{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import pandas as pd\n",
    "reviews = pd.read_csv(\"https://raw.githubusercontent.com/ra314ra/ml/master/ign.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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>Unnamed: 0</th>\n",
       "      <th>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita</td>\n",
       "      <td>/games/littlebigplanet-vita/vita-98907</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita -- Marvel Super Hero E...</td>\n",
       "      <td>/games/littlebigplanet-ps-vita-marvel-super-he...</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>Great</td>\n",
       "      <td>Splice: Tree of Life</td>\n",
       "      <td>/games/splice/ipad-141070</td>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/xbox-360-128182</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/ps3-128181</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 2,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "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>Unnamed: 0</th>\n",
       "      <th>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita</td>\n",
       "      <td>/games/littlebigplanet-vita/vita-98907</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita -- Marvel Super Hero E...</td>\n",
       "      <td>/games/littlebigplanet-ps-vita-marvel-super-he...</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>Great</td>\n",
       "      <td>Splice: Tree of Life</td>\n",
       "      <td>/games/splice/ipad-141070</td>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/xbox-360-128182</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/ps3-128181</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 4,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.iloc[0:5, :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "reviews = reviews.iloc[:, 1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita</td>\n",
       "      <td>/games/littlebigplanet-vita/vita-98907</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita -- Marvel Super Hero E...</td>\n",
       "      <td>/games/littlebigplanet-ps-vita-marvel-super-he...</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Great</td>\n",
       "      <td>Splice: Tree of Life</td>\n",
       "      <td>/games/splice/ipad-141070</td>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/xbox-360-128182</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/ps3-128181</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 6,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(18625, 10)"
      ]
     },
     "execution_count": 8,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "test_reviews_part1 = reviews.iloc[:,0:2]\n",
    "test_reviews_part2 = reviews.iloc[:,3:]\n",
    "test_reviews_dropped_column = pd.concat([test_reviews_part1, test_reviews_part2], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita -- Marvel Super Hero E...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Great</td>\n",
       "      <td>Splice: Tree of Life</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 18,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_reviews_part1.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "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>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 22,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_reviews_part2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "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>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 23,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_reviews_part2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita -- Marvel Super Hero E...</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Great</td>\n",
       "      <td>Splice: Tree of Life</td>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 25,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_drop_column = reviews.drop(['url'], axis=1)\n",
    "test_drop_column.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Good</td>\n",
       "      <td>Tekken Tag Tournament 2</td>\n",
       "      <td>/games/tekken-tag-tournament-2/ps3-124584</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>7.5</td>\n",
       "      <td>Fighting</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Good</td>\n",
       "      <td>Tekken Tag Tournament 2</td>\n",
       "      <td>/games/tekken-tag-tournament-2/xbox-360-124581</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>7.5</td>\n",
       "      <td>Fighting</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Good</td>\n",
       "      <td>Wild Blood</td>\n",
       "      <td>/games/wild-blood/iphone-139363</td>\n",
       "      <td>iPhone</td>\n",
       "      <td>7.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>Mark of the Ninja</td>\n",
       "      <td>/games/mark-of-the-ninja-135615/xbox-360-129276</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Action, Adventure</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>Mark of the Ninja</td>\n",
       "      <td>/games/mark-of-the-ninja-135615/pc-143761</td>\n",
       "      <td>PC</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Action, Adventure</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 27,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "some_reviews = reviews.loc[10:20,]\n",
    "some_reviews.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Mediocre</td>\n",
       "      <td>Way of the Samurai 4</td>\n",
       "      <td>/games/way-of-the-samurai-4/ps3-23516</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>5.5</td>\n",
       "      <td>Action, Adventure</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Good</td>\n",
       "      <td>JoJo's Bizarre Adventure HD</td>\n",
       "      <td>/games/jojos-bizarre-adventure/xbox-360-137717</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>7.0</td>\n",
       "      <td>Fighting</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Good</td>\n",
       "      <td>JoJo's Bizarre Adventure HD</td>\n",
       "      <td>/games/jojos-bizarre-adventure/ps3-137896</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>7.0</td>\n",
       "      <td>Fighting</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 29,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "some_reviews.loc[18:24,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    9.0\n",
       "1    9.0\n",
       "2    8.5\n",
       "3    8.5\n",
       "4    8.5\n",
       "5    7.0\n",
       "Name: score, dtype: float64"
      ]
     },
     "execution_count": 30,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.loc[:5, \"score\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "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>score</th>\n",
