n",
       "2  [Mel Gibson, Robert Downey Jr., Nancy Travis, ...                 NaN   \n",
       "3  [Alec Baldwin, Blythe Danner, Judy Davis, Mia ...                 NaN   \n",
       "4        [Paul Hogan, Elias Koteas, Linda Kozlowski]                 NaN   \n",
       "\n",
       "   Cinematography                                       Release date  \\\n",
       "0     Oliver Wood                  [July 11, 1990, (, 1990-07-11, )]   \n",
       "1    Mark Plummer  [May 17, 1990, (, 1990-05-17, ), (Cannes Film ...   \n",
       "2   Roger Deakins                [August 10, 1990, (, 1990-08-10, )]   \n",
       "3  Carlo Di Palma              [December 25, 1990, (, 1990-12-25, )]   \n",
       "4    Russell Boyd                                  December 19, 1990   \n",
       "\n",
       "  Running time  ... Created by Preceded by Suggested by alt_titles Recorded  \\\n",
       "0  102 minutes  ...        NaN         NaN          NaN        NaN      NaN   \n",
       "1  114 minutes  ...        NaN         NaN          NaN        NaN      NaN   \n",
       "2  113 minutes  ...        NaN         NaN          NaN        NaN      NaN   \n",
       "3  106 minutes  ...        NaN         NaN          NaN        NaN      NaN   \n",
       "4   95 minutes  ...        NaN         NaN          NaN        NaN      NaN   \n",
       "\n",
       "  Venue Label Animation by Color process    imdb_id  \n",
       "0   NaN   NaN          NaN           NaN  tt0098987  \n",
       "1   NaN   NaN          NaN           NaN  tt0098994  \n",
       "2   NaN   NaN          NaN           NaN  tt0099005  \n",
       "3   NaN   NaN          NaN           NaN  tt0099012  \n",
       "4   NaN   NaN          NaN           NaN  tt0099018  \n",
       "\n",
       "[5 rows x 40 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# \"(tt\\d{7}}\" the {7} says to match the last thing exactly 7 times\n",
    "# doing this to get each individual movie with an IMDb \n",
    "# need to put an 'r' in front of the quotes because there is a backslash being used\n",
    "wiki_movies_df['imdb_id'] = wiki_movies_df['imdb_link'].str.extract(r'(tt\\d{7})')\n",
    "print(len(wiki_movies_df))\n",
    "wiki_movies_df.drop_duplicates(subset='imdb_id', inplace=True)\n",
    "print(len(wiki_movies_df))\n",
    "wiki_movies_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['url', 0],\n",
       " ['year', 0],\n",
       " ['imdb_link', 0],\n",
       " ['title', 1],\n",
       " ['Based on', 4852],\n",
       " ['Starring', 184],\n",
       " ['Narrated by', 6752],\n",
       " ['Cinematography', 691],\n",
       " ['Release date', 32],\n",
       " ['Running time', 139],\n",
       " ['Country', 236],\n",
       " ['Language', 244],\n",
       " ['Budget', 2295],\n",
       " ['Box office', 1548],\n",
       " ['Director', 0],\n",
       " ['Distributor', 357],\n",
       " ['Editor(s)', 548],\n",
       " ['Composer(s)', 518],\n",
       " ['Producer(s)', 202],\n",
       " ['Production company(s)', 1678],\n",
       " ['Writer(s)', 199],\n",
       " ['Genre', 6923],\n",
       " ['Original language(s)', 6875],\n",
       " ['Original network', 6908],\n",
       " ['Executive producer(s)', 6936],\n",
       " ['Production location(s)', 6986],\n",
       " ['Picture format', 6969],\n",
       " ['Audio format', 6972],\n",
       " ['Voices of', 7031],\n",
       " ['Followed by', 7024],\n",
       " ['Created by', 7023],\n",
       " ['Preceded by', 7023],\n",
       " ['Suggested by', 7032],\n",
       " ['alt_titles', 7012],\n",
       " ['Recorded', 7031],\n",
       " ['Venue', 7032],\n",
       " ['Label', 7031],\n",
       " ['Animation by', 7031],\n",
       " ['Color process', 7032],\n",
       " ['imdb_id', 0]]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Find null values\n",
    "[[column,wiki_movies_df[column].isnull().sum()] for column in wiki_movies_df.columns]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "# How to get rid of columns where 90% of the values are null\n",
    "wiki_columns_to_keep = [column for column in wiki_movies_df.columns if wiki_movies_df[column].isnull().sum() < len(wiki_movies_df) * 0.9]\n",
    "wiki_movies_df = wiki_movies_df[wiki_columns_to_keep]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Based on',\n",
       " 'Box office',\n",
       " 'Budget',\n",
       " 'Cinematography',\n",
       " 'Composer(s)',\n",
       " 'Country',\n",
       " 'Director',\n",
       " 'Distributor',\n",
       " 'Editor(s)',\n",
       " 'Language',\n",
       " 'Producer(s)',\n",
       " 'Production company(s)',\n",
       " 'Release date',\n",
       " 'Running time',\n",
       " 'Starring',\n",
       " 'Writer(s)',\n",
       " 'imdb_id',\n",
       " 'imdb_link',\n",
       " 'title',\n",
       " 'url',\n",
       " 'year']"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# See what columns are left after eliminating columns with 90% null values\n",
    "sorted(wiki_movies_df.columns.tolist())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "url                      object\n",
       "year                      int64\n",
       "imdb_link                object\n",
       "title                    object\n",
       "Based on                 object\n",
       "Starring                 object\n",
       "Cinematography           object\n",
       "Release date             object\n",
       "Running time             object\n",
       "Country                  object\n",
       "Language                 object\n",
       "Budget                   object\n",
       "Box office               object\n",
       "Director                 object\n",
       "Distributor              object\n",
       "Editor(s)                object\n",
       "Composer(s)              object\n",
       "Producer(s)              object\n",
       "Production company(s)    object\n",
       "Writer(s)                object\n",
       "imdb_id                  object\n",
       "dtype: object"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Figure out what data types are in the DataFrame\n",
    "wiki_movies_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5485\n"
     ]
    }
   ],
   "source": [
    "# BOX OFFICE\n",
    "# Box office data should be numeric. Only want to look at rows that has defined data (aka drop missing values) \n",
    "box_office = wiki_movies_df[\"Box office\"].dropna()\n",
    "print(len(box_office))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Regular expressions - only work on strings, so make sure that box office data is entered as a string.\n",
    "def is_not_a_string(x):\n",
    "    return type(x) != str"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "34                           [US$, 4,212,828]\n",
       "54      [$6,698,361 (, United States, ), [2]]\n",
       "74                    [$6,488,144, (US), [1]]\n",
       "126                [US$1,531,489, (domestic)]\n",
       "130                          [US$, 4,803,039]\n",
       "                        ...                  \n",
       "6980               [$99.6, million, [4], [5]]\n",
       "6994                   [$365.6, million, [1]]\n",
       "6995                         [$53.8, million]\n",
       "7015                     [$435, million, [7]]\n",
       "7048                   [$529.3, million, [4]]\n",
       "Name: Box office, Length: 135, dtype: object"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# We don't want to have to create a new function every time we want to use map(), it is cumbersome and makes code harder to read\n",
    "# We want a stripped-down, one-line way of writing our functions\n",
    "# Also, do not need to use again outside of map(). So, we want to use a lambda function (does not have a name)\n",
    "box_office[box_office.map(lambda x: type(x) != str)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Can see that some are stored as lists. We want to use a join() function and use a space as our joining character\n",
    "box_office = box_office.apply(lambda x: \" \".join(x) if type(x) == list else x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a regular expression to catch all of the box office values\n",
    "# Fixing pattern matches\n",
    "#   Some values have spaces in between the dollar sign and the number...just need to add '\\s*' after the $\n",
    "#   When million is misspelled. Just need to make the second i optional\n",
    "form_one = r\"\\$\\s*\\d+\\.?\\d*\\s*[mb]illi?on\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3903"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Count how many box office values match our first form\n",
    "# To ignore whether letters are upper or lowercase, add the argument 'flags' and set it equal to 're.IGNORECASE'\n",
    "box_office.str.contains(form_one, flags=re.IGNORECASE).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1559"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Next, create a reg. ex. that matches the form '$123,456,789'\n",
    "# Fixing pattern matches\n",
    "#   Some values have spaces in between the dollar sign and the number...just need to add '\\s*'\n",
    "#   Some values use a period as a thousands separator, not a comma, add in '[,\\.]'\n",
    "#   Need to add a negatice lookahead because we don't want to catch values like '1.234 billion'\n",
    "form_two = r\"\\$\\s*\\d{1,3}(?:[,\\.]\\d{3})+(?!\\s[mb]illion)\"\n",
    "box_office.str.contains(form_two, flags=re.IGNORECASE).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Want to see if any values aren't descibed by either form, and if any value is described by both\n",
    "matches_form_one = box_office.str.contains(form_one, flags=re.IGNORECASE)\n",
    "matches_form_two = box_office.str.contains(form_two, flags=re.IGNORECASE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Try 'and' logical keyword\n",
    "#box_office[(not matches_form_one) and (not matches_form_two)]\n",
    "# This causes a ValueError"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "110              $4.35-4.37 million\n",
       "600                      $5000 (US)\n",
       "1070                     35,254,617\n",
       "1480                     £3 million\n",
       "1865                   ¥1.1 billion\n",
       "2032                            N/A\n",
       "2091                           $309\n",
       "2665    926,423 admissions (France)\n",
       "3088      $32 [2] –33.1 million [1]\n",
       "3631                            TBA\n",
       "3859             $38.9–40.3 million\n",
       "3879       CN¥3.650 million (China)\n",
       "4116                     £7,385,434\n",
       "4261             $20.7–23.9 million\n",
       "4306                         $20-30\n",
       "4561        $45.2k (only in Turkey)\n",
       "5447                          £2.56\n",
       "5784                       413 733$\n",
       "6013                        Unknown\n",
       "6145             $17.5–18.4 million\n",
       "6234             $41.8–41.9 million\n",
       "6369                          $111k\n",
       "6370                           $588\n",
       "6593                 less than $372\n",
       "6843                        8 crore\n",
       "Name: Box office, dtype: object"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# In Pandas must use a '~' for 'not', and a '&' for 'and'\n",
    "box_office[~matches_form_one & ~matches_form_two]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Solve values given as a range\n",
    "box_office = box_office.str.replace(r\"\\$.*[---](?![a-z])\", \"$\", regex=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>$21.4 million</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>$2.7 million</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>$57,718,089</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>$7,331,647</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>$6,939,946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7070</th>\n",
       "      <td>$19.4 million</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7071</th>\n",
       "      <td>$41.9 million</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7072</th>\n",
       "      <td>$76.1 million</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7073</th>\n",
       "      <td>$38.4 million</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7074</th>\n",
       "      <td>$5.5 million</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5485 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  0\n",
       "0     $21.4 million\n",
       "1      $2.7 million\n",
       "2       $57,718,089\n",
       "3        $7,331,647\n",
       "4        $6,939,946\n",
       "...             ...\n",
       "7070  $19.4 million\n",
       "7071  $41.9 million\n",
       "7072  $76.1 million\n",
       "7073  $38.4 million\n",
       "7074   $5.5 million\n",
       "\n",
       "[5485 rows x 1 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Extract and convert the box office values. Only want to extract the parts of the string that match. Use 'str.extract()'\n",
    "box_office.str.extract(f\"({form_one}|{form_two})\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Need a function to turn the extracted values into a numeric value\n",
    "def parse_dollars(s):\n",
    "    # if s is not a string, return NaN\n",
    "    if type(s) != str:\n",
    "        return np.nan\n",
    "\n",
    "    # if input is of the form $###.# million\n",
    "    if re.match(r'\\$\\s*\\d+\\.?\\d*\\s*milli?on', s, flags=re.IGNORECASE):\n",
    "\n",
    "        # remove dollar sign and \" million\"\n",
    "        s = re.sub('\\$|\\s|[a-zA-Z]','', s)\n",
    "\n",
    "        # convert to float and multiply by a million\n",
    "        value = float(s) * 10**6\n",
    "\n",
    "        # return value\n",
    "        return value\n",
    "\n",
    "    # if input is of the form $###.# billion\n",
    "    elif re.match(r'\\$\\s*\\d+\\.?\\d*\\s*billi?on', s, flags=re.IGNORECASE):\n",
    "\n",
    "        # remove dollar sign and \" billion\"\n",
    "        s = re.sub('\\$|\\s|[a-zA-Z]','', s)\n",
    "\n",
    "        # convert to float and multiply by a billion\n",
    "        value = float(s) * 10**9\n",
    "\n",
    "        # return value\n",
    "        return value\n",
    "\n",
    "    # if input is of the form $###,###,###\n",
    "    elif re.match(r'\\$\\s*\\d{1,3}(?:[,\\.]\\d{3})+(?!\\s[mb]illion)', s, flags=re.IGNORECASE):\n",
    "\n",
    "        # remove dollar sign and commas\n",
    "        s = re.sub('\\$|,','', s)\n",
    "\n",
    "        # convert to float\n",
    "        value = float(s)\n",
    "\n",
    "        # return value\n",
    "        return value\n",
    "\n",
    "    # otherwise, return NaN\n",
    "    else:\n",
    "        return np.nan\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now we can parse the box office values to numeric values\n",
    "#   Extract values from box_office using str.extract and apply parse_dollars to the first column of the dataframe\n",
    "wiki_movies_df['box_office'] = box_office.str.extract(f'({form_one}|{form_two})', flags=re.IGNORECASE)[0].apply(parse_dollars)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "# No longer need the box office column, so we may drop it \n",
    "wiki_movies_df.drop('Box office', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# BUDGET\n",
    "# Create a budget variable\n",
    "budget = wiki_movies_df['Budget'].dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert lists to strings\n",
    "budget = budget.map(lambda x: ' '.join(x) if type(x) == list else x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove values between a $ and a hyphen\n",
    "budget = budget.str.replace(r'\\$.*[-—–](?![a-z])', '$', regex=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "136                         Unknown\n",
       "204     60 million Norwegian Kroner\n",
       "478                         Unknown\n",
       "973             $34 [3] [4] million\n",
       "1126               $120 [4] million\n",
       "1226                        Unknown\n",
       "1278                            HBO\n",
       "1374                     £6,000,000\n",
       "1397                     13 million\n",
       "1480                   £2.8 million\n",
       "1734                   CAD2,000,000\n",
       "1913     PHP 85 million (estimated)\n",
       "1948                    102,888,900\n",
       "1953                   3,500,000 DM\n",
       "1973                     ₤2,300,874\n",
       "2281                     $14 milion\n",
       "2451                     ₤6,350,000\n",
       "3144                   € 40 million\n",
       "3360               $150 [6] million\n",
       "3418                        $218.32\n",
       "3802                   £4.2 million\n",
       "3906                            N/A\n",
       "3959                    760,000 USD\n",
       "4470                       19 crore\n",
       "4641                    £17 million\n",
       "5034              $$200 [4] million\n",
       "5055           $155 [2] [3] million\n",
       "5419                $40 [4] million\n",
       "5424                            N/A\n",
       "5447                     £4 million\n",
       "5671                    €14 million\n",
       "5687                   $ dead link]\n",
       "6385               £ 12 million [3]\n",
       "6593                     £3 million\n",
       "6821                  £12.9 million\n",
       "6843                      3.5 crore\n",
       "6895                        919,000\n",
       "7070                   €4.3 million\n",
       "Name: Budget, dtype: object"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Parse the budget data\n",
    "matches_form_one = budget.str.contains(form_one, flags=re.IGNORECASE)\n",
    "matches_form_two = budget.str.contains(form_two, flags=re.IGNORECASE)\n",
    "budget[~matches_form_one & ~matches_form_two]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "136                         Unknown\n",
       "204     60 million Norwegian Kroner\n",
       "478                         Unknown\n",
       "973                     $34 million\n",
       "1126                   $120 million\n",
       "1226                        Unknown\n",
       "1278                            HBO\n",
       "1374                     £6,000,000\n",
       "1397                     13 million\n",
       "1480                   £2.8 million\n",
       "1734                   CAD2,000,000\n",
       "1913     PHP 85 million (estimated)\n",
       "1948                    102,888,900\n",
       "1953                   3,500,000 DM\n",
       "1973                     ₤2,300,874\n",
       "2281                     $14 milion\n",
       "2451                     ₤6,350,000\n",
       "3144                   € 40 million\n",
       "3360                   $150 million\n",
       "3418                        $218.32\n",
       "3802                   £4.2 million\n",
       "3906                            N/A\n",
       "3959                    760,000 USD\n",
       "4470                       19 crore\n",
       "4641                    £17 million\n",
       "5034                  $$200 million\n",
       "5055                   $155 million\n",
       "5419                    $40 million\n",
       "5424                            N/A\n",
       "5447                     £4 million\n",
       "5671                    €14 million\n",
       "5687                   $ dead link]\n",
       "6385                  £ 12 million \n",
       "6593                     £3 million\n",
       "6821                  £12.9 million\n",
       "6843                      3.5 crore\n",
       "6895                        919,000\n",
       "7070                   €4.3 million\n",
       "Name: Budget, dtype: object"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remove citation references\n",
    "budget = budget.str.replace(r'\\[\\d+\\]\\s*', '')\n",
    "budget[~matches_form_one & ~matches_form_two]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Can now parse the budget values\n",
