rec-code/Chapter2/Chapter2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'1.4.3'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "pd.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Read the CSV File into df\n",
    "df = pd.read_csv('../data/movies_metadata.csv', low_memory=False)\n",
    "\n",
    "#We will find out what the following code does a little later!\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Output the type of df\n",
    "type(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(45466, 24)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Output the shape of df\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['adult', 'belongs_to_collection', 'budget', 'genres', 'homepage', 'id',\n",
       "       'imdb_id', 'original_language', 'original_title', 'overview',\n",
       "       'popularity', 'poster_path', 'production_companies',\n",
       "       'production_countries', 'release_date', 'revenue', 'runtime',\n",
       "       'spoken_languages', 'status', 'tagline', 'title', 'video',\n",
       "       'vote_average', 'vote_count'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Output the columns of df\n",
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "adult                                                                False\n",
       "belongs_to_collection                                                  NaN\n",
       "budget                                                            65000000\n",
       "genres                   [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...\n",
       "homepage                                                               NaN\n",
       "id                                                                    8844\n",
       "imdb_id                                                          tt0113497\n",
       "original_language                                                       en\n",
       "original_title                                                     Jumanji\n",
       "overview                 When siblings Judy and Peter discover an encha...\n",
       "popularity                                                       17.015539\n",
       "poster_path                               /vzmL6fP7aPKNKPRTFnZmiUfciyV.jpg\n",
       "production_companies     [{'name': 'TriStar Pictures', 'id': 559}, {'na...\n",
       "production_countries     [{'iso_3166_1': 'US', 'name': 'United States o...\n",
       "release_date                                                    1995-12-15\n",
       "revenue                                                        262797249.0\n",
       "runtime                                                              104.0\n",
       "spoken_languages         [{'iso_639_1': 'en', 'name': 'English'}, {'iso...\n",
       "status                                                            Released\n",
       "tagline                          Roll the dice and unleash the excitement!\n",
       "title                                                              Jumanji\n",
       "video                                                                False\n",
       "vote_average                                                           6.9\n",
       "vote_count                                                          2413.0\n",
       "Name: 1, dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Select the second movie in df\n",
    "second = df.iloc[1]\n",
    "second"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "adult                                                                False\n",
       "belongs_to_collection                                                  NaN\n",
       "budget                                                            65000000\n",
       "genres                   [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...\n",
       "homepage                                                               NaN\n",
       "id                                                                    8844\n",
       "imdb_id                                                          tt0113497\n",
       "original_language                                                       en\n",
       "original_title                                                     Jumanji\n",
       "overview                 When siblings Judy and Peter discover an encha...\n",
       "popularity                                                       17.015539\n",
       "poster_path                               /vzmL6fP7aPKNKPRTFnZmiUfciyV.jpg\n",
       "production_companies     [{'name': 'TriStar Pictures', 'id': 559}, {'na...\n",
       "production_countries     [{'iso_3166_1': 'US', 'name': 'United States o...\n",
       "release_date                                                    1995-12-15\n",
       "revenue                                                        262797249.0\n",
       "runtime                                                              104.0\n",
       "spoken_languages         [{'iso_639_1': 'en', 'name': 'English'}, {'iso...\n",
       "status                                                            Released\n",
       "tagline                          Roll the dice and unleash the excitement!\n",
       "video                                                                False\n",
       "vote_average                                                           6.9\n",
       "vote_count                                                          2413.0\n",
       "Name: Jumanji, dtype: object"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Change the index to the title\n",
    "df = df.set_index('title')\n",
    "\n",
    "#Access the movie with title 'Jumanji'\n",
    "jum = df.loc['Jumanji']\n",
    "jum"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index()"
   ]
  },
  {
   "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>title</th>\n",
       "      <th>release_date</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Toy Story</td>\n",
       "      <td>1995-10-30</td>\n",
       "      <td>30000000</td>\n",
       "      <td>373554033.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>[{'id': 16, 'name': 'Animation'}, {'id': 35, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jumanji</td>\n",
       "      <td>1995-12-15</td>\n",
       "      <td>65000000</td>\n",
       "      <td>262797249.0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Grumpier Old Men</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>101.0</td>\n",
       "      <td>[{'id': 10749, 'name': 'Romance'}, {'id': 35, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Waiting to Exhale</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>16000000</td>\n",
       "      <td>81452156.0</td>\n",
       "      <td>127.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}, {'id': 18, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Father of the Bride Part II</td>\n",
       "      <td>1995-02-10</td>\n",
       "      <td>0</td>\n",
       "      <td>76578911.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         title release_date    budget      revenue  runtime  \\\n",
       "0                    Toy Story   1995-10-30  30000000  373554033.0     81.0   \n",
       "1                      Jumanji   1995-12-15  65000000  262797249.0    104.0   \n",
       "2             Grumpier Old Men   1995-12-22         0          0.0    101.0   \n",
       "3            Waiting to Exhale   1995-12-22  16000000   81452156.0    127.0   \n",
       "4  Father of the Bride Part II   1995-02-10         0   76578911.0    106.0   \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'}]  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Create a smaller dataframe with a subset of all features\n",
    "small_df = df[['title', 'release_date', 'budget', 'revenue', 'runtime', 'genres']]\n",
    "\n",
    "#Output only the first 5 rows of small_df\n",
    "small_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>release_date</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Toy Story</td>\n",
       "      <td>1995-10-30</td>\n",
       "      <td>30000000</td>\n",
       "      <td>373554033.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>[{'id': 16, 'name': 'Animation'}, {'id': 35, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jumanji</td>\n",
       "      <td>1995-12-15</td>\n",
       "      <td>65000000</td>\n",
       "      <td>262797249.0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Grumpier Old Men</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>101.0</td>\n",
       "      <td>[{'id': 10749, 'name': 'Romance'}, {'id': 35, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Waiting to Exhale</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>16000000</td>\n",
       "      <td>81452156.0</td>\n",
       "      <td>127.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}, {'id': 18, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Father of the Bride Part II</td>\n",
       "      <td>1995-02-10</td>\n",
       "      <td>0</td>\n",
       "      <td>76578911.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Heat</td>\n",
       "      <td>1995-12-15</td>\n",
       "      <td>60000000</td>\n",
       "      <td>187436818.0</td>\n",
       "      <td>170.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 80, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Sabrina</td>\n",
       "      <td>1995-12-15</td>\n",
       "      <td>58000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>127.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}, {'id': 10749, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Tom and Huck</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Sudden Death</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>35000000</td>\n",
       "      <td>64350171.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>GoldenEye</td>\n",
       "      <td>1995-11-16</td>\n",
       "      <td>58000000</td>\n",
       "      <td>352194034.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 28, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>The American President</td>\n",
       "      <td>1995-11-17</td>\n",
       "      <td>62000000</td>\n",
       "      <td>107879496.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}, {'id': 18, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Dracula: Dead and Loving It</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>88.0</td>\n",
       "      <td>[{'id': 35, 'name': 'Comedy'}, {'id': 27, 'nam...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Balto</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>0</td>\n",
       "      <td>11348324.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 16, '...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Nixon</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>44000000</td>\n",
       "      <td>13681765.0</td>\n",
       "      <td>192.0</td>\n",
       "      <td>[{'id': 36, 'name': 'History'}, {'id': 18, 'na...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Cutthroat Island</td>\n",
       "      <td>1995-12-22</td>\n",
       "      <td>98000000</td>\n",
       "      <td>10017322.0</td>\n",
       "      <td>119.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          title release_date    budget      revenue  runtime  \\\n",
       "0                     Toy Story   1995-10-30  30000000  373554033.0     81.0   \n",
       "1                       Jumanji   1995-12-15  65000000  262797249.0    104.0   \n",
       "2              Grumpier Old Men   1995-12-22         0          0.0    101.0   \n",
       "3             Waiting to Exhale   1995-12-22  16000000   81452156.0    127.0   \n",
       "4   Father of the Bride Part II   1995-02-10         0   76578911.0    106.0   \n",
       "5                          Heat   1995-12-15  60000000  187436818.0    170.0   \n",
       "6                       Sabrina   1995-12-15  58000000          0.0    127.0   \n",
       "7                  Tom and Huck   1995-12-22         0          0.0     97.0   \n",
       "8                  Sudden Death   1995-12-22  35000000   64350171.0    106.0   \n",
       "9                     GoldenEye   1995-11-16  58000000  352194034.0    130.0   \n",
       "10       The American President   1995-11-17  62000000  107879496.0    106.0   \n",