       "      <th>release_year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9.0</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.0</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.5</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>7.0</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 31,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.loc[:5, [\"score\", \"release_year\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 32,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(reviews.loc[:5, [\"score\", \"release_year\"]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "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>score</th>\n",
       "      <th>editors_choice</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>3.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>6.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>6.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>8.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>5.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>8.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>6.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18595</th>\n",
       "      <td>4.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18596</th>\n",
       "      <td>6.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18597</th>\n",
       "      <td>4.9</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18598</th>\n",
       "      <td>6.8</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18599</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18600</th>\n",
       "      <td>7.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18601</th>\n",
       "      <td>7.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18602</th>\n",
       "      <td>7.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18603</th>\n",
       "      <td>7.8</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18604</th>\n",
       "      <td>8.6</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18605</th>\n",
       "      <td>6.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18606</th>\n",
       "      <td>6.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18607</th>\n",
       "      <td>7.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18608</th>\n",
       "      <td>5.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18609</th>\n",
       "      <td>8.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18610</th>\n",
       "      <td>6.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18611</th>\n",
       "      <td>5.8</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18612</th>\n",
       "      <td>7.8</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18613</th>\n",
       "      <td>8.0</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18614</th>\n",
       "      <td>9.2</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18615</th>\n",
       "      <td>9.2</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18616</th>\n",
       "      <td>7.5</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18617</th>\n",
       "      <td>8.4</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18618</th>\n",
       "      <td>9.1</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18619</th>\n",
       "      <td>7.9</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18620</th>\n",
       "      <td>7.6</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18621</th>\n",
       "      <td>9.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18622</th>\n",
       "      <td>5.8</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18623</th>\n",
       "      <td>10.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18624</th>\n",
       "      <td>10.0</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>18625 rows × 2 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 33,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews[[\"score\", \"editors_choice\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6.950459060402666"
      ]
     },
     "execution_count": 35,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews[\"score\"].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        510.500\n",
       "1        510.500\n",
       "2        510.375\n",
       "3        510.125\n",
       "4        510.125\n",
       "5        509.750\n",
       "6        508.750\n",
       "7        510.250\n",
       "8        508.750\n",
       "9        509.750\n",
       "10       509.875\n",
       "11       509.875\n",
       "12       509.500\n",
       "13       509.250\n",
       "14       509.250\n",
       "15       508.375\n",
       "16       508.375\n",
       "17       508.500\n",
       "18       507.375\n",
       "19       507.750\n",
       "20       507.750\n",
       "21       514.625\n",
       "22       514.625\n",
       "23       514.625\n",
       "24       515.000\n",
       "25       514.250\n",
       "26       514.750\n",
       "27       514.125\n",
       "28       514.250\n",
       "29       513.625\n",
       "          ...   \n",
       "18595    510.850\n",
       "18596    510.875\n",
       "18597    510.225\n",
       "18598    510.700\n",
       "18599    510.750\n",
       "18600    512.600\n",
       "18601    512.600\n",
       "18602    512.600\n",
       "18603    512.450\n",
       "18604    512.400\n",
       "18605    511.500\n",
       "18606    508.600\n",
       "18607    510.750\n",
       "18608    510.350\n",
       "18609    510.750\n",
       "18610    510.250\n",
       "18611    508.700\n",
       "18612    509.200\n",
       "18613    508.000\n",
       "18614    515.050\n",
       "18615    515.050\n",
       "18616    508.375\n",
       "18617    508.600\n",
       "18618    515.025\n",
       "18619    514.725\n",
       "18620    514.650\n",
       "18621    515.000\n",
       "18622    513.950\n",
       "18623    515.000\n",
       "18624    515.000\n",
       "Length: 18625, dtype: float64"
      ]
     },
     "execution_count": 36,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.mean(axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "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>score</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>score</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.062716</td>\n",
       "      <td>0.007632</td>\n",
       "      <td>0.020079</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>release_year</th>\n",
       "      <td>0.062716</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.115515</td>\n",
       "      <td>0.016867</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>release_month</th>\n",
       "      <td>0.007632</td>\n",
