.. _geopandasrst:

=========
Geopandas
=========


.. only:: html

    **Links:** :download:`notebook <geopandas.ipynb>`, :downloadlink:`html <geopandas2html.html>`, :download:`PDF <geopandas.pdf>`, :download:`python <geopandas.py>`, :downloadlink:`slides <geopandas.slides.html>`, :githublink:`GitHub|_doc/notebooks/decouverte/geopandas.ipynb|*`


`geopandas <https://geopandas.org/en/stable/>`__ est devenu le point
d’entrée à tout traitement lié aux coordonnées géographiques.

.. code:: ipython3

    from jyquickhelper import add_notebook_menu
    add_notebook_menu()






.. contents::
    :local:





Coordonnées géographiques, et geocoding
---------------------------------------

.. code:: ipython3

    import geopandas
    import pandas

.. code:: ipython3

    df = pandas.DataFrame(dict(name=["A", "B", "C", "D", "E"],
                               address=["50 rue du moulin 08000 Charleville-Mézières",
                                        "50 rue dumoulin 08000 Charleville-Mézières",
                                        "50 rue du moulin 08000 Charleville",
                                        "29 rue Ordener 75018 Paris",
                                        "Gare Lille"]))
    df






.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>name</th>
          <th>address</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>A</td>
          <td>50 rue du moulin 08000 Charleville-Mézières</td>
        </tr>
        <tr>
          <th>1</th>
          <td>B</td>
          <td>50 rue dumoulin 08000 Charleville-Mézières</td>
        </tr>
        <tr>
          <th>2</th>
          <td>C</td>
          <td>50 rue du moulin 08000 Charleville</td>
        </tr>
        <tr>
          <th>3</th>
          <td>D</td>
          <td>29 rue Ordener 75018 Paris</td>
        </tr>
        <tr>
          <th>4</th>
          <td>E</td>
          <td>Gare Lille</td>
        </tr>
      </tbody>
    </table>
    </div>



.. code:: ipython3

    from geopy.geocoders import Nominatim

.. code:: ipython3

    geolocator = Nominatim(timeout=10, user_agent = "myGeolocator")
    res = geolocator.geocode("50 rue du moulin 08000 Charleville-Mézières")
    res




.. parsed-literal::
    Location(50, Rue du Moulin, Charleville-Mézières, Ardennes, Grand Est, France métropolitaine, 08000, France, (49.775247, 4.721863, 0.0))



.. code:: ipython3

    res.latitude, res.longitude, res.point




.. parsed-literal::
    (49.775247, 4.721863, Point(49.775247, 4.721863, 0.0))



.. code:: ipython3

    coordinates = df['address'].apply(geolocator.geocode)

.. code:: ipython3

    import numpy
    from shapely.geometry import Point
    
    df['position'] = [numpy.nan if c is None else 
                      Point(c.point.longitude, c.point.latitude) for c in coordinates]
    df






.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>name</th>
          <th>address</th>
          <th>position</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>A</td>
          <td>50 rue du moulin 08000 Charleville-Mézières</td>
          <td>POINT (4.721863 49.775247)</td>
        </tr>
        <tr>
          <th>1</th>
          <td>B</td>
          <td>50 rue dumoulin 08000 Charleville-Mézières</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>2</th>
          <td>C</td>
          <td>50 rue du moulin 08000 Charleville</td>
          <td>POINT (4.721863 49.775247)</td>
        </tr>
        <tr>
          <th>3</th>
          <td>D</td>
          <td>29 rue Ordener 75018 Paris</td>
          <td>POINT (2.3539607 48.8906617)</td>
        </tr>
        <tr>
          <th>4</th>
          <td>E</td>
          <td>Gare Lille</td>
          <td>POINT (3.162718387293441 50.69456630000001)</td>
        </tr>
      </tbody>
    </table>
    </div>



.. code:: ipython3

    geodf = geopandas.GeoDataFrame(df)