       "11  Dracula: Dead and Loving It   1995-12-22         0          0.0     88.0   \n",
       "12                        Balto   1995-12-22         0   11348324.0     78.0   \n",
       "13                        Nixon   1995-12-22  44000000   13681765.0    192.0   \n",
       "14             Cutthroat Island   1995-12-22  98000000   10017322.0    119.0   \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",
       "5   [{'id': 28, 'name': 'Action'}, {'id': 80, 'nam...  \n",
       "6   [{'id': 35, 'name': 'Comedy'}, {'id': 10749, '...  \n",
       "7   [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  \n",
       "8   [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  \n",
       "9   [{'id': 12, 'name': 'Adventure'}, {'id': 28, '...  \n",
       "10  [{'id': 35, 'name': 'Comedy'}, {'id': 18, 'nam...  \n",
       "11  [{'id': 35, 'name': 'Comedy'}, {'id': 27, 'nam...  \n",
       "12  [{'id': 10751, 'name': 'Family'}, {'id': 16, '...  \n",
       "13  [{'id': 36, 'name': 'History'}, {'id': 18, 'na...  \n",
       "14  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Display the first 15 rows\n",
    "small_df.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 45466 entries, 0 to 45465\n",
      "Data columns (total 6 columns):\n",
      " #   Column        Non-Null Count  Dtype  \n",
      "---  ------        --------------  -----  \n",
      " 0   title         45460 non-null  object \n",
      " 1   release_date  45379 non-null  object \n",
      " 2   budget        45466 non-null  object \n",
      " 3   revenue       45460 non-null  float64\n",
      " 4   runtime       45203 non-null  float64\n",
      " 5   genres        45466 non-null  object \n",
      "dtypes: float64(2), object(4)\n",
      "memory usage: 2.1+ MB\n"
     ]
    }
   ],
   "source": [
    "#Get information of the data types of each feature\n",
    "small_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "could not convert string to float: '/ff9qCepilowshEtG2GYWwzt2bs4.jpg'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Input \u001b[0;32mIn [13]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mbudget\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mastype\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mfloat\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/generic.py:5912\u001b[0m, in \u001b[0;36mNDFrame.astype\u001b[0;34m(self, dtype, copy, errors)\u001b[0m\n\u001b[1;32m   5905\u001b[0m     results \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m   5906\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miloc[:, i]\u001b[38;5;241m.\u001b[39mastype(dtype, copy\u001b[38;5;241m=\u001b[39mcopy)\n\u001b[1;32m   5907\u001b[0m         \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns))\n\u001b[1;32m   5908\u001b[0m     ]\n\u001b[1;32m   5910\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   5911\u001b[0m     \u001b[38;5;66;03m# else, only a single dtype is given\u001b[39;00m\n\u001b[0;32m-> 5912\u001b[0m     new_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_mgr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mastype\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   5913\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_constructor(new_data)\u001b[38;5;241m.\u001b[39m__finalize__(\u001b[38;5;28mself\u001b[39m, method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mastype\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m   5915\u001b[0m \u001b[38;5;66;03m# GH 33113: handle empty frame or series\u001b[39;00m\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/internals/managers.py:419\u001b[0m, in \u001b[0;36mBaseBlockManager.astype\u001b[0;34m(self, dtype, copy, errors)\u001b[0m\n\u001b[1;32m    418\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mastype\u001b[39m(\u001b[38;5;28mself\u001b[39m: T, dtype, copy: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m, errors: \u001b[38;5;28mstr\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[0;32m--> 419\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mastype\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/internals/managers.py:304\u001b[0m, in \u001b[0;36mBaseBlockManager.apply\u001b[0;34m(self, f, align_keys, ignore_failures, **kwargs)\u001b[0m\n\u001b[1;32m    302\u001b[0m         applied \u001b[38;5;241m=\u001b[39m b\u001b[38;5;241m.\u001b[39mapply(f, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    303\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 304\u001b[0m         applied \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    305\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mTypeError\u001b[39;00m, \u001b[38;5;167;01mNotImplementedError\u001b[39;00m):\n\u001b[1;32m    306\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m ignore_failures:\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/internals/blocks.py:580\u001b[0m, in \u001b[0;36mBlock.astype\u001b[0;34m(self, dtype, copy, errors)\u001b[0m\n\u001b[1;32m    562\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    563\u001b[0m \u001b[38;5;124;03mCoerce to the new dtype.\u001b[39;00m\n\u001b[1;32m    564\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    576\u001b[0m \u001b[38;5;124;03mBlock\u001b[39;00m\n\u001b[1;32m    577\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    578\u001b[0m values \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvalues\n\u001b[0;32m--> 580\u001b[0m new_values \u001b[38;5;241m=\u001b[39m \u001b[43mastype_array_safe\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    582\u001b[0m new_values \u001b[38;5;241m=\u001b[39m maybe_coerce_values(new_values)\n\u001b[1;32m    583\u001b[0m newb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmake_block(new_values)\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/dtypes/cast.py:1292\u001b[0m, in \u001b[0;36mastype_array_safe\u001b[0;34m(values, dtype, copy, errors)\u001b[0m\n\u001b[1;32m   1289\u001b[0m     dtype \u001b[38;5;241m=\u001b[39m dtype\u001b[38;5;241m.