       "      <td>-0.115515</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.067964</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>release_day</th>\n",
       "      <td>0.020079</td>\n",
       "      <td>0.016867</td>\n",
       "      <td>-0.067964</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 37,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        4.50\n",
       "1        4.50\n",
       "2        4.25\n",
       "3        4.25\n",
       "4        4.25\n",
       "5        3.50\n",
       "6        1.50\n",
       "7        4.50\n",
       "8        1.50\n",
       "9        3.50\n",
       "10       3.75\n",
       "11       3.75\n",
       "12       3.50\n",
       "13       4.50\n",
       "14       4.50\n",
       "15       3.25\n",
       "16       3.25\n",
       "17       4.00\n",
       "18       2.75\n",
       "19       3.50\n",
       "20       3.50\n",
       "21       3.75\n",
       "22       3.75\n",
       "23       3.75\n",
       "24       4.50\n",
       "25       3.50\n",
       "26       4.50\n",
       "27       3.75\n",
       "28       4.00\n",
       "29       3.25\n",
       "         ... \n",
       "18595    2.20\n",
       "18596    3.25\n",
       "18597    2.45\n",
       "18598    3.40\n",
       "18599    3.50\n",
       "18600    3.70\n",
       "18601    3.70\n",
       "18602    3.70\n",
       "18603    3.90\n",
       "18604    4.30\n",
       "18605    3.00\n",
       "18606    3.20\n",
       "18607    3.50\n",
       "18608    2.70\n",
       "18609    4.00\n",
       "18610    3.00\n",
       "18611    2.90\n",
       "18612    3.90\n",
       "18613    4.00\n",
       "18614    4.60\n",
       "18615    4.60\n",
       "18616    3.75\n",
       "18617    4.20\n",
       "18618    4.55\n",
       "18619    3.95\n",
       "18620    3.80\n",
       "18621    4.50\n",
       "18622    2.90\n",
       "18623    5.00\n",
       "18624    5.00\n",
       "Name: score, Length: 18625, dtype: float64"
      ]
     },
     "execution_count": 39,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews[\"score\"] /2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0         True\n",
       "1         True\n",
       "2         True\n",
       "3         True\n",
       "4         True\n",
       "5        False\n",
       "6        False\n",
       "7         True\n",
       "8        False\n",
       "9        False\n",
       "10        True\n",
       "11        True\n",
       "12       False\n",
       "13        True\n",
       "14        True\n",
       "15       False\n",
       "16       False\n",
       "17        True\n",
       "18       False\n",
       "19       False\n",
       "20       False\n",
       "21        True\n",
       "22        True\n",
       "23        True\n",
       "24        True\n",
       "25       False\n",
       "26        True\n",
       "27        True\n",
       "28        True\n",
       "29       False\n",
       "         ...  \n",
       "18595    False\n",
       "18596    False\n",
       "18597    False\n",
       "18598    False\n",
       "18599    False\n",
       "18600     True\n",
       "18601     True\n",
       "18602     True\n",
       "18603     True\n",
       "18604     True\n",
       "18605    False\n",
       "18606    False\n",
       "18607    False\n",
       "18608    False\n",
       "18609     True\n",
       "18610    False\n",
       "18611    False\n",
       "18612     True\n",
       "18613     True\n",
       "18614     True\n",
       "18615     True\n",
       "18616     True\n",
       "18617     True\n",
       "18618     True\n",
       "18619     True\n",
       "18620     True\n",
       "18621     True\n",
       "18622    False\n",
       "18623     True\n",
       "18624     True\n",
       "Name: score, Length: 18625, dtype: bool"
      ]
     },
     "execution_count": 40,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score_filter = reviews[\"score\"] > 7\n",
    "score_filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita</td>\n",
       "      <td>/games/littlebigplanet-vita/vita-98907</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LittleBigPlanet PS Vita -- Marvel Super Hero E...</td>\n",
       "      <td>/games/littlebigplanet-ps-vita-marvel-super-he...</td>\n",
       "      <td>PlayStation Vita</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Great</td>\n",
       "      <td>Splice: Tree of Life</td>\n",
       "      <td>/games/splice/ipad-141070</td>\n",
       "      <td>iPad</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Puzzle</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/xbox-360-128182</td>\n",
       "      <td>Xbox 360</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Great</td>\n",
       "      <td>NHL 13</td>\n",
       "      <td>/games/nhl-13/ps3-128181</td>\n",
       "      <td>PlayStation 3</td>\n",
       "      <td>8.5</td>\n",
       "      <td>Sports</td>\n",
       "      <td>N</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 42,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_reviews = reviews.loc[score_filter].copy()\n",
    "filtered_reviews.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        1.0\n",
       "1        1.0\n",
       "2        1.0\n",
       "3        1.0\n",
       "4        1.0\n",
       "5        1.0\n",
       "6        1.0\n",
       "7        1.0\n",
       "8        1.0\n",
       "9        1.0\n",
       "10       1.0\n",
       "11       1.0\n",
       "12       1.0\n",
       "13       1.0\n",
       "14       1.0\n",
       "15       1.0\n",
       "16       1.0\n",
       "17       1.0\n",
       "18       1.0\n",
       "19       1.0\n",
       "20       1.0\n",
       "21       1.0\n",
       "22       1.0\n",
       "23       1.0\n",
       "24       1.0\n",
       "25       1.0\n",
       "26       1.0\n",
       "27       1.0\n",
       "28       1.0\n",
       "29       1.0\n",
       "        ... \n",
       "18595    1.0\n",
       "18596    1.0\n",
       "18597    1.0\n",
       "18598    1.0\n",
       "18599    1.0\n",
       "18600    1.0\n",
       "18601    1.0\n",
       "18602    1.0\n",
       "18603    1.0\n",
       "18604    1.0\n",
       "18605    1.0\n",
       "18606    1.0\n",
       "18607    1.0\n",
       "18608    1.0\n",
       "18609    1.0\n",
       "18610    1.0\n",
       "18611    1.0\n",
       "18612    1.0\n",
       "18613    1.0\n",
       "18614    1.0\n",
       "18615    1.0\n",
       "18616    1.0\n",
       "18617    1.0\n",
       "18618    1.0\n",
       "18619    1.0\n",
       "18620    1.0\n",
       "18621    1.0\n",
       "18622    1.0\n",
       "18623    1.0\n",
       "18624    1.0\n",
       "Name: score, Length: 18625, dtype: float64"
      ]
     },
