idk

pipeline/transform/test_poi_proximity.py

@@ -1,9 +1,44 @@
 import polars as pl
 
 from pipeline.transform.poi_proximity import (
+    POI_GROUPS_2KM,
     _build_poi_category_groups,
     _dynamic_poi_metric_renames,
+    _groceries_categories,
 )
+from pipeline.utils.poi_counts import count_pois_per_postcode
+
+
+def test_groceries_2km_counts_geolytix_brand_categories() -> None:
+    """The static groceries 2km count must include GEOLYTIX brand POIs.
+
+    GEOLYTIX stores the brand (e.g. "Tesco") in `category` with group
+    "Groceries" and never emits the literal "Supermarket"; matching only the
+    OSM strings counts the supermarket but drops the brand store.
+    """
+    postcodes = pl.DataFrame(
+        {
+            "postcode": ["SW1A 1AA"],
+            "lat": [51.5010],
+            "lon": [-0.1416],
+        }
+    )
+    pois = pl.DataFrame(
+        {
+            "category": ["Tesco", "Supermarket"],
+            "group": ["Groceries", "Groceries"],
+            "lat": [51.5011, 51.5012],
+            "lng": [-0.1417, -0.1418],
+        }
+    )
+
+    groups_2km = {**POI_GROUPS_2KM, "groceries": _groceries_categories(pois)}
+    result = count_pois_per_postcode(postcodes, pois, groups=groups_2km, radius_km=2)
+
+    # Both the GEOLYTIX brand ("Tesco") and the OSM "Supermarket" must count.
+    # Pre-fix the static list was ["Greengrocer", "Supermarket", "Convenience
+    # Store"], so "Tesco" was dropped and this was 1.
+    assert result["groceries_2km"][0] == 2
 
 
 def test_dynamic_poi_groups_include_requested_categories_only() -> None: