{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# GDP in German Federal States"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img src=\"imgs/eck.jpeg\">"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Required Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "import seaborn as sns\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Source"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "url = \"https://en.wikipedia.org/wiki/List_of_German_states_by_GDP\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Content of the Wikipedia page:\n",
    "* List of German states by GDP in 2015\n",
    "* List of German states by GDP in 2013\n",
    "* List of German states by GDP in 2012\n",
    "* List of German states by GDP in 2011\n",
    "* List of German states by GDP in 2010\n",
    "* List of German states by GDP in 2009\n",
    "* List of German states by GDP in 2008\n",
    "\n",
    "**NOTE!** List for 2014 is missing (Missing data is a very common case in practice)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# requirements: https://stackoverflow.com/questions/34555135/pandas-read-html\n",
    "# pd.read_html(url)[year_table_map[2015]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Methods to be used (Make sure to run all these cells)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "year_table_map = {\n",
    "    2015:3,\n",
    "    2013:4,\n",
    "    2012:5,\n",
    "    2011:6,\n",
    "    2010:7,\n",
    "    2009:8,\n",
    "    2008:9\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def calculate_population(gdp,gdp_pc):\n",
    "    return int((gdp*1000000000)/gdp_pc)\n",
    "\n",
    "def get_population():\n",
    "    global year_table_map\n",
    "    df = pd.read_html(url)\n",
    "#     print(df)\n",
    "    df = pd.read_html(url)[year_table_map[2015]]\n",
    "#     print(df)\n",
    "    df.columns = [\"STATE\", \"RANK\", \"GDP_EUR\", \"GDP_USD\", \"GDP_PC\"]\n",
    "    df = df.drop([\"RANK\",\"GDP_USD\"],axis=1)\n",
    "    df = df[~df[\"STATE\"].isin([\"States\",\"Germany\",\"Former GDR states and all of Berlin\"])]\n",
    "    df[[\"GDP_EUR\",\"GDP_PC\"]] = df[[\"GDP_EUR\", \"GDP_PC\"]].apply(pd.to_numeric)\n",
    "    df[\"POPULATION\"] = df.apply(lambda x: calculate_population(x[\"GDP_EUR\"], x[\"GDP_PC\"]), axis=1)\n",
    "    df = df[[\"STATE\", \"POPULATION\"]]\n",
    "    return df\n",
    "\n",
    "POPULATION = get_population()\n",
    "\n",
    "def population_for_state(state):\n",
    "    global POPULATION\n",
    "    return POPULATION[POPULATION[\"STATE\"] == state][\"POPULATION\"].values[0]\n",
    "\n",
    "def add_per_capita(x):\n",
    "    global POPULATION\n",
    "    gdp = x[\"GDP_EUR\"]\n",
    "    state = x[\"STATE\"]\n",
    "    population = population_for_state(state)\n",
    "    return (float(gdp)*1000000000)/population\n",
    "\n",
    "def plot_population(population_df):\n",
    "    ax = sns.barplot(population_df[\"POPULATION\"],population_df[\"STATE\"],estimator=abs)\n",
    "    plt.title(\"States by Population\")\n",
    "    ax.set(xlabel='POPULATION', ylabel='STATE')\n",
    "#     plt.xticks(population_df[\"POPULATION\"].valu)\n",
    "\n",
    "def get_table_for_year(url, year, no_per_capita=True):\n",
    "    \"\"\" Returns datafame representation of the table on wikipedia page\n",
    "    \"\"\"\n",
    "    global year_table_map, POPULATION\n",
    "    \n",
    "    if year not in year_table_map.keys():\n",
    "        return \"There is no table for the input year on the Wikipedia page\"\n",
    "    \n",
    "    df = pd.read_html(url)[year_table_map[year]]\n",
    "    if year == 2015:\n",
    "        df.columns = [\"STATE\", \"RANK\", \"GDP_EUR\", \"GDP_USD\", \"GDP_PC\"]\n",
    "        df = df[~df[\"STATE\"].isin([\"States\",\"Germany\",\"Former GDR states and all of Berlin\"])]\n",
    "        df[[\"RANK\",\"GDP_EUR\",\"GDP_USD\",\"GDP_PC\"]] = df[[\"RANK\",\"GDP_EUR\",\"GDP_USD\",\"GDP_PC\",]].apply(pd.to_numeric)\n",
    "        df = df.drop([\"GDP_USD\"], axis=1)\n",
    "        if no_per_capita:\n",
    "            df = df.drop([\"GDP_PC\", \"GDP_USD\"], axis=1)\n",
    "    else: \n",
    "        df.columns = [\"STATE\", \"RANK\", \"GDP_EUR\", \"GDP_USD\", \"GDP_SHARE\"]\n",
    "        df = df[~df[\"STATE\"].isin([\"States\",\"Germany\",\"Former GDR states and all of Berlin\"])]\n",
    "        df[[\"RANK\",\"GDP_EUR\",\"GDP_USD\"]] = df[[\"RANK\",\"GDP_EUR\",\"GDP_USD\"]].apply(pd.to_numeric)\n",
    "        df = df.drop([\"GDP_SHARE\", \"GDP_USD\"], axis=1)\n",
    "        if not no_per_capita:\n",
    "            df[\"GDP_PC\"] = df.apply(lambda x: add_per_capita(x), axis=1)\n",
    "            \n",
    "    return df\n",
    "\n",
    "def plot_gdp_per_capita(year):\n",
    "    df = get_table_for_year(url, 2015, no_per_capita=False)\n",
    "    ax = sns.barplot(df[\"GDP_PC\"],df[\"STATE\"],estimator=abs)\n",
    "    plt.title(\"States by GDP per capita\")\n",
    "    ax.set(xlabel='GDP PER CAPITA', ylabel='STATE')\n",
    "    \n",
    "def merge_tables(years):\n",
    "    df_lst = []\n",
    "    for year in years:\n",
    "        df = get_table_for_year(url, year, no_per_capita=False)\n",
