5_Groupby.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>.container { width:90% !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "##Some code to run at the beginning of the file, to be able to show images in the notebook\n",
    "##Don't worry about this cell\n",
    "\n",
    "#Print the plots in this screen\n",
    "%matplotlib inline \n",
    "\n",
    "#Be able to plot images saved in the hard drive\n",
    "from IPython.display import Image \n",
    "\n",
    "#Make the notebook wider\n",
    "from IPython.core.display import display, HTML \n",
    "display(HTML(\"<style>.container { width:90% !important; }</style>\"))\n",
    "\n",
    "import seaborn as sns\n",
    "import pylab as plt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Before starting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"./data/cities_cleaned.tsv\",sep=\"\\t\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Metropolitan areas      object\n",
       "Year                     int64\n",
       "CO2_PC                 float64\n",
       "GDP_PC                 float64\n",
       "GREEN_AREA_PC          float64\n",
       "LABOUR_PRODUCTIVITY    float64\n",
       "UNEMP_R                float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4650, 7)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Metropolitan areas', 'Year', 'CO2_PC', 'GDP_PC', 'GREEN_AREA_PC',\n",
       "       'LABOUR_PRODUCTIVITY', 'UNEMP_R'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Metropolitan areas</th>\n",
       "      <th>Year</th>\n",
       "      <th>CO2_PC</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>GREEN_AREA_PC</th>\n",
       "      <th>LABOUR_PRODUCTIVITY</th>\n",
       "      <th>UNEMP_R</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2000</td>\n",
       "      <td>12.77</td>\n",
       "      <td>45434.48</td>\n",
       "      <td>255.17</td>\n",
       "      <td>94254.60</td>\n",
       "      <td>4.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2001</td>\n",
       "      <td>NaN</td>\n",
       "      <td>45479.15</td>\n",
       "      <td>252.68</td>\n",
       "      <td>94805.82</td>\n",
       "      <td>4.83</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2002</td>\n",
       "      <td>NaN</td>\n",
       "      <td>46065.50</td>\n",
       "      <td>250.22</td>\n",
       "      <td>100463.10</td>\n",
       "      <td>5.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2003</td>\n",
       "      <td>NaN</td>\n",
       "      <td>45470.92</td>\n",
       "      <td>247.77</td>\n",
       "      <td>97851.61</td>\n",
       "      <td>6.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2004</td>\n",
       "      <td>NaN</td>\n",
       "      <td>46148.38</td>\n",
       "      <td>245.34</td>\n",
       "      <td>102259.13</td>\n",
       "      <td>7.20</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Metropolitan areas  Year  CO2_PC    GDP_PC  GREEN_AREA_PC  \\\n",
       "0             Vienna  2000   12.77  45434.48         255.17   \n",
       "1             Vienna  2001     NaN  45479.15         252.68   \n",
       "2             Vienna  2002     NaN  46065.50         250.22   \n",
       "3             Vienna  2003     NaN  45470.92         247.77   \n",
       "4             Vienna  2004     NaN  46148.38         245.34   \n",
       "\n",
       "   LABOUR_PRODUCTIVITY  UNEMP_R  \n",
       "0             94254.60     4.77  \n",
       "1             94805.82     4.83  \n",
       "2            100463.10     5.82  \n",
       "3             97851.61     6.24  \n",
       "4            102259.13     7.20  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Metropolitan areas</th>\n",
       "      <th>Year</th>\n",
       "      <th>CO2_PC</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>GREEN_AREA_PC</th>\n",
       "      <th>LABOUR_PRODUCTIVITY</th>\n",
       "      <th>UNEMP_R</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2000</td>\n",
       "      <td>12.77</td>\n",
       "      <td>45434.48</td>\n",
       "      <td>255.17</td>\n",
       "      <td>94254.60</td>\n",
       "      <td>4.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2005</td>\n",
       "      <td>15.42</td>\n",
       "      <td>46327.07</td>\n",
       "      <td>242.92</td>\n",
       "      <td>102121.39</td>\n",
       "      <td>7.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Vienna</td>\n",
       "      <td>2008</td>\n",
       "      <td>14.23</td>\n",
       "      <td>48755.43</td>\n",
       "      <td>235.79</td>\n",
       "      <td>102134.84</td>\n",
       "      <td>5.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Graz</td>\n",
       "      <td>2000</td>\n",
       "      <td>10.23</td>\n",
       "      <td>38661.86</td>\n",