\u001b[39mnumpy_dtype\n\u001b[1;32m   1291\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1292\u001b[0m     new_values \u001b[38;5;241m=\u001b[39m \u001b[43mastype_array\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1293\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[1;32m   1294\u001b[0m     \u001b[38;5;66;03m# e.g. astype_nansafe can fail on object-dtype of strings\u001b[39;00m\n\u001b[1;32m   1295\u001b[0m     \u001b[38;5;66;03m#  trying to convert to float\u001b[39;00m\n\u001b[1;32m   1296\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/dtypes/cast.py:1237\u001b[0m, in \u001b[0;36mastype_array\u001b[0;34m(values, dtype, copy)\u001b[0m\n\u001b[1;32m   1234\u001b[0m     values \u001b[38;5;241m=\u001b[39m values\u001b[38;5;241m.\u001b[39mastype(dtype, copy\u001b[38;5;241m=\u001b[39mcopy)\n\u001b[1;32m   1236\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1237\u001b[0m     values \u001b[38;5;241m=\u001b[39m \u001b[43mastype_nansafe\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1239\u001b[0m \u001b[38;5;66;03m# in pandas we don't store numpy str dtypes, so convert to object\u001b[39;00m\n\u001b[1;32m   1240\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(dtype, np\u001b[38;5;241m.\u001b[39mdtype) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28missubclass\u001b[39m(values\u001b[38;5;241m.\u001b[39mdtype\u001b[38;5;241m.\u001b[39mtype, \u001b[38;5;28mstr\u001b[39m):\n",
      "File \u001b[0;32m/usr/local/Cellar/ipython/8.4.0/libexec/lib/python3.10/site-packages/pandas/core/dtypes/cast.py:1181\u001b[0m, in \u001b[0;36mastype_nansafe\u001b[0;34m(arr, dtype, copy, skipna)\u001b[0m\n\u001b[1;32m   1177\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(msg)\n\u001b[1;32m   1179\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m copy \u001b[38;5;129;01mor\u001b[39;00m is_object_dtype(arr\u001b[38;5;241m.\u001b[39mdtype) \u001b[38;5;129;01mor\u001b[39;00m is_object_dtype(dtype):\n\u001b[1;32m   1180\u001b[0m     \u001b[38;5;66;03m# Explicit copy, or required since NumPy can't view from / to object.\u001b[39;00m\n\u001b[0;32m-> 1181\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43marr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mastype\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m   1183\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mastype(dtype, copy\u001b[38;5;241m=\u001b[39mcopy)\n",
      "\u001b[0;31mValueError\u001b[0m: could not convert string to float: '/ff9qCepilowshEtG2GYWwzt2bs4.jpg'"
     ]
    }
   ],
   "source": [
    "df['budget'].astype('float')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 45466 entries, 0 to 45465\n",
      "Data columns (total 6 columns):\n",
      " #   Column        Non-Null Count  Dtype  \n",
      "---  ------        --------------  -----  \n",
      " 0   title         45460 non-null  object \n",
      " 1   release_date  45379 non-null  object \n",
      " 2   budget        45463 non-null  float64\n",
      " 3   revenue       45460 non-null  float64\n",
      " 4   runtime       45203 non-null  float64\n",
      " 5   genres        45466 non-null  object \n",
      "dtypes: float64(3), object(3)\n",
      "memory usage: 2.1+ MB\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/dv/107570dd01b_m3wvmvv0g9lm0000gn/T/ipykernel_4472/1765380320.py:13: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  small_df['budget'] = small_df['budget'].apply(to_float)\n",
      "/var/folders/dv/107570dd01b_m3wvmvv0g9lm0000gn/T/ipykernel_4472/1765380320.py:16: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  small_df['budget'] = small_df['budget'].astype('float')\n"
     ]
    }
   ],
   "source": [
    "#Import the numpy library \n",
    "import numpy as np\n",
    "\n",
    "#Function to convert to float manually\n",
    "def to_float(x):\n",
    "    try:\n",
    "        x = float(x)\n",
    "    except: \n",
    "        x = np.nan\n",
    "    return x\n",
    "\n",
    "#Apply the to_float function to all values in the budget column\n",
    "small_df['budget'] = small_df['budget'].apply(to_float)\n",
    "\n",
    "#Try converting to float using pandas astype\n",
    "small_df['budget'] = small_df['budget'].astype('float')\n",
    "\n",
    "#Get the data types for all features\n",
    "small_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/dv/107570dd01b_m3wvmvv0g9lm0000gn/T/ipykernel_4472/2397457688.py:2: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  small_df['release_date'] = pd.to_datetime(small_df['release_date'], errors='coerce')\n",
      "/var/folders/dv/107570dd01b_m3wvmvv0g9lm0000gn/T/ipykernel_4472/2397457688.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  small_df['year'] = small_df['release_date'].apply(lambda x: str(x).split('-')[0] if x != np.nan else np.nan)\n"
     ]
    }
   ],
   "source": [
    "#Convert release_date into pandas datetime format\n",
    "small_df['release_date'] = pd.to_datetime(small_df['release_date'], errors='coerce')\n",
    "\n",
    "#Extract year from the datetime\n",
    "small_df['year'] = small_df['release_date'].apply(lambda x: str(x).split('-')[0] if x != np.nan else np.nan)"
   ]
  },
  {
   "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>title</th>\n",
       "      <th>release_date</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>34940</th>\n",
       "      <td>Passage of Venus</td>\n",
       "      <td>1874-12-09</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>[{'id': 99, 'name': 'Documentary'}]</td>\n",
       "      <td>1874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34937</th>\n",
       "      <td>Sallie Gardner at a Gallop</td>\n",
       "      <td>1878-06-14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>[{'id': 99, 'name': 'Documentary'}]</td>\n",
       "      <td>1878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41602</th>\n",
       "      <td>Buffalo Running</td>\n",
       "      <td>1883-11-19</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>[{'id': 99, 'name': 'Documentary'}]</td>\n",
       "      <td>1883</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34933</th>\n",
       "      <td>Man Walking Around a Corner</td>\n",
       "      <td>1887-08-18</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>[{'id': 99, 'name': 'Documentary'}]</td>\n",
