geo-l1-tokyo-busstop-buffer

Rerun

import geopandas as gpd

def main():
    # Load the input data
    input_file = 'tokyo_connectors.geojson'
    output_file = 'tokyo_stop_catchments.geoparquet'
    buffer_dist = 400  # meters

    print(f"Loading {input_file}...")
    gdf = gpd.read_file(input_file)

    # Check if the CRS is projected. Buffering in degrees is bad.
    # We need a metric CRS. For Tokyo, EPSG:6677 (JGD2011 / Japan Plane Rectangular CS VII) 
    # or EPSG:3857 (Web Mercator) are common. 
    # Let's check current CRS.
    print(f"Current CRS: {gdf.crs}")

    if gdf.crs is None:
        print("Warning: CRS is not defined. Assuming WGS84 and reprojecting to EPSG:6677.")
        gdf.set_crs(epsg=4326, inplace=True)

    # Reproject to a metric CRS (EPSG:6677 is suitable for Tokyo area)
    # If it's already projected, we might want to stay in it, but let's ensure it's metric.
    if gdf.crs.is_geographic:
        print("Reprojecting to EPSG:6677 for metric buffering...")
        gdf = gdf.to_crs(epsg=6677)
    
    # Perform the buffer
    print(f"Creating {buffer_dist}m buffers...")
    # We use dissolve=False (default) to keep one row per input geometry.
    # Since we want one Polygon/MultiPolygon per input connector, 
    # and input is likely points or lines, buffer() will return the geometry.
    gdf['geometry'] = gdf.geometry.buffer(buffer_dist)

    # Ensure we keep 'connector_id'
    if 'connector_id' not in gdf.columns:
        print(f"Error: 'connector_id' not found in columns: {gdf.columns}")
        return

    # Save to GeoParquet
    print(f"Saving to {output_file}...")
    gdf.to_parquet(output_file)
    print("Done!")

if __name__ == "__main__":
    main()

import geopandas as gpd

def main():
    # Load the output data to verify
    output_file = 'tokyo_stop_catchments.geoparquet'
    
    print(f"Verifying {output_file}...")
    gdf = gpd.read_file(output_file)
    
    print(f"Number of rows: {len(gdf)}")
    print(f"Columns: {gdf.columns.tolist()}")
    print(f"CRS: {gdf.crs}")
    
    # Check geometry type
    geom_types = gdf.geometry.type.unique()
    print(f"Geometry types present: {geom_types}")
    
    # Sample some data
    print("\nSample data:")
    print(gdf[['connector_id', 'geometry']].head())

    # Check if connector_id is present
    if 'connector_id' in gdf.columns:
        print("\n'connector_id' is present.")
    else:
        print("\n'connector_id' is MISSING!")

if __name__ == "__main__":
    main()

import geopandas as gpd
import pandas as pd

def main():
    # Load the output data to verify
    output_file = 'tokyo_stop_catchments.geoparquet'
    
    print(f"Verifying {output_file}...")
    # Use pandas to read parquet then convert to GeoDataFrame
    try:
        df = pd.read_parquet(output_file)
        gdf = gpd.GeoDataFrame(df, geometry='geometry', crs='EPSG:6677')
        
        print(f"Number of rows: {len(gdf)}")
        print(f"Columns: {gdf.columns.tolist()}")
        print(f"CRS: {gdf.crs}")
        
        # Check geometry type
        geom_types = gdf.geometry.type.unique()
        print(f"Geometry types present: {geom_types}")
        
        # Sample some data
        print("\nSample data:")
        print(gdf[['connector_id', 'geometry']].head())

        # Check if connector_id is present
        if 'connector_id' in gdf.columns:
            print("\n'connector_id' is present.")
        else:
            print("\n'connector_id' is MISSING!")
            
    except Exception as e:
        print(f"Error: {e}")

if __name__ == "__main__":
    main()

import geopandas as gpd

def main():
    # Load the input data
    input_file = 'tokyo_connectors.geojson'
    output_file = 'tokyo_stop_catchments.geoparquet'
    buffer_dist = 400  # meters

    print(f"Loading {input_file}...")
    gdf = gpd.read_file(input_file)

    # Check if the CRS is projected. Buffering in degrees is bad.
    print(f"Current CRS: {gdf.crs}")

    if gdf.crs is None:
        print("Warning: CRS is not defined. Assuming WGS84 and reprojecting to EPSG:6677.")
        gdf.set_crs(epsg=4326, inplace=True)

