dd-l1-london-parks-count

Rerun

import geopandas as gpd
import json

def main():
    # Load the data
    gdf = gpd.read_file('london_parks.fgb')
    
    # Assuming the area is in some projected CRS (like EPSG:27700 for UK).
    # If it's in WGS84, we need to reproject to get accurate areas.
    # Let's check the CRS first.
    print(f"Original CRS: {gdf.crs}")
    
    # Ensure we have an area column in hectares. 
    # We'll project to a metric CRS (EPSG:27700 is standard for UK) to calculate area accurately.
    if gdf.crs.is_geographic:
        gdf_projected = gdf.to_crs(epsg=27700)
    else:
        gdf_projected = gdf.copy()
    
    # Calculate area in square meters, then convert to hectares (1 ha = 10,000 m2)
    # We use the projected geometry for area calculation.
    gdf_projected['area_ha'] = gdf_projected.geometry.area / 10000.0
    
    # Filter parks that are 1 hectare or more
    large_parks = gdf_projected[gdf_projected['area_ha'] >= 1.0].copy()
    
    # Count
    count = len(large_parks)
    
    # Total area in hectares
    total_area_ha = large_parks['area_ha'].sum()
    
    # Calculate Bounding Box in WGS84
    # We need to transform back to WGS84 for the bbox
    if count > 0:
        large_parks_wgs84 = large_parks.to_crs(epsg=4326)
        bounds = large_parks_wgs84.total_bounds  # [xmin, ymin, xmax, ymax]
        bbox_wgs84 = bounds.tolist()
    else:
        bbox_wgs84 = []

    # Create output dictionary
    summary = {
        "count": int(count),
        "total_area_ha": float(total_area_ha),
        "bbox_wgs84": bbox_wgs84
    }
    
    # Save to JSON
    with open('parks_summary.json', 'w') as f:
        json.dump(summary, f, indent=4)
    
    print("Summary generated successfully.")
    print(summary)

if __name__ == "__main__":
    main()

import geopandas as gpd
import json
import numpy as np

def main():
    # Load the data
    gdf = gpd.read_file('london_parks.fgb')
    
    # The original CRS is EPSG:27700 (British National Grid)
    # Area calculation in square meters is accurate in this projection.
    gdf_projected = gdf.copy()
    
    # Calculate area in hectares (1 ha = 10,000 m2)
    gdf_projected['area_ha'] = gdf_projected.geometry.area / 10000.0
    
    # Filter parks that are 1 hectare or more
    large_parks = gdf_projected[gdf_projected['area_ha'] >= 1.0].copy()
    
    # Count
    count = len(large_parks)
    
    # Total area in hectares
    total_area_ha = large_parks['area_ha'].sum()
    
    # Calculate Bounding Box in WGS84
    if count > 0:
        large_parks_wgs84 = large_parks.to_crs(epsg=4326)
        bounds = large_parks_wgs84.total_bounds  # [xmin, ymin, xmax, ymax]
        bbox_wgs84 = bounds.tolist()
    else:
        bbox_wgs84 = []

    # Create output dictionary with clean types and rounding
    summary = {
        "count": int(count),
        "total_area_ha": float(round(total_area_ha, 2)),
        "bbox_wgs84": [float(round(x, 6)) for x in bbox_wgs84]
    }
    
    # Save to JSON
    with open('parks_summary.json', 'w') as f:
        json.dump(summary, f, indent=4)
    
    print("Summary generated successfully.")
    print(summary)

if __name__ == "__main__":
    main()