       "      <td>1887</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34938</th>\n",
       "      <td>Traffic Crossing Leeds Bridge</td>\n",
       "      <td>1888-10-15</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>[{'id': 99, 'name': 'Documentary'}]</td>\n",
       "      <td>1888</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                               title release_date  budget  revenue  runtime  \\\n",
       "34940               Passage of Venus   1874-12-09     0.0      0.0      1.0   \n",
       "34937     Sallie Gardner at a Gallop   1878-06-14     0.0      0.0      1.0   \n",
       "41602                Buffalo Running   1883-11-19     0.0      0.0      1.0   \n",
       "34933    Man Walking Around a Corner   1887-08-18     0.0      0.0      1.0   \n",
       "34938  Traffic Crossing Leeds Bridge   1888-10-15     0.0      0.0      1.0   \n",
       "\n",
       "                                    genres  year  \n",
       "34940  [{'id': 99, 'name': 'Documentary'}]  1874  \n",
       "34937  [{'id': 99, 'name': 'Documentary'}]  1878  \n",
       "41602  [{'id': 99, 'name': 'Documentary'}]  1883  \n",
       "34933  [{'id': 99, 'name': 'Documentary'}]  1887  \n",
       "34938  [{'id': 99, 'name': 'Documentary'}]  1888  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Sort DataFrame based on release year\n",
    "small_df = small_df.sort_values('year')\n",
    "\n",
    "small_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>release_date</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>14551</th>\n",
       "      <td>Avatar</td>\n",
       "      <td>2009-12-10</td>\n",
       "      <td>237000000.0</td>\n",
       "      <td>2.787965e+09</td>\n",
       "      <td>162.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26555</th>\n",
       "      <td>Star Wars: The Force Awakens</td>\n",
       "      <td>2015-12-15</td>\n",
       "      <td>245000000.0</td>\n",
       "      <td>2.068224e+09</td>\n",
       "      <td>136.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1639</th>\n",
       "      <td>Titanic</td>\n",
       "      <td>1997-11-18</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.845034e+09</td>\n",
       "      <td>194.0</td>\n",
       "      <td>[{'id': 18, 'name': 'Drama'}, {'id': 10749, 'n...</td>\n",
       "      <td>1997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17818</th>\n",
       "      <td>The Avengers</td>\n",
       "      <td>2012-04-25</td>\n",
       "      <td>220000000.0</td>\n",
       "      <td>1.519558e+09</td>\n",
       "      <td>143.0</td>\n",
       "      <td>[{'id': 878, 'name': 'Science Fiction'}, {'id'...</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25084</th>\n",
       "      <td>Jurassic World</td>\n",
       "      <td>2015-06-09</td>\n",
       "      <td>150000000.0</td>\n",
       "      <td>1.513529e+09</td>\n",
       "      <td>124.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                              title release_date       budget       revenue  \\\n",
       "14551                        Avatar   2009-12-10  237000000.0  2.787965e+09   \n",
       "26555  Star Wars: The Force Awakens   2015-12-15  245000000.0  2.068224e+09   \n",
       "1639                        Titanic   1997-11-18  200000000.0  1.845034e+09   \n",
       "17818                  The Avengers   2012-04-25  220000000.0  1.519558e+09   \n",
       "25084                Jurassic World   2015-06-09  150000000.0  1.513529e+09   \n",
       "\n",
       "       runtime                                             genres  year  \n",
       "14551    162.0  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2009  \n",
       "26555    136.0  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2015  \n",
       "1639     194.0  [{'id': 18, 'name': 'Drama'}, {'id': 10749, 'n...  1997  \n",
       "17818    143.0  [{'id': 878, 'name': 'Science Fiction'}, {'id'...  2012  \n",
       "25084    124.0  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2015  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Sort Movies based on revenue (in descending order)\n",
    "small_df = small_df.sort_values('revenue', ascending=False)\n",
    "\n",
    "small_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>title</th>\n",
       "      <th>release_date</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>14551</th>\n",
       "      <td>Avatar</td>\n",
       "      <td>2009-12-10</td>\n",
       "      <td>237000000.0</td>\n",
       "      <td>2.787965e+09</td>\n",
       "      <td>162.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26555</th>\n",
       "      <td>Star Wars: The Force Awakens</td>\n",
       "      <td>2015-12-15</td>\n",
       "      <td>245000000.0</td>\n",
       "      <td>2.068224e+09</td>\n",
       "      <td>136.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1639</th>\n",
       "      <td>Titanic</td>\n",
       "      <td>1997-11-18</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.845034e+09</td>\n",
       "      <td>194.0</td>\n",
       "      <td>[{'id': 18, 'name': 'Drama'}, {'id': 10749, 'n...</td>\n",
       "      <td>1997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17818</th>\n",
       "      <td>The Avengers</td>\n",
       "      <td>2012-04-25</td>\n",
       "      <td>220000000.0</td>\n",
       "      <td>1.519558e+09</td>\n",
       "      <td>143.0</td>\n",
       "      <td>[{'id': 878, 'name': 'Science Fiction'}, {'id'...</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25084</th>\n",
       "      <td>Jurassic World</td>\n",
       "      <td>2015-06-09</td>\n",
       "      <td>150000000.0</td>\n",
       "      <td>1.513529e+09</td>\n",
       "      <td>124.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28830</th>\n",
       "      <td>Furious 7</td>\n",
       "      <td>2015-04-01</td>\n",
       "      <td>190000000.0</td>\n",
       "      <td>1.506249e+09</td>\n",
       "      <td>137.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}]</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26558</th>\n",
       "      <td>Avengers: Age of Ultron</td>\n",
       "      <td>2015-04-22</td>\n",
