dd-l1-capetown-clinics-bbox

Rerun

import pandas as pd
import json

def main():
    file_path = 'capetown_clinics.csv'
    
    try:
        df = pd.read_csv(file_path)
    except Exception as e:
        print(f"Error reading CSV: {e}")
        return

    # Check columns to ensure we have what we need
    # Assuming columns like 'latitude', 'longitude', and 'subdistrict' exist.
    # Let's inspect the columns first if needed, but I'll try to be robust.
    
    # 1. Total count
    total_count = len(df)
    
    # 2. Bounding Box
    # We need to identify the longitude and latitude columns.
    # Common names: 'longitude', 'latitude', 'lon', 'lat', 'x', 'y'
    lon_col = None
    lat_col = None
    
    for col in df.columns:
        c = col.lower()
        if c in ['longitude', 'lon', 'x']:
            lon_col = col
        if c in ['latitude', 'lat', 'y']:
            lat_col = col
            
    if lon_col and lat_col:
        min_lon = df[lon_col].min()
        max_lon = df[lon_col].max()
        min_lat = df[lat_col].min()
        max_lat = df[lat_col].max()
        bbox = [min_lon, min_lat, max_lon, max_lat]
    else:
        bbox = None
        print(f"Warning: Could not identify lon/lat columns. Columns found: {df.columns.tolist()}")

    # 3. Count per subdistrict
    # Assuming 'subdistrict' is the column name.
    subdistrict_col = None
    for col in df.columns:
        if 'subdistrict' in col.lower():
            subdistrict_col = col
            break
            
    if subdistrict_col:
        count_per_subdistrict = df[subdistrict_col].value_counts().to_dict()
    else:
        count_per_subdistrict = {}
        print(f"Warning: Could not identify subdistrict column. Columns found: {df.columns.tolist()}")

    # Prepare JSON
    inventory = {
        "count": int(total_count),
        "bbox": bbox,
        "count_per_subdistrict": count_per_subdistrict
    }

    with open('clinic_inventory.json', 'w') as f:
        json.dump(inventory, f, indent=4)
    
    print("Successfully created clinic_inventory.json")

if __name__ == "__main__":
    main()

import pandas as pd
import json
from shapely import wkt

def main():
    file_path = 'capetown_clinics.csv'
    
    try:
        df = pd.read_csv(file_path)
    except Exception as e:
        print(f"Error reading CSV: {e}")
        return

    # 1. Total count
    total_count = len(df)
    
    # 2. Bounding Box from WKT
    # The columns are: ['clinic_id', 'name', 'subdistrict', 'wkt_geom']
    # We use the 'wkt_geom' column
    bbox = None
    if 'wkt_geom' in df.columns:
        # Convert WKT strings to shapely geometries
        geoms = df['wkt_geom'].apply(wkt.loads)
        # Get the union or individual bounds
        # For a bbox of all points/polygons:
        min_x = geoms.map(lambda g: g.bounds[0]).min()
        min_y = geoms.map(lambda g: g.bounds[1]).min()
        max_x = geoms.map(lambda g: g.bounds[2]).max()
        max_y = geoms.map(lambda g: g.bounds[3]).max()
        bbox = [min_x, min_y, max_x, max_y]
    else:
        print("Warning: Could not identify wkt_geom column.")

    # 3. Count per subdistrict
    subdistrict_col = 'subdistrict'
    if subdistrict_col in df.columns:
        count_per_subdistrict = df[subdistrict_col].value_counts().to_dict()
    else:
        count_per_subdistrict = {}
        print(f"Warning: Could not identify subdistrict column. Columns found: {df.columns.tolist()}")

    # Prepare JSON
    inventory = {
        "count": int(total_count),
        "bbox": bbox,
        "count_per_subdistrict": count_per_subdistrict
    }

    with open('clinic_inventory.json', 'w') as f:
        json.dump(inventory, f, indent=4)
    
    print("Successfully created clinic_inventory.json")

if __name__ == "__main__":
    main()