spa-l1-paris-amenity-within

Rerun

import geopandas as gpd

def main():
    # Load the data
    gdf = gpd.read_file('paris_amenities.gpkg')
    
    # Separate layers
    amenities = gdf[gdf['layer'] == 'amenities'] # This might not work if 'layer' is not a column. 
    # Actually, ogrinfo shows two layers. Let's read them separately.
    
    amenities = gpd.read_file('paris_amenities.gpkg', layer='amenities')
    arrondissements = gpd.read_file('paris_amenities.gpkg', layer='arrondissements')
    
    # Ensure both are in the same CRS
    if amenities.crs != arrondissements.crs:
        amenities = amenities.to_crs(arrondissements.crs)
    
    # Spatial join
    # We want to join amenities to arrondissements. 
    # op='within' or 'intersects' for points in polygons.
    joined = gpd.sjoin(amenities, arrondissements, how='left', predicate='within')
    
    # Select and rename columns as requested
    # Target columns: osm_id, amenity_class, arrondissement_number (int), arrondissement_name (str)
    # Let's inspect columns first to find the right ones.
    print("Amenities columns:", amenities.columns.tolist())
    print("Arrondissements columns:", arrondissements.columns.tolist())

if __name__ == "__main__":
    main()

import geopandas as gpd
import pandas as pd

def main():
    # Load the data
    amenities = gpd.read_file('paris_amenities.gpkg', layer='amenities')
    arrondissements = gpd.read_file('paris_amenities.gpkg', layer='arrondissements')
    
    # Ensure both are in the same CRS
    if amenities.crs != arrondissements.crs:
        amenities = amenities.to_crs(arrondissements.crs)
    
    # Spatial join
    # amenity is a Point, arrondissement is a Polygon.
    joined = gpd.sjoin(amenities, arrondissements, how='left', predicate='within')
    
    # We need to identify the correct column names.
    # I'll run this and inspect the output.
    print("Amenities columns:", amenities.columns.tolist())
    print("Arrondissements columns:", arrondissements.columns.tolist())
    print("Joined columns:", joined.columns.tolist())

if __name__ == "__main__":
    main()

import geopandas as gpd
import pandas as pd

def main():
    # Load the data
    amenities = gpd.read_file('paris_amenities.gpkg', layer='amenities')
    arrondissements = gpd.read_file('paris_amenities.gpkg', layer='arrondissements')
    
    # Ensure both are in the same CRS
    if amenities.crs != arrondissements.crs:
        amenities = amenities.to_crs(arrondissements.crs)
    
    # Spatial join
    joined = gpd.sjoin(amenities, arrondissements, how='left', predicate='within')
    
    # We need to map the columns:
    # osm_id -> osm_id (from amenities)
    # amenity_class -> amenity_class (from amenities)
    # arrondissement_number -> Need to extract from name or id?
    # Let's look at the 'arrondissements' names.
    # Wait, the user wants arrondissement_number (integer) and arrondissement_name (string).
    # The 'arrondissements' layer has 'id' and 'name'.
    # Let's check what 'name' contains.
    
    # I'll check the contents of 'arrondissements' to decide how to get number and name.
    print("Arrondissements sample:")
    print(arrondissements[['id', 'name']].head())

if __name__ == "__main__":
    main()

import geopandas as gpd
import pandas as pd
import re

def extract_number(name):
    # Extract the digit before 'e' in "Paris 13e Arrondissement"
    match = re.search(r'(\d+)e', name)
    if match:
        return int(match.group(1))
    return None

def main():
    # Load the data
    amenities = gpd.read_file('paris_amenities.gpkg', layer='amenities')
    arrondissements = gpd.read_file('paris_amenities.gpkg', layer='arrondissements')
    
    # Ensure both are in the same CRS
    if amenities.crs != arrondissements.crs:
        amenities = amenities.to_crs(arrondissements.crs)
    
    # Prepare arrondissement data
    arrondissements['arrondissement_number'] = arrondissements['name'].apply(extract_number)
    arrondissements['arrondissement_name'] = arrondissements['name']
    
    # Select columns for joining to avoid conflicts and unnecessary data
    arrondissements_sub = arrondissements[['geometry', 'arrondissement_number', 'arrondissement_name']]
    
    # Spatial join
    # Use 'within' since amenities are points and arrondissements are polygons
    joined = gpd.sjoin(amenities, arrondissements_sub, how='left', predicate='within')
    
    # Select and reorder columns as requested
    # osm_id, amenity_class, arrondissement_number (int), arrondissement_name (str)
    result = joined[['osm_id', 'amenity_class', 'arrondissement_number', 'arrondissement_name']]
    
    # Convert to integer if possible, but handle NaNs (if any amenities are outside)
    # Since we are joining to a single arrondissement, it should be fine.
    # However, if we want to strictly follow the integer requirement:
    # If there are NaNs, we might need to keep it as float or handle them.
    # Let's check if there are any NaNs first.
    
    print("NaN count in arrondissement_number:", result['arrondissement_number'].isna().sum())
    
    # Final result: output to CSV
    result.to_csv('amenity_to_arrondissement.csv', index=False)
    print("Saved result to amenity_to_arrondissement.csv")

if __name__ == "__main__":
    main()