    "        df[\"YEAR\"] = [year]*len(df)\n",
    "#         df = df\n",
    "        df_lst.append(df)\n",
    "    return pd.concat(df_lst).reset_index(drop=True)\n",
    "\n",
    "def plot_gdp_over_time(all_tables, states=[\"Rhineland-Palatinate\"]):\n",
    "    df = all_tables[all_tables[\"STATE\"].isin(states)]\n",
    "    df['UNIT'] = ['EUR']*len(df)\n",
    "    sns.tsplot(df, time=\"YEAR\",condition=\"STATE\", unit=\"UNIT\", value=\"GDP_EUR\")\n",
    "\n",
    "def get_stats(variable):\n",
    "    if variable == \"GDP_EUR\":\n",
    "        unit = \"billion\"\n",
    "    elif variable == \"GDP_PC\":\n",
    "        unit = \"thousands\"\n",
    "    else:\n",
    "        unit = \"\"\n",
    "    \n",
    "    print(\"Average {}: {} ({})\".format(variable,df[variable].mean(), unit))\n",
    "    print(\"Median {}: {} ({})\".format(variable,df[variable].median(),unit))\n",
    "    print(\"Minimal {}: {} ({})\".format(variable,df[variable].min(),unit))\n",
    "    print(\"Maximal {}: {} ({})\".format(variable,df[variable].max(),unit))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Aproximating the population"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As GDP per capita is given for year 2015 we can aproximate the population of each Bundesland and asume that the populations did not change dramaticaly in the meantime.\n",
    "\n",
    "**The population will be used to aproximate GDP PER CAPITA where it is missing**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATE</th>\n",
       "      <th>POPULATION</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>North Rhine-Westphalia</td>\n",
       "      <td>17683037</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bavaria</td>\n",
       "      <td>12744592</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Baden-Württemberg</td>\n",
       "      <td>10777564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Hesse</td>\n",
       "      <td>6116221</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Lower Saxony</td>\n",
       "      <td>7860443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Rhineland-Palatinate</td>\n",
       "      <td>4021179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Berlin</td>\n",
       "      <td>3485025</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Saxony</td>\n",
       "      <td>4055947</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Hamburg</td>\n",
       "      <td>1770172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Schleswig-Holstein</td>\n",
       "      <td>2840976</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Brandenburg</td>\n",
       "      <td>2464575</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Thuringia</td>\n",
       "      <td>2154870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Saxony-Anhalt</td>\n",
       "      <td>2231010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Mecklenburg-Vorpommern</td>\n",
       "      <td>1600586</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Saarland</td>\n",
       "      <td>989240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Bremen</td>\n",
       "      <td>663613</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     STATE  POPULATION\n",
       "2   North Rhine-Westphalia    17683037\n",
       "3                  Bavaria    12744592\n",
       "4        Baden-Württemberg    10777564\n",
       "6                    Hesse     6116221\n",
       "7             Lower Saxony     7860443\n",
       "8     Rhineland-Palatinate     4021179\n",
       "9                   Berlin     3485025\n",
       "10                  Saxony     4055947\n",
       "11                 Hamburg     1770172\n",
       "12      Schleswig-Holstein     2840976\n",
       "13             Brandenburg     2464575\n",
       "14               Thuringia     2154870\n",
       "15           Saxony-Anhalt     2231010\n",
       "16  Mecklenburg-Vorpommern     1600586\n",
       "17                Saarland      989240\n",
       "18                  Bremen      663613"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "POPULATION = get_population()\n",
    "POPULATION"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Try out states you find interesting!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12744592"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "population_for_state(\"Bavaria\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Let's plot the population!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAegAAAETCAYAAAD9BZXWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nJOiIiIgW9P+lLLY8VYKfOwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xc863ac8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_population(POPULATION)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Scraping data from Wikipedia "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, lets download data from the web page. Python has a nice feature that make it easy to download tables from websites automaticaly. For this task, we need just one line of code. However, data usually needs to be procesed and cleaned. The columns we need are:\n",