       "      <td>280000000.0</td>\n",
       "      <td>1.405404e+09</td>\n",
       "      <td>141.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17437</th>\n",
       "      <td>Harry Potter and the Deathly Hallows: Part 2</td>\n",
       "      <td>2011-07-07</td>\n",
       "      <td>125000000.0</td>\n",
       "      <td>1.342000e+09</td>\n",
       "      <td>130.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 14, '...</td>\n",
       "      <td>2011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22110</th>\n",
       "      <td>Frozen</td>\n",
       "      <td>2013-11-27</td>\n",
       "      <td>150000000.0</td>\n",
       "      <td>1.274219e+09</td>\n",
       "      <td>102.0</td>\n",
       "      <td>[{'id': 16, 'name': 'Animation'}, {'id': 12, '...</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42222</th>\n",
       "      <td>Beauty and the Beast</td>\n",
       "      <td>2017-03-16</td>\n",
       "      <td>160000000.0</td>\n",
       "      <td>1.262886e+09</td>\n",
       "      <td>129.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 14, '...</td>\n",
       "      <td>2017</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43255</th>\n",
       "      <td>The Fate of the Furious</td>\n",
       "      <td>2017-04-12</td>\n",
       "      <td>250000000.0</td>\n",
       "      <td>1.238765e+09</td>\n",
       "      <td>136.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 80, 'nam...</td>\n",
       "      <td>2017</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20830</th>\n",
       "      <td>Iron Man 3</td>\n",
       "      <td>2013-04-18</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.215440e+09</td>\n",
       "      <td>130.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30700</th>\n",
       "      <td>Minions</td>\n",
       "      <td>2015-06-17</td>\n",
       "      <td>74000000.0</td>\n",
       "      <td>1.156731e+09</td>\n",
       "      <td>91.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 16, '...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26567</th>\n",
       "      <td>Captain America: Civil War</td>\n",
       "      <td>2016-04-27</td>\n",
       "      <td>250000000.0</td>\n",
       "      <td>1.153304e+09</td>\n",
       "      <td>147.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 28, '...</td>\n",
       "      <td>2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17293</th>\n",
       "      <td>Transformers: Dark of the Moon</td>\n",
       "      <td>2011-06-28</td>\n",
       "      <td>195000000.0</td>\n",
       "      <td>1.123747e+09</td>\n",
       "      <td>154.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 878, 'na...</td>\n",
       "      <td>2011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7000</th>\n",
       "      <td>The Lord of the Rings: The Return of the King</td>\n",
       "      <td>2003-12-01</td>\n",
       "      <td>94000000.0</td>\n",
       "      <td>1.118889e+09</td>\n",
       "      <td>201.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "      <td>2003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19261</th>\n",
       "      <td>Skyfall</td>\n",
       "      <td>2012-10-25</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.108561e+09</td>\n",
       "      <td>143.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23617</th>\n",
       "      <td>Transformers: Age of Extinction</td>\n",
       "      <td>2014-06-25</td>\n",
       "      <td>210000000.0</td>\n",
       "      <td>1.091405e+09</td>\n",
       "      <td>165.0</td>\n",
       "      <td>[{'id': 878, 'name': 'Science Fiction'}, {'id'...</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18252</th>\n",
       "      <td>The Dark Knight Rises</td>\n",
       "      <td>2012-07-16</td>\n",
       "      <td>250000000.0</td>\n",
       "      <td>1.084939e+09</td>\n",
       "      <td>165.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 80, 'nam...</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15348</th>\n",
       "      <td>Toy Story 3</td>\n",
       "      <td>2010-06-16</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.066970e+09</td>\n",
       "      <td>103.0</td>\n",
       "      <td>[{'id': 16, 'name': 'Animation'}, {'id': 10751...</td>\n",
       "      <td>2010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11008</th>\n",
       "      <td>Pirates of the Caribbean: Dead Man's Chest</td>\n",
       "      <td>2006-06-20</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.065660e+09</td>\n",
       "      <td>151.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "      <td>2006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41489</th>\n",
       "      <td>Rogue One: A Star Wars Story</td>\n",
       "      <td>2016-12-14</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.056057e+09</td>\n",
       "      <td>133.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...</td>\n",
       "      <td>2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17124</th>\n",
       "      <td>Pirates of the Caribbean: On Stranger Tides</td>\n",
       "      <td>2011-05-14</td>\n",
       "      <td>380000000.0</td>\n",
       "      <td>1.045714e+09</td>\n",
       "      <td>136.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 28, '...</td>\n",
       "      <td>2011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38176</th>\n",
       "      <td>Finding Dory</td>\n",
       "      <td>2016-06-16</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.028571e+09</td>\n",
       "      <td>97.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 16, '...</td>\n",
       "      <td>2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14892</th>\n",
       "      <td>Alice in Wonderland</td>\n",
       "      <td>2010-03-03</td>\n",
       "      <td>200000000.0</td>\n",
       "      <td>1.025491e+09</td>\n",
       "      <td>108.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 14, '...</td>\n",
       "      <td>2010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36253</th>\n",
       "      <td>Zootopia</td>\n",
       "      <td>2016-02-11</td>\n",
       "      <td>150000000.0</td>\n",
