{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Spatial joins"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Goals of this notebook:\n",
    "\n",
    "- Based on the `countries` and `cities` dataframes, determine for each city the country in which it is located.\n",
    "- To solve this problem, we will use the the concept of a 'spatial join' operation: combining information of geospatial datasets based on their spatial relationship."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import pandas as pd\n",
    "import geopandas\n",
    "\n",
    "pd.options.display.max_rows = 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "countries = geopandas.read_file(\"zip://./data/ne_110m_admin_0_countries.zip\")\n",
    "cities = geopandas.read_file(\"zip://./data/ne_110m_populated_places.zip\")\n",
    "rivers = geopandas.read_file(\"zip://./data/ne_50m_rivers_lake_centerlines.zip\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Recap - joining dataframes\n",
    "\n",
    "Pandas provides functionality to join or merge dataframes in different ways, see https://chrisalbon.com/python/data_wrangling/pandas_join_merge_dataframe/ for an overview and https://pandas.pydata.org/pandas-docs/stable/merging.html for the full documentation."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To illustrate the concept of joining the information of two dataframes with pandas, let's take a small subset of our `cities` and `countries` datasets: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "cities2 = cities[cities['name'].isin(['Bern', 'Brussels', 'London', 'Paris'])].copy()\n",
    "cities2['iso_a3'] = ['CHE', 'BEL', 'GBR', 'FRA']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>name</th>\n",
       "      <th>geometry</th>\n",
       "      <th>iso_a3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>Bern</td>\n",
       "      <td>POINT (7.466975462482424 46.91668275866772)</td>\n",
       "      <td>CHE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>Brussels</td>\n",
       "      <td>POINT (4.33137074969045 50.83526293533032)</td>\n",
       "      <td>BEL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>219</th>\n",
       "      <td>London</td>\n",
       "      <td>POINT (-0.1186677024759319 51.5019405883275)</td>\n",
       "      <td>GBR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>235</th>\n",
       "      <td>Paris</td>\n",
       "      <td>POINT (2.33138946713035 48.86863878981461)</td>\n",
       "      <td>FRA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         name                                      geometry iso_a3\n",
       "26       Bern   POINT (7.466975462482424 46.91668275866772)    CHE\n",
       "170  Brussels    POINT (4.33137074969045 50.83526293533032)    BEL\n",
       "219    London  POINT (-0.1186677024759319 51.5019405883275)    GBR\n",
       "235     Paris    POINT (2.33138946713035 48.86863878981461)    FRA"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cities2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>iso_a3</th>\n",
       "      <th>name</th>\n",
       "      <th>continent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AFG</td>\n",
       "      <td>Afghanistan</td>\n",
       "      <td>Asia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AGO</td>\n",
       "      <td>Angola</td>\n",
       "      <td>Africa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ALB</td>\n",
       "      <td>Albania</td>\n",
       "      <td>Europe</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ARE</td>\n",
       "      <td>United Arab Emirates</td>\n",
       "      <td>Asia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ARG</td>\n",
       "      <td>Argentina</td>\n",
       "      <td>South America</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  iso_a3                  name      continent\n",
       "0    AFG           Afghanistan           Asia\n",
       "1    AGO                Angola         Africa\n",
       "2    ALB               Albania         Europe\n",
       "3    ARE  United Arab Emirates           Asia\n",
       "4    ARG             Argentina  South America"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "countries2 = countries[['iso_a3', 'name', 'continent']]\n",
    "countries2.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We added a 'iso_a3' column to the `cities` dataset, indicating a code of the country of the city. This country code is also present in the `countries` dataset, which allows us to merge those two dataframes based on the common column.\n",
    "\n",
    "Joining the `cities` dataframe with `countries` will transfer extra information about the countries (the full name, the continent) to the `cities` dataframe, based on a common key:"
