Last night

pipeline/transform/merge.py

@@ -113,7 +113,12 @@ def _build_wide(
             *[pl.col(c).fill_nan(None) for c in noise_cols],
         )
         .with_columns(
-            pl.max_horizontal(*noise_cols).fill_null(0).alias("noise_lden_db"),
+            pl.max_horizontal(*noise_cols).alias("noise_lden_db"),
+        )
+        .with_columns(
+            pl.col("noise_lden_db")
+            .fill_null(pl.col("noise_lden_db").min())
+            .alias("noise_lden_db"),
         )
         .select("postcode", "noise_lden_db")
     )
@@ -153,8 +158,8 @@ def _build_wide(
     wide = wide.with_columns(
         pl.when(pl.col("pp_property_type").is_in(["Terraced", "Semi-Detached"]))
         .then(pl.col("built_form"))
-        .otherwise(pl.col("epc_property_type"))
-        .alias("epc_property_type")
+        .otherwise(pl.col("pp_property_type"))
+        .alias("property_type")
     )
 
     wide = (
@@ -191,12 +196,13 @@ def _build_wide(
             "Barriers to Housing and Services Score",
             "lsoa21",
             "oa21",
+            "epc_property_type",
             "pp_property_type",
             "built_form",
         )
         .rename(
             {
-                "date_of_transfer": "Previous transaction date",
+                "date_of_transfer": "Date of last transaction",
                 "construction_age_band": "Construction age",
                 "is_construction_date_approximate": "Is construction date approximate",
                 "pp_address": "Address per Property Register",
@@ -206,11 +212,11 @@ def _build_wide(
                 "current_energy_rating": "Current energy rating",
                 "potential_energy_rating": "Potential energy rating",
                 "total_floor_area": "Total floor area (sqm)",
-                "epc_property_type": "Property type",
-                "restaurants_2km": "Restaurants within 2km",
-                "groceries_2km": "Groceries within 2km",
-                "parks_2km": "Parks within 2km",
-                "public_transport_2km": "Public transport within 2km",
+                "property_type": "Property type",
+                "restaurants_2km": "Number of restaurants within 2km",
+                "groceries_2km": "Number of grocery shops and supermarkets within 2km",
+                "parks_2km": "Number of parks within 2km",
+                "public_transport_2km": "Number of public transport stations within 2km",
                 "latest_price": "Last known price",
                 "number_habitable_rooms": "Number of bedrooms & living rooms",
                 "noise_lden_db": "Noise (dB)",
@@ -219,7 +225,6 @@ def _build_wide(
                 "max_download_speed": "Max available download speed (Mbps)",
                 "serious_crime_avg_yr": "Serious crime (avg/yr)",
                 "minor_crime_avg_yr": "Minor crime (avg/yr)",
-                "transaction_year": "Transaction year",
                 "environmental_risk": "Environmental risk",
                 "collapsible_deposits_risk": "Collapsible deposits risk",
                 "compressible_ground_risk": "Compressible ground risk",

pipeline/transform/postcode_boundaries/process_oa.py

@@ -42,7 +42,10 @@ def process_oa(
 
         for pc, polys in pc_inspire_polys.items():
             merged = unary_union(polys)
-            clipped = merged.intersection(oa_geom)
+            if not merged.is_valid:
+                merged = make_valid(merged)
+            valid_oa = oa_geom if oa_geom.is_valid else make_valid(oa_geom)
+            clipped = merged.intersection(valid_oa)
             if not clipped.is_empty:
                 if not clipped.is_valid:
                     clipped = make_valid(clipped)
@@ -58,11 +61,13 @@ def process_oa(
         used = None
         for pc, geom in claimed.items():
             if used is not None:
+                if not geom.is_valid:
+                    geom = make_valid(geom)
+                if not used.is_valid:
+                    used = make_valid(used)
                 geom = geom.difference(used)
                 if geom.is_empty:
                     continue
-                if not geom.is_valid:
-                    geom = make_valid(geom)
                 geom = _extract_polygonal(geom)
                 if geom is None:
                     continue
@@ -75,11 +80,12 @@ def process_oa(
         all_claimed = unary_union(list(claimed.values()))
         if not all_claimed.is_valid:
             all_claimed = make_valid(all_claimed)
-        remaining = oa_geom.difference(all_claimed)
+        valid_oa = oa_geom if oa_geom.is_valid else make_valid(oa_geom)
+        remaining = valid_oa.difference(all_claimed)
         if not remaining.is_valid:
             remaining = make_valid(remaining)
     else:
-        remaining = oa_geom
+        remaining = oa_geom if oa_geom.is_valid else make_valid(oa_geom)
 
     # Distribute remaining area via Voronoi
     if not remaining.is_empty and remaining.area > 0.01:

pipeline/transform/postcode_boundaries/voronoi.py

@@ -75,6 +75,9 @@ def compute_voronoi_regions(
     n_real = len(pts)
     pc_polys: dict[str, list[Polygon]] = defaultdict(list)
 
+    if not boundary.is_valid:
+        boundary = make_valid(boundary)
+
     for i in range(n_real):
         region_idx = vor.point_region[i]
         region = vor.regions[region_idx]
@@ -100,6 +103,8 @@ def _equal_split_fallback(
     postcodes: list[str], boundary: Polygon | MultiPolygon
 ) -> dict[str, Polygon | MultiPolygon]:
     """Split boundary into roughly equal horizontal strips, one per postcode."""
+    if not boundary.is_valid:
+        boundary = make_valid(boundary)
     min_x, min_y, max_x, max_y = boundary.bounds
     n = len(postcodes)
     result = {}