       "      <td>1.023784e+09</td>\n",
       "      <td>108.0</td>\n",
       "      <td>[{'id': 16, 'name': 'Animation'}, {'id': 12, '...</td>\n",
       "      <td>2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19971</th>\n",
       "      <td>The Hobbit: An Unexpected Journey</td>\n",
       "      <td>2012-11-26</td>\n",
       "      <td>250000000.0</td>\n",
       "      <td>1.021104e+09</td>\n",
       "      <td>169.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44009</th>\n",
       "      <td>Despicable Me 3</td>\n",
       "      <td>2017-06-15</td>\n",
       "      <td>80000000.0</td>\n",
       "      <td>1.020063e+09</td>\n",
       "      <td>96.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 16, 'nam...</td>\n",
       "      <td>2017</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12481</th>\n",
       "      <td>The Dark Knight</td>\n",
       "      <td>2008-07-16</td>\n",
       "      <td>185000000.0</td>\n",
       "      <td>1.004558e+09</td>\n",
       "      <td>152.0</td>\n",
       "      <td>[{'id': 18, 'name': 'Drama'}, {'id': 28, 'name...</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               title release_date  \\\n",
       "14551                                         Avatar   2009-12-10   \n",
       "26555                   Star Wars: The Force Awakens   2015-12-15   \n",
       "1639                                         Titanic   1997-11-18   \n",
       "17818                                   The Avengers   2012-04-25   \n",
       "25084                                 Jurassic World   2015-06-09   \n",
       "28830                                      Furious 7   2015-04-01   \n",
       "26558                        Avengers: Age of Ultron   2015-04-22   \n",
       "17437   Harry Potter and the Deathly Hallows: Part 2   2011-07-07   \n",
       "22110                                         Frozen   2013-11-27   \n",
       "42222                           Beauty and the Beast   2017-03-16   \n",
       "43255                        The Fate of the Furious   2017-04-12   \n",
       "20830                                     Iron Man 3   2013-04-18   \n",
       "30700                                        Minions   2015-06-17   \n",
       "26567                     Captain America: Civil War   2016-04-27   \n",
       "17293                 Transformers: Dark of the Moon   2011-06-28   \n",
       "7000   The Lord of the Rings: The Return of the King   2003-12-01   \n",
       "19261                                        Skyfall   2012-10-25   \n",
       "23617                Transformers: Age of Extinction   2014-06-25   \n",
       "18252                          The Dark Knight Rises   2012-07-16   \n",
       "15348                                    Toy Story 3   2010-06-16   \n",
       "11008     Pirates of the Caribbean: Dead Man's Chest   2006-06-20   \n",
       "41489                   Rogue One: A Star Wars Story   2016-12-14   \n",
       "17124    Pirates of the Caribbean: On Stranger Tides   2011-05-14   \n",
       "38176                                   Finding Dory   2016-06-16   \n",
       "14892                            Alice in Wonderland   2010-03-03   \n",
       "36253                                       Zootopia   2016-02-11   \n",
       "19971              The Hobbit: An Unexpected Journey   2012-11-26   \n",
       "44009                                Despicable Me 3   2017-06-15   \n",
       "12481                                The Dark Knight   2008-07-16   \n",
       "\n",
       "            budget       revenue  runtime  \\\n",
       "14551  237000000.0  2.787965e+09    162.0   \n",
       "26555  245000000.0  2.068224e+09    136.0   \n",
       "1639   200000000.0  1.845034e+09    194.0   \n",
       "17818  220000000.0  1.519558e+09    143.0   \n",
       "25084  150000000.0  1.513529e+09    124.0   \n",
       "28830  190000000.0  1.506249e+09    137.0   \n",
       "26558  280000000.0  1.405404e+09    141.0   \n",
       "17437  125000000.0  1.342000e+09    130.0   \n",
       "22110  150000000.0  1.274219e+09    102.0   \n",
       "42222  160000000.0  1.262886e+09    129.0   \n",
       "43255  250000000.0  1.238765e+09    136.0   \n",
       "20830  200000000.0  1.215440e+09    130.0   \n",
       "30700   74000000.0  1.156731e+09     91.0   \n",
       "26567  250000000.0  1.153304e+09    147.0   \n",
       "17293  195000000.0  1.123747e+09    154.0   \n",
       "7000    94000000.0  1.118889e+09    201.0   \n",
       "19261  200000000.0  1.108561e+09    143.0   \n",
       "23617  210000000.0  1.091405e+09    165.0   \n",
       "18252  250000000.0  1.084939e+09    165.0   \n",
       "15348  200000000.0  1.066970e+09    103.0   \n",
       "11008  200000000.0  1.065660e+09    151.0   \n",
       "41489  200000000.0  1.056057e+09    133.0   \n",
       "17124  380000000.0  1.045714e+09    136.0   \n",
       "38176  200000000.0  1.028571e+09     97.0   \n",
       "14892  200000000.0  1.025491e+09    108.0   \n",
       "36253  150000000.0  1.023784e+09    108.0   \n",
       "19971  250000000.0  1.021104e+09    169.0   \n",
       "44009   80000000.0  1.020063e+09     96.0   \n",
       "12481  185000000.0  1.004558e+09    152.0   \n",
       "\n",
       "                                                  genres  year  \n",
       "14551  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2009  \n",
       "26555  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2015  \n",
       "1639   [{'id': 18, 'name': 'Drama'}, {'id': 10749, 'n...  1997  \n",
       "17818  [{'id': 878, 'name': 'Science Fiction'}, {'id'...  2012  \n",
       "25084  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2015  \n",
       "28830                     [{'id': 28, 'name': 'Action'}]  2015  \n",
       "26558  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2015  \n",
       "17437  [{'id': 10751, 'name': 'Family'}, {'id': 14, '...  2011  \n",
       "22110  [{'id': 16, 'name': 'Animation'}, {'id': 12, '...  2013  \n",
       "42222  [{'id': 10751, 'name': 'Family'}, {'id': 14, '...  2017  \n",
