101 lines
3.3 KiB
Python
101 lines
3.3 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
"""Generate 100x100m resolution grid index for Wuhan city, China."""
|
||
|
|
|
||
|
|
import geopandas as gpd
|
||
|
|
import pandas as pd
|
||
|
|
import numpy as np
|
||
|
|
from shapely.geometry import box
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
|
||
|
|
def generate_wuhan_grid(
|
||
|
|
boundary_path: str = "Datas/武汉市.geojson",
|
||
|
|
output_dir: str = "processed",
|
||
|
|
grid_size: float = 100,
|
||
|
|
) -> tuple[gpd.GeoDataFrame, pd.DataFrame]:
|
||
|
|
"""Generate 100m resolution grid covering Wuhan boundary."""
|
||
|
|
print(f"Loading Wuhan boundary from {boundary_path}...")
|
||
|
|
wuhan = gpd.read_file(boundary_path)
|
||
|
|
|
||
|
|
bounds = wuhan.total_bounds
|
||
|
|
print(f"Wuhan bounds: minx={bounds[0]:.4f}, miny={bounds[1]:.4f}, maxx={bounds[2]:.4f}, maxy={bounds[3]:.4f}")
|
||
|
|
|
||
|
|
minx, miny, maxx, maxy = bounds
|
||
|
|
cell_size_deg = grid_size / 111000.0
|
||
|
|
|
||
|
|
print(f"Creating grid with {grid_size}m cells (vectorized)...")
|
||
|
|
|
||
|
|
x_coords = np.arange(minx, maxx, cell_size_deg)
|
||
|
|
y_coords = np.arange(miny, maxy, cell_size_deg)
|
||
|
|
print(f" Grid dimensions: {len(x_coords)} x {len(y_coords)}")
|
||
|
|
|
||
|
|
x_grid, y_grid = np.meshgrid(x_coords, y_coords)
|
||
|
|
x_flat = x_grid.flatten()
|
||
|
|
y_flat = y_grid.flatten()
|
||
|
|
|
||
|
|
print(f" Total cells in bounding box: {len(x_flat)}")
|
||
|
|
|
||
|
|
minxs = x_flat
|
||
|
|
minys = y_flat
|
||
|
|
maxxs = minxs + cell_size_deg
|
||
|
|
maxys = minys + cell_size_deg
|
||
|
|
|
||
|
|
geometries = [box(mx, my, Mx, My) for mx, my, Mx, My in zip(minxs, minys, maxxs, maxys)]
|
||
|
|
|
||
|
|
cells = np.arange(len(geometries))
|
||
|
|
rows = cells // len(x_coords)
|
||
|
|
cols = cells % len(x_coords)
|
||
|
|
|
||
|
|
print(" Building GeoDataFrame...")
|
||
|
|
grid_gdf = gpd.GeoDataFrame({
|
||
|
|
'row': rows,
|
||
|
|
'col': cols,
|
||
|
|
'geometry': geometries
|
||
|
|
}, crs="EPSG:4326")
|
||
|
|
|
||
|
|
print("Filtering to cells intersecting Wuhan boundary...")
|
||
|
|
wuhan_union = wuhan.unary_union
|
||
|
|
mask = grid_gdf.intersects(wuhan_union)
|
||
|
|
grid_gdf = grid_gdf[mask].copy().reset_index(drop=True)
|
||
|
|
|
||
|
|
print(f"Cells within Wuhan boundary: {len(grid_gdf)}")
|
||
|
|
|
||
|
|
grid_gdf['grid_id'] = [f"r{r}_c{c}" for r, c in zip(grid_gdf['row'], grid_gdf['col'])]
|
||
|
|
|
||
|
|
centroids = grid_gdf.geometry.centroid
|
||
|
|
grid_gdf['center_lon'] = centroids.x
|
||
|
|
grid_gdf['center_lat'] = centroids.y
|
||
|
|
grid_gdf['polygon'] = grid_gdf.geometry.apply(lambda g: g.wkt)
|
||
|
|
|
||
|
|
parquet_df = grid_gdf[['grid_id', 'center_lon', 'center_lat', 'row', 'col', 'polygon']].copy()
|
||
|
|
|
||
|
|
return grid_gdf, parquet_df
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
output_dir = Path("processed")
|
||
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
||
|
|
|
||
|
|
grid_gdf, parquet_df = generate_wuhan_grid()
|
||
|
|
|
||
|
|
geojson_path = output_dir / "grid_100m_index.geojson"
|
||
|
|
print(f"Exporting to GeoJSON: {geojson_path}")
|
||
|
|
grid_gdf.to_file(geojson_path, driver="GeoJSON")
|
||
|
|
print(f" Exported {len(grid_gdf)} features")
|
||
|
|
|
||
|
|
parquet_path = output_dir / "grid_100m_index.parquet"
|
||
|
|
print(f"Exporting to Parquet: {parquet_path}")
|
||
|
|
parquet_df.to_parquet(parquet_path, index=False)
|
||
|
|
print(f" Exported {len(parquet_df)} rows")
|
||
|
|
|
||
|
|
print("\n=== Grid Summary ===")
|
||
|
|
print(f"Total grid cells: {len(grid_gdf)}")
|
||
|
|
print(f"Bounds: {grid_gdf.total_bounds}")
|
||
|
|
print(f"Grid ID format example: {grid_gdf['grid_id'].iloc[0]}")
|
||
|
|
print(f"Center coordinate range:")
|
||
|
|
print(f" Lon: {parquet_df['center_lon'].min():.4f} to {parquet_df['center_lon'].max():.4f}")
|
||
|
|
print(f" Lat: {parquet_df['center_lat'].min():.4f} to {parquet_df['center_lat'].max():.4f}")
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|