.. code:: ipython3

    geodf






.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>name</th>
          <th>address</th>
          <th>position</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>A</td>
          <td>50 rue du moulin 08000 Charleville-Mézières</td>
          <td>POINT (4.721863 49.775247)</td>
        </tr>
        <tr>
          <th>1</th>
          <td>B</td>
          <td>50 rue dumoulin 08000 Charleville-Mézières</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>2</th>
          <td>C</td>
          <td>50 rue du moulin 08000 Charleville</td>
          <td>POINT (4.721863 49.775247)</td>
        </tr>
        <tr>
          <th>3</th>
          <td>D</td>
          <td>29 rue Ordener 75018 Paris</td>
          <td>POINT (2.3539607 48.8906617)</td>
        </tr>
        <tr>
          <th>4</th>
          <td>E</td>
          <td>Gare Lille</td>
          <td>POINT (3.162718387293441 50.69456630000001)</td>
        </tr>
      </tbody>
    </table>
    </div>



.. code:: ipython3

    geodf.dropna()






.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>name</th>
          <th>address</th>
          <th>position</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>A</td>
          <td>50 rue du moulin 08000 Charleville-Mézières</td>
          <td>POINT (4.721863 49.775247)</td>
        </tr>
        <tr>
          <th>2</th>
          <td>C</td>
          <td>50 rue du moulin 08000 Charleville</td>
          <td>POINT (4.721863 49.775247)</td>
        </tr>
        <tr>
          <th>3</th>
          <td>D</td>
          <td>29 rue Ordener 75018 Paris</td>
          <td>POINT (2.3539607 48.8906617)</td>
        </tr>
        <tr>
          <th>4</th>
          <td>E</td>
          <td>Gare Lille</td>
          <td>POINT (3.162718387293441 50.69456630000001)</td>
        </tr>
      </tbody>
    </table>
    </div>



.. code:: ipython3

    gdf = geodf.set_geometry('position')
    gdf






.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>name</th>
          <th>address</th>
          <th>position</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>A</td>
          <td>50 rue du moulin 08000 Charleville-Mézières</td>
          <td>POINT (4.72186 49.77525)</td>
        </tr>
        <tr>
          <th>1</th>
          <td>B</td>
          <td>50 rue dumoulin 08000 Charleville-Mézières</td>
          <td>None</td>
        </tr>
        <tr>
          <th>2</th>
          <td>C</td>
          <td>50 rue du moulin 08000 Charleville</td>
          <td>POINT (4.72186 49.77525)</td>
        </tr>
        <tr>
          <th>3</th>
          <td>D</td>
          <td>29 rue Ordener 75018 Paris</td>
          <td>POINT (2.35396 48.89066)</td>
        </tr>
        <tr>
          <th>4</th>
          <td>E</td>
          <td>Gare Lille</td>
          <td>POINT (3.16272 50.69457)</td>
        </tr>
      </tbody>
    </table>
    </div>



Carte
-----

.. code:: ipython3

    gdf.plot();



.. image:: geopandas_15_0.png


.. code:: ipython3

    import cartopy.crs as ccrs
    import cartopy.feature as cfeature
    import matplotlib.pyplot as plt

.. code:: ipython3

    fig = plt.figure(figsize=(7,7))
    ax = fig.add_subplot(1, 1, 1, projection=ccrs.PlateCarree())
    ax.set_extent([-5, 10, 42, 52])
    
    ax.add_feature(cfeature.OCEAN)
    ax.add_feature(cfeature.COASTLINE)
    ax.add_feature(cfeature.RIVERS)
    ax.add_feature(cfeature.LAKES)
    ax.add_feature(cfeature.LAND)
    ax.add_feature(cfeature.BORDERS, linestyle=':')
    ax.plot([2.35, 2.20], [48.85, 48.71], '.')
    ax.text(2.35, 48.85, "Paris")
    ax.text(2.20, 48.71, "Saclay", ha="right")
    ax.set_title('France');



.. image:: geopandas_17_0.png



.. code:: ipython3

    fig = plt.figure(figsize=(7,7))
    ax = fig.add_subplot(1, 1, 1, projection=ccrs.PlateCarree())
    ax = gdf.plot(ax=ax)
    ax.add_feature(cfeature.OCEAN)
    ax.add_feature(cfeature.COASTLINE)
    ax.add_feature(cfeature.RIVERS)
    ax.add_feature(cfeature.LAKES)
    ax.add_feature(cfeature.LAND)
    ax.add_feature(cfeature.BORDERS, linestyle=':')
    for i in range(gdf.shape[0]):
        if gdf.geometry[i] is None:
            continue
        ax.text(gdf.geometry[i].x, gdf.geometry[i].y, gdf.name[i])
    ax;



.. image:: geopandas_19_0.png


Régions administratives
-----------------------