    "* STATE - Federal states {NRW, Bavaria, etc..}\n",
    "* RANK - Best ranked state has value 1\n",
    "* GDP_EUR - total GDP for state in EUR **BILIONS**\n",
    "* GDP_PC - GDP per capita **THOUSANDS**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATE</th>\n",
       "      <th>RANK</th>\n",
       "      <th>GDP_EUR</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>North Rhine-Westphalia</td>\n",
       "      <td>1</td>\n",
       "      <td>547.54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bavaria</td>\n",
       "      <td>2</td>\n",
       "      <td>444.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Baden-Württemberg</td>\n",
       "      <td>3</td>\n",
       "      <td>365.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Hesse</td>\n",
       "      <td>4</td>\n",
       "      <td>221.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Lower Saxony</td>\n",
       "      <td>5</td>\n",
       "      <td>213.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Rhineland-Palatinate</td>\n",
       "      <td>6</td>\n",
       "      <td>106.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Saxony</td>\n",
       "      <td>7</td>\n",
       "      <td>94.92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Berlin</td>\n",
       "      <td>8</td>\n",
       "      <td>88.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Hamburg</td>\n",
       "      <td>9</td>\n",
       "      <td>87.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Schleswig-Holstein</td>\n",
       "      <td>10</td>\n",
       "      <td>73.94</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Brandenburg</td>\n",
       "      <td>11</td>\n",
       "      <td>54.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Saxony-Anhalt</td>\n",
       "      <td>12</td>\n",
       "      <td>53.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Thuringia</td>\n",
       "      <td>13</td>\n",
       "      <td>50.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Mecklenburg-Vorpommern</td>\n",
       "      <td>14</td>\n",
       "      <td>35.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Saarland</td>\n",
       "      <td>15</td>\n",
       "      <td>31.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Bremen</td>\n",
       "      <td>16</td>\n",
       "      <td>27.43</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     STATE  RANK  GDP_EUR\n",
       "2   North Rhine-Westphalia     1   547.54\n",
       "3                  Bavaria     2   444.81\n",
       "4        Baden-Württemberg     3   365.06\n",
       "5                    Hesse     4   221.35\n",
       "6             Lower Saxony     5   213.09\n",
       "7     Rhineland-Palatinate     6   106.37\n",
       "8                   Saxony     7    94.92\n",
       "9                   Berlin     8    88.58\n",
       "10                 Hamburg     9    87.48\n",
       "11      Schleswig-Holstein    10    73.94\n",
       "12             Brandenburg    11    54.37\n",
       "13           Saxony-Anhalt    12    53.72\n",
       "14               Thuringia    13    50.38\n",
       "15  Mecklenburg-Vorpommern    14    35.70\n",
       "16                Saarland    15    31.05\n",
       "17                  Bremen    16    27.43"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "get_table_for_year(url, 2008,no_per_capita=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Looking at the page, we can see that GDP per capita is specified only for years 2015 and 2008. This information is rather useful, it is GDP divided by the population of a state. For example, [India ranks 7th in the world by total GDP](https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)) which means it is a very large economy, but when the GDP is dividide by the population of [India takes the 122nd place in the world](https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(PPP)_per_capita), which means it's citizens are not among the richer in todays standings.\n",
    "\n",
    "But, if you remember, we have calculated the populations of all Federal states and this means we can aproximate GDP per capita for them! Just add a parameter **no_per_capita** to False."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATE</th>\n",
       "      <th>RANK</th>\n",
       "      <th>GDP_EUR</th>\n",
       "      <th>GDP_PC</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>North Rhine-Westphalia</td>\n",
       "      <td>1</td>\n",
       "      <td>645.590</td>\n",
       "      <td>36509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bavaria</td>\n",
       "      <td>2</td>\n",
       "      <td>549.190</td>\n",
       "      <td>43092</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Baden-Württemberg</td>\n",
       "      <td>3</td>\n",
       "      <td>460.687</td>\n",
       "      <td>42745</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Hesse</td>\n",
       "      <td>4</td>\n",
       "      <td>263.444</td>\n",
       "      <td>43073</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Lower Saxony</td>\n",
       "      <td>5</td>\n",
       "      <td>258.530</td>\n",
