test.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Cleaning "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**First, according to the previous decision, let's drop unncessary columns : `imdb_id`, `homepage`, `tagline`, `overview`.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 383,
   "metadata": {},
   "outputs": [],
   "source": [
    "# After discussing the structure of the data and any problems that need to be\n",
    "#   cleaned, perform those cleaning steps in the second part of this section.\n",
    "# Drop extraneous columns\n",
    "col = ['imdb_id', 'homepage', 'tagline', 'overview', 'budget_adj', 'revenue_adj']\n",
    "df.drop(col, axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 384,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>popularity</th>\n",
       "      <th>budget</th>\n",
       "      <th>revenue</th>\n",
       "      <th>original_title</th>\n",
       "      <th>cast</th>\n",
       "      <th>director</th>\n",
       "      <th>keywords</th>\n",
       "      <th>runtime</th>\n",
       "      <th>genres</th>\n",
       "      <th>production_companies</th>\n",
       "      <th>release_date</th>\n",
       "      <th>vote_count</th>\n",
       "      <th>vote_average</th>\n",
       "      <th>release_year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>135397</td>\n",
       "      <td>32.985763</td>\n",
       "      <td>150000000</td>\n",
       "      <td>1513528810</td>\n",
       "      <td>Jurassic World</td>\n",
       "      <td>Chris Pratt|Bryce Dallas Howard|Irrfan Khan|Vi...</td>\n",
       "      <td>Colin Trevorrow</td>\n",
       "      <td>monster|dna|tyrannosaurus rex|velociraptor|island</td>\n",
       "      <td>124</td>\n",
       "      <td>Action|Adventure|Science Fiction|Thriller</td>\n",
       "      <td>Universal Studios|Amblin Entertainment|Legenda...</td>\n",
       "      <td>6/9/15</td>\n",
       "      <td>5562</td>\n",
       "      <td>6.5</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  popularity     budget     revenue  original_title  \\\n",
       "0  135397   32.985763  150000000  1513528810  Jurassic World   \n",
       "\n",
       "                                                cast         director  \\\n",
       "0  Chris Pratt|Bryce Dallas Howard|Irrfan Khan|Vi...  Colin Trevorrow   \n",
       "\n",
       "                                            keywords  runtime  \\\n",
       "0  monster|dna|tyrannosaurus rex|velociraptor|island      124   \n",
       "\n",
       "                                      genres  \\\n",
       "0  Action|Adventure|Science Fiction|Thriller   \n",
       "\n",
       "                                production_companies release_date  vote_count  \\\n",
       "0  Universal Studios|Amblin Entertainment|Legenda...       6/9/15        5562   \n",
       "\n",
       "   vote_average  release_year  \n",
       "0           6.5          2015  "
      ]
     },
     "execution_count": 384,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# see if these columns are dropped.\n",
    "df.head(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "** Drop the duplicates.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 385,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Drop the duplicates\n",
    "df.drop_duplicates(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:py3]",
   "language": "python",
   "name": "conda-env-py3-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}