    "wiki_movies_df['budget'] = budget.str.extract(f'({form_one}|{form_two})', flags=re.IGNORECASE)[0].apply(parse_dollars)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop the original budget column\n",
    "wiki_movies_df.drop('Budget', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "# RELEASE DATE\n",
    "# Make a variable that holds non-null values of Release date in the dataframe, converting lists to strings\n",
    "release_date = wiki_movies_df['Release date'].dropna().apply(lambda x: ' '.join(x) if type(x) == list else x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "# What we'll be parsing:\n",
    "#   January 1, 2000....form_one\n",
    "#   2000-01-01....form_two\n",
    "#   January 2000....form_three\n",
    "#   four-digit year....form_four\n",
    "date_form_one = r\"(?:January|February|March|April|May|June|July|August|September|October|November|December)\\s[123]\\d,\\s\\d{4}\"\n",
    "date_form_two = r\"\\d{4}.[01]\\d.[123]\\d\"\n",
    "date_form_three = r\"(?:January|February|March|April|May|June|July|August|September|October|November|December)\\s\\d{4}\"\n",
    "date_form_four = r\"\\d{4}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>July 11, 1990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>May 17, 1990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>August 10, 1990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>December 25, 1990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>December 19, 1990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7071</th>\n",
       "      <td>December 25, 2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7072</th>\n",
       "      <td>December 11, 2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7073</th>\n",
       "      <td>2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7074</th>\n",
       "      <td>August 31, 2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7075</th>\n",
       "      <td>December 2018</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7001 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                      0\n",
       "0         July 11, 1990\n",
       "1          May 17, 1990\n",
       "2       August 10, 1990\n",
       "3     December 25, 1990\n",
       "4     December 19, 1990\n",
       "...                 ...\n",
       "7071  December 25, 2018\n",
       "7072  December 11, 2018\n",
       "7073               2018\n",
       "7074    August 31, 2018\n",
       "7075      December 2018\n",
       "\n",
       "[7001 rows x 1 columns]"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Extract the dates\n",
    "release_date.str.extract(f'({date_form_one}|{date_form_two}|{date_form_three}|{date_form_four})', flags=re.IGNORECASE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use the built-in to_datetime() method in Pandas\n",
    "# There are different date formats, want to set the 'infer_datetime_format' to 'True'\n",
    "wiki_movies_df['release_date'] = pd.to_datetime(release_date.str.extract(f'({date_form_one}|{date_form_two}|{date_form_three}|{date_form_four})')[0], infer_datetime_format=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "# RUNNING TIME\n",
    "# Make a variable that holds the non-null values of Running time in the dataframe\n",
    "running_time = wiki_movies_df['Running time'].dropna().apply(lambda x: ' '.join(x) if type(x) == list else x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6894"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many movies with a running time\n",
    "running_time\n",
    "running_time.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6528"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Figure out how many movies have running time that look like 100 minutes\n",
    "running_time.str.contains(r'^\\d*\\s*minutes$', flags=re.IGNORECASE).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9                                                 102 min\n",
       "26                                                 93 min\n",
       "28                                                32 min.\n",
       "34                                                101 min\n",
       "35                                                 97 min\n",
       "                              ...                        \n",
       "6500       114 minutes [1] 120 minutes (extended edition)\n",
       "6643                                             104 mins\n",
       "6709    90 minutes (theatrical) [1] 91 minutes (unrate...\n",
       "7057    108 minutes (Original cut) 98 minutes (UK cut)...\n",
       "7075                Variable; 90 minutes for default path\n",
       "Name: Running time, Length: 366, dtype: object"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# What do the 366 entries look like??\n",
    "running_time[running_time.str.contains(r'^\\d*\\s*minutes$', flags=re.IGNORECASE) != True]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6877"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Some have min or minutes plus other words\n",
    "# Look at just the beginning of the string 'm'\n",
    "running_time.str.contains(r'^\\d*\\s*m', flags=re.IGNORECASE).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "668                     UK:84 min (DVD version) US:86 min\n",
       "727                         78-102 min (depending on cut)\n",
       "840                       Varies (79 [3] –84 [1] minutes)\n",
       "1347                                              25 : 03\n",
       "1443    United States: 77 minutes Argentina: 94 minute...\n",
       "1499                                            1hr 35min\n",
       "1551                                               varies\n",
       "1774                    Netherlands:96 min, Canada:95 min\n",
       "1777                                       approx. 14 min\n",
       "2273                                           1 h 43 min\n",
       "2993                                               1h 48m\n",
       "3925                                              4 hours\n",
       "4425    US domestic version: 86 minutes Original versi...\n",
       "4967    Theatrical cut: 97 minutes Unrated cut: 107 mi...\n",
       "5424                    115 [1] /123 [2] /128 [3] minutes\n",
       "5447                                    1 hour 32 minutes\n",
       "7075                Variable; 90 minutes for default path\n",
       "Name: Running time, dtype: object"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look at the 17 remaining...do they not use minutes for a unit of time??\n",
    "running_time[running_time.str.contains(r'^\\d*\\s*m', flags=re.IGNORECASE) != True]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6891"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Change the regex that relaxes the condition of patterns starting at the beginning of the string...remove the caret ^\n",
    "running_time.str.contains(r'\\d*\\s*m', flags=re.IGNORECASE).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Need to match all the hour + minute patterns with one regex. Must:\n",
    "#   Start with one digit\n",
    "#   Have an optional space after the digit and before \"h\"\n",
    "#   Capture all abbreviations of \"hour(s)\". Need to make every letter optional except the \"h\"\n",
    "#   Have an optional space after hours marker\n",
    "#   Have optional number of digits for minutes\n",
    "#   CODE = \\d+\\s*ho?u?r?s?\\s*\\d*\n",
    "#   Want to only extract digits, so add capture groups () around the digits. Also, add in the or statement | for the other form\n",
    "running_time_extract = running_time.str.extract(r'(\\d+)\\s*ho?u?r?s?\\s*(\\d*)|(\\d+)\\s*m')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>102</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>113</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7071</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7072</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>132</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7073</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7074</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7075</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6894 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        0    1    2\n",
       "0     NaN  NaN  102\n",
       "1     NaN  NaN  114\n",
       "2     NaN  NaN  113\n",
       "3     NaN  NaN  106\n",
       "4     NaN  NaN   95\n",
       "...   ...  ...  ...\n",
       "7071  NaN  NaN   90\n",
       "7072  NaN  NaN  132\n",
       "7073  NaN  NaN  120\n",
       "7074  NaN  NaN  123\n",
       "7075  NaN  NaN   90\n",
       "\n",
       "[6894 rows x 3 columns]"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "running_time_extract"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The dataframe is all strings, so we need to convert to numeric values. Use 'to_numeric()'\n",
    "# Set the errors arguement to 'coerce', this will turn empty strings to NaN\n",
    "# We can then use 'fillna()' to change all NaN's to zero \n",
    "running_time_extract = running_time_extract.apply(lambda col: pd.to_numeric(col, errors='coerce')).fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>102.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>114.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>113.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>106.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>95.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7071</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7072</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>132.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7073</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>120.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7074</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>123.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7075</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6894 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        0    1      2\n",
       "0     0.0  0.0  102.0\n",
       "1     0.0  0.0  114.0\n",
       "2     0.0  0.0  113.0\n",
       "3     0.0  0.0  106.0\n",
       "4     0.0  0.0   95.0\n",
       "...   ...  ...    ...\n",
       "7071  0.0  0.0   90.0\n",
       "7072  0.0  0.0  132.0\n",
       "7073  0.0  0.0  120.0\n",
       "7074  0.0  0.0  123.0\n",
       "7075  0.0  0.0   90.0\n",
       "\n",
       "[6894 rows x 3 columns]"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "running_time_extract"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Apply a function that will convert the hour and minute capture groups to minutes\n",
    "wiki_movies_df['running_time'] = running_time_extract.apply(lambda row: row[0]*60 + row[1] if row[2] == 0 else row[2], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Can now drop Running time from the dataset\n",
    "wiki_movies_df.drop('Running time', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "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>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>Cinematography</th>\n",
       "      <th>Release date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Language</th>\n",
       "      <th>...</th>\n",
       "      <th>Editor(s)</th>\n",
       "      <th>Composer(s)</th>\n",
       "      <th>Producer(s)</th>\n",
       "      <th>Production company(s)</th>\n",
       "      <th>Writer(s)</th>\n",
       "      <th>imdb_id</th>\n",
       "      <th>box_office</th>\n",
       "      <th>budget</th>\n",
       "      <th>release_date</th>\n",
       "      <th>running_time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>[Characters, by Rex Weiner]</td>\n",
       "      <td>[Andrew Dice Clay, Wayne Newton, Priscilla Pre...</td>\n",
       "      <td>Oliver Wood</td>\n",
       "      <td>[July 11, 1990, (, 1990-07-11, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Michael Tronick</td>\n",
       "      <td>[Cliff Eidelman, Yello]</td>\n",
       "      <td>[Steve Perry, Joel Silver]</td>\n",
       "      <td>Silver Pictures</td>\n",
       "      <td>[David Arnott, James Cappe]</td>\n",
       "      <td>tt0098987</td>\n",
       "      <td>21400000.0</td>\n",
       "      <td>20000000.0</td>\n",
       "      <td>1990-07-11</td>\n",
       "      <td>102.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>[the novel, After Dark, My Sweet, by, Jim Thom...</td>\n",
       "      <td>[Jason Patric, Rachel Ward, Bruce Dern, George...</td>\n",
       "      <td>Mark Plummer</td>\n",
       "      <td>[May 17, 1990, (, 1990-05-17, ), (Cannes Film ...</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Howard E. Smith</td>\n",
       "      <td>Maurice Jarre</td>\n",
       "      <td>[Ric Kidney, Robert Redlin]</td>\n",
       "      <td>Avenue Pictures</td>\n",
       "      <td>[James Foley, Robert Redlin]</td>\n",
       "      <td>tt0098994</td>\n",
       "      <td>2700000.0</td>\n",
       "      <td>6000000.0</td>\n",
       "      <td>1990-05-17</td>\n",
       "      <td>114.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>Air America</td>\n",
       "      <td>[Air America, by, Christopher Robbins]</td>\n",
       "      <td>[Mel Gibson, Robert Downey Jr., Nancy Travis, ...</td>\n",
       "      <td>Roger Deakins</td>\n",
       "      <td>[August 10, 1990, (, 1990-08-10, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>[English, Lao]</td>\n",
       "      <td>...</td>\n",
       "      <td>[John Bloom, Lois Freeman-Fox]</td>\n",
       "      <td>Charles Gross</td>\n",
       "      <td>Daniel Melnick</td>\n",
       "      <td>[Carolco Pictures, IndieProd Company]</td>\n",
       "      <td>[John Eskow, Richard Rush]</td>\n",
       "      <td>tt0099005</td>\n",
       "      <td>57718089.0</td>\n",
       "      <td>35000000.0</td>\n",
       "      <td>1990-08-10</td>\n",
       "      <td>113.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>Alice</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Alec Baldwin, Blythe Danner, Judy Davis, Mia ...</td>\n",
       "      <td>Carlo Di Palma</td>\n",
       "      <td>[December 25, 1990, (, 1990-12-25, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Susan E. Morse</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Robert Greenhut</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Woody Allen</td>\n",
       "      <td>tt0099012</td>\n",
       "      <td>7331647.0</td>\n",
       "      <td>12000000.0</td>\n",
       "      <td>1990-12-25</td>\n",
       "      <td>106.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Paul Hogan, Elias Koteas, Linda Kozlowski]</td>\n",
       "      <td>Russell Boyd</td>\n",
       "      <td>December 19, 1990</td>\n",
       "      <td>US</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>David Stiven</td>\n",
       "      <td>Maurice Jarre</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Paul Hogan</td>\n",
       "      <td>tt0099018</td>\n",
       "      <td>6939946.0</td>\n",
       "      <td>25000000.0</td>\n",
       "      <td>1990-12-19</td>\n",
       "      <td>95.0</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>7071</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Holmes_%26_Watson</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt1255919/</td>\n",
       "      <td>Holmes &amp; Watson</td>\n",
       "      <td>[Sherlock Holmes, and, Dr. Watson, by, Sir Art...</td>\n",
       "      <td>[Will Ferrell, John C. Reilly, Rebecca Hall, R...</td>\n",
       "      <td>Oliver Wood</td>\n",
       "      <td>[December 25, 2018, (, 2018-12-25, ), (United ...</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Dean Zimmerman</td>\n",
       "      <td>Mark Mothersbaugh</td>\n",
       "      <td>[Will Ferrell, Adam McKay, Jimmy Miller, Clayt...</td>\n",
       "      <td>[Columbia Pictures, Gary Sanchez Productions, ...</td>\n",
       "      <td>Etan Cohen</td>\n",
       "      <td>tt1255919</td>\n",
       "      <td>41900000.0</td>\n",
       "      <td>42000000.0</td>\n",
       "      <td>2018-12-25</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7072</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Vice_(2018_film)</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt6266538/</td>\n",
       "      <td>Vice</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Christian Bale, Amy Adams, Steve Carell, Sam ...</td>\n",
       "      <td>Greig Fraser</td>\n",
       "      <td>[December 11, 2018, (, 2018-12-11, ), (, Samue...</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Hank Corwin</td>\n",
       "      <td>Nicholas Britell</td>\n",
       "      <td>[Brad Pitt, Dede Gardner, Jeremy Kleiner, Kevi...</td>\n",
       "      <td>[Plan B Entertainment, Gary Sanchez Production...</td>\n",
       "      <td>Adam McKay</td>\n",
       "      <td>tt6266538</td>\n",
       "      <td>76100000.0</td>\n",
       "      <td>60000000.0</td>\n",
       "      <td>2018-12-11</td>\n",
       "      <td>132.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7073</th>\n",
       "      <td>https://en.wikipedia.org/wiki/On_the_Basis_of_Sex</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt4669788/</td>\n",
       "      <td>On the Basis of Sex</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Felicity Jones, Armie Hammer, Justin Theroux,...</td>\n",
       "      <td>Michael Grady</td>\n",
       "      <td>[November 8, 2018, (, 2018-11-08, ), (, AFI Fe...</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Michelle Tesoro</td>\n",
       "      <td>Mychael Danna</td>\n",
       "      <td>Robert W. Cort</td>\n",
       "      <td>[Focus Features, [1], Participant Media, [1], ...</td>\n",
       "      <td>Daniel Stiepleman</td>\n",
       "      <td>tt4669788</td>\n",
       "      <td>38400000.0</td>\n",
       "      <td>20000000.0</td>\n",
       "      <td>2018-01-01</td>\n",
       "      <td>120.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7074</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Destroyer_(2018_...</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt7137380/</td>\n",
       "      <td>Destroyer</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Nicole Kidman, Sebastian Stan, Toby Kebbell, ...</td>\n",
       "      <td>Julie Kirkwood</td>\n",
       "      <td>[August 31, 2018, (, 2018-08-31, ), (, Telluri...</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Plummy Tucker</td>\n",
       "      <td>Theodore Shapiro</td>\n",
       "      <td>[Fred Berger, Phil Hay, Matt Manfredi]</td>\n",
       "      <td>[30West, Automatik Entertainment, Annapurna Pi...</td>\n",
       "      <td>[Phil Hay, Matt Manfredi]</td>\n",
       "      <td>tt7137380</td>\n",
       "      <td>5500000.0</td>\n",
       "      <td>9000000.0</td>\n",
       "      <td>2018-08-31</td>\n",
       "      <td>123.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7075</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Black_Mirror:_Ba...</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt9495224/</td>\n",
       "      <td>Bandersnatch</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Fionn Whitehead, Will Poulter, Craig Parkinso...</td>\n",
       "      <td>[Aaron Morton, Jake Polonsky]</td>\n",
       "      <td>[28 December 2018, (, 2018-12-28, )]</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>Tony Kearns</td>\n",
       "      <td>Brian Reitzell</td>\n",
       "      <td>Russell McLean</td>\n",
       "      <td>[House of Tomorrow, Netflix]</td>\n",
       "      <td>Charlie Brooker</td>\n",
       "      <td>tt9495224</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2018-12-01</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7033 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    url  year  \\\n",
       "0     https://en.wikipedia.org/wiki/The_Adventures_o...  1990   \n",
       "1     https://en.wikipedia.org/wiki/After_Dark,_My_S...  1990   \n",
       "2      https://en.wikipedia.org/wiki/Air_America_(film)  1990   \n",
