good changes

pipeline/transform/poi_proximity.py

@@ -13,7 +13,6 @@ from pipeline.utils.poi_counts import count_pois_per_postcode, min_distance_per_
 POI_GROUPS_2KM = {
     "restaurants": ["Restaurant", "Fast Food"],
     "groceries": ["Greengrocer", "Supermarket", "Convenience Store"],
-    "parks": ["Park"],
 }
 
 # Train/tube stations counted at 1km radius
@@ -21,11 +20,18 @@ TRAIN_TUBE_GROUP = {
     "train_tube": ["Metro or Tram stop", "Rail station"],
 }
 
-# Groups for which to compute distance to nearest POI
+# Groups for which to compute distance to nearest POI (from filtered POIs)
 DISTANCE_GROUPS = {
     "train_tube": ["Metro or Tram stop", "Rail station"],
 }
 
+# OS Open Greenspace function types used for park counts and distance calculation.
+# Uses the authoritative OS dataset instead of OSM point POIs for better coverage
+# of green spaces that are only mapped as polygons in OSM.
+GREENSPACE_PARK_FUNCTIONS = {
+    "parks": ["Public Park Or Garden", "Playing Field", "Play Space"],
+}
+
 
 def main():
     parser = argparse.ArgumentParser(
@@ -37,6 +43,12 @@ def main():
     parser.add_argument(
         "--pois", type=Path, required=True, help="Filtered POIs parquet"
     )
+    parser.add_argument(
+        "--greenspace",
+        type=Path,
+        required=True,
+        help="OS Open Greenspace centroids parquet",
+    )
     parser.add_argument(
         "--output", type=Path, required=True, help="Output parquet path"
     )
@@ -60,11 +72,25 @@ def main():
         postcodes, pois, groups=TRAIN_TUBE_GROUP, radius_km=1
     )
 
-    # Distance to nearest train/tube station
+    # Distance to nearest train/tube station (from filtered POIs)
     distances = min_distance_per_postcode(postcodes, pois, groups=DISTANCE_GROUPS)
 
+    # Park counts and distances from OS Open Greenspace
+    greenspace = pl.read_parquet(args.greenspace)
+    park_counts_2km = count_pois_per_postcode(
+        postcodes, greenspace, groups=GREENSPACE_PARK_FUNCTIONS, radius_km=2
+    )
+    park_distances = min_distance_per_postcode(
+        postcodes, greenspace, groups=GREENSPACE_PARK_FUNCTIONS
+    )
+
     # Join all results on postcode
-    result = counts_2km.join(counts_1km, on="postcode").join(distances, on="postcode")
+    result = (
+        counts_2km.join(counts_1km, on="postcode")
+        .join(distances, on="postcode")
+        .join(park_counts_2km, on="postcode")
+        .join(park_distances, on="postcode")
+    )
 
     result.write_parquet(args.output)
     size_mb = args.output.stat().st_size / (1024 * 1024)