       "      <td>32890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Rhineland-Palatinate</td>\n",
       "      <td>6</td>\n",
       "      <td>131.951</td>\n",
       "      <td>32814</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Berlin</td>\n",
       "      <td>7</td>\n",
       "      <td>124.161</td>\n",
       "      <td>35627</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Saxony</td>\n",
       "      <td>8</td>\n",
       "      <td>112.658</td>\n",
       "      <td>27776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Hamburg</td>\n",
       "      <td>9</td>\n",
       "      <td>109.271</td>\n",
       "      <td>61729</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Schleswig-Holstein</td>\n",
       "      <td>10</td>\n",
       "      <td>85.610</td>\n",
       "      <td>30134</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Brandenburg</td>\n",
       "      <td>11</td>\n",
       "      <td>65.294</td>\n",
       "      <td>26493</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Thuringia</td>\n",
       "      <td>12</td>\n",
       "      <td>56.811</td>\n",
       "      <td>26364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Saxony-Anhalt</td>\n",
       "      <td>13</td>\n",
       "      <td>56.217</td>\n",
       "      <td>25198</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Mecklenburg-Vorpommern</td>\n",
       "      <td>14</td>\n",
       "      <td>39.869</td>\n",
       "      <td>24909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Saarland</td>\n",
       "      <td>15</td>\n",
       "      <td>35.028</td>\n",
       "      <td>35409</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Bremen</td>\n",
       "      <td>16</td>\n",
       "      <td>31.590</td>\n",
       "      <td>47603</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     STATE  RANK  GDP_EUR  GDP_PC\n",
       "2   North Rhine-Westphalia     1  645.590   36509\n",
       "3                  Bavaria     2  549.190   43092\n",
       "4        Baden-Württemberg     3  460.687   42745\n",
       "6                    Hesse     4  263.444   43073\n",
       "7             Lower Saxony     5  258.530   32890\n",
       "8     Rhineland-Palatinate     6  131.951   32814\n",
       "9                   Berlin     7  124.161   35627\n",
       "10                  Saxony     8  112.658   27776\n",
       "11                 Hamburg     9  109.271   61729\n",
       "12      Schleswig-Holstein    10   85.610   30134\n",
       "13             Brandenburg    11   65.294   26493\n",
       "14               Thuringia    12   56.811   26364\n",
       "15           Saxony-Anhalt    13   56.217   25198\n",
       "16  Mecklenburg-Vorpommern    14   39.869   24909\n",
       "17                Saarland    15   35.028   35409\n",
       "18                  Bremen    16   31.590   47603"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "get_table_for_year(url, 2015, no_per_capita=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Some stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = get_table_for_year(url, 2015, no_per_capita=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Average GDP_EUR: 189.11881250000002 (billion)\n",
      "Median GDP_EUR: 110.96449999999999 (billion)\n",
      "Minimal GDP_EUR: 31.59 (billion)\n",
      "Maximal GDP_EUR: 645.59 (billion)\n"
     ]
    }
   ],
   "source": [
    "get_stats(\"GDP_EUR\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Average GDP_PC: 35772.8125 (thousands)\n",
      "Median GDP_PC: 34149.5 (thousands)\n",
      "Minimal GDP_PC: 24909 (thousands)\n",
      "Maximal GDP_PC: 61729 (thousands)\n"
     ]
    }
   ],
   "source": [
    "get_stats(\"GDP_PC\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Lets se which states have the richest population!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAegAAAETCAYAAAD9BZXWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xb451240>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_gdp_per_capita(2015)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Lets see how GDP changed over the years!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = merge_tables([2008,2009,2010,2011,2012,2013,2015])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATE</th>\n",
       "      <th>RANK</th>\n",
       "      <th>GDP_EUR</th>\n",
       "      <th>GDP_PC</th>\n",
       "      <th>YEAR</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Rhine-Westphalia</td>\n",
       "      <td>1</td>\n",
       "      <td>547.54</td>\n",
       "      <td>30964.138117</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bavaria</td>\n",
       "      <td>2</td>\n",
       "      <td>444.81</td>\n",
       "      <td>34901.862688</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Baden-Württemberg</td>\n",
       "      <td>3</td>\n",
       "      <td>365.06</td>\n",
       "      <td>33872.218249</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hesse</td>\n",
       "      <td>4</td>\n",
       "      <td>221.35</td>\n",
       "      <td>36190.647787</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Lower Saxony</td>\n",
       "      <td>5</td>\n",