       "3       https://en.wikipedia.org/wiki/Alice_(1990_film)  1990   \n",
       "4         https://en.wikipedia.org/wiki/Almost_an_Angel  1990   \n",
       "...                                                 ...   ...   \n",
       "7071    https://en.wikipedia.org/wiki/Holmes_%26_Watson  2018   \n",
       "7072     https://en.wikipedia.org/wiki/Vice_(2018_film)  2018   \n",
       "7073  https://en.wikipedia.org/wiki/On_the_Basis_of_Sex  2018   \n",
       "7074  https://en.wikipedia.org/wiki/Destroyer_(2018_...  2018   \n",
       "7075  https://en.wikipedia.org/wiki/Black_Mirror:_Ba...  2018   \n",
       "\n",
       "                                  imdb_link                            title  \\\n",
       "0     https://www.imdb.com/title/tt0098987/  The Adventures of Ford Fairlane   \n",
       "1     https://www.imdb.com/title/tt0098994/             After Dark, My Sweet   \n",
       "2     https://www.imdb.com/title/tt0099005/                      Air America   \n",
       "3     https://www.imdb.com/title/tt0099012/                            Alice   \n",
       "4     https://www.imdb.com/title/tt0099018/                  Almost an Angel   \n",
       "...                                     ...                              ...   \n",
       "7071  https://www.imdb.com/title/tt1255919/                  Holmes & Watson   \n",
       "7072  https://www.imdb.com/title/tt6266538/                             Vice   \n",
       "7073  https://www.imdb.com/title/tt4669788/              On the Basis of Sex   \n",
       "7074  https://www.imdb.com/title/tt7137380/                        Destroyer   \n",
       "7075  https://www.imdb.com/title/tt9495224/                     Bandersnatch   \n",
       "\n",
       "                                               Based on  \\\n",
       "0                           [Characters, by Rex Weiner]   \n",
       "1     [the novel, After Dark, My Sweet, by, Jim Thom...   \n",
       "2                [Air America, by, Christopher Robbins]   \n",
       "3                                                   NaN   \n",
       "4                                                   NaN   \n",
       "...                                                 ...   \n",
       "7071  [Sherlock Holmes, and, Dr. Watson, by, Sir Art...   \n",
       "7072                                                NaN   \n",
       "7073                                                NaN   \n",
       "7074                                                NaN   \n",
       "7075                                                NaN   \n",
       "\n",
       "                                               Starring  \\\n",
       "0     [Andrew Dice Clay, Wayne Newton, Priscilla Pre...   \n",
       "1     [Jason Patric, Rachel Ward, Bruce Dern, George...   \n",
       "2     [Mel Gibson, Robert Downey Jr., Nancy Travis, ...   \n",
       "3     [Alec Baldwin, Blythe Danner, Judy Davis, Mia ...   \n",
       "4           [Paul Hogan, Elias Koteas, Linda Kozlowski]   \n",
       "...                                                 ...   \n",
       "7071  [Will Ferrell, John C. Reilly, Rebecca Hall, R...   \n",
       "7072  [Christian Bale, Amy Adams, Steve Carell, Sam ...   \n",
       "7073  [Felicity Jones, Armie Hammer, Justin Theroux,...   \n",
       "7074  [Nicole Kidman, Sebastian Stan, Toby Kebbell, ...   \n",
       "7075  [Fionn Whitehead, Will Poulter, Craig Parkinso...   \n",
       "\n",
       "                     Cinematography  \\\n",
       "0                       Oliver Wood   \n",
       "1                      Mark Plummer   \n",
       "2                     Roger Deakins   \n",
       "3                    Carlo Di Palma   \n",
       "4                      Russell Boyd   \n",
       "...                             ...   \n",
       "7071                    Oliver Wood   \n",
       "7072                   Greig Fraser   \n",
       "7073                  Michael Grady   \n",
       "7074                 Julie Kirkwood   \n",
       "7075  [Aaron Morton, Jake Polonsky]   \n",
       "\n",
       "                                           Release date         Country  \\\n",
       "0                     [July 11, 1990, (, 1990-07-11, )]   United States   \n",
       "1     [May 17, 1990, (, 1990-05-17, ), (Cannes Film ...   United States   \n",
       "2                   [August 10, 1990, (, 1990-08-10, )]   United States   \n",
       "3                 [December 25, 1990, (, 1990-12-25, )]   United States   \n",
       "4                                     December 19, 1990              US   \n",
       "...                                                 ...             ...   \n",
       "7071  [December 25, 2018, (, 2018-12-25, ), (United ...   United States   \n",
       "7072  [December 11, 2018, (, 2018-12-11, ), (, Samue...   United States   \n",
       "7073  [November 8, 2018, (, 2018-11-08, ), (, AFI Fe...   United States   \n",
       "7074  [August 31, 2018, (, 2018-08-31, ), (, Telluri...   United States   \n",
       "7075               [28 December 2018, (, 2018-12-28, )]  United Kingdom   \n",
       "\n",
       "            Language  ...                       Editor(s)  \\\n",
       "0            English  ...                 Michael Tronick   \n",
       "1            English  ...                 Howard E. Smith   \n",
       "2     [English, Lao]  ...  [John Bloom, Lois Freeman-Fox]   \n",
       "3            English  ...                  Susan E. Morse   \n",
       "4            English  ...                    David Stiven   \n",
       "...              ...  ...                             ...   \n",
       "7071         English  ...                  Dean Zimmerman   \n",
       "7072         English  ...                     Hank Corwin   \n",
       "7073         English  ...                 Michelle Tesoro   \n",
       "7074         English  ...                   Plummy Tucker   \n",
       "7075         English  ...                     Tony Kearns   \n",
       "\n",
       "                  Composer(s)  \\\n",
       "0     [Cliff Eidelman, Yello]   \n",
       "1               Maurice Jarre   \n",
       "2               Charles Gross   \n",
       "3                         NaN   \n",
       "4               Maurice Jarre   \n",
       "...                       ...   \n",
       "7071        Mark Mothersbaugh   \n",
       "7072         Nicholas Britell   \n",
       "7073            Mychael Danna   \n",
       "7074         Theodore Shapiro   \n",
       "7075           Brian Reitzell   \n",
       "\n",
       "                                            Producer(s)  \\\n",
       "0                            [Steve Perry, Joel Silver]   \n",
       "1                           [Ric Kidney, Robert Redlin]   \n",
       "2                                        Daniel Melnick   \n",
       "3                                       Robert Greenhut   \n",
       "4                                          John Cornell   \n",
       "...                                                 ...   \n",
       "7071  [Will Ferrell, Adam McKay, Jimmy Miller, Clayt...   \n",
       "7072  [Brad Pitt, Dede Gardner, Jeremy Kleiner, Kevi...   \n",
       "7073                                     Robert W. Cort   \n",
       "7074             [Fred Berger, Phil Hay, Matt Manfredi]   \n",
       "7075                                     Russell McLean   \n",
       "\n",
       "                                  Production company(s)  \\\n",
       "0                                       Silver Pictures   \n",
       "1                                       Avenue Pictures   \n",
       "2                 [Carolco Pictures, IndieProd Company]   \n",
       "3                                                   NaN   \n",
       "4                                                   NaN   \n",
       "...                                                 ...   \n",
       "7071  [Columbia Pictures, Gary Sanchez Productions, ...   \n",
       "7072  [Plan B Entertainment, Gary Sanchez Production...   \n",
       "7073  [Focus Features, [1], Participant Media, [1], ...   \n",
       "7074  [30West, Automatik Entertainment, Annapurna Pi...   \n",
       "7075                       [House of Tomorrow, Netflix]   \n",
       "\n",
       "                         Writer(s)    imdb_id  box_office      budget  \\\n",
       "0      [David Arnott, James Cappe]  tt0098987  21400000.0  20000000.0   \n",
       "1     [James Foley, Robert Redlin]  tt0098994   2700000.0   6000000.0   \n",
       "2       [John Eskow, Richard Rush]  tt0099005  57718089.0  35000000.0   \n",
       "3                      Woody Allen  tt0099012   7331647.0  12000000.0   \n",
       "4                       Paul Hogan  tt0099018   6939946.0  25000000.0   \n",
       "...                            ...        ...         ...         ...   \n",
       "7071                    Etan Cohen  tt1255919  41900000.0  42000000.0   \n",
       "7072                    Adam McKay  tt6266538  76100000.0  60000000.0   \n",
       "7073             Daniel Stiepleman  tt4669788  38400000.0  20000000.0   \n",
       "7074     [Phil Hay, Matt Manfredi]  tt7137380   5500000.0   9000000.0   \n",
       "7075               Charlie Brooker  tt9495224         NaN         NaN   \n",
       "\n",
       "      release_date  running_time  \n",
       "0       1990-07-11         102.0  \n",
       "1       1990-05-17         114.0  \n",
       "2       1990-08-10         113.0  \n",
       "3       1990-12-25         106.0  \n",
       "4       1990-12-19          95.0  \n",
       "...            ...           ...  \n",
       "7071    2018-12-25          90.0  \n",
       "7072    2018-12-11         132.0  \n",
       "7073    2018-01-01         120.0  \n",
       "7074    2018-08-31         123.0  \n",
       "7075    2018-12-01          90.0  \n",
       "\n",
       "[7033 rows x 22 columns]"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wiki_movies_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "adult                     object\n",
       "belongs_to_collection     object\n",
       "budget                    object\n",
       "genres                    object\n",
       "homepage                  object\n",
       "id                        object\n",
       "imdb_id                   object\n",
       "original_language         object\n",
       "original_title            object\n",
       "overview                  object\n",
       "popularity                object\n",
       "poster_path               object\n",
       "production_companies      object\n",
       "production_countries      object\n",
       "release_date              object\n",
       "revenue                  float64\n",
       "runtime                  float64\n",
       "spoken_languages          object\n",
       "status                    object\n",
       "tagline                   object\n",
       "title                     object\n",
       "video                     object\n",
       "vote_average             float64\n",
       "vote_count               float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# LOOKING AT MOVIE METADATA - KAGGLE\n",
    "kaggle_metadata.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False                                                                                                                             45454\n",
       "True                                                                                                                                  9\n",
       " Avalanche Sharks tells the story of a bikini contest that turns into a horrifying affair when it is hit by a shark avalanche.        1\n",
       " Rune Balot goes to a casino connected to the October corporation to try to wrap up her case once and for all.                        1\n",
       " - Written by Ørnås                                                                                                                   1\n",
       "Name: adult, dtype: int64"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Make sure that adult and video columns are either true or false\n",
    "kaggle_metadata[\"adult\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "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>adult</th>\n",
       "      <th>belongs_to_collection</th>\n",
       "      <th>budget</th>\n",
       "      <th>genres</th>\n",
       "      <th>homepage</th>\n",
       "      <th>id</th>\n",
       "      <th>imdb_id</th>\n",
       "      <th>original_language</th>\n",
       "      <th>original_title</th>\n",
       "      <th>overview</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>19730</th>\n",
       "      <td>- Written by Ørnås</td>\n",
       "      <td>0.065736</td>\n",
       "      <td>/ff9qCepilowshEtG2GYWwzt2bs4.jpg</td>\n",
       "      <td>[{'name': 'Carousel Productions', 'id': 11176}...</td>\n",
       "      <td>[{'iso_3166_1': 'CA', 'name': 'Canada'}, {'iso...</td>\n",
       "      <td>1997-08-20</td>\n",
       "      <td>0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29503</th>\n",
       "      <td>Rune Balot goes to a casino connected to the ...</td>\n",
       "      <td>1.931659</td>\n",
       "      <td>/zV8bHuSL6WXoD6FWogP9j4x80bL.jpg</td>\n",
       "      <td>[{'name': 'Aniplex', 'id': 2883}, {'name': 'Go...</td>\n",
       "      <td>[{'iso_3166_1': 'US', 'name': 'United States o...</td>\n",
       "      <td>2012-09-29</td>\n",
       "      <td>0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>[{'iso_639_1': 'ja', 'name': '日本語'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>...</td>\n",
       "      <td>12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35587</th>\n",
       "      <td>Avalanche Sharks tells the story of a bikini ...</td>\n",
       "      <td>2.185485</td>\n",
       "      <td>/zaSf5OG7V8X8gqFvly88zDdRm46.jpg</td>\n",
       "      <td>[{'name': 'Odyssey Media', 'id': 17161}, {'nam...</td>\n",
       "      <td>[{'iso_3166_1': 'CA', 'name': 'Canada'}]</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>...</td>\n",
       "      <td>22</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   adult  \\\n",
       "19730                                 - Written by Ørnås   \n",
       "29503   Rune Balot goes to a casino connected to the ...   \n",
       "35587   Avalanche Sharks tells the story of a bikini ...   \n",
       "\n",
       "      belongs_to_collection                            budget  \\\n",
       "19730              0.065736  /ff9qCepilowshEtG2GYWwzt2bs4.jpg   \n",
       "29503              1.931659  /zV8bHuSL6WXoD6FWogP9j4x80bL.jpg   \n",
       "35587              2.185485  /zaSf5OG7V8X8gqFvly88zDdRm46.jpg   \n",
       "\n",
       "                                                  genres  \\\n",
       "19730  [{'name': 'Carousel Productions', 'id': 11176}...   \n",
       "29503  [{'name': 'Aniplex', 'id': 2883}, {'name': 'Go...   \n",
       "35587  [{'name': 'Odyssey Media', 'id': 17161}, {'nam...   \n",
       "\n",
       "                                                homepage          id imdb_id  \\\n",
       "19730  [{'iso_3166_1': 'CA', 'name': 'Canada'}, {'iso...  1997-08-20       0   \n",
       "29503  [{'iso_3166_1': 'US', 'name': 'United States o...  2012-09-29       0   \n",
       "35587           [{'iso_3166_1': 'CA', 'name': 'Canada'}]  2014-01-01       0   \n",
       "\n",
       "      original_language                            original_title  overview  \\\n",
       "19730             104.0  [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "29503              68.0      [{'iso_639_1': 'ja', 'name': '日本語'}]  Released   \n",
       "35587              82.0  [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "\n",
       "       ... release_date revenue runtime spoken_languages status  tagline  \\\n",
       "19730  ...            1     NaN     NaN              NaN    NaN      NaN   \n",
       "29503  ...           12     NaN     NaN              NaN    NaN      NaN   \n",
       "35587  ...           22     NaN     NaN              NaN    NaN      NaN   \n",
       "\n",
       "       title video vote_average vote_count  \n",
       "19730    NaN   NaN          NaN        NaN  \n",
       "29503    NaN   NaN          NaN        NaN  \n",
       "35587    NaN   NaN          NaN        NaN  \n",
       "\n",
       "[3 rows x 24 columns]"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remove the bad data\n",
    "kaggle_metadata[~kaggle_metadata[\"adult\"].isin([\"True\",\"False\"])]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Keep rows where adult column is False, and drop adult column\n",
    "kaggle_metadata = kaggle_metadata[kaggle_metadata['adult'] == 'False'].drop('adult',axis='columns')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    45358\n",
       "True        93\n",
       "Name: video, dtype: int64"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look at values in video column\n",
    "kaggle_metadata['video'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        False\n",
       "1        False\n",
       "2        False\n",
       "3        False\n",
       "4        False\n",
       "         ...  \n",
       "45461    False\n",
       "45462    False\n",
       "45463    False\n",
       "45464    False\n",
       "45465    False\n",
       "Name: video, Length: 45454, dtype: bool"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Convert data types\n",
    "kaggle_metadata['video'] == 'True'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Assign  it back to video\n",
    "kaggle_metadata['video'] = kaggle_metadata['video'] == 'True'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "# For numeric columns: use to_numeric(), and make sure errors= is set to 'raise' so we know of any data that can't be converted to numbers\n",
    "kaggle_metadata['budget'] = kaggle_metadata['budget'].astype(int)\n",
    "kaggle_metadata['id'] = pd.to_numeric(kaggle_metadata['id'], errors='raise')\n",
    "kaggle_metadata['popularity'] = pd.to_numeric(kaggle_metadata['popularity'], errors='raise')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert release_date to datetime\n",
    "kaggle_metadata['release_date'] = pd.to_datetime(kaggle_metadata['release_date'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 26024289 entries, 0 to 26024288\n",
      "Data columns (total 4 columns):\n",
      "userId       26024289 non-null int64\n",
      "movieId      26024289 non-null int64\n",
      "rating       26024289 non-null float64\n",
      "timestamp    26024289 non-null int64\n",
      "dtypes: float64(1), int64(3)\n",
      "memory usage: 794.2 MB\n"
     ]
    }
   ],
   "source": [
    "# RATINGS DATA\n",
    "# Use null_counts with option True \n",
    "ratings.info(null_counts=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0          2015-03-09 22:52:09\n",
       "1          2015-03-09 23:07:15\n",
       "2          2015-03-09 22:52:03\n",
       "3          2015-03-09 22:52:26\n",
       "4          2015-03-09 22:52:36\n",
       "                   ...        \n",
       "26024284   2009-10-31 23:26:04\n",
       "26024285   2009-10-31 23:33:52\n",
       "26024286   2009-10-31 23:29:24\n",
       "26024287   2009-11-01 00:06:30\n",
       "26024288   2009-10-31 23:30:58\n",
       "Name: timestamp, Length: 26024289, dtype: datetime64[ns]"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Use to_datetime() 'unix' as the time unit in seconds(s)\n",
    "pd.to_datetime(ratings['timestamp'], unit='s')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Dates look good, so assign to timestamp column\n",
    "ratings['timestamp'] = pd.to_datetime(ratings['timestamp'], unit='s')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    2.602429e+07\n",
       "mean     3.528090e+00\n",
       "std      1.065443e+00\n",
       "min      5.000000e-01\n",
       "25%      3.000000e+00\n",
       "50%      3.500000e+00\n",
       "75%      4.000000e+00\n",
       "max      5.000000e+00\n",