   ]
  },
  {
   "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>name_x</th>\n",
       "      <th>geometry</th>\n",
       "      <th>iso_a3</th>\n",
       "      <th>name_y</th>\n",
       "      <th>continent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Bern</td>\n",
       "      <td>POINT (7.466975462482424 46.91668275866772)</td>\n",
       "      <td>CHE</td>\n",
       "      <td>Switzerland</td>\n",
       "      <td>Europe</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brussels</td>\n",
       "      <td>POINT (4.33137074969045 50.83526293533032)</td>\n",
       "      <td>BEL</td>\n",
       "      <td>Belgium</td>\n",
       "      <td>Europe</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>London</td>\n",
       "      <td>POINT (-0.1186677024759319 51.5019405883275)</td>\n",
       "      <td>GBR</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Europe</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Paris</td>\n",
       "      <td>POINT (2.33138946713035 48.86863878981461)</td>\n",
       "      <td>FRA</td>\n",
       "      <td>France</td>\n",
       "      <td>Europe</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     name_x                                      geometry iso_a3  \\\n",
       "0      Bern   POINT (7.466975462482424 46.91668275866772)    CHE   \n",
       "1  Brussels    POINT (4.33137074969045 50.83526293533032)    BEL   \n",
       "2    London  POINT (-0.1186677024759319 51.5019405883275)    GBR   \n",
       "3     Paris    POINT (2.33138946713035 48.86863878981461)    FRA   \n",
       "\n",
       "           name_y continent  \n",
       "0     Switzerland    Europe  \n",
       "1         Belgium    Europe  \n",
       "2  United Kingdom    Europe  \n",
       "3          France    Europe  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cities2.merge(countries2, on='iso_a3')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**But**, for this illustrative example, we added the common column manually, it is not present in the original dataset. However, we can still know how to join those two datasets based on their spatial coordinates."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Recap - spatial relationships between objects\n",
    "\n",
    "In the previous notebook [02-spatial-relationships.ipynb](./02-spatial-relationships-operations.ipynb), we have seen the notion of spatial relationships between geometry objects: within, contains, intersects, ...\n",
    "\n",
    "In this case, we know that each of the cities is located *within* one of the countries, or the other way around that each country can *contain* multiple cities.\n",
    "\n",
    "We can test such relationships using the methods we have seen in the previous notebook:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "france = countries.loc[countries['name'] == 'France', 'geometry'].squeeze()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      False\n",
       "1      False\n",
       "2      False\n",
       "3      False\n",
       "4      False\n",
       "       ...  \n",
       "238    False\n",
       "239    False\n",
       "240    False\n",
       "241    False\n",
       "242    False\n",
       "Length: 243, dtype: bool"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cities.within(france)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The above gives us a boolean series, indicating for each point in our `cities` dataframe whether it is located within the area of France or not.  \n",
    "Because this is a boolean series as result, we can use it to filter the original dataframe to only show those cities that are actually within France:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Monaco</td>\n",
       "      <td>POINT (7.406913173465057 43.73964568785249)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>POINT (1.51648596050552 42.5000014435459)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>186</th>\n",
       "      <td>Geneva</td>\n",
       "      <td>POINT (6.140028034091699 46.21000754707626)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>235</th>\n",
       "      <td>Paris</td>\n",
       "      <td>POINT (2.33138946713035 48.86863878981461)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        name                                     geometry\n",
       "10    Monaco  POINT (7.406913173465057 43.73964568785249)\n",
       "13   Andorra    POINT (1.51648596050552 42.5000014435459)\n",
       "186   Geneva  POINT (6.140028034091699 46.21000754707626)\n",