       "      <td>213.09</td>\n",
       "      <td>27109.159115</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Rhineland-Palatinate</td>\n",
       "      <td>6</td>\n",
       "      <td>106.37</td>\n",
       "      <td>26452.440938</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Saxony</td>\n",
       "      <td>7</td>\n",
       "      <td>94.92</td>\n",
       "      <td>23402.672668</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Berlin</td>\n",
       "      <td>8</td>\n",
       "      <td>88.58</td>\n",
       "      <td>25417.321253</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Hamburg</td>\n",
       "      <td>9</td>\n",
       "      <td>87.48</td>\n",
       "      <td>49418.926522</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Schleswig-Holstein</td>\n",
       "      <td>10</td>\n",
       "      <td>73.94</td>\n",
       "      <td>26026.267029</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Brandenburg</td>\n",
       "      <td>11</td>\n",
       "      <td>54.37</td>\n",
       "      <td>22060.598683</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Saxony-Anhalt</td>\n",
       "      <td>12</td>\n",
       "      <td>53.72</td>\n",
       "      <td>24078.780463</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Thuringia</td>\n",
       "      <td>13</td>\n",
       "      <td>50.38</td>\n",
       "      <td>23379.600626</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Mecklenburg-Vorpommern</td>\n",
       "      <td>14</td>\n",
       "      <td>35.70</td>\n",
       "      <td>22304.331039</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Saarland</td>\n",
       "      <td>15</td>\n",
       "      <td>31.05</td>\n",
       "      <td>31387.731996</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Bremen</td>\n",
       "      <td>16</td>\n",
       "      <td>27.43</td>\n",
       "      <td>41334.331907</td>\n",
       "      <td>2008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>North Rhine-Westphalia</td>\n",
       "      <td>1</td>\n",
       "      <td>522.92</td>\n",
       "      <td>29571.843343</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Bavaria</td>\n",
       "      <td>2</td>\n",
       "      <td>423.84</td>\n",
       "      <td>33256.458896</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Baden-Württemberg</td>\n",
       "      <td>3</td>\n",
       "      <td>341.23</td>\n",
       "      <td>31661.143464</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Hesse</td>\n",
       "      <td>4</td>\n",
       "      <td>215.29</td>\n",
       "      <td>35199.839901</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     STATE  RANK  GDP_EUR        GDP_PC  YEAR\n",
       "0   North Rhine-Westphalia     1   547.54  30964.138117  2008\n",
       "1                  Bavaria     2   444.81  34901.862688  2008\n",
       "2        Baden-Württemberg     3   365.06  33872.218249  2008\n",
       "3                    Hesse     4   221.35  36190.647787  2008\n",
       "4             Lower Saxony     5   213.09  27109.159115  2008\n",
       "5     Rhineland-Palatinate     6   106.37  26452.440938  2008\n",
       "6                   Saxony     7    94.92  23402.672668  2008\n",
       "7                   Berlin     8    88.58  25417.321253  2008\n",
       "8                  Hamburg     9    87.48  49418.926522  2008\n",
       "9       Schleswig-Holstein    10    73.94  26026.267029  2008\n",
       "10             Brandenburg    11    54.37  22060.598683  2008\n",
       "11           Saxony-Anhalt    12    53.72  24078.780463  2008\n",
       "12               Thuringia    13    50.38  23379.600626  2008\n",
       "13  Mecklenburg-Vorpommern    14    35.70  22304.331039  2008\n",
       "14                Saarland    15    31.05  31387.731996  2008\n",
       "15                  Bremen    16    27.43  41334.331907  2008\n",
       "16  North Rhine-Westphalia     1   522.92  29571.843343  2009\n",
       "17                 Bavaria     2   423.84  33256.458896  2009\n",
       "18       Baden-Württemberg     3   341.23  31661.143464  2009\n",
       "19                   Hesse     4   215.29  35199.839901  2009"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(20) #first 20 rows"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# How did the GDP of Rheinland-Pfalz change over time?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY4AAAEFCAYAAAD0cwBnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nwIwoUPk/rlIAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xb3cdfd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_gdp_over_time(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Let's compare states! (Choose on your own)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY4AAAEFCAYAAAD0cwBnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n5EQShxBCiJz8f9vD2dh2G0tUAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7b6b5f8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "states = [\"Rhineland-Palatinate\",\"Bavaria\",\"Hesse\",\"North Rhine-Westphalia\"]\n",
    "plot_gdp_over_time(df, states=states)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}