     "execution_count": 44,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews[\"score\"].divide(reviews[\"score\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": false
   },
   "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>score_phrase</th>\n",
       "      <th>title</th>\n",
       "      <th>url</th>\n",
       "      <th>platform</th>\n",
       "      <th>score</th>\n",
       "      <th>genre</th>\n",
       "      <th>editors_choice</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17137</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>Gone Home</td>\n",
       "      <td>/games/gone-home/xbox-one-20014361</td>\n",
       "      <td>Xbox One</td>\n",
       "      <td>9.5</td>\n",
       "      <td>Simulation</td>\n",
       "      <td>Y</td>\n",
       "      <td>2013</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17197</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>Rayman Legends</td>\n",
       "      <td>/games/rayman-legends/xbox-one-20008449</td>\n",
       "      <td>Xbox One</td>\n",
       "      <td>9.5</td>\n",
       "      <td>Platformer</td>\n",
       "      <td>Y</td>\n",
       "      <td>2013</td>\n",
       "      <td>8</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17295</th>\n",
       "      <td>Amazing</td>\n",
       "      <td>LEGO Marvel Super Heroes</td>\n",
       "      <td>/games/lego-marvel-super-heroes/xbox-one-20000826</td>\n",
       "      <td>Xbox One</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Action</td>\n",
       "      <td>Y</td>\n",
       "      <td>2013</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17313</th>\n",
       "      <td>Great</td>\n",
       "      <td>Dead Rising 3</td>\n",
       "      <td>/games/dead-rising-3/xbox-one-124306</td>\n",
       "      <td>Xbox One</td>\n",
       "      <td>8.3</td>\n",
       "      <td>Action</td>\n",
       "      <td>N</td>\n",
       "      <td>2013</td>\n",
       "      <td>11</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17317</th>\n",
       "      <td>Great</td>\n",
       "      <td>Killer Instinct</td>\n",
       "      <td>/games/killer-instinct-2013/xbox-one-20000538</td>\n",
       "      <td>Xbox One</td>\n",
       "      <td>8.4</td>\n",
       "      <td>Fighting</td>\n",
       "      <td>N</td>\n",
       "      <td>2013</td>\n",
       "      <td>11</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 45,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xbox_one_filter = (reviews[\"score\"] > 7) & (reviews[\"platform\"] == \"Xbox One\")\n",
    "filtered_reviews = reviews[xbox_one_filter]\n",
    "filtered_reviews.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f80f7b5e3c8>"
      ]
     },
     "execution_count": 46,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "c7f4a0aa9195c0217e4f6b43cfad50b1ac288090"
     },
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 384
      }
     }
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "reviews[reviews[\"platform\"] == \"Xbox One\"][\"score\"].plot(kind=\"hist\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f80f7b710f0>"
      ]
     },
     "execution_count": 47,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "6eb8b80c69eb2b4d2fd3ae67cdc84e756871044d"
     },
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 384
      }
     }
    }
   ],
   "source": [
    "reviews[reviews[\"platform\"] == \"PlayStation 4\"][\"score\"].plot(kind=\"hist\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false
   },
   "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>score</th>\n",
       "      <th>release_year</th>\n",
       "      <th>release_month</th>\n",
       "      <th>release_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>18625.000000</td>\n",
       "      <td>18625.000000</td>\n",
       "      <td>18625.00000</td>\n",
       "      <td>18625.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>6.950459</td>\n",
       "      <td>2006.515329</td>\n",
       "      <td>7.13847</td>\n",
       "      <td>15.603866</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.711736</td>\n",
       "      <td>4.587529</td>\n",
       "      <td>3.47671</td>\n",
       "      <td>8.690128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.500000</td>\n",
       "      <td>1970.000000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>2003.000000</td>\n",
       "      <td>4.00000</td>\n",
       "      <td>8.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>7.300000</td>\n",
       "      <td>2007.000000</td>\n",
       "      <td>8.00000</td>\n",
       "      <td>16.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.200000</td>\n",
       "      <td>2010.000000</td>\n",
       "      <td>10.00000</td>\n",
       "      <td>23.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>2016.000000</td>\n",
       "      <td>12.00000</td>\n",
       "      <td>31.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 48,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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>RespondentID</th>\n",
       "      <th>Do you celebrate Thanksgiving?</th>\n",
       "      <th>What is typically the main dish at your Thanksgiving dinner?</th>\n",
       "      <th>What is typically the main dish at your Thanksgiving dinner? - Other (please specify)</th>\n",
       "      <th>How is the main dish typically cooked?</th>\n",
       "      <th>How is the main dish typically cooked? - Other (please specify)</th>\n",
       "      <th>What kind of stuffing/dressing do you typically have?</th>\n",
       "      <th>What kind of stuffing/dressing do you typically have? - Other (please specify)</th>\n",
       "      <th>What type of cranberry saucedo you typically have?</th>\n",
       "      <th>What type of cranberry saucedo you typically have? - Other (please specify)</th>\n",
       "      <th>...</th>\n",
       "      <th>Have you ever tried to meet up with hometown friends on Thanksgiving night?</th>\n",
       "      <th>Have you ever attended a \"Friendsgiving?\"</th>\n",
       "      <th>Will you shop any Black Friday sales on Thanksgiving Day?</th>\n",
       "      <th>Do you work in retail?</th>\n",
       "      <th>Will you employer make you work on Black Friday?</th>\n",
       "      <th>How would you describe where you live?</th>\n",
       "      <th>Age</th>\n",
       "      <th>What is your gender?</th>\n",
       "      <th>How much total combined money did all members of your HOUSEHOLD earn last year?</th>\n",
       "      <th>US Region</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4337954960</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Turkey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Baked</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bread-based</td>\n",
       "      <td>NaN</td>\n",