       "43255  [{'id': 28, 'name': 'Action'}, {'id': 80, 'nam...  2017  \n",
       "20830  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2013  \n",
       "30700  [{'id': 10751, 'name': 'Family'}, {'id': 16, '...  2015  \n",
       "26567  [{'id': 12, 'name': 'Adventure'}, {'id': 28, '...  2016  \n",
       "17293  [{'id': 28, 'name': 'Action'}, {'id': 878, 'na...  2011  \n",
       "7000   [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...  2003  \n",
       "19261  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2012  \n",
       "23617  [{'id': 878, 'name': 'Science Fiction'}, {'id'...  2014  \n",
       "18252  [{'id': 28, 'name': 'Action'}, {'id': 80, 'nam...  2012  \n",
       "15348  [{'id': 16, 'name': 'Animation'}, {'id': 10751...  2010  \n",
       "11008  [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...  2006  \n",
       "41489  [{'id': 28, 'name': 'Action'}, {'id': 12, 'nam...  2016  \n",
       "17124  [{'id': 12, 'name': 'Adventure'}, {'id': 28, '...  2011  \n",
       "38176  [{'id': 12, 'name': 'Adventure'}, {'id': 16, '...  2016  \n",
       "14892  [{'id': 10751, 'name': 'Family'}, {'id': 14, '...  2010  \n",
       "36253  [{'id': 16, 'name': 'Animation'}, {'id': 12, '...  2016  \n",
       "19971  [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...  2012  \n",
       "44009  [{'id': 28, 'name': 'Action'}, {'id': 16, 'nam...  2017  \n",
       "12481  [{'id': 18, 'name': 'Drama'}, {'id': 28, 'name...  2008  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Select only those movies which earned more than 1 billion\n",
    "new = small_df[small_df['revenue'] > 1e9]\n",
    "\n",
    "new"
   ]
  },
  {
   "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>title</th>\n",
       "      <th>release_date</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17437</th>\n",
       "      <td>Harry Potter and the Deathly Hallows: Part 2</td>\n",
       "      <td>2011-07-07</td>\n",
       "      <td>125000000.0</td>\n",
       "      <td>1.342000e+09</td>\n",
       "      <td>130.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 14, '...</td>\n",
       "      <td>2011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30700</th>\n",
       "      <td>Minions</td>\n",
       "      <td>2015-06-17</td>\n",
       "      <td>74000000.0</td>\n",
       "      <td>1.156731e+09</td>\n",
       "      <td>91.0</td>\n",
       "      <td>[{'id': 10751, 'name': 'Family'}, {'id': 16, '...</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7000</th>\n",
       "      <td>The Lord of the Rings: The Return of the King</td>\n",
       "      <td>2003-12-01</td>\n",
       "      <td>94000000.0</td>\n",
       "      <td>1.118889e+09</td>\n",
       "      <td>201.0</td>\n",
       "      <td>[{'id': 12, 'name': 'Adventure'}, {'id': 14, '...</td>\n",
       "      <td>2003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44009</th>\n",
       "      <td>Despicable Me 3</td>\n",
       "      <td>2017-06-15</td>\n",
       "      <td>80000000.0</td>\n",
       "      <td>1.020063e+09</td>\n",
       "      <td>96.0</td>\n",
       "      <td>[{'id': 28, 'name': 'Action'}, {'id': 16, 'nam...</td>\n",
       "      <td>2017</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               title release_date  \\\n",
       "17437   Harry Potter and the Deathly Hallows: Part 2   2011-07-07   \n",
       "30700                                        Minions   2015-06-17   \n",
       "7000   The Lord of the Rings: The Return of the King   2003-12-01   \n",
       "44009                                Despicable Me 3   2017-06-15   \n",
       "\n",
       "            budget       revenue  runtime  \\\n",
       "17437  125000000.0  1.342000e+09    130.0   \n",
       "30700   74000000.0  1.156731e+09     91.0   \n",
       "7000    94000000.0  1.118889e+09    201.0   \n",
       "44009   80000000.0  1.020063e+09     96.0   \n",
       "\n",
       "                                                  genres  year  \n",
       "17437  [{'id': 10751, 'name': 'Family'}, {'id': 14, '...  2011  \n",
       "30700  [{'id': 10751, 'name': 'Family'}, {'id': 16, '...  2015  \n",
       "7000   [{'id': 12, 'name': 'Adventure'}, {'id': 14, '...  2003  \n",
       "44009  [{'id': 28, 'name': 'Action'}, {'id': 16, 'nam...  2017  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Select only those movies which earned more than 1 billion and spent less than 150 million\n",
    "\n",
    "new2 = small_df[(small_df['revenue'] > 1e9) & (small_df['budget'] < 1.5e8)]\n",
    "new2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(small_df['year'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1256.0\n",
      "0.0\n"
     ]
    }
   ],
   "source": [
    "\n",
    "#Get the runtime Series object\n",
    "runtime = small_df['runtime']\n",
    "\n",
    "#Print the longest runtime of any movie\n",
    "print(runtime.max())\n",
    "\n",
    "#Print the shortest runtime of any movie\n",
    "print(runtime.min())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4224578.813474693\n",
      "0.0\n"
     ]
    }
   ],
   "source": [
    "#Get the budget Series object\n",
    "budget = small_df['budget']\n",
    "\n",
    "#Print the mean budget of the movies\n",
    "print(budget.mean())\n",
    "\n",
    "#Print the median budget of the movies\n",
    "print(budget.median())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "8267610.399999982"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Get the revenue Series object\n",
    "revenue = small_df['revenue']\n",
    "\n",
    "#Revenue generated by the 90th percentile movie\n",
    "revenue.quantile(0.90)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2014    1974\n",
       "2015    1905\n",
       "2013    1889\n",
       "2012    1722\n",
       "2011    1667\n",
       "        ... \n",
       "1887       1\n",
       "1883       1\n",
       "1893       1\n",
       "2020       1\n",
       "1878       1\n",
       "Name: year, Length: 136, dtype: int64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Get number of movies released each year\n",
    "small_df['year'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}