Fun changes

pipeline/transform/merge.py

@@ -49,7 +49,7 @@ _AREA_COLUMNS = [
     # Amenities
     "Number of restaurants within 2km",
     "Number of grocery shops and supermarkets within 2km",
-    "Number of parks within 2km",
+    "Number of parks within 1km",
     "Distance to nearest train or tube station (km)",
     "Distance to nearest park (km)",
     # Environment
@@ -62,6 +62,16 @@ _AREA_COLUMNS = [
     "Good+ secondary schools within 2km",
     # Demographics
     "Median age",
+    # Politics
+    "Winning party",
+    "Voter turnout (%)",
+    "Majority (%)",
+    "% Labour",
+    "% Conservative",
+    "% Liberal Democrat",
+    "% Reform UK",
+    "% Green",
+    "% Other parties",
 ]
 
 
@@ -78,6 +88,7 @@ def _build(
     rental_prices_path: Path,
     lsoa_population_path: Path,
     median_age_path: Path,
+    election_results_path: Path,
 ) -> tuple[pl.DataFrame, pl.DataFrame]:
     """Build postcode and properties dataframes from epc_pp + auxiliary data.
 
@@ -113,6 +124,7 @@ def _build(
             pl.col("long").alias("lon"),
             "lsoa21",
             "oa21",
+            "pcon",
         )
     )
     wide = wide.join(arcgis, on="postcode", how="left")
@@ -193,6 +205,9 @@ def _build(
     median_age = pl.scan_parquet(median_age_path)
     wide = wide.join(median_age, on="lsoa21", how="left")
 
+    election = pl.scan_parquet(election_results_path)
+    wide = wide.join(election, on="pcon", how="left")
+
     poi_counts = pl.scan_parquet(poi_proximity_path)
     wide = wide.join(poi_counts, on="postcode", how="left")
 
@@ -304,6 +319,7 @@ def _build(
             "Barriers to Housing and Services Score",
             "lsoa21",
             "oa21",
+            "pcon",
             "epc_property_type",
             "pp_property_type",
             "built_form",
@@ -323,7 +339,7 @@ def _build(
                 "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",
+                "parks_1km": "Number of parks within 1km",
                 "train_tube_nearest_km": "Distance to nearest train or tube station (km)",
                 "parks_nearest_km": "Distance to nearest park (km)",
                 "latest_price": "Last known price",
@@ -342,6 +358,9 @@ def _build(
                 "floor_height": "Interior height (m)",
                 "was_council_house": "Former council house",
                 "median_age": "Median age",
+                "winning_party": "Winning party",
+                "turnout_pct": "Voter turnout (%)",
+                "majority_pct": "Majority (%)",
             }
         )
     )
@@ -427,6 +446,12 @@ def main():
         required=True,
         help="Census 2021 median age by LSOA parquet file",
     )
+    parser.add_argument(
+        "--election-results",
+        type=Path,
+        required=True,
+        help="2024 General Election results by constituency parquet file",
+    )
     parser.add_argument(
         "--output-postcodes",
         type=Path,
@@ -454,6 +479,7 @@ def main():
         rental_prices_path=args.rental_prices,
         lsoa_population_path=args.lsoa_population,
         median_age_path=args.median_age,
+        election_results_path=args.election_results,
     )
 
     print(f"\nPostcode columns: {postcode_df.columns}")

pipeline/transform/poi_proximity.py

@@ -17,7 +17,7 @@ POI_GROUPS_2KM = {
 
 # Groups for which to compute distance to nearest POI (from filtered POIs)
 DISTANCE_GROUPS = {
-    "train_tube": ["Metro or Tram stop", "Rail station"],
+    "train_tube": ["Tube station", "Rail station"],
 }
 
 # OS Open Greenspace function types used for park counts and distance calculation.
@@ -67,8 +67,8 @@ def main():
 
     # 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_counts_1km = count_pois_per_postcode(
+        postcodes, greenspace, groups=GREENSPACE_PARK_FUNCTIONS, radius_km=1
     )
     park_distances = min_distance_per_postcode(
         postcodes, greenspace, groups=GREENSPACE_PARK_FUNCTIONS
@@ -77,7 +77,7 @@ def main():
     # Join all results on postcode
     result = (
         counts_2km.join(distances, on="postcode")
-        .join(park_counts_2km, on="postcode")
+        .join(park_counts_1km, on="postcode")
         .join(park_distances, on="postcode")
     )
 

pipeline/transform/transform_poi.py

@@ -1054,7 +1054,7 @@ NAPTAN_EMOJIS: dict[str, str] = {
     "Bus stop": "🚏",
     "Bus station": "🚌",
     "Taxi rank": "🚕",
-    "Metro or Tram stop": "🚊",
+    "Tube station": "🚇",
 }