Format

pipeline/transform/crime.py

@@ -10,7 +10,11 @@ def transform_crime(crime_dir: Path, output_path: Path) -> None:
 
     df = pl.scan_csv(
         csvs,
-        schema_overrides={"LSOA code": pl.Utf8, "Crime type": pl.Utf8, "Month": pl.Utf8},
+        schema_overrides={
+            "LSOA code": pl.Utf8,
+            "Crime type": pl.Utf8,
+            "Month": pl.Utf8,
+        },
     ).select("LSOA code", "Crime type", "Month")
 
     # Extract year, count crimes per LSOA / year / crime type

pipeline/transform/poi_proximity.py

@@ -5,7 +5,7 @@ from pathlib import Path
 
 import polars as pl
 
-from pipeline.utils.poi_counts import _count_pois_per_postcode
+from pipeline.utils.poi_counts import count_pois_per_postcode
 
 
 # POI category groups for proximity counting
@@ -13,11 +13,15 @@ POI_GROUPS = {
     "restaurants": ["Restaurant", "Fast Food"],
     "groceries": ["Greengrocer", "Grocery Shop", "Supermarket", "Convenience Store"],
     "parks": ["Park", "Garden", "Nature Reserve"],
-    "public_transport": ["Metro or Tram stop", "Rail station", "Bus stop", "Bus station"], # comes from naptan.py
+    "public_transport": [
+        "Metro or Tram stop",
+        "Rail station",
+        "Bus stop",
+        "Bus station",
+    ],  # comes from naptan.py
 }
 
 
-
 def main():
     parser = argparse.ArgumentParser(
         description="Count POIs within radius per postcode"
@@ -41,7 +45,7 @@ def main():
 
     pois = pl.read_parquet(args.pois)
 
-    result = _count_pois_per_postcode(postcodes, pois, groups=POI_GROUPS, radius_km=2)
+    result = count_pois_per_postcode(postcodes, pois, groups=POI_GROUPS, radius_km=2)
 
     result.write_parquet(args.output)
     size_mb = args.output.stat().st_size / (1024 * 1024)