       "Name: rating, dtype: float64"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Need to look at actual ratings and see if there are outliers. Use a histogram\n",
    "ratings['rating'].plot(kind='hist')\n",
    "ratings['rating'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "# MERGING DATA\n",
    "# Print list of columns so we can see what is redundant\n",
    "movies_df = pd.merge(wiki_movies_df, kaggle_metadata, on='imdb_id', suffixes=['_wiki','_kaggle'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Competing data:\n",
    "# Wiki                     Movielens                Resolution\n",
    "#--------------------------------------------------------------------------\n",
    "# title_wiki               title_kaggle\n",
    "# running_time             runtime\n",
    "# budget_wiki              budget_kaggle\n",
    "# box_office               revenue\n",
    "# release_date_wiki        release_date_kaggle\n",
    "# Language                 original_language\n",
    "# Production company(s)    production_companies    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "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_wiki</th>\n",
       "      <th>title_kaggle</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Air America</td>\n",
       "      <td>Air America</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Alice</td>\n",
       "      <td>Alice</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>Almost an Angel</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6047</th>\n",
       "      <td>A Fantastic Woman</td>\n",
       "      <td>A Fantastic Woman</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6048</th>\n",
       "      <td>Permission</td>\n",
       "      <td>Permission</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6049</th>\n",
       "      <td>Loveless</td>\n",
       "      <td>Loveless</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6050</th>\n",
       "      <td>Gemini</td>\n",
       "      <td>Gemini</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6051</th>\n",
       "      <td>How to Talk to Girls at Parties</td>\n",
       "      <td>How to Talk to Girls at Parties</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6052 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                           title_wiki                     title_kaggle\n",
       "0     The Adventures of Ford Fairlane  The Adventures of Ford Fairlane\n",
       "1                After Dark, My Sweet             After Dark, My Sweet\n",
       "2                         Air America                      Air America\n",
       "3                               Alice                            Alice\n",
       "4                     Almost an Angel                  Almost an Angel\n",
       "...                               ...                              ...\n",
       "6047                A Fantastic Woman                A Fantastic Woman\n",
       "6048                       Permission                       Permission\n",
       "6049                         Loveless                         Loveless\n",
       "6050                           Gemini                           Gemini\n",
       "6051  How to Talk to Girls at Parties  How to Talk to Girls at Parties\n",
       "\n",
       "[6052 rows x 2 columns]"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Start comparing columns\n",
    "# Title\n",
    "movies_df[['title_wiki','title_kaggle']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "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_wiki</th>\n",
       "      <th>title_kaggle</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>China Cry</td>\n",
       "      <td>China Cry: A True Story</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>Daddy's Dyin' ...Who's Got the Will?</td>\n",
       "      <td>Daddy's Dyin'... Who's Got the Will?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>The Dark Side of the Moon</td>\n",
       "      <td>The Dark Side of The Moon</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>Delta Force 2</td>\n",
       "      <td>Delta Force 2: The Colombian Connection</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48</th>\n",
       "      <td>DuckTales the Movie:Treasure of the Lost Lamp</td>\n",
       "      <td>DuckTales: The Movie - Treasure of the Lost Lamp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5956</th>\n",
       "      <td>Chips</td>\n",
       "      <td>CHiPS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5971</th>\n",
       "      <td>Spark</td>\n",
       "      <td>Spark: A Space Tail</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5994</th>\n",
       "      <td>Pirates of the Caribbean:Dead Men Tell No Tales</td>\n",
       "      <td>Pirates of the Caribbean: Dead Men Tell No Tales</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6023</th>\n",
       "      <td>Valerian and the Cityof a Thousand Planets</td>\n",
       "      <td>Valerian and the City of a Thousand Planets</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6028</th>\n",
       "      <td>An Inconvenient Sequel:Truth to Power</td>\n",
       "      <td>An Inconvenient Sequel: Truth to Power</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>438 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                           title_wiki  \\\n",
       "27                                          China Cry   \n",
       "36               Daddy's Dyin' ...Who's Got the Will?   \n",
       "38                          The Dark Side of the Moon   \n",
       "42                                      Delta Force 2   \n",
       "48      DuckTales the Movie:Treasure of the Lost Lamp   \n",
       "...                                               ...   \n",
       "5956                                            Chips   \n",
       "5971                                            Spark   \n",
       "5994  Pirates of the Caribbean:Dead Men Tell No Tales   \n",
       "6023       Valerian and the Cityof a Thousand Planets   \n",
       "6028            An Inconvenient Sequel:Truth to Power   \n",
       "\n",
       "                                          title_kaggle  \n",
       "27                             China Cry: A True Story  \n",
       "36                Daddy's Dyin'... Who's Got the Will?  \n",
       "38                           The Dark Side of The Moon  \n",
       "42             Delta Force 2: The Colombian Connection  \n",
       "48    DuckTales: The Movie - Treasure of the Lost Lamp  \n",
       "...                                                ...  \n",
       "5956                                             CHiPS  \n",
       "5971                               Spark: A Space Tail  \n",
       "5994  Pirates of the Caribbean: Dead Men Tell No Tales  \n",
       "6023       Valerian and the City of a Thousand Planets  \n",
       "6028            An Inconvenient Sequel: Truth to Power  \n",
       "\n",
       "[438 rows x 2 columns]"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look at rows that don't have matchin titles\n",
    "movies_df[movies_df['title_wiki'] != movies_df['title_kaggle']][['title_wiki','title_kaggle']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title_wiki</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>Cinematography</th>\n",
       "      <th>Release date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Language</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date_kaggle</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title_kaggle</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>0 rows × 44 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [url, year, imdb_link, title_wiki, Based on, Starring, Cinematography, Release date, Country, Language, Director, Distributor, Editor(s), Composer(s), Producer(s), Production company(s), Writer(s), imdb_id, box_office, budget_wiki, release_date_wiki, running_time, belongs_to_collection, budget_kaggle, genres, homepage, id, original_language, original_title, overview, popularity, poster_path, production_companies, production_countries, release_date_kaggle, revenue, runtime, spoken_languages, status, tagline, title_kaggle, video, vote_average, vote_count]\n",
       "Index: []\n",
       "\n",
       "[0 rows x 44 columns]"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Make sure there isn't any missing titles in kaggle data\n",
    "movies_df[(movies_df['title_kaggle'] == '') | (movies_df['title_kaggle'].isnull())]\n",
    "#   We can drop wikipedia"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1b20dbb3a20>"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# RUNNING TIME\n",
    "# Look at running_time and runtime\n",
    "# Use a scatter plot to see how similar the columns are\n",
    "movies_df.fillna(0).plot(x='running_time', y='runtime', kind='scatter')\n",
    "# Keep kaggle data, but fill in zeros with wikipedia data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1b20dcfee10>"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# BUDGET\n",
    "# Use a scatter plot to compare budget_wiki and budget_kaggle\n",
    "movies_df.fillna(0).plot(x='budget_wiki',y='budget_kaggle', kind='scatter')\n",
    "# Keep kaggle data, but fill in zeros with wikipedia data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1b21042c898>"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# BOX OFFICE\n",
    "# Use a scatter plot to look at box_office and revenue\n",
    "movies_df.fillna(0).plot(x='box_office', y='revenue', kind='scatter')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1b210499978>"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Look at scatter plot for everything less than 1 billion\n",
    "movies_df.fillna(0)[movies_df['box_office'] < 10**9].plot(x='box_office', y='revenue', kind='scatter')\n",
    "# Keep kaggle data, but fill in zeros with wikipedia data\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1b211320630>"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# RELEASE DATE\n",
    "# Use a regular line pot and make 'style=\".\"' to plot \n",
    "movies_df[['release_date_wiki','release_date_kaggle']].plot(x='release_date_wiki', y='release_date_kaggle', style='.')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title_wiki</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>Cinematography</th>\n",
       "      <th>Release date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Language</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date_kaggle</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title_kaggle</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3607</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Holiday</td>\n",
       "      <td>2006</td>\n",
       "      <td>https://www.imdb.com/title/tt00457939/</td>\n",
       "      <td>The Holiday</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Kate Winslet, Cameron Diaz, Jude Law, Jack Bl...</td>\n",
       "      <td>Dean Cundey</td>\n",
       "      <td>[December 8, 2006, (, 2006-12-08, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>1953-08-28</td>\n",
       "      <td>30500000.0</td>\n",
       "      <td>118.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Pouring out of impassioned pages...brawling th...</td>\n",
       "      <td>From Here to Eternity</td>\n",
       "      <td>False</td>\n",
       "      <td>7.2</td>\n",
       "      <td>137.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 44 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            url  year  \\\n",
       "3607  https://en.wikipedia.org/wiki/The_Holiday  2006   \n",
       "\n",
       "                                   imdb_link   title_wiki Based on  \\\n",
       "3607  https://www.imdb.com/title/tt00457939/  The Holiday      NaN   \n",
       "\n",
       "                                               Starring Cinematography  \\\n",
       "3607  [Kate Winslet, Cameron Diaz, Jude Law, Jack Bl...    Dean Cundey   \n",
       "\n",
       "                              Release date        Country Language  ...  \\\n",
       "3607  [December 8, 2006, (, 2006-12-08, )]  United States  English  ...   \n",
       "\n",
       "     release_date_kaggle     revenue runtime  \\\n",
       "3607          1953-08-28  30500000.0   118.0   \n",
       "\n",
       "                              spoken_languages    status  \\\n",
       "3607  [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "\n",
       "                                                tagline  \\\n",
       "3607  Pouring out of impassioned pages...brawling th...   \n",
       "\n",
       "               title_kaggle  video  vote_average  vote_count  \n",
       "3607  From Here to Eternity  False           7.2       137.0  \n",
       "\n",
       "[1 rows x 44 columns]"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look for the outlier\n",
    "# Choose dates for wiki after 1996, but 1965 for kaggle\n",
    "movies_df[(movies_df['release_date_wiki'] > '1996-01-01') & (movies_df['release_date_kaggle'] < '1965-01-01')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Int64Index([3607], dtype='int64')"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Drop this row\n",
    "# Filter for the row\n",
    "movies_df[(movies_df['release_date_wiki'] > '1996-01-01') & (movies_df['release_date_kaggle'] < '1965-01-01')].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop the row\n",
    "movies_df = movies_df.drop(movies_df[(movies_df['release_date_wiki'] > '1996-01-01') & (movies_df['release_date_kaggle'] < '1965-01-01')].index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>title_wiki</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>Cinematography</th>\n",
       "      <th>Release date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Language</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date_kaggle</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title_kaggle</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1008</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Black_Scorpion_(...</td>\n",
       "      <td>1995</td>\n",
       "      <td>https://www.imdb.com/title/tt0112519/</td>\n",
       "      <td>Black Scorpion</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Joan Severance, Bruce Abbott, Garrett Morris]</td>\n",
       "      <td>Geoff George</td>\n",
       "      <td>NaN</td>\n",
       "      <td>United States</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-08-22</td>\n",
       "      <td>0.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Justice has a nasty sting.</td>\n",
       "      <td>Black Scorpion</td>\n",
       "      <td>False</td>\n",
       "      <td>6.1</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1061</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Flirt_(1995_film)</td>\n",
       "      <td>1995</td>\n",
       "      <td>https://www.imdb.com/title/tt0113080/</td>\n",
       "      <td>Flirt</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Bill Sage, Dwight Ewell, Miho Nikaido]</td>\n",
       "      <td>Michael Spiller</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[United States, Germany, Japan, [1]]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-09-14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}, {'iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Flirt</td>\n",
       "      <td>False</td>\n",
       "      <td>7.5</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1121</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Let_It_Be_Me_(19...</td>\n",
       "      <td>1995</td>\n",
       "      <td>https://www.imdb.com/title/tt0113638/</td>\n",
       "      <td>Let It Be Me</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Miroslav Ondrícek</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1995-11-17</td>\n",
       "      <td>0.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>[]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Let It Be Me</td>\n",
       "      <td>False</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1564</th>\n",
       "      <td>https://en.wikipedia.org/wiki/A_Brooklyn_State...</td>\n",
       "      <td>1997</td>\n",
       "      <td>https://www.imdb.com/title/tt0118782/</td>\n",
       "      <td>A Brooklyn State of Mind</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Ken Kelsch</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1998-01-01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>A Brooklyn State of Mind</td>\n",
       "      <td>False</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1633</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Highball_(film)</td>\n",
       "      <td>1997</td>\n",
       "      <td>https://www.imdb.com/title/tt0119291/</td>\n",
       "      <td>Highball</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Justine Bateman, Peter Bogdanovich, Chris Eig...</td>\n",
       "      <td>Steven Bernstein</td>\n",
       "      <td>NaN</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>1997-01-01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>110.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Highball</td>\n",
       "      <td>False</td>\n",
       "      <td>4.5</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1775</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Velocity_Trap</td>\n",
       "      <td>1997</td>\n",
       "      <td>https://www.imdb.com/title/tt0120435/</td>\n",
       "      <td>Velocity Trap</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Olivier Gruner, Alicia Coppola, Ken Olandt]</td>\n",
       "      <td>Philip D. Schwartz</td>\n",
       "      <td>NaN</td>\n",
       "      <td>United States</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1999-02-22</td>\n",
       "      <td>0.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Crime at the Speed of Light</td>\n",
       "      <td>Velocity Trap</td>\n",
       "      <td>False</td>\n",
       "      <td>4.7</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2386</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Visit_(2000_...</td>\n",
       "      <td>2000</td>\n",
       "      <td>https://www.imdb.com/title/tt0199129/</td>\n",
       "      <td>The Visit</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Hill Harper, Billy Dee Williams, Obba Babatun...</td>\n",
       "      <td>John L. Demps Jr.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>2000-01-01</td>\n",
       "      <td>0.0</td>\n",
       "      <td>107.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}, {'iso...</td>\n",
       "      <td>Rumored</td>\n",
       "      <td>NaN</td>\n",
       "      <td>The Visit</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2786</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Stevie_(2002_film)</td>\n",
       "      <td>2002</td>\n",
       "      <td>https://www.imdb.com/title/tt0334416/</td>\n",
       "      <td>Stevie</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Dana Kupper, Gordon Quinn, Peter Gilbert]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>2002-09-09</td>\n",
       "      <td>97000.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>[]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Stevie</td>\n",
       "      <td>False</td>\n",
       "      <td>6.7</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3174</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Return_to_Sender...</td>\n",
       "      <td>2004</td>\n",
       "      <td>https://www.imdb.com/title/tt0396190/</td>\n",
       "      <td>Return to Sender</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Aidan Quinn, Connie Nielsen, Mark Holton]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Denmark, USA, UK]</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>2004-09-17</td>\n",
       "      <td>0.0</td>\n",
       "      <td>109.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>How can you save someone, who won't save herself?</td>\n",
       "      <td>Return to Sender</td>\n",
       "      <td>False</td>\n",