       "235    Paris   POINT (2.33138946713035 48.86863878981461)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cities[cities.within(france)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We could now repeat the above analysis for each of the countries, and add a column to the `cities` dataframe indicating this country. However, that would be tedious to do manually, and is also exactly what the spatial join operation provides us.\n",
    "\n",
    "*(note: the above result is incorrect, but this is just because of the coarse-ness of the countries dataset)*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Spatial join operation\n",
    "\n",
    "<div class=\"alert alert-info\" style=\"font-size:120%\">\n",
    "    \n",
    "**SPATIAL JOIN** = *transferring attributes from one layer to another based on their spatial relationship* <br><br>\n",
    "\n",
    "\n",
    "Different parts of this operations:\n",
    "\n",
    "* The GeoDataFrame to which we want add information\n",
    "* The GeoDataFrame that contains the information we want to add\n",
    "* The spatial relationship we want to use to match both datasets ('intersects', 'contains', 'within')\n",
    "* The type of join: left or inner join\n",
    "\n",
    "\n",
    "![](img/illustration-spatial-join.svg)\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "-"
    }
   },
   "source": [
    "In this case, we want to join the `cities` dataframe with the information of the `countries` dataframe, based on the spatial relationship between both datasets.\n",
    "\n",
    "We use the [`geopandas.sjoin`](http://geopandas.readthedocs.io/en/latest/reference/geopandas.sjoin.html) function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "joined = geopandas.sjoin(cities, countries, op='within', how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>name_left</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>iso_a3</th>\n",
       "      <th>name_right</th>\n",
       "      <th>continent</th>\n",
       "      <th>pop_est</th>\n",
       "      <th>gdp_md_est</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vatican City</td>\n",
       "      <td>POINT (12.45338654497177 41.90328217996012)</td>\n",
       "      <td>79.0</td>\n",
       "      <td>ITA</td>\n",
       "      <td>Italy</td>\n",
       "      <td>Europe</td>\n",
       "      <td>6.213780e+07</td>\n",
       "      <td>2221000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>San Marino</td>\n",
       "      <td>POINT (12.44177015780014 43.936095834768)</td>\n",
       "      <td>79.0</td>\n",
       "      <td>ITA</td>\n",
       "      <td>Italy</td>\n",
       "      <td>Europe</td>\n",
       "      <td>6.213780e+07</td>\n",
       "      <td>2221000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Vaduz</td>\n",
       "      <td>POINT (9.516669472907267 47.13372377429357)</td>\n",
       "      <td>9.0</td>\n",
       "      <td>AUT</td>\n",
       "      <td>Austria</td>\n",
       "      <td>Europe</td>\n",
       "      <td>8.754413e+06</td>\n",
       "      <td>416600.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Lobamba</td>\n",
       "      <td>POINT (31.19999710971274 -26.46666746135247)</td>\n",
       "      <td>152.0</td>\n",
       "      <td>SWZ</td>\n",
       "      <td>Swaziland</td>\n",
       "      <td>Africa</td>\n",
       "      <td>1.467152e+06</td>\n",
       "      <td>11060.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Luxembourg</td>\n",
       "      <td>POINT (6.130002806227083 49.61166037912108)</td>\n",
       "      <td>97.0</td>\n",
       "      <td>LUX</td>\n",
       "      <td>Luxembourg</td>\n",
       "      <td>Europe</td>\n",
       "      <td>5.941300e+05</td>\n",
       "      <td>58740.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>238</th>\n",
       "      <td>Rio de Janeiro</td>\n",
       "      <td>POINT (-43.22696665284366 -22.92307731561596)</td>\n",
       "      <td>22.0</td>\n",
       "      <td>BRA</td>\n",
       "      <td>Brazil</td>\n",
       "      <td>South America</td>\n",
       "      <td>2.073534e+08</td>\n",
       "      <td>3081000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>239</th>\n",
       "      <td>São Paulo</td>\n",
       "      <td>POINT (-46.62696583905523 -23.55673372837896)</td>\n",
       "      <td>22.0</td>\n",
       "      <td>BRA</td>\n",
       "      <td>Brazil</td>\n",
       "      <td>South America</td>\n",
       "      <td>2.073534e+08</td>\n",
       "      <td>3081000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>Sydney</td>\n",
       "      <td>POINT (151.1832339501475 -33.91806510862875)</td>\n",
       "      <td>8.0</td>\n",
       "      <td>AUS</td>\n",
