Hide POIs, show overlay state, remove zoom button, rotate vpn

pipeline/transform/test_merge.py

@@ -162,6 +162,89 @@ def test_epc_council_by_postcode_null_latest_tenure_counts_as_ex_council() -> No
     ]
 
 
+def test_epc_council_shares_exclude_unmatched_listing_seed_rows(tmp_path) -> None:
+    # The council shares must describe the DWELLING universe, so `_build`
+    # aggregates them before splicing listings in. An unmatched listing appends a
+    # seed row, which is not a dwelling: it would both pad the denominator and,
+    # having no latest_tenure_status, count as ex-council.
+    #
+    # This pins the two aggregates against each other to show what the ordering
+    # buys. It does not exercise `_build`, whose 15 parquet inputs no test in this
+    # file fixtures, so it cannot catch the call being moved back after the
+    # splice; the server warns at boot if the columns go missing entirely.
+    listings_path = tmp_path / "listings.parquet"
+    arcgis_path = tmp_path / "arcgis.parquet"
+    # A number-less listing on an unknown street matches no dwelling, so it is
+    # spliced in as its own seed row.
+    _sample_listings_frame().with_columns(
+        pl.lit("Juniper Crescent").alias("Address per Property Register"),
+    ).write_parquet(listings_path)
+    _stub_arcgis(arcgis_path)
+
+    # Two real dwellings in SW1A 1AA: one ever-council and still social.
+    # % Council housing = 1/2 = 50.0; % Ex-council = 0/2 = 0.0.
+    wide = pl.LazyFrame(
+        {
+            "postcode": ["SW1A 1AA", "SW1A 1AA"],
+            "pp_address": ["Old Cottage High Street", "New Cottage High Street"],
+            "pp_property_type": ["Terraced", "Terraced"],
+            "duration": ["Freehold", "Freehold"],
+            "total_floor_area": [120.0, 110.0],
+            "number_habitable_rooms": [4, 4],
+            "latest_price": [750_000, 700_000],
+            "epc_address": ["Old Cottage High Street", "New Cottage High Street"],
+            "current_energy_rating": ["C", "C"],
+            "potential_energy_rating": ["B", "B"],
+            "floor_height": [2.4, 2.4],
+            "construction_age_band": [1930, 1930],
+            "is_construction_date_approximate": [1, 1],
+            "was_council_house": ["Yes", "No"],
+            "latest_tenure_status": ["Rented (social)", "Owner-occupied"],
+            # `_build` has always attached this by the time it aggregates, and
+            # `_fill_property_level_no_defaults` defaults it alongside council.
+            LISTED_BUILDING_FEATURE: [None, None],
+        },
+        schema={
+            "postcode": pl.Utf8,
+            "pp_address": pl.Utf8,
+            "pp_property_type": pl.Utf8,
+            "duration": pl.Utf8,
+            "total_floor_area": pl.Float64,
+            "number_habitable_rooms": pl.Int16,
+            "latest_price": pl.Int64,
+            "epc_address": pl.Utf8,
+            "current_energy_rating": pl.Utf8,
+            "potential_energy_rating": pl.Utf8,
+            "floor_height": pl.Float64,
+            "construction_age_band": pl.UInt16,
+            "is_construction_date_approximate": pl.UInt8,
+            "was_council_house": pl.Utf8,
+            "latest_tenure_status": pl.Utf8,
+            LISTED_BUILDING_FEATURE: pl.Utf8,
+        },
+    )
+
+    dwelling_shares = _epc_council_by_postcode(
+        _fill_property_level_no_defaults(wide)
+    ).collect()
+    assert dwelling_shares.to_dicts() == [
+        {"postcode": "SW1A 1AA", "% Council housing": 50.0, "% Ex-council": 0.0}
+    ]
+
+    spliced = _integrate_listings(wide, listings_path, arcgis_path, epc_path=None)
+    spliced_shares = _epc_council_by_postcode(
+        _fill_property_level_no_defaults(spliced)
+    ).collect()
+
+    # The seed row pads the denominator to 3, understating the council share as
+    # 1/3 and disagreeing with postcode.parquet for the same postcode. That is
+    # exactly why the aggregate is taken before the splice.
+    assert spliced.collect().height == 3
+    assert spliced_shares.to_dicts() == [
+        {"postcode": "SW1A 1AA", "% Council housing": 33.3, "% Ex-council": 0.0}
+    ]
+
+
 def test_epc_council_columns_are_area_level_and_survive_the_split() -> None:
     # The EPC council shares are postcode-level AREA columns: they must route to
     # the postcode output and NOT appear in the property output. The per-property