       "      <td>997.39</td>\n",
       "      <td>82440.05</td>\n",
       "      <td>3.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Graz</td>\n",
       "      <td>2005</td>\n",
       "      <td>11.99</td>\n",
       "      <td>41570.98</td>\n",
       "      <td>951.75</td>\n",
       "      <td>86716.61</td>\n",
       "      <td>4.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4598</th>\n",
       "      <td>Tampa</td>\n",
       "      <td>2008</td>\n",
       "      <td>18.19</td>\n",
       "      <td>55829.92</td>\n",
       "      <td>481.46</td>\n",
       "      <td>117411.16</td>\n",
       "      <td>6.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4610</th>\n",
       "      <td>Miami</td>\n",
       "      <td>2005</td>\n",
       "      <td>15.36</td>\n",
       "      <td>50872.67</td>\n",
       "      <td>154.99</td>\n",
       "      <td>104816.19</td>\n",
       "      <td>4.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4613</th>\n",
       "      <td>Miami</td>\n",
       "      <td>2008</td>\n",
       "      <td>14.47</td>\n",
       "      <td>49435.87</td>\n",
       "      <td>150.16</td>\n",
       "      <td>99799.52</td>\n",
       "      <td>6.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4625</th>\n",
       "      <td>Mcallen</td>\n",
       "      <td>2005</td>\n",
       "      <td>9.77</td>\n",
       "      <td>18603.91</td>\n",
       "      <td>163.20</td>\n",
       "      <td>51357.97</td>\n",
       "      <td>7.87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4628</th>\n",
       "      <td>Mcallen</td>\n",
       "      <td>2008</td>\n",
       "      <td>8.33</td>\n",
       "      <td>19007.76</td>\n",
       "      <td>148.80</td>\n",
       "      <td>52943.61</td>\n",
       "      <td>7.31</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>666 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Metropolitan areas  Year  CO2_PC    GDP_PC  GREEN_AREA_PC  \\\n",
       "0                Vienna  2000   12.77  45434.48         255.17   \n",
       "5                Vienna  2005   15.42  46327.07         242.92   \n",
       "8                Vienna  2008   14.23  48755.43         235.79   \n",
       "15                 Graz  2000   10.23  38661.86         997.39   \n",
       "20                 Graz  2005   11.99  41570.98         951.75   \n",
       "...                 ...   ...     ...       ...            ...   \n",
       "4598              Tampa  2008   18.19  55829.92         481.46   \n",
       "4610              Miami  2005   15.36  50872.67         154.99   \n",
       "4613              Miami  2008   14.47  49435.87         150.16   \n",
       "4625            Mcallen  2005    9.77  18603.91         163.20   \n",
       "4628            Mcallen  2008    8.33  19007.76         148.80   \n",
       "\n",
       "      LABOUR_PRODUCTIVITY  UNEMP_R  \n",
       "0                94254.60     4.77  \n",
       "5               102121.39     7.37  \n",
       "8               102134.84     5.51  \n",
       "15               82440.05     3.06  \n",
       "20               86716.61     4.20  \n",
       "...                   ...      ...  \n",
       "4598            117411.16     6.33  \n",
       "4610            104816.19     4.17  \n",
       "4613             99799.52     6.00  \n",
       "4625             51357.97     7.87  \n",
       "4628             52943.61     7.31  \n",
       "\n",
       "[666 rows x 7 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Year</th>\n",
       "      <th>CO2_PC</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>GREEN_AREA_PC</th>\n",
       "      <th>LABOUR_PRODUCTIVITY</th>\n",
       "      <th>UNEMP_R</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4650.000000</td>\n",
       "      <td>930.000000</td>\n",
       "      <td>3974.000000</td>\n",
       "      <td>4215.000000</td>\n",
       "      <td>3934.000000</td>\n",
       "      <td>4570.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2007.000000</td>\n",
       "      <td>10.551398</td>\n",
       "      <td>37756.897725</td>\n",
       "      <td>539.565848</td>\n",
       "      <td>81455.477692</td>\n",
       "      <td>6.703803</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>4.320958</td>\n",
       "      <td>7.323933</td>\n",
       "      <td>14803.840039</td>\n",
       "      <td>962.157729</td>\n",
       "      <td>28481.251453</td>\n",
       "      <td>4.085292</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2000.000000</td>\n",
       "      <td>0.700000</td>\n",
       "      <td>6049.830000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>16301.610000</td>\n",
       "      <td>0.240000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2003.000000</td>\n",
