perfect-postcode/pipeline/transform/poi_proximity.py

42 lines
1.1 KiB
Python

"""Compute POI proximity counts per postcode from ArcGIS + filtered POIs."""
import argparse
from pathlib import Path
import polars as pl
from pipeline.utils.poi_counts import _count_pois_per_postcode
def main():
parser = argparse.ArgumentParser(
description="Count POIs within radius per postcode"
)
parser.add_argument(
"--arcgis", type=Path, required=True, help="ArcGIS postcode parquet"
)
parser.add_argument(
"--pois", type=Path, required=True, help="Filtered POIs parquet"
)
parser.add_argument(
"--output", type=Path, required=True, help="Output parquet path"
)
args = parser.parse_args()
postcodes = pl.read_parquet(args.arcgis).select(
pl.col("pcds").alias("postcode"),
"lat",
pl.col("long").alias("lon"),
)
pois = pl.read_parquet(args.pois)
result = _count_pois_per_postcode(postcodes, pois, radius_km=2)
result.write_parquet(args.output)
size_mb = args.output.stat().st_size / (1024 * 1024)
print(f"Wrote {args.output} ({size_mb:.1f} MB)")
if __name__ == "__main__":
main()