       "      <td>5.9</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3651</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Live_Free_or_Die...</td>\n",
       "      <td>2006</td>\n",
       "      <td>https://www.imdb.com/title/tt0432318/</td>\n",
       "      <td>Live Free or Die</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Aaron Stanford, Paul Schneider, Ebon Moss-Bac...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>United States</td>\n",
       "      <td>English</td>\n",
       "      <td>...</td>\n",
       "      <td>2006-03-11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Live Free or Die</td>\n",
       "      <td>False</td>\n",
       "      <td>5.5</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4967</th>\n",
       "      <td>https://en.wikipedia.org/wiki/For_the_Love_of_...</td>\n",
       "      <td>2012</td>\n",
       "      <td>https://www.imdb.com/title/tt1730294/</td>\n",
       "      <td>For the Love of Money</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Yehuda Levi, Edward Furlong, James Caan, Jeff...</td>\n",
       "      <td>Andrzej Sekuła</td>\n",
       "      <td>NaN</td>\n",
       "      <td>United States</td>\n",
       "      <td>English/Hebrew</td>\n",
       "      <td>...</td>\n",
       "      <td>2012-06-08</td>\n",
       "      <td>0.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}, {'iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>For the love of money is the root of all evil.</td>\n",
       "      <td>For the Love of Money</td>\n",
       "      <td>False</td>\n",
       "      <td>5.6</td>\n",
       "      <td>9.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>11 rows × 44 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    url  year  \\\n",
       "1008  https://en.wikipedia.org/wiki/Black_Scorpion_(...  1995   \n",
       "1061    https://en.wikipedia.org/wiki/Flirt_(1995_film)  1995   \n",
       "1121  https://en.wikipedia.org/wiki/Let_It_Be_Me_(19...  1995   \n",
       "1564  https://en.wikipedia.org/wiki/A_Brooklyn_State...  1997   \n",
       "1633      https://en.wikipedia.org/wiki/Highball_(film)  1997   \n",
       "1775        https://en.wikipedia.org/wiki/Velocity_Trap  1997   \n",
       "2386  https://en.wikipedia.org/wiki/The_Visit_(2000_...  2000   \n",
       "2786   https://en.wikipedia.org/wiki/Stevie_(2002_film)  2002   \n",
       "3174  https://en.wikipedia.org/wiki/Return_to_Sender...  2004   \n",
       "3651  https://en.wikipedia.org/wiki/Live_Free_or_Die...  2006   \n",
       "4967  https://en.wikipedia.org/wiki/For_the_Love_of_...  2012   \n",
       "\n",
       "                                  imdb_link                title_wiki  \\\n",
       "1008  https://www.imdb.com/title/tt0112519/            Black Scorpion   \n",
       "1061  https://www.imdb.com/title/tt0113080/                     Flirt   \n",
       "1121  https://www.imdb.com/title/tt0113638/              Let It Be Me   \n",
       "1564  https://www.imdb.com/title/tt0118782/  A Brooklyn State of Mind   \n",
       "1633  https://www.imdb.com/title/tt0119291/                  Highball   \n",
       "1775  https://www.imdb.com/title/tt0120435/             Velocity Trap   \n",
       "2386  https://www.imdb.com/title/tt0199129/                 The Visit   \n",
       "2786  https://www.imdb.com/title/tt0334416/                    Stevie   \n",
       "3174  https://www.imdb.com/title/tt0396190/          Return to Sender   \n",
       "3651  https://www.imdb.com/title/tt0432318/          Live Free or Die   \n",
       "4967  https://www.imdb.com/title/tt1730294/     For the Love of Money   \n",
       "\n",
       "     Based on                                           Starring  \\\n",
       "1008      NaN     [Joan Severance, Bruce Abbott, Garrett Morris]   \n",
       "1061      NaN            [Bill Sage, Dwight Ewell, Miho Nikaido]   \n",
       "1121      NaN                                                NaN   \n",
       "1564      NaN                                                NaN   \n",
       "1633      NaN  [Justine Bateman, Peter Bogdanovich, Chris Eig...   \n",
       "1775      NaN       [Olivier Gruner, Alicia Coppola, Ken Olandt]   \n",
       "2386      NaN  [Hill Harper, Billy Dee Williams, Obba Babatun...   \n",
       "2786      NaN                                                NaN   \n",
       "3174      NaN         [Aidan Quinn, Connie Nielsen, Mark Holton]   \n",
       "3651      NaN  [Aaron Stanford, Paul Schneider, Ebon Moss-Bac...   \n",
       "4967      NaN  [Yehuda Levi, Edward Furlong, James Caan, Jeff...   \n",
       "\n",
       "                                  Cinematography Release date  \\\n",
       "1008                                Geoff George          NaN   \n",
       "1061                             Michael Spiller          NaN   \n",
       "1121                           Miroslav Ondrícek          NaN   \n",
       "1564                                  Ken Kelsch          NaN   \n",
       "1633                            Steven Bernstein          NaN   \n",
       "1775                          Philip D. Schwartz          NaN   \n",
       "2386                           John L. Demps Jr.          NaN   \n",
       "2786  [Dana Kupper, Gordon Quinn, Peter Gilbert]          NaN   \n",
       "3174                                         NaN          NaN   \n",
       "3651                                         NaN          NaN   \n",
       "4967                              Andrzej Sekuła          NaN   \n",
       "\n",
       "                                   Country        Language  ...  \\\n",
       "1008                         United States             NaN  ...   \n",
       "1061  [United States, Germany, Japan, [1]]             NaN  ...   \n",
       "1121                                   NaN             NaN  ...   \n",
       "1564                                   NaN             NaN  ...   \n",
       "1633                         United States         English  ...   \n",
       "1775                         United States             NaN  ...   \n",
       "2386                                   NaN         English  ...   \n",
       "2786                         United States         English  ...   \n",
       "3174                    [Denmark, USA, UK]             NaN  ...   \n",
       "3651                         United States         English  ...   \n",
       "4967                         United States  English/Hebrew  ...   \n",
       "\n",
       "     release_date_kaggle  revenue runtime  \\\n",
       "1008          1995-08-22      0.0    92.0   \n",
       "1061          1995-09-14      0.0    85.0   \n",
       "1121          1995-11-17      0.0    95.0   \n",
       "1564          1998-01-01      0.0    89.0   \n",
       "1633          1997-01-01      0.0   110.0   \n",
       "1775          1999-02-22      0.0    86.0   \n",
       "2386          2000-01-01      0.0   107.0   \n",
       "2786          2002-09-09  97000.0   140.0   \n",
       "3174          2004-09-17      0.0   109.0   \n",
       "3651          2006-03-11      0.0    89.0   \n",
       "4967          2012-06-08      0.0    93.0   \n",
       "\n",
       "                                       spoken_languages    status  \\\n",
       "1008           [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "1061  [{'iso_639_1': 'en', 'name': 'English'}, {'iso...  Released   \n",
       "1121                                                 []  Released   \n",
       "1564           [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "1633           [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "1775           [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "2386  [{'iso_639_1': 'en', 'name': 'English'}, {'iso...   Rumored   \n",
       "2786                                                 []       NaN   \n",
       "3174           [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "3651           [{'iso_639_1': 'en', 'name': 'English'}]  Released   \n",
       "4967  [{'iso_639_1': 'en', 'name': 'English'}, {'iso...  Released   \n",
       "\n",
       "                                                tagline  \\\n",
       "1008                         Justice has a nasty sting.   \n",
       "1061                                                NaN   \n",
       "1121                                                NaN   \n",
       "1564                                                NaN   \n",
       "1633                                                NaN   \n",
       "1775                        Crime at the Speed of Light   \n",
       "2386                                                NaN   \n",
       "2786                                                NaN   \n",
       "3174  How can you save someone, who won't save herself?   \n",
       "3651                                                NaN   \n",
       "4967     For the love of money is the root of all evil.   \n",
       "\n",
       "                  title_kaggle  video  vote_average  vote_count  \n",
       "1008            Black Scorpion  False           6.1         7.0  \n",
       "1061                     Flirt  False           7.5         4.0  \n",
       "1121              Let It Be Me  False           8.0         2.0  \n",
       "1564  A Brooklyn State of Mind  False           5.0         1.0  \n",
       "1633                  Highball  False           4.5         4.0  \n",
       "1775             Velocity Trap  False           4.7         6.0  \n",
       "2386                 The Visit  False           0.0         0.0  \n",
       "2786                    Stevie  False           6.7        13.0  \n",
       "3174          Return to Sender  False           5.9        13.0  \n",
       "3651          Live Free or Die  False           5.5         8.0  \n",
       "4967     For the Love of Money  False           5.6         9.0  \n",
       "\n",
       "[11 rows x 44 columns]"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look for any null values\n",
    "movies_df[movies_df['release_date_wiki'].isnull()]\n",
    "# Wiki is missing 11 release dates, so drop wiki"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [],
   "source": [
    "# LANGUAGE\n",
    "# Compare value counts of each\n",
    "#movies_df['Language'].value_counts()\n",
    "# Error beacuse some language data points are stored as lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "English                                 5479\n",
       "NaN                                      134\n",
       "(English, Spanish)                        68\n",
       "(English, French)                         35\n",
       "(English, Japanese)                       25\n",
       "                                        ... \n",
       "(English, German, Dutch)                   1\n",
       "(English, Italian, Portuguese)             1\n",
       "(English, Scottish Gaelic, Irish)          1\n",
       "(English, Afrikaans, German)               1\n",
       "(Albanian, English, French, Spanish)       1\n",
       "Name: Language, Length: 198, dtype: int64"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Convert the lists in Language to tuples so that value_counts() method works\n",
    "movies_df['Language'].apply(lambda x: tuple(x) if type(x) == list else x).value_counts(dropna=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "en    5987\n",
       "fr      16\n",
       "es      10\n",
       "it       8\n",
       "de       6\n",
       "zh       4\n",
       "ja       4\n",
       "pt       4\n",
       "hi       2\n",
       "da       2\n",
       "cn       1\n",
       "ab       1\n",
       "ru       1\n",
       "tr       1\n",
       "he       1\n",
       "sv       1\n",
       "ar       1\n",
       "ko       1\n",
       "Name: original_language, dtype: int64"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Kaggle data has no lists, so we can just run value_counts()\n",
    "movies_df['original_language'].value_counts(dropna=False)\n",
    "# Drop wikipedia "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "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>Production company(s)</th>\n",
       "      <th>production_companies</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Silver Pictures</td>\n",
       "      <td>[{'name': 'Twentieth Century Fox Film Corporat...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Avenue Pictures</td>\n",
       "      <td>[{'name': 'Avenue Pictures Productions', 'id':...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[Carolco Pictures, IndieProd Company]</td>\n",
       "      <td>[{'name': 'IndieProd Company Productions', 'id...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>[{'name': 'Orion Pictures', 'id': 41}]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>[{'name': 'Paramount Pictures', 'id': 4}]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6047</th>\n",
       "      <td>[Fabula, Komplizen Film]</td>\n",
       "      <td>[{'name': 'Komplizen Film', 'id': 1618}, {'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6048</th>\n",
       "      <td>Ball &amp; Chain Productions</td>\n",
       "      <td>[{'name': 'Ball &amp; Chain Productions', 'id': 74...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6049</th>\n",
       "      <td>[Arte France Cinéma, Why Not Productions]</td>\n",
       "      <td>[{'name': 'ARTE France Cinéma', 'id': 94}, {'n...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6050</th>\n",
       "      <td>[Film Science, Rough House Pictures, Syncopate...</td>\n",
       "      <td>[{'name': 'Film Science', 'id': 1976}, {'name'...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6051</th>\n",
       "      <td>[HanWay Films, Little Punk, See-Saw Films]</td>\n",
       "      <td>[{'name': 'HanWay Films', 'id': 2395}, {'name'...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6051 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  Production company(s)  \\\n",
       "0                                       Silver Pictures   \n",
       "1                                       Avenue Pictures   \n",
       "2                 [Carolco Pictures, IndieProd Company]   \n",
       "3                                                   NaN   \n",
       "4                                                   NaN   \n",
       "...                                                 ...   \n",
       "6047                           [Fabula, Komplizen Film]   \n",
       "6048                           Ball & Chain Productions   \n",
       "6049          [Arte France Cinéma, Why Not Productions]   \n",
       "6050  [Film Science, Rough House Pictures, Syncopate...   \n",
       "6051         [HanWay Films, Little Punk, See-Saw Films]   \n",
       "\n",
       "                                   production_companies  \n",
       "0     [{'name': 'Twentieth Century Fox Film Corporat...  \n",
       "1     [{'name': 'Avenue Pictures Productions', 'id':...  \n",
       "2     [{'name': 'IndieProd Company Productions', 'id...  \n",
       "3                [{'name': 'Orion Pictures', 'id': 41}]  \n",
       "4             [{'name': 'Paramount Pictures', 'id': 4}]  \n",
       "...                                                 ...  \n",
       "6047  [{'name': 'Komplizen Film', 'id': 1618}, {'nam...  \n",
       "6048  [{'name': 'Ball & Chain Productions', 'id': 74...  \n",
       "6049  [{'name': 'ARTE France Cinéma', 'id': 94}, {'n...  \n",
       "6050  [{'name': 'Film Science', 'id': 1976}, {'name'...  \n",
       "6051  [{'name': 'HanWay Films', 'id': 2395}, {'name'...  \n",
       "\n",
       "[6051 rows x 2 columns]"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# PRODUCTION COMPANIES\n",
    "# Look at a small number of samples\n",
    "movies_df[['Production company(s)','production_companies']]\n",
    "# Kaggle data is more consistent and would be VERY difficult to translate wikipedia data into same format\n",
    "# Drop wikipedia"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [],
   "source": [
    "# PUT IT ALL TOGETHER\n",
    "movies_df.drop(columns=['title_wiki','release_date_wiki','Language','Production company(s)'], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fill_missing_kaggle_data(df, kaggle_column, wiki_column):\n",
    "    df[kaggle_column] = df.apply(\n",
    "        lambda row: row[wiki_column] if row[kaggle_column] == 0 else row[kaggle_column]\n",
    "        , axis=1)\n",
    "    df.drop(columns=wiki_column, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "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>url</th>\n",
       "      <th>year</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>Based on</th>\n",
       "      <th>Starring</th>\n",
       "      <th>Cinematography</th>\n",
       "      <th>Release date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Director</th>\n",
       "      <th>Distributor</th>\n",
       "      <th>...</th>\n",
       "      <th>release_date_kaggle</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>spoken_languages</th>\n",
       "      <th>status</th>\n",
       "      <th>tagline</th>\n",
       "      <th>title_kaggle</th>\n",
       "      <th>video</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>vote_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>[Characters, by Rex Weiner]</td>\n",
       "      <td>[Andrew Dice Clay, Wayne Newton, Priscilla Pre...</td>\n",
       "      <td>Oliver Wood</td>\n",
       "      <td>[July 11, 1990, (, 1990-07-11, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>Renny Harlin</td>\n",
       "      <td>20th Century Fox</td>\n",
       "      <td>...</td>\n",
       "      <td>1990-07-11</td>\n",
       "      <td>20423389.0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Kojak. Columbo. Dirty Harry. Wimps.</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>False</td>\n",
       "      <td>6.2</td>\n",
       "      <td>72.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>[the novel, After Dark, My Sweet, by, Jim Thom...</td>\n",
       "      <td>[Jason Patric, Rachel Ward, Bruce Dern, George...</td>\n",
       "      <td>Mark Plummer</td>\n",
       "      <td>[May 17, 1990, (, 1990-05-17, ), (Cannes Film ...</td>\n",
       "      <td>United States</td>\n",
       "      <td>James Foley</td>\n",
       "      <td>Avenue Pictures</td>\n",
       "      <td>...</td>\n",
       "      <td>1990-08-24</td>\n",
       "      <td>2700000.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>All they risked was everything.</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>False</td>\n",
       "      <td>6.5</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>[Air America, by, Christopher Robbins]</td>\n",
       "      <td>[Mel Gibson, Robert Downey Jr., Nancy Travis, ...</td>\n",
       "      <td>Roger Deakins</td>\n",
       "      <td>[August 10, 1990, (, 1990-08-10, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>Roger Spottiswoode</td>\n",
       "      <td>TriStar Pictures</td>\n",
       "      <td>...</td>\n",
       "      <td>1990-08-10</td>\n",
       "      <td>33461269.0</td>\n",
       "      <td>112.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}, {'iso...</td>\n",
       "      <td>Released</td>\n",
       "      <td>The few. The proud. The totally insane.</td>\n",
       "      <td>Air America</td>\n",
       "      <td>False</td>\n",
       "      <td>5.3</td>\n",
       "      <td>146.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Alec Baldwin, Blythe Danner, Judy Davis, Mia ...</td>\n",
       "      <td>Carlo Di Palma</td>\n",
       "      <td>[December 25, 1990, (, 1990-12-25, )]</td>\n",
       "      <td>United States</td>\n",
       "      <td>Woody Allen</td>\n",
       "      <td>Orion Pictures</td>\n",
       "      <td>...</td>\n",
       "      <td>1990-12-25</td>\n",
       "      <td>7331647.0</td>\n",
       "      <td>102.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Alice</td>\n",
       "      <td>False</td>\n",
       "      <td>6.3</td>\n",