       "      <td>None</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>18 - 29</td>\n",
       "      <td>Male</td>\n",
       "      <td>$75,000 to $99,999</td>\n",
       "      <td>Middle Atlantic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4337951949</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Turkey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Baked</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bread-based</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Other (please specify)</td>\n",
       "      <td>Homemade cranberry gelatin ring</td>\n",
       "      <td>...</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Rural</td>\n",
       "      <td>18 - 29</td>\n",
       "      <td>Female</td>\n",
       "      <td>$50,000 to $74,999</td>\n",
       "      <td>East South Central</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4337935621</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Turkey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Roasted</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Rice-based</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Homemade</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>18 - 29</td>\n",
       "      <td>Male</td>\n",
       "      <td>$0 to $9,999</td>\n",
       "      <td>Mountain</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4337933040</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Turkey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Baked</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bread-based</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Homemade</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Urban</td>\n",
       "      <td>30 - 44</td>\n",
       "      <td>Male</td>\n",
       "      <td>$200,000 and up</td>\n",
       "      <td>Pacific</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4337931983</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Tofurkey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Baked</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bread-based</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Canned</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Urban</td>\n",
       "      <td>30 - 44</td>\n",
       "      <td>Male</td>\n",
       "      <td>$100,000 to $124,999</td>\n",
       "      <td>Pacific</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 65 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 50,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv(\"https://raw.githubusercontent.com/ra314ra/ml/master/thanksgiving-2015-poll-data.csv\", encoding = 'latin-1')\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1058, 65)"
      ]
     },
     "execution_count": 51,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Yes', 'No'], dtype=object)"
      ]
     },
     "execution_count": 52,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"Do you celebrate Thanksgiving?\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Which of these desserts do you typically have at Thanksgiving dinner? Please select all that apply.   - Other (please specify).1',\n",
       "       'Do you typically pray before or after the Thanksgiving meal?',\n",
       "       'How far will you travel for Thanksgiving?',\n",
       "       'Will you watch any of the following programs on Thanksgiving? Please select all that apply. - Macy's Parade',\n",
       "       'What's the age cutoff at your \"kids' table\" at Thanksgiving?',\n",
       "       'Have you ever tried to meet up with hometown friends on Thanksgiving night?',\n",
       "       'Have you ever attended a \"Friendsgiving?\"',\n",
       "       'Will you shop any Black Friday sales on Thanksgiving Day?',\n",
       "       'Do you work in retail?',\n",
       "       'Will you employer make you work on Black Friday?',\n",
       "       'How would you describe where you live?', 'Age', 'What is your gender?',\n",
       "       'How much total combined money did all members of your HOUSEHOLD earn last year?',\n",
       "       'US Region'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 53,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.columns[50:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Female    544\n",
       "Male      481\n",
       "NaN        33\n",
       "Name: What is your gender?, dtype: int64"
      ]
     },
     "execution_count": 54,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"What is your gender?\"].value_counts(dropna=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import math\n",
    "\n",
    "def gender_code(gender_string):\n",
    "    if isinstance(gender_string, float) and math.isnan(gender_string):\n",
    "        return gender_string\n",
    "    return int(gender_string == \"Female\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       " 1.0    544\n",
       " 0.0    481\n",
       "NaN      33\n",
       "Name: gender, dtype: int64"
      ]
     },
     "execution_count": 56,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"gender\"] = data[\"What is your gender?\"].apply(gender_code)\n",
    "data[\"gender\"].value_counts(dropna=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RespondentID                                                                             object\n",
       "Do you celebrate Thanksgiving?                                                           object\n",
       "What is typically the main dish at your Thanksgiving dinner?                             object\n",
       "What is typically the main dish at your Thanksgiving dinner? - Other (please specify)    object\n",
       "How is the main dish typically cooked?                                                   object\n",
       "dtype: object"
      ]
     },
     "execution_count": 58,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.apply(lambda x: x.dtype).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "$25,000 to $49,999      180\n",
       "Prefer not to answer    136\n",
       "$50,000 to $74,999      135\n",
       "$75,000 to $99,999      133\n",
       "$100,000 to $124,999    111\n",
       "$200,000 and up          80\n",
       "$10,000 to $24,999       68\n",
       "$0 to $9,999             66\n",
       "$125,000 to $149,999     49\n",
       "$150,000 to $174,999     40\n",
       "NaN                      33\n",
       "$175,000 to $199,999     27\n",
       "Name: How much total combined money did all members of your HOUSEHOLD earn last year?, dtype: int64"
      ]
     },
     "execution_count": 59,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"How much total combined money did all members of your HOUSEHOLD earn last year?\"].value_counts(dropna=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "def clean_income(value):\n",