       "      <td>5.260000</td>\n",
       "      <td>28277.207500</td>\n",
       "      <td>40.470000</td>\n",
       "      <td>62993.030000</td>\n",
       "      <td>4.120000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2007.000000</td>\n",
       "      <td>8.450000</td>\n",
       "      <td>36807.360000</td>\n",
       "      <td>195.110000</td>\n",
       "      <td>81163.410000</td>\n",
       "      <td>5.670000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2011.000000</td>\n",
       "      <td>14.417500</td>\n",
       "      <td>47578.545000</td>\n",
       "      <td>561.345000</td>\n",
       "      <td>100164.232500</td>\n",
       "      <td>8.180000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2014.000000</td>\n",
       "      <td>52.100000</td>\n",
       "      <td>86730.270000</td>\n",
       "      <td>6660.620000</td>\n",
       "      <td>170584.800000</td>\n",
       "      <td>35.700000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Year      CO2_PC        GDP_PC  GREEN_AREA_PC  \\\n",
       "count  4650.000000  930.000000   3974.000000    4215.000000   \n",
       "mean   2007.000000   10.551398  37756.897725     539.565848   \n",
       "std       4.320958    7.323933  14803.840039     962.157729   \n",
       "min    2000.000000    0.700000   6049.830000       0.000000   \n",
       "25%    2003.000000    5.260000  28277.207500      40.470000   \n",
       "50%    2007.000000    8.450000  36807.360000     195.110000   \n",
       "75%    2011.000000   14.417500  47578.545000     561.345000   \n",
       "max    2014.000000   52.100000  86730.270000    6660.620000   \n",
       "\n",
       "       LABOUR_PRODUCTIVITY      UNEMP_R  \n",
       "count          3934.000000  4570.000000  \n",
       "mean          81455.477692     6.703803  \n",
       "std           28481.251453     4.085292  \n",
       "min           16301.610000     0.240000  \n",
       "25%           62993.030000     4.120000  \n",
       "50%           81163.410000     5.670000  \n",
       "75%          100164.232500     8.180000  \n",
       "max          170584.800000    35.700000  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Groupby\n",
    "- Splitting the data into groups based on some criteria\n",
    "- Applying a function to each group independently\n",
    "- Combining the results into a data structure\n",
    "\n",
    "For instance, if we have data on temperatures by country and month and we want to calculate the mean temperature for each country:\n",
    "- We split the data by country\n",
    "- We calculate the mean for each group\n",
    "- We combine all of it. \n",
    "\n",
    "Luckily, python can make this easier (in one line)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.1 Describe the data by group"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">Year</th>\n",
       "      <th colspan=\"2\" halign=\"left\">CO2_PC</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">LABOUR_PRODUCTIVITY</th>\n",
       "      <th colspan=\"8\" halign=\"left\">UNEMP_R</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Metropolitan areas</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Aachen</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>27.953333</td>\n",
       "      <td>...</td>\n",
       "      <td>76754.0375</td>\n",
       "      <td>79186.22</td>\n",
       "      <td>14.0</td>\n",
       "      <td>7.729286</td>\n",
       "      <td>1.875475</td>\n",
       "      <td>5.35</td>\n",
       "      <td>6.1000</td>\n",
       "      <td>7.315</td>\n",
       "      <td>8.8750</td>\n",
       "      <td>11.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Acapulco de Juárez</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.580000</td>\n",
       "      <td>...</td>\n",
       "      <td>20730.3200</td>\n",
       "      <td>22189.78</td>\n",
       "      <td>15.0</td>\n",
       "      <td>1.260667</td>\n",
       "      <td>0.617905</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.9000</td>\n",
       "      <td>1.170</td>\n",
       "      <td>1.5900</td>\n",
       "      <td>2.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Adelaide</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7.813333</td>\n",
       "      <td>...</td>\n",
       "      <td>74499.3225</td>\n",
       "      <td>76381.54</td>\n",
       "      <td>14.0</td>\n",
       "      <td>5.827143</td>\n",
       "      <td>0.854638</td>\n",
       "      <td>4.71</td>\n",
       "      <td>5.2200</td>\n",
       "      <td>5.520</td>\n",
       "      <td>6.2425</td>\n",
       "      <td>7.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aguascalientes</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.180000</td>\n",
       "      <td>...</td>\n",