       "      <td>57.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>1990</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Paul Hogan, Elias Koteas, Linda Kozlowski]</td>\n",
       "      <td>Russell Boyd</td>\n",
       "      <td>December 19, 1990</td>\n",
       "      <td>US</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>Paramount Pictures</td>\n",
       "      <td>...</td>\n",
       "      <td>1990-12-21</td>\n",
       "      <td>6939946.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Who does he think he is?</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>False</td>\n",
       "      <td>5.6</td>\n",
       "      <td>23.0</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>6047</th>\n",
       "      <td>https://en.wikipedia.org/wiki/A_Fantastic_Woman</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt5639354/</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Daniela Vega, Francisco Reyes]</td>\n",
       "      <td>Benjamín Echazarreta</td>\n",
       "      <td>[12 February 2017, (, 2017-02-12, ), (, Berlin...</td>\n",
       "      <td>[Chile, Germany, Spain, United States, [2]]</td>\n",
       "      <td>Sebastián Lelio</td>\n",
       "      <td>[Participant Media (Chile), Piffl Medien (Germ...</td>\n",
       "      <td>...</td>\n",
       "      <td>2017-04-06</td>\n",
       "      <td>3700000.0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>[{'iso_639_1': 'es', 'name': 'Español'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>A Fantastic Woman</td>\n",
       "      <td>False</td>\n",
       "      <td>7.2</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6048</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Permission_(film)</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt5390066/</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Rebecca Hall, Dan Stevens, Morgan Spector, Fr...</td>\n",
       "      <td>Adam Bricker</td>\n",
       "      <td>[April 22, 2017, (, 2017-04-22, ), (, Tribeca ...</td>\n",
       "      <td>United States</td>\n",
       "      <td>Brian Crano</td>\n",
       "      <td>Good Deed Entertainment</td>\n",
       "      <td>...</td>\n",
       "      <td>2017-04-22</td>\n",
       "      <td>NaN</td>\n",
       "      <td>96.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Permission</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6049</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Loveless_(film)</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt6304162/</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Maryana Spivak, Aleksey Rozin, Matvey Novikov...</td>\n",
       "      <td>Mikhail Krichman</td>\n",
       "      <td>[18 May 2017, (, 2017-05-18, ), (, Cannes, ), ...</td>\n",
       "      <td>[Russia, France, Belgium, Germany, [3]]</td>\n",
       "      <td>Andrey Zvyagintsev</td>\n",
       "      <td>[Sony Pictures Releasing, (Russia), [1]]</td>\n",
       "      <td>...</td>\n",
       "      <td>2017-06-01</td>\n",
       "      <td>4800000.0</td>\n",
       "      <td>128.0</td>\n",
       "      <td>[{'iso_639_1': 'ru', 'name': 'Pусский'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Loveless</td>\n",
       "      <td>False</td>\n",
       "      <td>7.8</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6050</th>\n",
       "      <td>https://en.wikipedia.org/wiki/Gemini_(2017_film)</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt5795086/</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[Lola Kirke, Zoë Kravitz, Greta Lee, Michelle ...</td>\n",
       "      <td>Andrew Reed</td>\n",
       "      <td>[March 12, 2017, (, 2017-03-12, ), (, SXSW, ),...</td>\n",
       "      <td>United States</td>\n",
       "      <td>Aaron Katz</td>\n",
       "      <td>Neon</td>\n",
       "      <td>...</td>\n",
       "      <td>2017-03-12</td>\n",
       "      <td>200340.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Post Production</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Gemini</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6051</th>\n",
       "      <td>https://en.wikipedia.org/wiki/How_to_Talk_to_G...</td>\n",
       "      <td>2018</td>\n",
       "      <td>https://www.imdb.com/title/tt3859310/</td>\n",
       "      <td>[\", How to Talk to Girls at Parties, \", by, Ne...</td>\n",
       "      <td>[Elle Fanning, Alex Sharp, Nicole Kidman, Ruth...</td>\n",
       "      <td>Frank G. DeMarco</td>\n",
       "      <td>[May 21, 2017, (, 2017-05-21, ), (, Cannes, ),...</td>\n",
       "      <td>[United Kingdom, United States]</td>\n",
       "      <td>John Cameron Mitchell</td>\n",
       "      <td>[A24, StudioCanal UK]</td>\n",
       "      <td>...</td>\n",
       "      <td>2017-12-27</td>\n",
       "      <td>382053.0</td>\n",
       "      <td>102.0</td>\n",
       "      <td>[{'iso_639_1': 'en', 'name': 'English'}]</td>\n",
       "      <td>Released</td>\n",
       "      <td>Some girls are out of this world.</td>\n",
       "      <td>How to Talk to Girls at Parties</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6051 rows × 37 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    url  year  \\\n",
       "0     https://en.wikipedia.org/wiki/The_Adventures_o...  1990   \n",
       "1     https://en.wikipedia.org/wiki/After_Dark,_My_S...  1990   \n",
       "2      https://en.wikipedia.org/wiki/Air_America_(film)  1990   \n",
       "3       https://en.wikipedia.org/wiki/Alice_(1990_film)  1990   \n",
       "4         https://en.wikipedia.org/wiki/Almost_an_Angel  1990   \n",
       "...                                                 ...   ...   \n",
       "6047    https://en.wikipedia.org/wiki/A_Fantastic_Woman  2018   \n",
       "6048    https://en.wikipedia.org/wiki/Permission_(film)  2018   \n",
       "6049      https://en.wikipedia.org/wiki/Loveless_(film)  2018   \n",
       "6050   https://en.wikipedia.org/wiki/Gemini_(2017_film)  2018   \n",
       "6051  https://en.wikipedia.org/wiki/How_to_Talk_to_G...  2018   \n",
       "\n",
       "                                  imdb_link  \\\n",
       "0     https://www.imdb.com/title/tt0098987/   \n",
       "1     https://www.imdb.com/title/tt0098994/   \n",
       "2     https://www.imdb.com/title/tt0099005/   \n",
       "3     https://www.imdb.com/title/tt0099012/   \n",
       "4     https://www.imdb.com/title/tt0099018/   \n",
       "...                                     ...   \n",
       "6047  https://www.imdb.com/title/tt5639354/   \n",
       "6048  https://www.imdb.com/title/tt5390066/   \n",
       "6049  https://www.imdb.com/title/tt6304162/   \n",
       "6050  https://www.imdb.com/title/tt5795086/   \n",
       "6051  https://www.imdb.com/title/tt3859310/   \n",
       "\n",
       "                                               Based on  \\\n",
       "0                           [Characters, by Rex Weiner]   \n",
       "1     [the novel, After Dark, My Sweet, by, Jim Thom...   \n",
       "2                [Air America, by, Christopher Robbins]   \n",
       "3                                                   NaN   \n",
       "4                                                   NaN   \n",
       "...                                                 ...   \n",
       "6047                                                NaN   \n",
       "6048                                                NaN   \n",
       "6049                                                NaN   \n",
       "6050                                                NaN   \n",
       "6051  [\", How to Talk to Girls at Parties, \", by, Ne...   \n",
       "\n",
       "                                               Starring        Cinematography  \\\n",
       "0     [Andrew Dice Clay, Wayne Newton, Priscilla Pre...           Oliver Wood   \n",
       "1     [Jason Patric, Rachel Ward, Bruce Dern, George...          Mark Plummer   \n",
       "2     [Mel Gibson, Robert Downey Jr., Nancy Travis, ...         Roger Deakins   \n",
       "3     [Alec Baldwin, Blythe Danner, Judy Davis, Mia ...        Carlo Di Palma   \n",
       "4           [Paul Hogan, Elias Koteas, Linda Kozlowski]          Russell Boyd   \n",
       "...                                                 ...                   ...   \n",
       "6047                    [Daniela Vega, Francisco Reyes]  Benjamín Echazarreta   \n",
       "6048  [Rebecca Hall, Dan Stevens, Morgan Spector, Fr...          Adam Bricker   \n",
       "6049  [Maryana Spivak, Aleksey Rozin, Matvey Novikov...      Mikhail Krichman   \n",
       "6050  [Lola Kirke, Zoë Kravitz, Greta Lee, Michelle ...           Andrew Reed   \n",
       "6051  [Elle Fanning, Alex Sharp, Nicole Kidman, Ruth...      Frank G. DeMarco   \n",
       "\n",
       "                                           Release date  \\\n",
       "0                     [July 11, 1990, (, 1990-07-11, )]   \n",
       "1     [May 17, 1990, (, 1990-05-17, ), (Cannes Film ...   \n",
       "2                   [August 10, 1990, (, 1990-08-10, )]   \n",
       "3                 [December 25, 1990, (, 1990-12-25, )]   \n",
       "4                                     December 19, 1990   \n",
       "...                                                 ...   \n",
       "6047  [12 February 2017, (, 2017-02-12, ), (, Berlin...   \n",
       "6048  [April 22, 2017, (, 2017-04-22, ), (, Tribeca ...   \n",
       "6049  [18 May 2017, (, 2017-05-18, ), (, Cannes, ), ...   \n",
       "6050  [March 12, 2017, (, 2017-03-12, ), (, SXSW, ),...   \n",
       "6051  [May 21, 2017, (, 2017-05-21, ), (, Cannes, ),...   \n",
       "\n",
       "                                          Country               Director  \\\n",
       "0                                   United States           Renny Harlin   \n",
       "1                                   United States            James Foley   \n",
       "2                                   United States     Roger Spottiswoode   \n",
       "3                                   United States            Woody Allen   \n",
       "4                                              US           John Cornell   \n",
       "...                                           ...                    ...   \n",
       "6047  [Chile, Germany, Spain, United States, [2]]        Sebastián Lelio   \n",
       "6048                                United States            Brian Crano   \n",
       "6049      [Russia, France, Belgium, Germany, [3]]     Andrey Zvyagintsev   \n",
       "6050                                United States             Aaron Katz   \n",
       "6051              [United Kingdom, United States]  John Cameron Mitchell   \n",
       "\n",
       "                                            Distributor  ...  \\\n",
       "0                                      20th Century Fox  ...   \n",
       "1                                       Avenue Pictures  ...   \n",
       "2                                      TriStar Pictures  ...   \n",
       "3                                        Orion Pictures  ...   \n",
       "4                                    Paramount Pictures  ...   \n",
       "...                                                 ...  ...   \n",
       "6047  [Participant Media (Chile), Piffl Medien (Germ...  ...   \n",
       "6048                            Good Deed Entertainment  ...   \n",
       "6049           [Sony Pictures Releasing, (Russia), [1]]  ...   \n",
       "6050                                               Neon  ...   \n",
       "6051                              [A24, StudioCanal UK]  ...   \n",
       "\n",
       "     release_date_kaggle     revenue runtime  \\\n",
       "0             1990-07-11  20423389.0   104.0   \n",
       "1             1990-08-24   2700000.0   114.0   \n",
       "2             1990-08-10  33461269.0   112.0   \n",
       "3             1990-12-25   7331647.0   102.0   \n",
       "4             1990-12-21   6939946.0    95.0   \n",
       "...                  ...         ...     ...   \n",
       "6047          2017-04-06   3700000.0   104.0   \n",
       "6048          2017-04-22         NaN    96.0   \n",
       "6049          2017-06-01   4800000.0   128.0   \n",
       "6050          2017-03-12    200340.0    92.0   \n",
       "6051          2017-12-27    382053.0   102.0   \n",
       "\n",
       "                                       spoken_languages           status  \\\n",
       "0              [{'iso_639_1': 'en', 'name': 'English'}]         Released   \n",
       "1              [{'iso_639_1': 'en', 'name': 'English'}]         Released   \n",
       "2     [{'iso_639_1': 'en', 'name': 'English'}, {'iso...         Released   \n",
       "3              [{'iso_639_1': 'en', 'name': 'English'}]         Released   \n",
       "4              [{'iso_639_1': 'en', 'name': 'English'}]         Released   \n",
       "...                                                 ...              ...   \n",
       "6047           [{'iso_639_1': 'es', 'name': 'Español'}]         Released   \n",
       "6048           [{'iso_639_1': 'en', 'name': 'English'}]         Released   \n",
       "6049           [{'iso_639_1': 'ru', 'name': 'Pусский'}]         Released   \n",
       "6050           [{'iso_639_1': 'en', 'name': 'English'}]  Post Production   \n",
       "6051           [{'iso_639_1': 'en', 'name': 'English'}]         Released   \n",
       "\n",
       "                                      tagline  \\\n",
       "0         Kojak. Columbo. Dirty Harry. Wimps.   \n",
       "1             All they risked was everything.   \n",
       "2     The few. The proud. The totally insane.   \n",
       "3                                         NaN   \n",
       "4                    Who does he think he is?   \n",
       "...                                       ...   \n",
       "6047                                      NaN   \n",
       "6048                                      NaN   \n",
       "6049                                      NaN   \n",
       "6050                                      NaN   \n",
       "6051        Some girls are out of this world.   \n",
       "\n",
       "                         title_kaggle  video vote_average  vote_count  \n",
       "0     The Adventures of Ford Fairlane  False          6.2        72.0  \n",
       "1                After Dark, My Sweet  False          6.5        17.0  \n",
       "2                         Air America  False          5.3       146.0  \n",
       "3                               Alice  False          6.3        57.0  \n",
       "4                     Almost an Angel  False          5.6        23.0  \n",
       "...                               ...    ...          ...         ...  \n",
       "6047                A Fantastic Woman  False          7.2        13.0  \n",
       "6048                       Permission  False          0.0         1.0  \n",
       "6049                         Loveless  False          7.8        26.0  \n",
       "6050                           Gemini  False          0.0         0.0  \n",
       "6051  How to Talk to Girls at Parties  False          0.0        10.0  \n",
       "\n",
       "[6051 rows x 37 columns]"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fill_missing_kaggle_data(movies_df, 'runtime', 'running_time')\n",
    "fill_missing_kaggle_data(movies_df, 'budget_kaggle', 'budget_wiki')\n",
    "fill_missing_kaggle_data(movies_df, 'revenue', 'box_office')\n",
    "movies_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "video\n"
     ]
    }
   ],
   "source": [
    "for col in movies_df.columns:\n",
    "    lists_to_tuples = lambda x: tuple(x) if type(x) == list else x\n",
    "    value_counts = movies_df[col].apply(lists_to_tuples).value_counts(dropna=False)\n",
    "    num_values = len(value_counts)\n",
    "    if num_values == 1:\n",
    "        print(col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    6051\n",
       "Name: video, dtype: int64"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_df['video'].value_counts(dropna=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Reorder the rows\n",
    "movies_df = movies_df[['imdb_id','id','title_kaggle','original_title','tagline','belongs_to_collection','url','imdb_link',\n",
    "                       'runtime','budget_kaggle','revenue','release_date_kaggle','popularity','vote_average','vote_count',\n",
    "                       'genres','original_language','overview','spoken_languages','Country',\n",
    "                       'production_companies','production_countries','Distributor',\n",
    "                       'Producer(s)','Director','Starring','Cinematography','Editor(s)','Writer(s)','Composer(s)','Based on'\n",
    "                      ]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\krumb\\Anaconda3\\envs\\PythonData\\lib\\site-packages\\pandas\\core\\frame.py:4238: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  return super().rename(**kwargs)\n"
     ]
    }
   ],
   "source": [
    "# Rename columns\n",
    "movies_df.rename({'id':'kaggle_id',\n",
    "                  'title_kaggle':'title',\n",
    "                  'url':'wikipedia_url',\n",
    "                  'budget_kaggle':'budget',\n",
    "                  'release_date_kaggle':'release_date',\n",
    "                  'Country':'country',\n",
    "                  'Distributor':'distributor',\n",
    "                  'Producer(s)':'producers',\n",
    "                  'Director':'director',\n",
    "                  'Starring':'starring',\n",
    "                  'Cinematography':'cinematography',\n",
    "                  'Editor(s)':'editors',\n",
    "                  'Writer(s)':'writers',\n",
    "                  'Composer(s)':'composers',\n",
    "                  'Based on':'based_on'\n",
    "                 }, axis='columns', inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "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>imdb_id</th>\n",
       "      <th>kaggle_id</th>\n",
       "      <th>title</th>\n",
       "      <th>original_title</th>\n",
       "      <th>tagline</th>\n",
       "      <th>belongs_to_collection</th>\n",
       "      <th>wikipedia_url</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>runtime</th>\n",
       "      <th>budget</th>\n",
       "      <th>...</th>\n",
       "      <th>production_countries</th>\n",
       "      <th>distributor</th>\n",
       "      <th>producers</th>\n",
       "      <th>director</th>\n",
       "      <th>starring</th>\n",
       "      <th>cinematography</th>\n",
       "      <th>editors</th>\n",
       "      <th>writers</th>\n",
       "      <th>composers</th>\n",
       "      <th>based_on</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>tt0098987</td>\n",
       "      <td>9548</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>Kojak. Columbo. Dirty Harry. Wimps.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>104.0</td>\n",
       "      <td>49000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>[{'iso_3166_1': 'US', 'name': 'United States o...</td>\n",
       "      <td>20th Century Fox</td>\n",
       "      <td>[Steve Perry, Joel Silver]</td>\n",
       "      <td>Renny Harlin</td>\n",
       "      <td>[Andrew Dice Clay, Wayne Newton, Priscilla Pre...</td>\n",
       "      <td>Oliver Wood</td>\n",
       "      <td>Michael Tronick</td>\n",
       "      <td>[David Arnott, James Cappe]</td>\n",
       "      <td>[Cliff Eidelman, Yello]</td>\n",
       "      <td>[Characters, by Rex Weiner]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>tt0098994</td>\n",
       "      <td>25501</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>All they risked was everything.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>114.0</td>\n",
       "      <td>6000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>[{'iso_3166_1': 'US', 'name': 'United States o...</td>\n",
       "      <td>Avenue Pictures</td>\n",
       "      <td>[Ric Kidney, Robert Redlin]</td>\n",
       "      <td>James Foley</td>\n",
       "      <td>[Jason Patric, Rachel Ward, Bruce Dern, George...</td>\n",
       "      <td>Mark Plummer</td>\n",
