Lots of improvements

pipeline/transform/merge.py

@@ -50,7 +50,6 @@ _AREA_COLUMNS = [
     "Number of restaurants within 2km",
     "Number of grocery shops and supermarkets within 2km",
     "Number of parks within 2km",
-    "Train or tube stations within 1km",
     "Distance to nearest train or tube station (km)",
     "Distance to nearest park (km)",
     # Environment
@@ -325,7 +324,6 @@ def _build(
                 "restaurants_2km": "Number of restaurants within 2km",
                 "groceries_2km": "Number of grocery shops and supermarkets within 2km",
                 "parks_2km": "Number of parks within 2km",
-                "train_tube_1km": "Train or tube stations 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",

pipeline/transform/poi_proximity.py

@@ -15,11 +15,6 @@ POI_GROUPS_2KM = {
     "groceries": ["Greengrocer", "Supermarket", "Convenience Store"],
 }
 
-# Train/tube stations counted at 1km radius
-TRAIN_TUBE_GROUP = {
-    "train_tube": ["Metro or Tram stop", "Rail station"],
-}
-
 # Groups for which to compute distance to nearest POI (from filtered POIs)
 DISTANCE_GROUPS = {
     "train_tube": ["Metro or Tram stop", "Rail station"],
@@ -67,11 +62,6 @@ def main():
         postcodes, pois, groups=POI_GROUPS_2KM, radius_km=2
     )
 
-    # Count train/tube stations within 1km
-    counts_1km = count_pois_per_postcode(
-        postcodes, pois, groups=TRAIN_TUBE_GROUP, radius_km=1
-    )
-
     # Distance to nearest train/tube station (from filtered POIs)
     distances = min_distance_per_postcode(postcodes, pois, groups=DISTANCE_GROUPS)
 
@@ -86,8 +76,7 @@ def main():
 
     # Join all results on postcode
     result = (
-        counts_2km.join(counts_1km, on="postcode")
-        .join(distances, on="postcode")
+        counts_2km.join(distances, on="postcode")
         .join(park_counts_2km, on="postcode")
         .join(park_distances, on="postcode")
     )