       "      <td>41643.6350</td>\n",
       "      <td>42959.93</td>\n",
       "      <td>15.0</td>\n",
       "      <td>4.614667</td>\n",
       "      <td>1.512386</td>\n",
       "      <td>2.39</td>\n",
       "      <td>3.4100</td>\n",
       "      <td>4.730</td>\n",
       "      <td>5.8900</td>\n",
       "      <td>7.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Akron</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>15.203333</td>\n",
       "      <td>...</td>\n",
       "      <td>92757.8400</td>\n",
       "      <td>96074.20</td>\n",
       "      <td>15.0</td>\n",
       "      <td>6.498667</td>\n",
       "      <td>1.715613</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5.5450</td>\n",
       "      <td>6.030</td>\n",
       "      <td>7.1000</td>\n",
       "      <td>9.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wroclaw</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7.113333</td>\n",
       "      <td>...</td>\n",
       "      <td>69386.8000</td>\n",
       "      <td>82017.65</td>\n",
       "      <td>15.0</td>\n",
       "      <td>16.655333</td>\n",
       "      <td>6.974446</td>\n",
       "      <td>9.13</td>\n",
       "      <td>10.8750</td>\n",
       "      <td>12.670</td>\n",
       "      <td>23.4550</td>\n",
       "      <td>26.71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Xalapa</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.743333</td>\n",
       "      <td>...</td>\n",
       "      <td>30434.7650</td>\n",
       "      <td>31114.01</td>\n",
       "      <td>15.0</td>\n",
       "      <td>2.636000</td>\n",
       "      <td>0.623616</td>\n",
       "      <td>1.90</td>\n",
       "      <td>2.1450</td>\n",
       "      <td>2.450</td>\n",
       "      <td>3.0900</td>\n",
       "      <td>3.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yokkaichi</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>21.920000</td>\n",
       "      <td>...</td>\n",
       "      <td>72037.6375</td>\n",
       "      <td>74652.62</td>\n",
       "      <td>15.0</td>\n",
       "      <td>3.377333</td>\n",
       "      <td>0.651673</td>\n",
       "      <td>2.31</td>\n",
       "      <td>2.9300</td>\n",
       "      <td>3.420</td>\n",
       "      <td>4.0050</td>\n",
       "      <td>4.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zaragoza</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.376667</td>\n",
       "      <td>...</td>\n",
       "      <td>83337.7300</td>\n",
       "      <td>88827.59</td>\n",
       "      <td>15.0</td>\n",
       "      <td>11.164000</td>\n",
       "      <td>6.494151</td>\n",
       "      <td>5.04</td>\n",
       "      <td>5.8250</td>\n",
       "      <td>7.520</td>\n",
       "      <td>16.9350</td>\n",
       "      <td>22.47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zurich</th>\n",
       "      <td>15.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>4.472136</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2003.5</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>2010.5</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>6.656667</td>\n",
       "      <td>...</td>\n",
       "      <td>111757.0850</td>\n",
       "      <td>112250.18</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.975000</td>\n",
       "      <td>0.360786</td>\n",
       "      <td>3.51</td>\n",
       "      <td>3.7875</td>\n",
       "      <td>4.035</td>\n",
       "      <td>4.2225</td>\n",
       "      <td>4.32</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>310 rows × 48 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Year                                                    \\\n",
       "                   count    mean       std     min     25%     50%     75%   \n",
       "Metropolitan areas                                                           \n",
       "Aachen              15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Acapulco de Juárez  15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Adelaide            15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Aguascalientes      15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Akron               15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "...                  ...     ...       ...     ...     ...     ...     ...   \n",
       "Wroclaw             15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Xalapa              15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Yokkaichi           15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Zaragoza            15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "Zurich              15.0  2007.0  4.472136  2000.0  2003.5  2007.0  2010.5   \n",
       "\n",
       "                           CO2_PC             ... LABOUR_PRODUCTIVITY  \\\n",