       "      <td>Howard E. Smith</td>\n",
       "      <td>[James Foley, Robert Redlin]</td>\n",
       "      <td>Maurice Jarre</td>\n",
       "      <td>[the novel, After Dark, My Sweet, by, Jim Thom...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>tt0099005</td>\n",
       "      <td>11856</td>\n",
       "      <td>Air America</td>\n",
       "      <td>Air America</td>\n",
       "      <td>The few. The proud. The totally insane.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>112.0</td>\n",
       "      <td>35000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>[{'iso_3166_1': 'US', 'name': 'United States o...</td>\n",
       "      <td>TriStar Pictures</td>\n",
       "      <td>Daniel Melnick</td>\n",
       "      <td>Roger Spottiswoode</td>\n",
       "      <td>[Mel Gibson, Robert Downey Jr., Nancy Travis, ...</td>\n",
       "      <td>Roger Deakins</td>\n",
       "      <td>[John Bloom, Lois Freeman-Fox]</td>\n",
       "      <td>[John Eskow, Richard Rush]</td>\n",
       "      <td>Charles Gross</td>\n",
       "      <td>[Air America, by, Christopher Robbins]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>tt0099012</td>\n",
       "      <td>8217</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Alice</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>102.0</td>\n",
       "      <td>12000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>[{'iso_3166_1': 'US', 'name': 'United States o...</td>\n",
       "      <td>Orion Pictures</td>\n",
       "      <td>Robert Greenhut</td>\n",
       "      <td>Woody Allen</td>\n",
       "      <td>[Alec Baldwin, Blythe Danner, Judy Davis, Mia ...</td>\n",
       "      <td>Carlo Di Palma</td>\n",
       "      <td>Susan E. Morse</td>\n",
       "      <td>Woody Allen</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>tt0099018</td>\n",
       "      <td>25943</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>Who does he think he is?</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>95.0</td>\n",
       "      <td>25000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>[{'iso_3166_1': 'US', 'name': 'United States o...</td>\n",
       "      <td>Paramount Pictures</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>John Cornell</td>\n",
       "      <td>[Paul Hogan, Elias Koteas, Linda Kozlowski]</td>\n",
       "      <td>Russell Boyd</td>\n",
       "      <td>David Stiven</td>\n",
       "      <td>Paul Hogan</td>\n",
       "      <td>Maurice Jarre</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 31 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     imdb_id  kaggle_id                            title  \\\n",
       "0  tt0098987       9548  The Adventures of Ford Fairlane   \n",
       "1  tt0098994      25501             After Dark, My Sweet   \n",
       "2  tt0099005      11856                      Air America   \n",
       "3  tt0099012       8217                            Alice   \n",
       "4  tt0099018      25943                  Almost an Angel   \n",
       "\n",
       "                    original_title                                  tagline  \\\n",
       "0  The Adventures of Ford Fairlane      Kojak. Columbo. Dirty Harry. Wimps.   \n",
       "1             After Dark, My Sweet          All they risked was everything.   \n",
       "2                      Air America  The few. The proud. The totally insane.   \n",
       "3                            Alice                                      NaN   \n",
       "4                  Almost an Angel                 Who does he think he is?   \n",
       "\n",
       "  belongs_to_collection                                      wikipedia_url  \\\n",
       "0                   NaN  https://en.wikipedia.org/wiki/The_Adventures_o...   \n",
       "1                   NaN  https://en.wikipedia.org/wiki/After_Dark,_My_S...   \n",
       "2                   NaN   https://en.wikipedia.org/wiki/Air_America_(film)   \n",
       "3                   NaN    https://en.wikipedia.org/wiki/Alice_(1990_film)   \n",
       "4                   NaN      https://en.wikipedia.org/wiki/Almost_an_Angel   \n",
       "\n",
       "                               imdb_link  runtime      budget  ...  \\\n",
       "0  https://www.imdb.com/title/tt0098987/    104.0  49000000.0  ...   \n",
       "1  https://www.imdb.com/title/tt0098994/    114.0   6000000.0  ...   \n",
       "2  https://www.imdb.com/title/tt0099005/    112.0  35000000.0  ...   \n",
       "3  https://www.imdb.com/title/tt0099012/    102.0  12000000.0  ...   \n",
       "4  https://www.imdb.com/title/tt0099018/     95.0  25000000.0  ...   \n",
       "\n",
       "                                production_countries         distributor  \\\n",
       "0  [{'iso_3166_1': 'US', 'name': 'United States o...    20th Century Fox   \n",
       "1  [{'iso_3166_1': 'US', 'name': 'United States o...     Avenue Pictures   \n",
       "2  [{'iso_3166_1': 'US', 'name': 'United States o...    TriStar Pictures   \n",
       "3  [{'iso_3166_1': 'US', 'name': 'United States o...      Orion Pictures   \n",
       "4  [{'iso_3166_1': 'US', 'name': 'United States o...  Paramount Pictures   \n",
       "\n",
       "                     producers            director  \\\n",
       "0   [Steve Perry, Joel Silver]        Renny Harlin   \n",
       "1  [Ric Kidney, Robert Redlin]         James Foley   \n",
       "2               Daniel Melnick  Roger Spottiswoode   \n",
       "3              Robert Greenhut         Woody Allen   \n",
       "4                 John Cornell        John Cornell   \n",
       "\n",
       "                                            starring  cinematography  \\\n",
       "0  [Andrew Dice Clay, Wayne Newton, Priscilla Pre...     Oliver Wood   \n",
       "1  [Jason Patric, Rachel Ward, Bruce Dern, George...    Mark Plummer   \n",
       "2  [Mel Gibson, Robert Downey Jr., Nancy Travis, ...   Roger Deakins   \n",
       "3  [Alec Baldwin, Blythe Danner, Judy Davis, Mia ...  Carlo Di Palma   \n",
       "4        [Paul Hogan, Elias Koteas, Linda Kozlowski]    Russell Boyd   \n",
       "\n",
       "                          editors                       writers  \\\n",
       "0                 Michael Tronick   [David Arnott, James Cappe]   \n",
       "1                 Howard E. Smith  [James Foley, Robert Redlin]   \n",
       "2  [John Bloom, Lois Freeman-Fox]    [John Eskow, Richard Rush]   \n",
       "3                  Susan E. Morse                   Woody Allen   \n",
       "4                    David Stiven                    Paul Hogan   \n",
       "\n",
       "                 composers                                           based_on  \n",
       "0  [Cliff Eidelman, Yello]                        [Characters, by Rex Weiner]  \n",
       "1            Maurice Jarre  [the novel, After Dark, My Sweet, by, Jim Thom...  \n",
       "2            Charles Gross             [Air America, by, Christopher Robbins]  \n",
       "3                      NaN                                                NaN  \n",
       "4            Maurice Jarre                                                NaN  \n",
       "\n",
       "[5 rows x 31 columns]"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "rating_counts = ratings.groupby(['movieId','rating'], as_index=False).count() \\\n",
    "                .rename({'userId':'count'}, axis=1) \\\n",
    "                .pivot(index='movieId',columns='rating', values='count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [],
   "source": [
    "rating_counts.columns = ['rating_' + str(col) for col in rating_counts.columns]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use a left merge\n",
    "movies_with_ratings_df = pd.merge(movies_df, rating_counts, left_on='kaggle_id', right_index=True, how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [],
   "source": [
    "movies_with_ratings_df[rating_counts.columns] = movies_with_ratings_df[rating_counts.columns].fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "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>imdb_id</th>\n",
       "      <th>kaggle_id</th>\n",
       "      <th>title</th>\n",
       "      <th>original_title</th>\n",
       "      <th>tagline</th>\n",
       "      <th>belongs_to_collection</th>\n",
       "      <th>wikipedia_url</th>\n",
       "      <th>imdb_link</th>\n",
       "      <th>runtime</th>\n",
       "      <th>budget</th>\n",
       "      <th>...</th>\n",
       "      <th>rating_0.5</th>\n",
       "      <th>rating_1.0</th>\n",
       "      <th>rating_1.5</th>\n",
       "      <th>rating_2.0</th>\n",
       "      <th>rating_2.5</th>\n",
       "      <th>rating_3.0</th>\n",
       "      <th>rating_3.5</th>\n",
       "      <th>rating_4.0</th>\n",
       "      <th>rating_4.5</th>\n",
       "      <th>rating_5.0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>tt0098987</td>\n",
       "      <td>9548</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>The Adventures of Ford Fairlane</td>\n",
       "      <td>Kojak. Columbo. Dirty Harry. Wimps.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/The_Adventures_o...</td>\n",
       "      <td>https://www.imdb.com/title/tt0098987/</td>\n",
       "      <td>104.0</td>\n",
       "      <td>49000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>tt0098994</td>\n",
       "      <td>25501</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>After Dark, My Sweet</td>\n",
       "      <td>All they risked was everything.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/After_Dark,_My_S...</td>\n",
       "      <td>https://www.imdb.com/title/tt0098994/</td>\n",
       "      <td>114.0</td>\n",
       "      <td>6000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>tt0099005</td>\n",
       "      <td>11856</td>\n",
       "      <td>Air America</td>\n",
       "      <td>Air America</td>\n",
       "      <td>The few. The proud. The totally insane.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Air_America_(film)</td>\n",
       "      <td>https://www.imdb.com/title/tt0099005/</td>\n",
       "      <td>112.0</td>\n",
       "      <td>35000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>tt0099012</td>\n",
       "      <td>8217</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Alice</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Alice_(1990_film)</td>\n",
       "      <td>https://www.imdb.com/title/tt0099012/</td>\n",
       "      <td>102.0</td>\n",
       "      <td>12000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>tt0099018</td>\n",
       "      <td>25943</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>Almost an Angel</td>\n",
       "      <td>Who does he think he is?</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://en.wikipedia.org/wiki/Almost_an_Angel</td>\n",
       "      <td>https://www.imdb.com/title/tt0099018/</td>\n",
       "      <td>95.0</td>\n",
       "      <td>25000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>46.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>11.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 41 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     imdb_id  kaggle_id                            title  \\\n",
       "0  tt0098987       9548  The Adventures of Ford Fairlane   \n",
       "1  tt0098994      25501             After Dark, My Sweet   \n",
       "2  tt0099005      11856                      Air America   \n",
       "3  tt0099012       8217                            Alice   \n",
       "4  tt0099018      25943                  Almost an Angel   \n",
       "\n",
       "                    original_title                                  tagline  \\\n",
       "0  The Adventures of Ford Fairlane      Kojak. Columbo. Dirty Harry. Wimps.   \n",
       "1             After Dark, My Sweet          All they risked was everything.   \n",
       "2                      Air America  The few. The proud. The totally insane.   \n",
       "3                            Alice                                      NaN   \n",
       "4                  Almost an Angel                 Who does he think he is?   \n",
       "\n",
       "  belongs_to_collection                                      wikipedia_url  \\\n",
       "0                   NaN  https://en.wikipedia.org/wiki/The_Adventures_o...   \n",
       "1                   NaN  https://en.wikipedia.org/wiki/After_Dark,_My_S...   \n",
       "2                   NaN   https://en.wikipedia.org/wiki/Air_America_(film)   \n",
       "3                   NaN    https://en.wikipedia.org/wiki/Alice_(1990_film)   \n",
       "4                   NaN      https://en.wikipedia.org/wiki/Almost_an_Angel   \n",
       "\n",
       "                               imdb_link  runtime      budget  ...  \\\n",
       "0  https://www.imdb.com/title/tt0098987/    104.0  49000000.0  ...   \n",
       "1  https://www.imdb.com/title/tt0098994/    114.0   6000000.0  ...   \n",
       "2  https://www.imdb.com/title/tt0099005/    112.0  35000000.0  ...   \n",
       "3  https://www.imdb.com/title/tt0099012/    102.0  12000000.0  ...   \n",
       "4  https://www.imdb.com/title/tt0099018/     95.0  25000000.0  ...   \n",
       "\n",
       "   rating_0.5 rating_1.0  rating_1.5  rating_2.0  rating_2.5 rating_3.0  \\\n",
       "0         0.0        0.0         0.0         0.0         0.0        0.0   \n",
       "1         0.0        0.0         0.0         0.0         0.0        0.0   \n",
       "2         0.0        0.0         0.0         0.0         0.0        0.0   \n",
       "3         0.0        0.0         0.0         0.0         0.0        0.0   \n",
       "4         3.0        0.0         3.0         2.0         5.0       26.0   \n",
       "\n",
       "  rating_3.5 rating_4.0 rating_4.5 rating_5.0  \n",
       "0        0.0        0.0        0.0        0.0  \n",
       "1        0.0        0.0        0.0        0.0  \n",
       "2        0.0        0.0        0.0        0.0  \n",
       "3        0.0        0.0        0.0        0.0  \n",
       "4       37.0       46.0       16.0       11.0  \n",
       "\n",
       "[5 rows x 41 columns]"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movies_with_ratings_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [],
   "source": [
    "# IMPORT TO SQL\n",
    "from config import db_password"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'postgres://postgres:M0neym0ve$@127.0.0.1:5432/movie_data'"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "db_string = f\"postgres://postgres:{db_password}@127.0.0.1:5432/movie_data\"\n",
    "db_string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Engine(postgres://postgres:***@127.0.0.1:5432/movie_data)"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create a database engine \n",
    "engine = create_engine(db_string)\n",
    "engine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [],
   "source": [
    "# IMPORT MOVIE DATA\n",
    "movies_df.to_sql(name='Movies', con=engine)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "importing rows 0 to 100000...Done. 11.809548377990723 total seconds elapsed\n",
      "importing rows 100000 to 200000...Done. 23.43744468688965 total seconds elapsed\n",
      "importing rows 200000 to 300000...Done. 35.33266091346741 total seconds elapsed\n",
      "importing rows 300000 to 400000...Done. 46.854854345321655 total seconds elapsed\n",
      "importing rows 400000 to 500000...Done. 58.397000312805176 total seconds elapsed\n",
      "importing rows 500000 to 600000...Done. 70.38891792297363 total seconds elapsed\n",
      "importing rows 600000 to 700000...Done. 81.93106174468994 total seconds elapsed\n",
      "importing rows 700000 to 800000...Done. 93.45525789260864 total seconds elapsed\n",
      "importing rows 800000 to 900000...Done. 105.36641359329224 total seconds elapsed\n",
      "importing rows 900000 to 1000000...Done. 116.87362027168274 total seconds elapsed\n",
      "importing rows 1000000 to 1100000...Done. 128.9533567428589 total seconds elapsed\n",
      "importing rows 1100000 to 1200000...Done. 141.1497678756714 total seconds elapsed\n",
      "importing rows 1200000 to 1300000...Done. 152.77357745170593 total seconds elapsed\n",
      "importing rows 1300000 to 1400000...Done. 164.26102876663208 total seconds elapsed\n",
      "importing rows 1400000 to 1500000...Done. 176.1272873878479 total seconds elapsed\n",
      "importing rows 1500000 to 1600000...Done. 187.61758637428284 total seconds elapsed\n",
      "importing rows 1600000 to 1700000...Done. 199.53869462013245 total seconds elapsed\n",
      "importing rows 1700000 to 1800000...Done. 211.13595294952393 total seconds elapsed\n",
      "importing rows 1800000 to 1900000...Done. 222.85968542099 total seconds elapsed\n",
      "importing rows 1900000 to 2000000...Done. 234.84171628952026 total seconds elapsed\n",
      "importing rows 2000000 to 2100000...Done. 246.26626229286194 total seconds elapsed\n",
      "importing rows 2100000 to 2200000...Done. 257.6170103549957 total seconds elapsed\n",
      "importing rows 2200000 to 2300000...Done. 269.4594020843506 total seconds elapsed\n",
      "importing rows 2300000 to 2400000...Done. 280.8529632091522 total seconds elapsed\n",
      "importing rows 2400000 to 2500000...Done. 292.1457314491272 total seconds elapsed\n",
      "importing rows 2500000 to 2600000...Done. 303.46945977211 total seconds elapsed\n",
      "importing rows 2600000 to 2700000...Done. 315.2509825229645 total seconds elapsed\n",
      "importing rows 2700000 to 2800000...Done. 326.8280336856842 total seconds elapsed\n",
      "importing rows 2800000 to 2900000...Done. 338.5666334629059 total seconds elapsed\n",
      "importing rows 2900000 to 3000000...Done. 350.13569498062134 total seconds elapsed\n",
      "importing rows 3000000 to 3100000...Done. 361.60413217544556 total seconds elapsed\n",
      "importing rows 3100000 to 3200000...Done. 373.8535120487213 total seconds elapsed\n",
      "importing rows 3200000 to 3300000...Done. 385.38284730911255 total seconds elapsed\n",
      "importing rows 3300000 to 3400000...Done. 396.9010548591614 total seconds elapsed\n",
      "importing rows 3400000 to 3500000...Done. 408.6555781364441 total seconds elapsed\n",
      "importing rows 3500000 to 3600000...Done. 419.9853582382202 total seconds elapsed\n",
      "importing rows 3600000 to 3700000...Done. 431.4788661003113 total seconds elapsed\n",
      "importing rows 3700000 to 3800000...Done. 443.3372483253479 total seconds elapsed\n",
      "importing rows 3800000 to 3900000...Done. 454.7605211734772 total seconds elapsed\n",
      "importing rows 3900000 to 4000000...Done. 466.1284954547882 total seconds elapsed\n",
      "importing rows 4000000 to 4100000...Done. 477.8884358406067 total seconds elapsed\n",
      "importing rows 4100000 to 4200000...Done. 489.2785186767578 total seconds elapsed\n",
      "importing rows 4200000 to 4300000...Done. 500.81080865859985 total seconds elapsed\n",
      "importing rows 4300000 to 4400000...Done. 512.8559513092041 total seconds elapsed\n",
      "importing rows 4400000 to 4500000...Done. 524.2457377910614 total seconds elapsed\n",
      "importing rows 4500000 to 4600000...Done. 535.9069216251373 total seconds elapsed\n",
      "importing rows 4600000 to 4700000...Done. 548.246013879776 total seconds elapsed\n",
      "importing rows 4700000 to 4800000...Done. 570.7981519699097 total seconds elapsed\n",
      "importing rows 4800000 to 4900000...Done. 585.4240243434906 total seconds elapsed\n",
      "importing rows 4900000 to 5000000...Done. 598.7045149803162 total seconds elapsed\n",
      "importing rows 5000000 to 5100000...Done. 610.201801776886 total seconds elapsed\n",
      "importing rows 5100000 to 5200000...Done. 621.9801015853882 total seconds elapsed\n",
      "importing rows 5200000 to 5300000...Done. 633.9734606742859 total seconds elapsed\n",
      "importing rows 5300000 to 5400000...Done. 645.3512363433838 total seconds elapsed\n",
      "importing rows 5400000 to 5500000...Done. 656.8325517177582 total seconds elapsed\n",