       "      <td>Australia</td>\n",
       "      <td>Oceania</td>\n",
       "      <td>2.323241e+07</td>\n",
       "      <td>1189000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>241</th>\n",
       "      <td>Singapore</td>\n",
       "      <td>POINT (103.853874819099 1.294979325105942)</td>\n",
       "      <td>111.0</td>\n",
       "      <td>MYS</td>\n",
       "      <td>Malaysia</td>\n",
       "      <td>Asia</td>\n",
       "      <td>3.138199e+07</td>\n",
       "      <td>863000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>242</th>\n",
       "      <td>Hong Kong</td>\n",
       "      <td>POINT (114.183063458463 22.30692675357551)</td>\n",
       "      <td>30.0</td>\n",
       "      <td>CHN</td>\n",
       "      <td>China</td>\n",
       "      <td>Asia</td>\n",
       "      <td>1.379303e+09</td>\n",
       "      <td>21140000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>243 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          name_left                                       geometry  \\\n",
       "0      Vatican City    POINT (12.45338654497177 41.90328217996012)   \n",
       "1        San Marino      POINT (12.44177015780014 43.936095834768)   \n",
       "2             Vaduz    POINT (9.516669472907267 47.13372377429357)   \n",
       "3           Lobamba   POINT (31.19999710971274 -26.46666746135247)   \n",
       "4        Luxembourg    POINT (6.130002806227083 49.61166037912108)   \n",
       "..              ...                                            ...   \n",
       "238  Rio de Janeiro  POINT (-43.22696665284366 -22.92307731561596)   \n",
       "239       São Paulo  POINT (-46.62696583905523 -23.55673372837896)   \n",
       "240          Sydney   POINT (151.1832339501475 -33.91806510862875)   \n",
       "241       Singapore     POINT (103.853874819099 1.294979325105942)   \n",
       "242       Hong Kong     POINT (114.183063458463 22.30692675357551)   \n",
       "\n",
       "     index_right iso_a3  name_right      continent       pop_est  gdp_md_est  \n",
       "0           79.0    ITA       Italy         Europe  6.213780e+07   2221000.0  \n",
       "1           79.0    ITA       Italy         Europe  6.213780e+07   2221000.0  \n",
       "2            9.0    AUT     Austria         Europe  8.754413e+06    416600.0  \n",
       "3          152.0    SWZ   Swaziland         Africa  1.467152e+06     11060.0  \n",
       "4           97.0    LUX  Luxembourg         Europe  5.941300e+05     58740.0  \n",
       "..           ...    ...         ...            ...           ...         ...  \n",
       "238         22.0    BRA      Brazil  South America  2.073534e+08   3081000.0  \n",
       "239         22.0    BRA      Brazil  South America  2.073534e+08   3081000.0  \n",
       "240          8.0    AUS   Australia        Oceania  2.323241e+07   1189000.0  \n",
       "241        111.0    MYS    Malaysia           Asia  3.138199e+07    863000.0  \n",
       "242         30.0    CHN       China           Asia  1.379303e+09  21140000.0  \n",
       "\n",
       "[243 rows x 8 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joined"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Asia             59\n",
       "Africa           57\n",
       "Europe           46\n",
       "North America    26\n",
       "South America    14\n",
       "Oceania           8\n",
       "Name: continent, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joined['continent'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Lets's practice!\n",
    "\n",
    "We will again use the Paris datasets to do some exercises. Let's start importing them again:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "districts = geopandas.read_file(\"data/paris_districts_utm.geojson\")\n",
    "stations = geopandas.read_file(\"data/paris_sharing_bike_stations_utm.geojson\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-success\">\n",
    " <b>EXERCISE: Make a plot of the density of bike stations by district</b>\n",
    " <p>\n",
    " <ul>\n",
    "  <li>Determine for each bike station in which district it is located (using a spatial join!). Call the result `joined`.</li>\n",
    "  <li>Based on this result, calculate the number of bike stations in each district (e.g. using `groupby` method; you can use the `size` size method to know the size of each group).\n",
    "    <ul>\n",
    "      <li>Make sure the result is a DataFrame called `counts` with the columns 'district_name' and 'n_bike_stations'.</li>\n",
    "      <li>To go from a Series to a DataFrame, you can use the `reset_index` or `to_frame` method (both have a `name` keyword to specify a column name for the original Series values.\n",