       "                       max  count       mean  ...                 75%   \n",
       "Metropolitan areas                            ...                       \n",
       "Aachen              2014.0    3.0  27.953333  ...          76754.0375   \n",
       "Acapulco de Juárez  2014.0    3.0   1.580000  ...          20730.3200   \n",
       "Adelaide            2014.0    3.0   7.813333  ...          74499.3225   \n",
       "Aguascalientes      2014.0    3.0   1.180000  ...          41643.6350   \n",
       "Akron               2014.0    3.0  15.203333  ...          92757.8400   \n",
       "...                    ...    ...        ...  ...                 ...   \n",
       "Wroclaw             2014.0    3.0   7.113333  ...          69386.8000   \n",
       "Xalapa              2014.0    3.0   3.743333  ...          30434.7650   \n",
       "Yokkaichi           2014.0    3.0  21.920000  ...          72037.6375   \n",
       "Zaragoza            2014.0    3.0   5.376667  ...          83337.7300   \n",
       "Zurich              2014.0    3.0   6.656667  ...         111757.0850   \n",
       "\n",
       "                              UNEMP_R                                      \\\n",
       "                          max   count       mean       std   min      25%   \n",
       "Metropolitan areas                                                          \n",
       "Aachen               79186.22    14.0   7.729286  1.875475  5.35   6.1000   \n",
       "Acapulco de Juárez   22189.78    15.0   1.260667  0.617905  0.24   0.9000   \n",
       "Adelaide             76381.54    14.0   5.827143  0.854638  4.71   5.2200   \n",
       "Aguascalientes       42959.93    15.0   4.614667  1.512386  2.39   3.4100   \n",
       "Akron                96074.20    15.0   6.498667  1.715613  4.15   5.5450   \n",
       "...                       ...     ...        ...       ...   ...      ...   \n",
       "Wroclaw              82017.65    15.0  16.655333  6.974446  9.13  10.8750   \n",
       "Xalapa               31114.01    15.0   2.636000  0.623616  1.90   2.1450   \n",
       "Yokkaichi            74652.62    15.0   3.377333  0.651673  2.31   2.9300   \n",
       "Zaragoza             88827.59    15.0  11.164000  6.494151  5.04   5.8250   \n",
       "Zurich              112250.18     4.0   3.975000  0.360786  3.51   3.7875   \n",
       "\n",
       "                                            \n",
       "                       50%      75%    max  \n",
       "Metropolitan areas                          \n",
       "Aachen               7.315   8.8750  11.17  \n",
       "Acapulco de Juárez   1.170   1.5900   2.45  \n",
       "Adelaide             5.520   6.2425   7.62  \n",
       "Aguascalientes       4.730   5.8900   7.19  \n",
       "Akron                6.030   7.1000   9.95  \n",
       "...                    ...      ...    ...  \n",
       "Wroclaw             12.670  23.4550  26.71  \n",
       "Xalapa               2.450   3.0900   3.66  \n",
       "Yokkaichi            3.420   4.0050   4.36  \n",
       "Zaragoza             7.520  16.9350  22.47  \n",
       "Zurich               4.035   4.2225   4.32  \n",
       "\n",
       "[310 rows x 48 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"Metropolitan areas\"]).describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2 Calculate the mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Year</th>\n",
       "      <th>CO2_PC</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>GREEN_AREA_PC</th>\n",
       "      <th>LABOUR_PRODUCTIVITY</th>\n",
       "      <th>UNEMP_R</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Metropolitan areas</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Aachen</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>27.953333</td>\n",
       "      <td>31460.207692</td>\n",
       "      <td>246.048000</td>\n",
       "      <td>74734.025000</td>\n",
       "      <td>7.729286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Acapulco de Juárez</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>1.580000</td>\n",
       "      <td>7424.196364</td>\n",
       "      <td>752.199333</td>\n",
       "      <td>19944.554545</td>\n",
       "      <td>1.260667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Adelaide</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>7.813333</td>\n",
       "      <td>35516.405000</td>\n",
       "      <td>30.683333</td>\n",
       "      <td>72122.112857</td>\n",
       "      <td>5.827143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aguascalientes</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>1.180000</td>\n",
       "      <td>15485.192727</td>\n",
       "      <td>244.816000</td>\n",
       "      <td>40801.903636</td>\n",