      "importing rows 5500000 to 5600000...Done. 668.7059726715088 total seconds elapsed\n",
      "importing rows 5600000 to 5700000...Done. 681.0935871601105 total seconds elapsed\n",
      "importing rows 5700000 to 5800000...Done. 692.4482259750366 total seconds elapsed\n",
      "importing rows 5800000 to 5900000...Done. 704.1920027732849 total seconds elapsed\n",
      "importing rows 5900000 to 6000000...Done. 715.5934739112854 total seconds elapsed\n",
      "importing rows 6000000 to 6100000...Done. 726.918249130249 total seconds elapsed\n",
      "importing rows 6100000 to 6200000...Done. 738.6878261566162 total seconds elapsed\n",
      "importing rows 6200000 to 6300000...Done. 750.1266446113586 total seconds elapsed\n",
      "importing rows 6300000 to 6400000...Done. 761.6950244903564 total seconds elapsed\n",
      "importing rows 6400000 to 6500000...Done. 773.3890194892883 total seconds elapsed\n",
      "importing rows 6500000 to 6600000...Done. 1752.332764863968 total seconds elapsed\n",
      "importing rows 6700000 to 6800000...Done. 1765.2783575057983 total seconds elapsed\n",
      "importing rows 6800000 to 6900000...Done. 1777.2645423412323 total seconds elapsed\n",
      "importing rows 6900000 to 7000000...Done. 1789.108876466751 total seconds elapsed\n",
      "importing rows 7000000 to 7100000...Done. 1801.6513240337372 total seconds elapsed\n",
      "importing rows 7100000 to 7200000...Done. 1813.0179588794708 total seconds elapsed\n",
      "importing rows 7200000 to 7300000...Done. 1824.345829486847 total seconds elapsed\n",
      "importing rows 7300000 to 7400000...Done. 1836.108330488205 total seconds elapsed\n",
      "importing rows 7400000 to 7500000...Done. 1847.521850824356 total seconds elapsed\n",
      "importing rows 7500000 to 7600000...Done. 1858.884440422058 total seconds elapsed\n",
      "importing rows 7600000 to 7700000...Done. 1870.6280455589294 total seconds elapsed\n",
      "importing rows 7700000 to 7800000...Done. 1882.064579963684 total seconds elapsed\n",
      "importing rows 7800000 to 7900000...Done. 1893.668557882309 total seconds elapsed\n",
      "importing rows 7900000 to 8000000...Done. 1905.4969146251678 total seconds elapsed\n",
      "importing rows 8000000 to 8100000...Done. 1917.0023045539856 total seconds elapsed\n",
      "importing rows 8100000 to 8200000...Done. 1928.4179151058197 total seconds elapsed\n",
      "importing rows 8200000 to 8300000...Done. 1940.1495513916016 total seconds elapsed\n",
      "importing rows 8300000 to 8400000...Done. 1951.521183013916 total seconds elapsed\n",
      "importing rows 8400000 to 8500000...Done. 1962.876840353012 total seconds elapsed\n",
      "importing rows 8500000 to 8600000...Done. 1975.133155822754 total seconds elapsed\n",
      "importing rows 8600000 to 8700000...Done. 1986.6464312076569 total seconds elapsed\n",
      "importing rows 8700000 to 8800000...Done. 1998.0240206718445 total seconds elapsed\n",
      "importing rows 8800000 to 8900000...Done. 2009.8374285697937 total seconds elapsed\n",
      "importing rows 8900000 to 9000000...Done. 2021.280840396881 total seconds elapsed\n",
      "importing rows 9000000 to 9100000...Done. 2032.78506565094 total seconds elapsed\n",
      "importing rows 9100000 to 9200000...Done. 2044.9587137699127 total seconds elapsed\n",
      "importing rows 9200000 to 9300000...Done. 2056.3692026138306 total seconds elapsed\n",
      "importing rows 9300000 to 9400000...Done. 2068.2275795936584 total seconds elapsed\n",
      "importing rows 9400000 to 9500000...Done. 2080.397121667862 total seconds elapsed\n",
      "importing rows 9500000 to 9600000...Done. 2092.0958201885223 total seconds elapsed\n",
      "importing rows 9600000 to 9700000...Done. 2103.605081796646 total seconds elapsed\n",
      "importing rows 9700000 to 9800000...Done. 2115.3935463428497 total seconds elapsed\n",
      "importing rows 9800000 to 9900000...Done. 2126.769096136093 total seconds elapsed\n",
      "importing rows 9900000 to 10000000...Done. 2138.2753732204437 total seconds elapsed\n",
      "importing rows 10000000 to 10100000...Done. 2150.044898748398 total seconds elapsed\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "importing rows 10100000 to 10200000...Done. 2161.370649576187 total seconds elapsed\n",
      "importing rows 10200000 to 10300000...Done. 2172.7533555030823 total seconds elapsed\n",
      "importing rows 10300000 to 10400000...Done. 2184.5268507003784 total seconds elapsed\n",
      "importing rows 10400000 to 10500000...Done. 2196.2644879817963 total seconds elapsed\n",
      "importing rows 10500000 to 10600000...Done. 2207.5504353046417 total seconds elapsed\n",
      "importing rows 10600000 to 10700000...Done. 2219.626247882843 total seconds elapsed\n",
      "importing rows 10700000 to 10800000...Done. 2231.221354484558 total seconds elapsed\n",
      "importing rows 10800000 to 10900000...Done. 2242.705658197403 total seconds elapsed\n",
      "importing rows 10900000 to 11000000...Done. 2254.4442734718323 total seconds elapsed\n",
      "importing rows 11000000 to 11100000...Done. 2265.813879966736 total seconds elapsed\n",
      "importing rows 11100000 to 11200000...Done. 2277.202470302582 total seconds elapsed\n",
      "importing rows 11200000 to 11300000...Done. 2288.8971672058105 total seconds elapsed\n",
      "importing rows 11300000 to 11400000...Done. 2300.357499599457 total seconds elapsed\n",
      "importing rows 11400000 to 11500000...Done. 2312.0131204128265 total seconds elapsed\n",
      "importing rows 11500000 to 11600000...Done. 2324.0289964675903 total seconds elapsed\n",
      "importing rows 11600000 to 11700000...Done. 2335.792384624481 total seconds elapsed\n",
      "importing rows 11700000 to 11800000...Done. 2347.7853479385376 total seconds elapsed\n",
      "importing rows 11800000 to 11900000...Done. 2359.6297924518585 total seconds elapsed\n",
      "importing rows 11900000 to 12000000...Done. 2371.0763585567474 total seconds elapsed\n",
      "importing rows 12000000 to 12100000...Done. 2382.3344292640686 total seconds elapsed\n",
      "importing rows 12100000 to 12200000...Done. 2394.109946489334 total seconds elapsed\n",
      "importing rows 12200000 to 12300000...Done. 2405.52543091774 total seconds elapsed\n",
      "importing rows 12300000 to 12400000...Done. 2416.844731092453 total seconds elapsed\n",
      "importing rows 12400000 to 12500000...Done. 2428.6891009807587 total seconds elapsed\n",
      "importing rows 12500000 to 12600000...Done. 2440.478579044342 total seconds elapsed\n",
      "importing rows 12600000 to 12700000...Done. 2451.882253885269 total seconds elapsed\n",
      "importing rows 12700000 to 12800000...Done. 2463.594059944153 total seconds elapsed\n",
      "importing rows 12800000 to 12900000...Done. 2476.22203207016 total seconds elapsed\n",
      "importing rows 12900000 to 13000000...Done. 2488.312501192093 total seconds elapsed\n",
      "importing rows 13000000 to 13100000...Done. 2500.236602783203 total seconds elapsed\n",
      "importing rows 13100000 to 13200000...Done. 2511.5623054504395 total seconds elapsed\n",
      "importing rows 13200000 to 13300000...Done. 2523.295926094055 total seconds elapsed\n",
      "importing rows 13300000 to 13400000...Done. 2535.191133260727 total seconds elapsed\n",
      "importing rows 13400000 to 13500000...Done. 2546.862022638321 total seconds elapsed\n",
      "importing rows 13500000 to 13600000...Done. 2558.314393758774 total seconds elapsed\n",
      "importing rows 13600000 to 13700000...Done. 2570.2057161331177 total seconds elapsed\n",
      "importing rows 13700000 to 13800000...Done. 2581.7679069042206 total seconds elapsed\n",
      "importing rows 13800000 to 13900000...Done. 2593.110584259033 total seconds elapsed\n",
      "importing rows 13900000 to 14000000...Done. 2604.99880194664 total seconds elapsed\n",
      "importing rows 14000000 to 14100000...Done. 2616.6567718982697 total seconds elapsed\n",
      "importing rows 14100000 to 14200000...Done. 2628.132259130478 total seconds elapsed\n",
      "importing rows 14200000 to 14300000...Done. 2640.876239299774 total seconds elapsed\n",
      "importing rows 14300000 to 14400000...Done. 2653.271225452423 total seconds elapsed\n",
      "importing rows 14400000 to 14500000...Done. 2664.695776939392 total seconds elapsed\n",
      "importing rows 14500000 to 14600000...Done. 2676.4838132858276 total seconds elapsed\n",
      "importing rows 14600000 to 14700000...Done. 2687.75803899765 total seconds elapsed\n",
      "importing rows 14700000 to 14800000...Done. 2699.1749012470245 total seconds elapsed\n",
      "importing rows 14800000 to 14900000...Done. 2711.1988458633423 total seconds elapsed\n",
      "importing rows 14900000 to 15000000...Done. 2726.4350707530975 total seconds elapsed\n",
      "importing rows 15000000 to 15100000...Done. 2737.801740884781 total seconds elapsed\n",
      "importing rows 15100000 to 15200000...Done. 2749.545455932617 total seconds elapsed\n",
      "importing rows 15200000 to 15300000...Done. 2761.4526727199554 total seconds elapsed\n",
      "importing rows 15300000 to 15400000...Done. 2772.874138355255 total seconds elapsed\n",
      "importing rows 15400000 to 15500000...Done. 2784.5828201770782 total seconds elapsed\n",
      "importing rows 15500000 to 15600000...Done. 2796.1421525478363 total seconds elapsed\n",
      "importing rows 15600000 to 15700000...Done. 2807.616549015045 total seconds elapsed\n",
      "importing rows 15700000 to 15800000...Done. 2819.523222208023 total seconds elapsed\n",
      "importing rows 15800000 to 15900000...Done. 2831.246976852417 total seconds elapsed\n",
      "importing rows 15900000 to 16000000...Done. 2842.8279995918274 total seconds elapsed\n",
      "importing rows 16000000 to 16100000...Done. 2854.8818142414093 total seconds elapsed\n",
      "importing rows 16100000 to 16200000...Done. 2866.295270204544 total seconds elapsed\n",
      "importing rows 16200000 to 16300000...Done. 2877.734748363495 total seconds elapsed\n",
      "importing rows 16300000 to 16400000...Done. 2889.64191198349 total seconds elapsed\n",
      "importing rows 16400000 to 16500000...Done. 2901.0703513622284 total seconds elapsed\n",
      "importing rows 16500000 to 16600000...Done. 2912.4279379844666 total seconds elapsed\n",
      "importing rows 16600000 to 16700000...Done. 2924.353082180023 total seconds elapsed\n",
      "importing rows 16700000 to 16800000...Done. 2936.2981581687927 total seconds elapsed\n",
      "importing rows 16800000 to 16900000...Done. 2948.0008976459503 total seconds elapsed\n",
      "importing rows 16900000 to 17000000...Done. 2959.7723684310913 total seconds elapsed\n",
      "importing rows 17000000 to 17100000...Done. 2971.93190073967 total seconds elapsed\n",
      "importing rows 17100000 to 17200000...Done. 2983.8660378456116 total seconds elapsed\n",
      "importing rows 17200000 to 17300000...Done. 2995.6801838874817 total seconds elapsed\n",
      "importing rows 17300000 to 17400000...Done. 3006.98197388649 total seconds elapsed\n",
      "importing rows 17400000 to 17500000...Done. 3018.41362118721 total seconds elapsed\n",
      "importing rows 17500000 to 17600000...Done. 3030.287138938904 total seconds elapsed\n",
      "importing rows 17600000 to 17700000...Done. 3041.604998588562 total seconds elapsed\n",
      "importing rows 17700000 to 17800000...Done. 3053.0874485969543 total seconds elapsed\n",
      "importing rows 17800000 to 17900000...Done. 3064.7966985702515 total seconds elapsed\n",
      "importing rows 17900000 to 18000000...Done. 3076.22212767601 total seconds elapsed\n",
      "importing rows 18000000 to 18100000...Done. 3087.5421257019043 total seconds elapsed\n",
      "importing rows 18100000 to 18200000...Done. 3099.3555974960327 total seconds elapsed\n",
      "importing rows 18200000 to 18300000...Done. 3110.8411507606506 total seconds elapsed\n",
      "importing rows 18300000 to 18400000...Done. 3122.374377012253 total seconds elapsed\n",
      "importing rows 18400000 to 18500000...Done. 3134.1172709465027 total seconds elapsed\n",
      "importing rows 18500000 to 18600000...Done. 3145.6028683185577 total seconds elapsed\n",
      "importing rows 18600000 to 18700000...Done. 3157.5094122886658 total seconds elapsed\n",
      "importing rows 18700000 to 18800000...Done. 3169.2124905586243 total seconds elapsed\n",
      "importing rows 18800000 to 18900000...Done. 3180.772967338562 total seconds elapsed\n",
      "importing rows 18900000 to 19000000...Done. 3192.19450712204 total seconds elapsed\n",
      "importing rows 19000000 to 19100000...Done. 3204.01939702034 total seconds elapsed\n",
      "importing rows 19100000 to 19200000...Done. 3215.3245556354523 total seconds elapsed\n",
      "importing rows 19200000 to 19300000...Done. 3226.7081184387207 total seconds elapsed\n",
      "importing rows 19300000 to 19400000...Done. 3238.5411384105682 total seconds elapsed\n",
      "importing rows 19400000 to 19500000...Done. 3249.9648158550262 total seconds elapsed\n",
      "importing rows 19500000 to 19600000...Done. 3261.3476955890656 total seconds elapsed\n",
      "importing rows 19600000 to 19700000...Done. 3273.307094812393 total seconds elapsed\n",
      "importing rows 19700000 to 19800000...Done. 3284.761693239212 total seconds elapsed\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "importing rows 19800000 to 19900000...Done. 3296.100790500641 total seconds elapsed\n",
      "importing rows 19900000 to 20000000...Done. 3307.8526158332825 total seconds elapsed\n",
      "importing rows 20000000 to 20100000...Done. 3319.2791182994843 total seconds elapsed\n",
      "importing rows 20100000 to 20200000...Done. 3330.647325515747 total seconds elapsed\n",
      "importing rows 20200000 to 20300000...Done. 3342.4926569461823 total seconds elapsed\n",
      "importing rows 20300000 to 20400000...Done. 4599.354989290237 total seconds elapsed\n",
      "importing rows 20400000 to 20500000...Done. 4613.02946805954 total seconds elapsed\n",
      "importing rows 20500000 to 20600000...Done. 4624.889894247055 total seconds elapsed\n",
      "importing rows 20600000 to 20700000...Done. 4636.2544865608215 total seconds elapsed\n",
      "importing rows 20700000 to 20800000...Done. 4647.741796731949 total seconds elapsed\n",
      "importing rows 20800000 to 20900000...Done. 4659.538177251816 total seconds elapsed\n",
      "importing rows 20900000 to 21000000...Done. 4670.866872310638 total seconds elapsed\n",
      "importing rows 21000000 to 21100000...Done. 4682.2943296432495 total seconds elapsed\n",
      "importing rows 21100000 to 21200000...Done. 4693.995052099228 total seconds elapsed\n",
      "importing rows 21200000 to 21300000...Done. 4705.322795629501 total seconds elapsed\n",
      "importing rows 21300000 to 21400000...Done. 4716.723305463791 total seconds elapsed\n",
      "importing rows 21400000 to 21500000...Done. 4728.650548219681 total seconds elapsed\n",
      "importing rows 21500000 to 21600000...Done. 4740.209751367569 total seconds elapsed\n",
      "importing rows 21600000 to 21700000...Done. 4751.611275672913 total seconds elapsed\n",
      "importing rows 21700000 to 21800000...Done. 4763.443618297577 total seconds elapsed\n",
      "importing rows 21800000 to 21900000...Done. 4775.030885219574 total seconds elapsed\n",
      "importing rows 21900000 to 22000000...Done. 4786.677770853043 total seconds elapsed\n",
      "importing rows 22000000 to 22100000...Done. 4798.35652589798 total seconds elapsed\n",
      "importing rows 22100000 to 22200000...Done. 4809.850818872452 total seconds elapsed\n",
      "importing rows 22200000 to 22300000...Done. 4821.505701541901 total seconds elapsed\n",
      "importing rows 22300000 to 22400000...Done. 4833.595470190048 total seconds elapsed\n",
      "importing rows 22400000 to 22500000...Done. 4845.203420162201 total seconds elapsed\n",
      "importing rows 22500000 to 22600000...Done. 4856.674240350723 total seconds elapsed\n",
      "importing rows 22600000 to 22700000...Done. 4868.4906504154205 total seconds elapsed\n",
      "importing rows 22700000 to 22800000...Done. 4879.9340562820435 total seconds elapsed\n",
      "importing rows 22800000 to 22900000...Done. 4891.322607755661 total seconds elapsed\n",
      "importing rows 22900000 to 23000000...Done. 4903.412316083908 total seconds elapsed\n",
      "importing rows 23000000 to 23100000...Done. 4914.826740503311 total seconds elapsed\n",
      "importing rows 23100000 to 23200000...Done. 4926.12403678894 total seconds elapsed\n",
      "importing rows 23200000 to 23300000...Done. 4937.9205503463745 total seconds elapsed\n",
      "importing rows 23300000 to 23400000...Done. 4949.399866819382 total seconds elapsed\n",
      "importing rows 23400000 to 23500000...Done. 4960.949958086014 total seconds elapsed\n",
      "importing rows 23500000 to 23600000...Done. 4972.85925412178 total seconds elapsed\n",
      "importing rows 23600000 to 23700000...Done. 4984.239002227783 total seconds elapsed\n",
      "importing rows 23700000 to 23800000...Done. 4995.616606235504 total seconds elapsed\n",
      "importing rows 23800000 to 23900000...Done. 5007.223601818085 total seconds elapsed\n",
      "importing rows 23900000 to 24000000...Done. 5018.73592209816 total seconds elapsed\n",
      "importing rows 24000000 to 24100000...Done. 5030.1952867507935 total seconds elapsed\n",
      "importing rows 24100000 to 24200000...Done. 5042.150303840637 total seconds elapsed\n",
      "importing rows 24200000 to 24300000...Done. 5053.545262813568 total seconds elapsed\n",
      "importing rows 24300000 to 24400000...Done. 5064.976903676987 total seconds elapsed\n",
      "importing rows 24400000 to 24500000...Done. 5077.153465747833 total seconds elapsed\n",
      "importing rows 24500000 to 24600000...Done. 5088.526077747345 total seconds elapsed\n",
      "importing rows 24600000 to 24700000...Done. 5099.8806965351105 total seconds elapsed\n",
      "importing rows 24700000 to 24800000...Done. 5111.805842876434 total seconds elapsed\n",
      "importing rows 24800000 to 24900000...Done. 5123.423908233643 total seconds elapsed\n",
      "importing rows 24900000 to 25000000...Done. 5134.927176475525 total seconds elapsed\n",
      "importing rows 25000000 to 25100000...Done. 5146.79786324501 total seconds elapsed\n",
      "importing rows 25100000 to 25200000...Done. 5158.256454229355 total seconds elapsed\n",
      "importing rows 25200000 to 25300000...Done. 5169.593167066574 total seconds elapsed\n",
      "importing rows 25300000 to 25400000...Done. 5181.256728887558 total seconds elapsed\n",
      "importing rows 25400000 to 25500000...Done. 5192.781136274338 total seconds elapsed\n",
      "importing rows 25500000 to 25600000...Done. 5204.301426410675 total seconds elapsed\n",
      "importing rows 25600000 to 25700000...Done. 5215.975876092911 total seconds elapsed\n",
      "importing rows 25700000 to 25800000...Done. 5227.348761558533 total seconds elapsed\n",
      "importing rows 25800000 to 25900000...Done. 5238.849979639053 total seconds elapsed\n",
      "importing rows 25900000 to 26000000...Done. 5250.947049617767 total seconds elapsed\n",
      "importing rows 26000000 to 26024289...Done. 5253.703676700592 total seconds elapsed\n"
     ]
    }
   ],
   "source": [
    "rows_imported = 0\n",
    "# get the start_time from time.time()\n",
    "start_time = time.time()\n",
    "for data in pd.read_csv(f'{file_dir}/Data/ratings.csv', chunksize=100000):\n",
    "    print(f'importing rows {rows_imported} to {rows_imported + len(data)}...', end='')\n",
    "    data.to_sql(name='ratings', con=engine, if_exists='append')\n",
    "    rows_imported += len(data)\n",
    "\n",
    "    # add elapsed time to final print out\n",
    "    print(f'Done. {time.time() - start_time} total seconds elapsed')"
   ]
  },
  {
   "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}