..

pipeline/transform/poi_proximity.py

@@ -43,7 +43,7 @@ GROCERY_STATIC_EXCLUDED_CATEGORIES = {
 # Scope: "Public Park Or Garden" is the core park function. "Playing Field"
 # (open public recreation grounds) is borderline but kept: outside big cities
 # the local rec ground is the de facto park. "Play Space" (playgrounds) is
-# excluded — a playground is not a park, and "Playground" is already its own
+# excluded: a playground is not a park, and "Playground" is already its own
 # OSM-derived category. The remaining functions (Religious Grounds, Golf
 # Course, Cemetery, Allotments, Bowling Green, Tennis Court, Other Sports
 # Facility) are clearly not parks.
@@ -76,7 +76,7 @@ def _groceries_categories(pois: pl.DataFrame) -> list[str]:
     with group "Groceries"; it never emits the literal "Supermarket". Collecting
     every Groceries category captures both the OSM strings and the brand names.
     Speciality food retail (bakeries, butchers, delis, off-licences) is
-    excluded — see GROCERY_STATIC_EXCLUDED_CATEGORIES.
+    excluded. See GROCERY_STATIC_EXCLUDED_CATEGORIES.
     """
     if "group" not in pois.columns:
         raise ValueError("POI dataframe must include a 'group' column")
@@ -138,7 +138,7 @@ def _greenspace_count_frame(greenspace: pl.DataFrame) -> pl.DataFrame:
 
     os_greenspace.parquet is one row per ACCESS POINT (park gate), which is the
     right grain for nearest-distance (the nearest gate is what matters) but
-    wildly over-counts "Number of amenities (Park) within Xkm" — a large park
+    wildly over-counts "Number of amenities (Park) within Xkm": a large park
     with 30 gates counted as 30 parks. Counting uses one row per site at the
     site centroid (falling back to the first access point when no centroid is
     available). Degrades gracefully: a legacy parquet without `site_id` is