       "      <td>4.614667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Akron</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>15.203333</td>\n",
       "      <td>44450.320769</td>\n",
       "      <td>1285.302000</td>\n",
       "      <td>90121.096154</td>\n",
       "      <td>6.498667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wroclaw</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>7.113333</td>\n",
       "      <td>23515.091538</td>\n",
       "      <td>603.150667</td>\n",
       "      <td>65119.701538</td>\n",
       "      <td>16.655333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Xalapa</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>3.743333</td>\n",
       "      <td>11106.818182</td>\n",
       "      <td>516.716667</td>\n",
       "      <td>29269.303636</td>\n",
       "      <td>2.636000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yokkaichi</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>21.920000</td>\n",
       "      <td>34175.006667</td>\n",
       "      <td>27.490000</td>\n",
       "      <td>68554.737500</td>\n",
       "      <td>3.377333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zaragoza</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>5.376667</td>\n",
       "      <td>35222.715385</td>\n",
       "      <td>58.720667</td>\n",
       "      <td>81204.056154</td>\n",
       "      <td>11.164000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zurich</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>6.656667</td>\n",
       "      <td>62294.066000</td>\n",
       "      <td>284.436000</td>\n",
       "      <td>110918.333333</td>\n",
       "      <td>3.975000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>310 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Year     CO2_PC        GDP_PC  GREEN_AREA_PC  \\\n",
       "Metropolitan areas                                                   \n",
       "Aachen              2007.0  27.953333  31460.207692     246.048000   \n",
       "Acapulco de Juárez  2007.0   1.580000   7424.196364     752.199333   \n",
       "Adelaide            2007.0   7.813333  35516.405000      30.683333   \n",
       "Aguascalientes      2007.0   1.180000  15485.192727     244.816000   \n",
       "Akron               2007.0  15.203333  44450.320769    1285.302000   \n",
       "...                    ...        ...           ...            ...   \n",
       "Wroclaw             2007.0   7.113333  23515.091538     603.150667   \n",
       "Xalapa              2007.0   3.743333  11106.818182     516.716667   \n",
       "Yokkaichi           2007.0  21.920000  34175.006667      27.490000   \n",
       "Zaragoza            2007.0   5.376667  35222.715385      58.720667   \n",
       "Zurich              2007.0   6.656667  62294.066000     284.436000   \n",
       "\n",
       "                    LABOUR_PRODUCTIVITY    UNEMP_R  \n",
       "Metropolitan areas                                  \n",
       "Aachen                     74734.025000   7.729286  \n",
       "Acapulco de Juárez         19944.554545   1.260667  \n",
       "Adelaide                   72122.112857   5.827143  \n",
       "Aguascalientes             40801.903636   4.614667  \n",
       "Akron                      90121.096154   6.498667  \n",
       "...                                 ...        ...  \n",
       "Wroclaw                    65119.701538  16.655333  \n",
       "Xalapa                     29269.303636   2.636000  \n",
       "Yokkaichi                  68554.737500   3.377333  \n",
       "Zaragoza                   81204.056154  11.164000  \n",
       "Zurich                    110918.333333   3.975000  \n",
       "\n",
       "[310 rows x 6 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"Metropolitan areas\"]).mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.3 Apply a custom variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda3/lib/python3.7/site-packages/numpy/core/fromnumeric.py:3370: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
      "  return mean(axis=axis, dtype=dtype, out=out, **kwargs)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Year</th>\n",
       "      <th>CO2_PC</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>GREEN_AREA_PC</th>\n",
       "      <th>LABOUR_PRODUCTIVITY</th>\n",
       "      <th>UNEMP_R</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Metropolitan areas</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Aachen</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>27.953333</td>\n",
       "      <td>31460.207692</td>\n",
       "      <td>246.048000</td>\n",
       "      <td>74734.025000</td>\n",
       "      <td>7.729286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Acapulco de Juárez</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>1.580000</td>\n",
