GeoData DareData Blog

distance_to_closest_metro.py

# Read the metro data
metro = pd.read_csv(Path("data", "metro_stations.csv"))

# Convert to a GeoDataFrame
metro = gpd.GeoDataFrame(
    metro,
    geometry=gpd.points_from_xy(metro.longitude, metro.latitude),
    crs="epsg:4326"
).to_crs(epsg=3857)

# Get the closest metro station to each house
closest_metros = gpd.sjoin_nearest(
    house_data_gdf,
    metro,
    how="left"
).loc[:, ["latitude_right", "longitude_right"]]

# Convert the closest metro location to a geometry
house_data_gdf["closest_metro"] = gpd.points_from_xy(
    closest_metros.longitude_right,
    closest_metros.latitude_right,
    crs="epsg:4326"
).to_crs(epsg=3857)

# Calculate the distance to the closest metro station
house_data_gdf.assign(
    metro_distance=house_data_gdf.distance(
        house_data_gdf.closest_metro, align=True))