CA/scripts/validate_grid.py

#!/usr/bin/env python3
"""Validate Wuhan 100m grid index."""

import sys
import geopandas as gpd
import pandas as pd


def validate_grid():
    print("=== Grid Validation ===\n")

    errors = []

    geojson_path = "processed/grid_100m_index.geojson"
    parquet_path = "processed/grid_100m_index.parquet"

    print(f"1. Checking files exist...")
    try:
        grid = gpd.read_file(geojson_path)
        print(f"   GeoJSON: {geojson_path} - OK ({len(grid)} features)")
    except Exception as e:
        errors.append(f"GeoJSON read failed: {e}")
        print(f"   GeoJSON: FAILED - {e}")
        return errors

    try:
        df = pd.read_parquet(parquet_path)
        print(f"   Parquet: {parquet_path} - OK ({len(df)} rows)")
    except Exception as e:
        errors.append(f"Parquet read failed: {e}")
        print(f"   Parquet: FAILED - {e}")
        return errors

    print(f"\n2. Validating grid count...")
    expected_min = 800000
    expected_max = 1000000
    actual = len(grid)
    print(f"   Expected: {expected_min}-{expected_max}")
    print(f"   Actual: {actual}")
    if actual < expected_min or actual > expected_max:
        errors.append(f"Grid count {actual} outside expected range {expected_min}-{expected_max}")
        print(f"   Status: FAILED")
    else:
        print(f"   Status: OK")

    print(f"\n3. Validating grid_id format...")
    sample_ids = df['grid_id'].head(5).tolist()
    print(f"   Sample: {sample_ids}")
    invalid_ids = df[~df['grid_id'].str.match(r'^r\d+_c\d+$')]
    if len(invalid_ids) > 0:
        errors.append(f"Invalid grid_id format in {len(invalid_ids)} rows")
        print(f"   Invalid format: {len(invalid_ids)} rows")
    else:
        print(f"   All {len(df)} grid_ids valid")

    print(f"\n4. Validating center coordinates...")
    lon_min, lat_min, lon_max, lat_max = df['center_lon'].min(), df['center_lat'].min(), df['center_lon'].max(), df['center_lat'].max()
    print(f"   Lon range: {lon_min:.4f} to {lon_max:.4f}")
    print(f"   Lat range: {lat_min:.4f} to {lat_max:.4f}")

    wuhan_lon_range = (113.7, 115.2)
    wuhan_lat_range = (29.9, 31.4)
    if lon_min < wuhan_lon_range[0] or lon_max > wuhan_lon_range[1]:
        errors.append(f"Longitude range {lon_min:.4f}-{lon_max:.4f} outside Wuhan bounds")
        print(f"   WARNING: Longitude outside expected Wuhan bounds")
    if lat_min < wuhan_lat_range[0] or lat_max > wuhan_lat_range[1]:
        errors.append(f"Latitude range {lat_min:.4f}-{lat_max:.4f} outside Wuhan bounds")
        print(f"   WARNING: Latitude outside expected Wuhan bounds")
    if not errors:
        print(f"   Coordinates within Wuhan bounds")

    print(f"\n5. Validating required columns...")
    required_cols = ['grid_id', 'center_lon', 'center_lat', 'row', 'col', 'polygon']
    missing = [c for c in required_cols if c not in df.columns]
    if missing:
        errors.append(f"Missing columns: {missing}")
        print(f"   Missing: {missing}")
    else:
        print(f"   All required columns present: {required_cols}")

    print(f"\n6. Validating geometry in GeoJSON...")
    if grid.geometry.is_valid.all():
        print(f"   All geometries valid")
    else:
        invalid_count = (~grid.geometry.is_valid).sum()
        errors.append(f"{invalid_count} invalid geometries")
        print(f"   WARNING: {invalid_count} invalid geometries")

    print(f"\n=== Validation Summary ===")
    if errors:
        print(f"ERRORS: {len(errors)}")
        for e in errors:
            print(f"  - {e}")
        return errors
    else:
        print(f"PASSED: All validations passed")
        return []


if __name__ == "__main__":
    errors = validate_grid()
    sys.exit(1 if errors else 0)