       "      <td>7424.196364</td>\n",
       "      <td>752.199333</td>\n",
       "      <td>19944.554545</td>\n",
       "      <td>1.260667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Adelaide</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>7.813333</td>\n",
       "      <td>35516.405000</td>\n",
       "      <td>30.683333</td>\n",
       "      <td>72122.112857</td>\n",
       "      <td>5.827143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aguascalientes</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>1.180000</td>\n",
       "      <td>15485.192727</td>\n",
       "      <td>244.816000</td>\n",
       "      <td>40801.903636</td>\n",
       "      <td>4.614667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Akron</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>15.203333</td>\n",
       "      <td>44450.320769</td>\n",
       "      <td>1285.302000</td>\n",
       "      <td>90121.096154</td>\n",
       "      <td>6.498667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wroclaw</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>7.113333</td>\n",
       "      <td>23515.091538</td>\n",
       "      <td>603.150667</td>\n",
       "      <td>65119.701538</td>\n",
       "      <td>16.655333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Xalapa</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>3.743333</td>\n",
       "      <td>11106.818182</td>\n",
       "      <td>516.716667</td>\n",
       "      <td>29269.303636</td>\n",
       "      <td>2.636000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yokkaichi</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>21.920000</td>\n",
       "      <td>34175.006667</td>\n",
       "      <td>27.490000</td>\n",
       "      <td>68554.737500</td>\n",
       "      <td>3.377333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zaragoza</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>5.376667</td>\n",
       "      <td>35222.715385</td>\n",
       "      <td>58.720667</td>\n",
       "      <td>81204.056154</td>\n",
       "      <td>11.164000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zurich</th>\n",
       "      <td>2007.0</td>\n",
       "      <td>6.656667</td>\n",
       "      <td>62294.066000</td>\n",
       "      <td>284.436000</td>\n",
       "      <td>110918.333333</td>\n",
       "      <td>3.975000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>310 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Year     CO2_PC        GDP_PC  GREEN_AREA_PC  \\\n",
       "Metropolitan areas                                                   \n",
       "Aachen              2007.0  27.953333  31460.207692     246.048000   \n",
       "Acapulco de Juárez  2007.0   1.580000   7424.196364     752.199333   \n",
       "Adelaide            2007.0   7.813333  35516.405000      30.683333   \n",
       "Aguascalientes      2007.0   1.180000  15485.192727     244.816000   \n",
       "Akron               2007.0  15.203333  44450.320769    1285.302000   \n",
       "...                    ...        ...           ...            ...   \n",
       "Wroclaw             2007.0   7.113333  23515.091538     603.150667   \n",
       "Xalapa              2007.0   3.743333  11106.818182     516.716667   \n",
       "Yokkaichi           2007.0  21.920000  34175.006667      27.490000   \n",
       "Zaragoza            2007.0   5.376667  35222.715385      58.720667   \n",
       "Zurich              2007.0   6.656667  62294.066000     284.436000   \n",
       "\n",
       "                    LABOUR_PRODUCTIVITY    UNEMP_R  \n",
       "Metropolitan areas                                  \n",
       "Aachen                     74734.025000   7.729286  \n",
       "Acapulco de Juárez         19944.554545   1.260667  \n",
       "Adelaide                   72122.112857   5.827143  \n",
       "Aguascalientes             40801.903636   4.614667  \n",
       "Akron                      90121.096154   6.498667  \n",
       "...                                 ...        ...  \n",
       "Wroclaw                    65119.701538  16.655333  \n",
       "Xalapa                     29269.303636   2.636000  \n",
       "Yokkaichi                  68554.737500   3.377333  \n",
       "Zaragoza                   81204.056154  11.164000  \n",
       "Zurich                    110918.333333   3.975000  \n",
       "\n",
       "[310 rows x 6 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"Metropolitan areas\"]).apply(np.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Year</th>\n",
       "      <th>CO2_PC</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>GREEN_AREA_PC</th>\n",
       "      <th>LABOUR_PRODUCTIVITY</th>\n",