    "    </ul>   \n",
    "   </li>\n",
    "  <li>Add those counts to the original `districts` dataframe, creating a new `districts2` dataframe (tip: this is a merge operation).</li>\n",
    "  <li>Calculate a new column 'n_bike_stations_by_area'.</li>\n",
    "  <li>Make a plot showing the density in bike stations of the districts.</li>  \n",
    " </ul> \n",
    " </p>\n",
    " \n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "clear_cell": true
   },
   "outputs": [],
   "source": [
    "joined = geopandas.sjoin(stations, districts[['district_name', 'geometry']], op='within')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "clear_cell": 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>name</th>\n",
       "      <th>bike_stands</th>\n",
       "      <th>available_bikes</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>district_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>14002 - RASPAIL QUINET</td>\n",
       "      <td>44</td>\n",
       "      <td>4</td>\n",
       "      <td>POINT (450804.448740735 5409797.268203795)</td>\n",
       "      <td>52</td>\n",
       "      <td>Montparnasse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>143</th>\n",
       "      <td>14112 - FAUBOURG SAINT JACQUES CASSINI</td>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "      <td>POINT (451419.446715647 5409421.528587255)</td>\n",
       "      <td>52</td>\n",
       "      <td>Montparnasse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>14033 - DAGUERRE GASSENDI</td>\n",
       "      <td>38</td>\n",
       "      <td>1</td>\n",
       "      <td>POINT (450708.2275807534 5409406.941172979)</td>\n",
       "      <td>52</td>\n",
       "      <td>Montparnasse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>346</th>\n",
       "      <td>14006 - SAINT JACQUES TOMBE ISSOIRE</td>\n",
       "      <td>22</td>\n",
       "      <td>0</td>\n",
       "      <td>POINT (451340.0264470892 5409124.574548723)</td>\n",
       "      <td>52</td>\n",
       "      <td>Montparnasse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>429</th>\n",
       "      <td>14111 - DENFERT-ROCHEREAU CASSINI</td>\n",
       "      <td>24</td>\n",
       "      <td>8</td>\n",
       "      <td>POINT (451274.5111513372 5409609.730783217)</td>\n",
       "      <td>52</td>\n",
       "      <td>Montparnasse</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       name  bike_stands  available_bikes  \\\n",
       "0                    14002 - RASPAIL QUINET           44                4   \n",
       "143  14112 - FAUBOURG SAINT JACQUES CASSINI           16                0   \n",
       "293               14033 - DAGUERRE GASSENDI           38                1   \n",
       "346     14006 - SAINT JACQUES TOMBE ISSOIRE           22                0   \n",
       "429       14111 - DENFERT-ROCHEREAU CASSINI           24                8   \n",
       "\n",
       "                                        geometry  index_right district_name  \n",
       "0     POINT (450804.448740735 5409797.268203795)           52  Montparnasse  \n",
       "143   POINT (451419.446715647 5409421.528587255)           52  Montparnasse  \n",
       "293  POINT (450708.2275807534 5409406.941172979)           52  Montparnasse  \n",
       "346  POINT (451340.0264470892 5409124.574548723)           52  Montparnasse  \n",
       "429  POINT (451274.5111513372 5409609.730783217)           52  Montparnasse  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joined.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "clear_cell": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "district_name\n",
       "Amérique           17\n",
       "Archives            4\n",
       "Arsenal             7\n",
       "Arts-et-Metiers     4\n",
       "Auteuil            21\n",
       "dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# counting the number of stations in each district\n",
    "counts = joined.groupby('district_name').size()\n",
    "counts.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "clear_cell": 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>district_name</th>\n",
       "      <th>n_bike_stations</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Amérique</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Archives</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Arsenal</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Arts-et-Metiers</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Auteuil</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     district_name  n_bike_stations\n",
       "0         Amérique               17\n",