    # Reproject to a metric CRS (EPSG:6677 is suitable for Tokyo area)
    if gdf.crs.is_geographic:
        print("Reprojecting to EPSG:6677 for metric buffering...")
        gdf = gdf.to_crs(epsg=6677)
    
    # Perform the buffer
    print(f"Creating {buffer_dist}m buffers...")
    gdf['geometry'] = gdf.geometry.buffer(buffer_dist)

    # Ensure we keep 'connector_id'
    if 'connector_id' not in gdf.columns:
        print(f"Error: 'connector_id' not found in columns: {gdf.columns}")
        return

    # Save to GeoParquet using the correct engine/method
    print(f"Saving to {output_file}...")
    gdf.to_parquet(output_file)
    print("Done!")

if __name__ == "__main__":
    main()

import geopandas as gpd

def main():
    output_file = 'tokyo_stop_catchments.geoparquet'
    print(f"Verifying {output_file}...")
    
    # GeoPandas' read_file should work for GeoParquet if pyogrio or fiona is installed correctly
    # But let's try the standard way for GeoParquet
    try:
        gdf = gpd.read_file(output_file)
        print("Successfully read with gpd.read_file")
    except Exception as e:
        print(f"gpd.read_file failed: {e}")
        try:
            import pandas as pd
            df = pd.read_parquet(output_file)
            gdf = gpd.GeoDataFrame(df, geometry='geometry')
            print("Successfully read with pandas + GeoDataFrame conversion")
        except Exception as e2:
            print(f"pandas fallback failed: {e2}")
            return

    print(f"Number of rows: {len(gdf)}")
    print(f"Columns: {gdf.columns.tolist()}")
    print(f"CRS: {gdf.crs}")
    print(f"Geometry types: {gdf.geometry.type.unique()}")
    print("\nSample data:")
    print(gdf[['connector_id', 'geometry']].head())

if __name__ == "__main__":
    main()

import geopandas as gpd

def main():
    # Load the input data
    input_file = 'tokyo_connectors.geojson'
    output_file = 'tokyo_stop_catchments.geoparquet'
    buffer_dist = 400  # meters

    print(f"Loading {input_file}...")
    gdf = gpd.read_file(input_file)

    # Ensure metric CRS for Tokyo area
    if gdf.crs is None:
        gdf.set_crs(epsg=4326, inplace=True)

    if gdf.crs.is_geographic:
        print("Reprojecting to EPSG:6677 for metric buffering...")
        gdf = gdf.to_crs(epsg=6677)
    
    # Perform the buffer
    print(f"Creating {buffer_dist}m buffers...")
    gdf['geometry'] = gdf.geometry.buffer(buffer_dist)

    # Ensure we keep 'connector_id'
    if 'connector_id' not in gdf.columns:
        print(f"Error: 'connector_id' not found in columns: {gdf.columns}")
        return

    # Save to GeoParquet. 
    # To avoid the issues with pyogrio/fiona detection, 
    # we'll use the geopandas standard to_parquet.
    print(f"Saving to {output_file}...")
    gdf.to_parquet(output_file)
    print("Done!")

if __name__ == "__main__":
    main()

import geopandas as gpd
import pandas as pd
from shapely import wkb

def main():
    output_file = 'tokyo_stop_catchments.geoparquet'
    print(f"Verifying {output_file}...")
    
    try:
        # Try reading as a normal parquet via pandas first
        df = pd.read_parquet(output_file)
        print("Successfully read with pandas.read_parquet")
        
        # Check if the geometry column contains WKB or is already interpreted
        # In recent geopandas/pyarrow, it might be stored as WKB bytes in a column
        if 'geometry' in df.columns:
            print("Found 'geometry' column.")
            # If it's bytes, convert it to shapely objects
            if df['geometry'].dtype == 'object' and isinstance(df['geometry'].iloc[0], bytes):
                print("Geometry column contains bytes. Converting...")
                df['geometry'] = df['geometry'].apply(lambda x: wkb.loads(x) if x is not None else None)
            
            gdf = gpd.GeoDataFrame(df, geometry='geometry', crs='EPSG:6677')
            print("Successfully converted to GeoDataFrame")
        else:
            print(f"No 'geometry' column found. Columns: {df.columns}")
            return

        print(f"Number of rows: {len(gdf)}")
        print(f"Columns: {gdf.columns.tolist()}")
        print(f"CRS: {gdf.crs}")
        print(f"Geometry types: {gdf.geometry.type.unique()}")
        print("\nSample data:")
        print(gdf[['connector_id', 'geometry']].head())

    except Exception as e:
        print(f"Verification failed: {e}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    main()