       "      <th>UNEMP_R</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Metropolitan areas</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Aachen</th>\n",
       "      <td>14.0</td>\n",
       "      <td>4.65</td>\n",
       "      <td>5361.53</td>\n",
       "      <td>6.26</td>\n",
       "      <td>8161.92</td>\n",
       "      <td>5.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Acapulco de Juárez</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.22</td>\n",
       "      <td>533.71</td>\n",
       "      <td>123.58</td>\n",
       "      <td>4058.88</td>\n",
       "      <td>2.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Adelaide</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.53</td>\n",
       "      <td>5571.68</td>\n",
       "      <td>4.14</td>\n",
       "      <td>20802.33</td>\n",
       "      <td>2.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aguascalientes</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1820.46</td>\n",
       "      <td>87.54</td>\n",
       "      <td>4116.48</td>\n",
       "      <td>4.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Akron</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.85</td>\n",
       "      <td>5557.79</td>\n",
       "      <td>3.71</td>\n",
       "      <td>13683.53</td>\n",
       "      <td>5.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wroclaw</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.54</td>\n",
       "      <td>13011.02</td>\n",
       "      <td>10.82</td>\n",
       "      <td>27092.46</td>\n",
       "      <td>17.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Xalapa</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.86</td>\n",
       "      <td>3184.71</td>\n",
       "      <td>140.94</td>\n",
       "      <td>4289.30</td>\n",
       "      <td>1.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yokkaichi</th>\n",
       "      <td>14.0</td>\n",
       "      <td>3.60</td>\n",
       "      <td>8030.34</td>\n",
       "      <td>1.81</td>\n",
       "      <td>17161.18</td>\n",
       "      <td>2.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zaragoza</th>\n",
       "      <td>14.0</td>\n",
       "      <td>1.25</td>\n",
       "      <td>6687.15</td>\n",
       "      <td>11.20</td>\n",
       "      <td>11957.67</td>\n",
       "      <td>17.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zurich</th>\n",
       "      <td>14.0</td>\n",
       "      <td>0.25</td>\n",
       "      <td>1950.37</td>\n",
       "      <td>31.85</td>\n",
       "      <td>3009.35</td>\n",
       "      <td>0.81</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>310 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Year  CO2_PC    GDP_PC  GREEN_AREA_PC  \\\n",
       "Metropolitan areas                                          \n",
       "Aachen              14.0    4.65   5361.53           6.26   \n",
       "Acapulco de Juárez  14.0    0.22    533.71         123.58   \n",
       "Adelaide            14.0    0.53   5571.68           4.14   \n",
       "Aguascalientes      14.0    0.10   1820.46          87.54   \n",
       "Akron               14.0    0.85   5557.79           3.71   \n",
       "...                  ...     ...       ...            ...   \n",
       "Wroclaw             14.0    0.54  13011.02          10.82   \n",
       "Xalapa              14.0    0.86   3184.71         140.94   \n",
       "Yokkaichi           14.0    3.60   8030.34           1.81   \n",
       "Zaragoza            14.0    1.25   6687.15          11.20   \n",
       "Zurich              14.0    0.25   1950.37          31.85   \n",
       "\n",
       "                    LABOUR_PRODUCTIVITY  UNEMP_R  \n",
       "Metropolitan areas                                \n",
       "Aachen                          8161.92     5.82  \n",
       "Acapulco de Juárez              4058.88     2.21  \n",
       "Adelaide                       20802.33     2.91  \n",
       "Aguascalientes                  4116.48     4.80  \n",
       "Akron                          13683.53     5.80  \n",
       "...                                 ...      ...  \n",
       "Wroclaw                        27092.46    17.58  \n",
       "Xalapa                          4289.30     1.76  \n",
       "Yokkaichi                      17161.18     2.05  \n",
       "Zaragoza                       11957.67    17.43  \n",
       "Zurich                          3009.35     0.81  \n",
       "\n",
       "[310 rows x 6 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def diff(column_values):\n",
    "    diff = np.max(column_values)-np.min(column_values)\n",
    "    return diff\n",
    "\n",
    "df.groupby([\"Metropolitan areas\"]).apply(diff)"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}