    "    if value == \"$200,000 and up\":\n",
    "        return 200000\n",
    "    elif value == \"Prefer not to answer\":\n",
    "        return np.nan\n",
    "    elif isinstance(value, float) and math.isnan(value):\n",
    "        return np.nan\n",
    "    value = value.replace(\",\", \"\").replace(\"$\", \"\")\n",
    "    income_high, income_low = value.split(\" to \")\n",
    "    return (int(income_high) + int(income_low)) / 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     87499.5\n",
       "1     62499.5\n",
       "2      4999.5\n",
       "3    200000.0\n",
       "4    112499.5\n",
       "Name: income, dtype: float64"
      ]
     },
     "execution_count": 61,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"income\"] = data[\"How much total combined money did all members of your HOUSEHOLD earn last year?\"].apply(clean_income)\n",
    "data[\"income\"].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       " 37499.5     180\n",
       "NaN          169\n",
       " 62499.5     135\n",
       " 87499.5     133\n",
       " 112499.5    111\n",
       " 200000.0     80\n",
       " 17499.5      68\n",
       " 4999.5       66\n",
       " 137499.5     49\n",
       " 162499.5     40\n",
       " 187499.5     27\n",
       "Name: income, dtype: int64"
      ]
     },
     "execution_count": 62,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"income\"].value_counts(dropna=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Canned                    502\n",
       "Homemade                  301\n",
       "None                      146\n",
       "Other (please specify)     25\n",
       "Name: What type of cranberry saucedo you typically have?, dtype: int64"
      ]
     },
     "execution_count": 63,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[\"What type of cranberry saucedo you typically have?\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "homemade = data[data[\"What type of cranberry saucedo you typically have?\"] == \"Homemade\"]\n",
    "canned = data[data[\"What type of cranberry saucedo you typically have?\"] == \"Canned\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "94878.1072874494\n",
      "83823.40340909091\n"
     ]
    }
   ],
   "source": [
    "print(homemade[\"income\"].mean())\n",
    "print(canned[\"income\"].mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<pandas.core.groupby.DataFrameGroupBy object at 0x7f80f678bd30>"
      ]
     },
     "execution_count": 66,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped = data.groupby(\"What type of cranberry saucedo you typically have?\")\n",
    "grouped"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Canned': Int64Index([   4,    6,    8,   11,   12,   15,   18,   19,   26,   27,\n",
       "             ...\n",
       "             1040, 1041, 1042, 1044, 1045, 1046, 1047, 1051, 1054, 1057],\n",
       "            dtype='int64', length=502),\n",
       " 'Homemade': Int64Index([   2,    3,    5,    7,   13,   14,   16,   20,   21,   23,\n",
       "             ...\n",
       "             1016, 1017, 1025, 1027, 1030, 1034, 1048, 1049, 1053, 1056],\n",
       "            dtype='int64', length=301),\n",
       " 'None': Int64Index([   0,   17,   24,   29,   34,   36,   40,   47,   49,   51,\n",
       "             ...\n",
       "              980,  981,  997, 1015, 1018, 1031, 1037, 1043, 1050, 1055],\n",
       "            dtype='int64', length=146),\n",
       " 'Other (please specify)': Int64Index([   1,    9,  154,  216,  221,  233,  249,  265,  301,  336,  380,\n",
       "              435,  444,  447,  513,  550,  749,  750,  784,  807,  860,  872,\n",
       "              905, 1000, 1007],\n",
       "            dtype='int64')}"
      ]
     },
     "execution_count": 67,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "What type of cranberry saucedo you typically have?\n",
       "Canned                    502\n",
       "Homemade                  301\n",
       "None                      146\n",
       "Other (please specify)     25\n",
       "dtype: int64"
      ]
     },
     "execution_count": 68,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "What type of cranberry saucedo you typically have?\n",
       "Canned                    83823.403409\n",
       "Homemade                  94878.107287\n",
       "None                      78886.084034\n",
       "Other (please specify)    86629.978261\n",
       "Name: income, dtype: float64"
      ]
     },
     "execution_count": 69,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped[\"income\"].agg(np.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "collapsed": false
   },
   "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>RespondentID</th>\n",
       "      <th>gender</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>What type of cranberry saucedo you typically have?</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Canned</th>\n",
       "      <td>4.336699e+09</td>\n",
       "      <td>0.552846</td>\n",
       "      <td>83823.403409</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Homemade</th>\n",
       "      <td>4.336792e+09</td>\n",
       "      <td>0.533101</td>\n",
       "      <td>94878.107287</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>None</th>\n",
       "      <td>4.336765e+09</td>\n",
       "      <td>0.517483</td>\n",
       "      <td>78886.084034</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other (please specify)</th>\n",
       "      <td>4.336763e+09</td>\n",
       "      <td>0.640000</td>\n",
       "      <td>86629.978261</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 70,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.agg(np.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f80f6713630>"
      ]
     },
     "execution_count": 71,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "8bf1c38f22f20f81ebe8d3e3dd5526f5bf742ec1"
     },
     "metadata": {
      "image/png": {
       "height": 365,
       "width": 390
      }
     }
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "sauce = grouped.agg(np.mean)\n",
    "sauce[\"income\"].plot(kind=\"bar\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "collapsed": false
   },
   "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></th>\n",
       "      <th>RespondentID</th>\n",
       "      <th>gender</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>What type of cranberry saucedo you typically have?</th>\n",
       "      <th>What is typically the main dish at your Thanksgiving dinner?</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"7\" valign=\"top\">Canned</th>\n",
       "      <th>Chicken</th>\n",
       "      <td>4.336354e+09</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>80999.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ham/Pork</th>\n",