       "1         Archives                4\n",
       "2          Arsenal                7\n",
       "3  Arts-et-Metiers                4\n",
       "4          Auteuil               21"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert the above in a DataFrame with two columns\n",
    "counts = counts.reset_index(name='n_bike_stations')\n",
    "counts.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "clear_cell": 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>id</th>\n",
       "      <th>district_name</th>\n",
       "      <th>population</th>\n",
       "      <th>geometry</th>\n",
       "      <th>n_bike_stations</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>St-Germain-l'Auxerrois</td>\n",
       "      <td>1672</td>\n",
       "      <td>POLYGON ((451922.1333912524 5411438.484355546,...</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Halles</td>\n",
       "      <td>8984</td>\n",
       "      <td>POLYGON ((452278.4194036503 5412160.89282334, ...</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Palais-Royal</td>\n",
       "      <td>3195</td>\n",
       "      <td>POLYGON ((451553.8057660239 5412340.522224233,...</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Place-Vendôme</td>\n",
       "      <td>3044</td>\n",
       "      <td>POLYGON ((451004.907944323 5412654.094913081, ...</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Gaillon</td>\n",
       "      <td>1345</td>\n",
       "      <td>POLYGON ((451328.7522686935 5412991.278156867,...</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id           district_name  population  \\\n",
       "0   1  St-Germain-l'Auxerrois        1672   \n",
       "1   2                  Halles        8984   \n",
       "2   3            Palais-Royal        3195   \n",
       "3   4           Place-Vendôme        3044   \n",
       "4   5                 Gaillon        1345   \n",
       "\n",
       "                                            geometry  n_bike_stations  \n",
       "0  POLYGON ((451922.1333912524 5411438.484355546,...                4  \n",
       "1  POLYGON ((452278.4194036503 5412160.89282334, ...               13  \n",
       "2  POLYGON ((451553.8057660239 5412340.522224233,...                6  \n",
       "3  POLYGON ((451004.907944323 5412654.094913081, ...                5  \n",
       "4  POLYGON ((451328.7522686935 5412991.278156867,...                4  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# merging those counts back into the districts dataset\n",
    "districts2 = districts.merge(counts, on='district_name')\n",
    "districts2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "clear_cell": true
   },
   "outputs": [],
   "source": [
    "# calculating the relative number of bike stations by area\n",
    "districts2['n_bike_stations_by_area'] = (\n",
    "    districts2['n_bike_stations'] / districts2.geometry.area)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "clear_cell": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = districts2.plot(column='n_bike_stations_by_area',\n",
    "                    figsize=(15, 6))\n",
    "ax.set_axis_off()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The overlay operation\n",
    "\n",
    "In the spatial join operation above, we are not changing the geometries itself. We are not joining geometries, but joining attributes based on a spatial relationship between the geometries. This also means that the geometries need to at least overlap partially.\n",
    "\n",
    "If you want to create new geometries based on joining (combining) geometries of different dataframes into one new dataframe (eg by taking the intersection of the geometries), you want an **overlay** operation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "africa = countries[countries['continent'] == 'Africa']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f9e890c1f98>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "africa.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "cities['geometry'] = cities.buffer(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f9e80dbfb00>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "geopandas.overlay(africa, cities, how='difference').plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\" style=\"font-size:120%\">\n",
    "<b>REMEMBER</b> <br>\n",
    "\n",
    "* **Spatial join**: transfer attributes from one dataframe to another based on the spatial relationship\n",
    "* **Spatial overlay**: construct new geometries based on spatial operation between both dataframes (and combining attributes of both dataframes)\n",
    "\n",
    "</div>"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}