Fix data pipelines once and for all

pipeline/transform/test_poi_proximity.py

@@ -1,9 +1,11 @@
 import polars as pl
 
 from pipeline.transform.poi_proximity import (
+    GREENSPACE_PARK_FUNCTIONS,
     POI_GROUPS_2KM,
     _build_poi_category_groups,
     _dynamic_poi_metric_renames,
+    _greenspace_count_frame,
     _groceries_categories,
 )
 from pipeline.utils.poi_counts import count_pois_per_postcode
@@ -88,3 +90,84 @@ def test_dynamic_poi_metric_renames_support_park_count_options() -> None:
         "parks_2km": "Number of amenities (Park) within 2km",
         "parks_5km": "Number of amenities (Park) within 5km",
     }
+
+
+def test_groceries_categories_exclude_speciality_food_retail() -> None:
+    """The static groceries metric must not count bakeries/butchers/delis/
+    off-licences (speciality retail, ~a third of the group), while keeping
+    Supermarket, Convenience Store, Greengrocer and GEOLYTIX brands."""
+    pois = pl.DataFrame(
+        {
+            "category": [
+                "Tesco",
+                "Supermarket",
+                "Convenience Store",
+                "Greengrocer",
+                "Bakery",
+                "Butcher & Fishmonger",
+                "Deli & Specialty",
+                "Off-Licence",
+                "Café",
+            ],
+            "group": ["Groceries"] * 8 + ["Leisure"],
+            "lat": [51.5] * 9,
+            "lng": [-0.1] * 9,
+        }
+    )
+
+    assert _groceries_categories(pois) == [
+        "Convenience Store",
+        "Greengrocer",
+        "Supermarket",
+        "Tesco",
+    ]
+
+
+def test_park_group_excludes_playgrounds_and_play_space() -> None:
+    # "Play Space" (playgrounds) must not count as a Park; Public Park Or
+    # Garden and Playing Field (open recreation grounds) are in scope.
+    assert GREENSPACE_PARK_FUNCTIONS == {
+        "parks": ["Public Park Or Garden", "Playing Field"]
+    }
+
+
+def test_greenspace_count_frame_collapses_to_one_row_per_site() -> None:
+    # Three gates of one park (with a site centroid), one gate of another park
+    # without a centroid, and one centroid-fallback row with a null site_id.
+    greenspace = pl.DataFrame(
+        {
+            "lat": [51.50, 51.51, 51.52, 53.0, 54.0],
+            "lng": [-0.10, -0.11, -0.12, -2.0, -3.0],
+            "category": ["Public Park Or Garden"] * 3
+            + ["Playing Field", "Public Park Or Garden"],
+            "site_id": ["site-a", "site-a", "site-a", "site-b", None],
+            "site_lat": [51.505, 51.505, 51.505, None, None],
+            "site_lng": [-0.105, -0.105, -0.105, None, None],
+        }
+    )
+
+    result = _greenspace_count_frame(greenspace).sort("lat")
+
+    # One row per site (site-a collapses 3 → 1), null-site rows preserved.
+    assert result.height == 3
+    site_a = result.filter(pl.col("site_id") == "site-a")
+    # The representative point is the site centroid…
+    assert site_a["lat"].to_list() == [51.505]
+    assert site_a["lng"].to_list() == [-0.105]
+    # …or the first access point when no centroid is available.
+    site_b = result.filter(pl.col("site_id") == "site-b")
+    assert site_b["lat"].to_list() == [53.0]
+
+
+def test_greenspace_count_frame_passes_legacy_parquet_through() -> None:
+    # The shipped parquet predates the site_id column; counting must not crash
+    # (it keeps the old access-point grain until regenerated).
+    legacy = pl.DataFrame(
+        {
+            "lat": [51.50, 51.51],
+            "lng": [-0.10, -0.11],
+            "category": ["Public Park Or Garden", "Play Space"],
+        }
+    )
+
+    assert _greenspace_count_frame(legacy).equals(legacy)