       "      <td>4.336757e+09</td>\n",
       "      <td>0.642857</td>\n",
       "      <td>77499.535714</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>I don't know</th>\n",
       "      <td>4.335987e+09</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>4999.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other (please specify)</th>\n",
       "      <td>4.336682e+09</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>53213.785714</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Roast beef</th>\n",
       "      <td>4.336254e+09</td>\n",
       "      <td>0.571429</td>\n",
       "      <td>25499.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tofurkey</th>\n",
       "      <td>4.337157e+09</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>100713.857143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turkey</th>\n",
       "      <td>4.336705e+09</td>\n",
       "      <td>0.544444</td>\n",
       "      <td>85242.682045</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">Homemade</th>\n",
       "      <th>Chicken</th>\n",
       "      <td>4.336540e+09</td>\n",
       "      <td>0.750000</td>\n",
       "      <td>19999.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ham/Pork</th>\n",
       "      <td>4.337253e+09</td>\n",
       "      <td>0.250000</td>\n",
       "      <td>96874.625000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>I don't know</th>\n",
       "      <td>4.336084e+09</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other (please specify)</th>\n",
       "      <td>4.336863e+09</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>55356.642857</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Roast beef</th>\n",
       "      <td>4.336174e+09</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>33749.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tofurkey</th>\n",
       "      <td>4.336790e+09</td>\n",
       "      <td>0.666667</td>\n",
       "      <td>57916.166667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turducken</th>\n",
       "      <td>4.337475e+09</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>200000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turkey</th>\n",
       "      <td>4.336791e+09</td>\n",
       "      <td>0.531008</td>\n",
       "      <td>97690.147982</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">None</th>\n",
       "      <th>Chicken</th>\n",
       "      <td>4.336151e+09</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>11249.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ham/Pork</th>\n",
       "      <td>4.336680e+09</td>\n",
       "      <td>0.444444</td>\n",
       "      <td>61249.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>I don't know</th>\n",
       "      <td>4.336412e+09</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>33749.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other (please specify)</th>\n",
       "      <td>4.336688e+09</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>119106.678571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Roast beef</th>\n",
       "      <td>4.337424e+09</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>162499.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tofurkey</th>\n",
       "      <td>4.336950e+09</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>112499.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turducken</th>\n",
       "      <td>4.336739e+09</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turkey</th>\n",
       "      <td>4.336784e+09</td>\n",
       "      <td>0.523364</td>\n",
       "      <td>74606.275281</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">Other (please specify)</th>\n",
       "      <th>Ham/Pork</th>\n",
       "      <td>4.336465e+09</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>87499.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other (please specify)</th>\n",
       "      <td>4.337335e+09</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>124999.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tofurkey</th>\n",
       "      <td>4.336122e+09</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>37499.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turkey</th>\n",
       "      <td>4.336724e+09</td>\n",
       "      <td>0.700000</td>\n",
       "      <td>82916.194444</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 72,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped = data.groupby([\"What type of cranberry saucedo you typically have?\", \"What is typically the main dish at your Thanksgiving dinner?\"])\n",
    "grouped.agg(np.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "collapsed": false
   },
   "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></th>\n",
       "      <th>mean</th>\n",
       "      <th>sum</th>\n",
       "      <th>std</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>What type of cranberry saucedo you typically have?</th>\n",
       "      <th>What is typically the main dish at your Thanksgiving dinner?</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"7\" valign=\"top\">Canned</th>\n",
       "      <th>Chicken</th>\n",
       "      <td>80999.600000</td>\n",
       "      <td>404998.0</td>\n",
       "      <td>75779.481062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ham/Pork</th>\n",
       "      <td>77499.535714</td>\n",
       "      <td>1084993.5</td>\n",
       "      <td>56645.063944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>I don't know</th>\n",
       "      <td>4999.500000</td>\n",
       "      <td>4999.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other (please specify)</th>\n",
       "      <td>53213.785714</td>\n",
       "      <td>372496.5</td>\n",
       "      <td>29780.946290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Roast beef</th>\n",
       "      <td>25499.500000</td>\n",
       "      <td>127497.5</td>\n",
       "      <td>24584.039538</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tofurkey</th>\n",
       "      <td>100713.857143</td>\n",
       "      <td>704997.0</td>\n",
       "      <td>61351.484439</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turkey</th>\n",
       "      <td>85242.682045</td>\n",
       "      <td>34182315.5</td>\n",
       "      <td>55687.436102</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">Homemade</th>\n",
       "      <th>Chicken</th>\n",
       "      <td>19999.500000</td>\n",
       "      <td>59998.5</td>\n",
       "      <td>16393.596311</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ham/Pork</th>\n",
       "      <td>96874.625000</td>\n",
       "      <td>387498.5</td>\n",
