geo-l1-tokyo-busstop-buffer

Rerun

import geopandas as gpd

def main():
    # Load the input file
    input_file = 'tokyo_connectors.geojson'
    output_file = 'tokyo_stop_catchments.geoparquet'
    
    print(f"Loading {input_file}...")
    gdf = gpd.read_file(input_file)
    
    # Check if connector_id exists
    if 'connector_id' not in gdf.columns:
        print(f"Warning: 'connector_id' not found in columns. Available columns: {gdf.columns.tolist()}")
        # For debugging, let's see what's in there
        # gdf.head()
    
    # Ensure we are in a metric CRS for buffering (e.g., UTM or similar)
    # Tokyo is roughly in UTM zone 54N (EPSG:32654)
    # Let's check the current CRS
    print(f"Current CRS: {gdf.crs}")
    
    # If it's WGS84 (EPSG:4326), we need to reproject to a metric system
    if gdf.crs is None or gdf.crs.is_geographic:
        print("Reprojecting to EPSG:32654 for accurate buffering...")
        gdf_metric = gdf.to_crs(epsg=32654)
    else:
        gdf_metric = gdf.copy()

    # Create 400m buffer
    print("Creating 400m buffers...")
    gdf_metric['geometry'] = gdf_metric.buffer(400)
    
    # Project back to original CRS (optional, but often good practice to keep original CRS)
    # However, the user might want the result in the original CRS or a metric one.
    # Usually, for catchments, we keep the original if it was lat/lon or the metric one.
    # Let's check what the original was.
    if gdf.crs is not None and gdf.crs.is_geographic:
         print(f"Reprojecting back to {gdf.crs}...")
         gdf_metric = gdf_metric.to_crs(gdf.crs)
    
    # Select only necessary columns if needed, but the prompt says "keep connector_id"
    # and implies we should preserve it. It doesn't say "only" connector_id,
    # but "one Polygon or MultiPolygon row per input connector".
    # Since buffer() preserves the row count and index, we are good.
    
    # Save to GeoParquet
    print(f"Saving to {output_file}...")
    gdf_metric.to_parquet(output_file)
    print("Done!")

if __name__ == "__main__":
    main()

import geopandas as gpd

def main():
    # Load the output file to verify
    output_file = 'tokyo_stop_catchments.geoparquet'
    print(f"Verifying {output_file}...")
    gdf = gpd.read_file(output_file)
    
    print("\nSummary of the resulting GeoDataFrame:")
    print(gdf.info())
    print("\nFirst few rows:")
    print(gdf.head())
    
    # Verify connector_id preservation
    if 'connector_id' in gdf.columns:
        print("\nSuccess: 'connector_id' is present.")
    else:
        print("\nError: 'connector_id' is missing!")
        
    # Verify geometry type
    print(f"\nGeometry type: {gdf.geometry.type.unique()}")

if __name__ == "__main__":
    main()

import geopandas as gpd

def main():
    # Load the output file to verify
    output_file = 'tokyo_stop_catchments.geoparquet'
    print(f"Verifying {output_file}...")
    
    # For GeoParquet, use read_parquet if read_file fails
    try:
        gdf = gpd.read_parquet(output_file)
    except Exception as e:
        print(f"Error reading parquet: {e}")
        return
    
    print("\nSummary of the resulting GeoDataFrame:")
    print(gdf.info())
    print("\nFirst few rows:")
    print(gdf.head())
    
    # Verify connector_id preservation
    if 'connector_id' in gdf.columns:
        print("\nSuccess: 'connector_id' is present.")
    else:
        print("\nError: 'connector_id' is missing!")
        
    # Verify geometry type
    print(f"\nGeometry type: {gdf.geometry.type.unique()}")

if __name__ == "__main__":
    main()