claude

import geopandas as gpd
import pandas as pd
from shapely.geometry import Point
import os

def process_zipcodes(exposure_data_path, gfk_zipcodes_path, output_folder):
    """
    Process zipcodes by identifying missing zipcodes and assigning nearest zipcodes.
    
    Parameters:
    - exposure_data_path: Path to the exposure data CSV/Excel file
    - gfk_zipcodes_path: Path to the GFK zipcodes shapefile
    - output_folder: Folder to save output files
    """
    # Create output folder if it doesn't exist
    os.makedirs(output_folder, exist_ok=True)
    
    # Read exposure data
    exposure_df = pd.read_csv(exposure_data_path)
    
    # Read GFK zipcodes
    gfk_gdf = gpd.read_file(gfk_zipcodes_path)
    
    # Create a GeoDataFrame from exposure data
    exposure_gdf = gpd.GeoDataFrame(
        exposure_df, 
        geometry=gpd.points_from_xy(exposure_df.lon, exposure_df.lat),
        crs=gfk_gdf.crs
    )
    
    # Find unique zipcodes in exposure data
    exposure_zipcodes = set(exposure_df['zipcode'])
    gfk_zipcodes = set(gfk_gdf['zipcode'])  # Assuming 'zipcode' column exists in GFK data
    
    # Zipcodes in exposure data but not in GFK zipcodes
    missing_zipcodes = exposure_zipcodes - gfk_zipcodes
    
    # Filter exposure data for missing zipcodes
    missing_zipcodes_df = exposure_gdf[exposure_gdf['zipcode'].isin(missing_zipcodes)]
    
    # Export missing zipcodes data
    missing_zipcodes_path = os.path.join(output_folder, 'missing_zipcodes.csv')
    missing_zipcodes_df.drop('geometry', axis=1).to_csv(missing_zipcodes_path, index=False)
    
    # Find nearest zipcode for missing zipcodes
    def find_nearest_zipcode(point):
        # Calculate distances to all GFK zipcode polygons
        distances = gfk_gdf.geometry.distance(point)
        # Return the zipcode of the nearest polygon
        return gfk_gdf.iloc[distances.argmin()]['zipcode']
    
    # Assign nearest zipcodes
    missing_zipcodes_df['nearest_zipcode'] = missing_zipcodes_df['geometry'].apply(find_nearest_zipcode)
    
    # Export nearest zipcode assignments
    nearest_zipcodes_path = os.path.join(output_folder, 'nearest_zipcodes.csv')
    missing_zipcodes_df.drop('geometry', axis=1).to_csv(nearest_zipcodes_path, index=False)
    
    # Print summary
    print(f"Total missing zipcodes: {len(missing_zipcodes)}")
    print(f"Missing zipcodes exported to: {missing_zipcodes_path}")
    print(f"Nearest zipcodes exported to: {nearest_zipcodes_path}")

# Example usage
# process_zipcodes(
#     exposure_data_path='path/to/exposure_data.csv', 
#     gfk_zipcodes_path='path/to/gfk_zipcodes.shp', 
#     output_folder='path/to/output_folder'
# )