       "      <td>77308.452805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>I don't know</th>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 73,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped[\"income\"].agg([np.mean, np.sum, np.std]).head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "What type of cranberry saucedo you typically have?  What is typically the main dish at your Thanksgiving dinner?\n",
       "Canned                                              Chicken                                                           6\n",
       "                                                    Ham/Pork                                                         15\n",
       "                                                    I don't know                                                      2\n",
       "                                                    Other (please specify)                                            7\n",
       "                                                    Roast beef                                                        7\n",
       "                                                    Tofurkey                                                          7\n",
       "                                                    Turkey                                                          458\n",
       "Homemade                                            Chicken                                                           4\n",
       "                                                    Ham/Pork                                                          4\n",
       "                                                    I don't know                                                      1\n",
       "                                                    Other (please specify)                                           10\n",
       "                                                    Roast beef                                                        3\n",
       "                                                    Tofurkey                                                          6\n",
       "                                                    Turducken                                                         2\n",
       "                                                    Turkey                                                          271\n",
       "None                                                Chicken                                                           2\n",
       "                                                    Ham/Pork                                                          9\n",
       "                                                    I don't know                                                      2\n",
       "                                                    Other (please specify)                                           15\n",
       "                                                    Roast beef                                                        1\n",
       "                                                    Tofurkey                                                          6\n",
       "                                                    Turducken                                                         1\n",
       "                                                    Turkey                                                          110\n",
       "Other (please specify)                              Ham/Pork                                                          1\n",
       "                                                    Other (please specify)                                            3\n",
       "                                                    Tofurkey                                                          1\n",
       "                                                    Turkey                                                           20\n",
       "dtype: int64"
      ]
     },
     "execution_count": 74,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "How would you describe where you live?\n",
       "Rural       216\n",
       "Suburban    496\n",
       "Urban       236\n",
       "Name: What is typically the main dish at your Thanksgiving dinner?, dtype: int64"
      ]
     },
     "execution_count": 75,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped = data.groupby(\"How would you describe where you live?\")[\"What is typically the main dish at your Thanksgiving dinner?\"]\n",
    "grouped.size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "How would you describe where you live?                        \n",
       "Rural                                   Turkey                    189\n",
       "                                        Other (please specify)      9\n",
       "                                        Ham/Pork                    7\n",
       "                                        I don't know                3\n",
       "                                        Tofurkey                    3\n",
       "                                        Turducken                   2\n",
       "                                        Chicken                     2\n",
       "                                        Roast beef                  1\n",
       "Suburban                                Turkey                    449\n",
       "                                        Ham/Pork                   17\n",
       "                                        Other (please specify)     13\n",
       "                                        Tofurkey                    9\n",
       "                                        Roast beef                  3\n",
       "                                        Chicken                     3\n",
       "                                        Turducken                   1\n",
       "                                        I don't know                1\n",
       "Urban                                   Turkey                    198\n",
       "                                        Other (please specify)     13\n",
       "                                        Tofurkey                    8\n",
       "                                        Chicken                     7\n",
       "                                        Roast beef                  6\n",
       "                                        Ham/Pork                    4\n",
       "Name: What is typically the main dish at your Thanksgiving dinner?, dtype: int64"
      ]
     },
     "execution_count": 76,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.apply(lambda x:x.value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (Anaconda)",
   "language": "python",
   "name": "anaconda3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}