LGTM

pipeline/transform/test_merge.py

@@ -1,8 +1,14 @@
 import polars as pl
+import pytest
 
 from pipeline.transform.merge import (
+    _AREA_COLUMNS,
+    TREE_DENSITY_FEATURE,
     _is_dynamic_poi_metric_column,
     _less_deprived_percentile_expr,
+    _tree_density_by_postcode,
+    _validate_lad_source_coverage,
+    _validate_property_postcodes,
 )
 
 
@@ -36,3 +42,103 @@ def test_dynamic_poi_metric_columns_are_area_level() -> None:
     assert _is_dynamic_poi_metric_column("Number of amenities (Cafe) within 2km")
     assert _is_dynamic_poi_metric_column("Number of amenities (Cafe) within 5km")
     assert not _is_dynamic_poi_metric_column("Number of restaurants within 2km")
+
+
+def test_country_code_is_kept_in_postcode_area_columns() -> None:
+    assert "ctry25cd" in _AREA_COLUMNS
+
+
+def test_validate_property_postcodes_rejects_blank_rows() -> None:
+    df = pl.DataFrame(
+        {
+            "Postcode": ["AA1 1AA", ""],
+            "Address per Property Register": ["1 Example Street", "2 Example Street"],
+            "Last known price": [100_000, 200_000],
+        }
+    )
+
+    with pytest.raises(ValueError, match="Property rows missing a postcode"):
+        _validate_property_postcodes(df)
+
+
+def test_validate_lad_source_coverage_allows_only_known_rent_no_data_lads(
+    tmp_path,
+) -> None:
+    iod_path = tmp_path / "iod.parquet"
+    ethnicity_path = tmp_path / "ethnicity.parquet"
+    rental_path = tmp_path / "rental.parquet"
+    pl.DataFrame(
+        {
+            "Local Authority District code (2024)": [
+                "E08000016",
+                "E06000053",
+                "E09000001",
+            ],
+            "Local Authority District name (2024)": [
+                "Barnsley",
+                "Isles of Scilly",
+                "City of London",
+            ],
+        }
+    ).write_parquet(iod_path)
+    pl.DataFrame(
+        {"Geography_code": ["E08000016", "E06000053", "E09000001"]}
+    ).write_parquet(ethnicity_path)
+    pl.DataFrame({"area_code": ["E08000016"], "bedrooms": [1]}).write_parquet(
+        rental_path
+    )
+
+    _validate_lad_source_coverage(iod_path, ethnicity_path, rental_path)
+
+
+def test_validate_lad_source_coverage_rejects_unexpected_rent_holes(tmp_path) -> None:
+    iod_path = tmp_path / "iod.parquet"
+    ethnicity_path = tmp_path / "ethnicity.parquet"
+    rental_path = tmp_path / "rental.parquet"
+    pl.DataFrame(
+        {
+            "Local Authority District code (2024)": ["E08000016"],
+            "Local Authority District name (2024)": ["Barnsley"],
+        }
+    ).write_parquet(iod_path)
+    pl.DataFrame({"Geography_code": ["E08000016"]}).write_parquet(ethnicity_path)
+    pl.DataFrame({"area_code": ["E08000019"], "bedrooms": [1]}).write_parquet(
+        rental_path
+    )
+
+    with pytest.raises(ValueError, match="Rental data is missing"):
+        _validate_lad_source_coverage(iod_path, ethnicity_path, rental_path)
+
+
+def test_tree_density_by_postcode_aliases_radius_percentile(tmp_path) -> None:
+    path = tmp_path / "tree_density_by_postcode.parquet"
+    pl.DataFrame(
+        {
+            "postcode": ["AB1 2CD", "EF3 4GH"],
+            "Tree canopy density percentile within 50m": [12.5, 99.0],
+        }
+    ).write_parquet(path)
+
+    result = _tree_density_by_postcode(path).collect().sort("postcode")
+
+    assert result.columns == ["postcode", TREE_DENSITY_FEATURE]
+    assert result[TREE_DENSITY_FEATURE].to_list() == [12.5, 99.0]
+    assert result.schema[TREE_DENSITY_FEATURE] == pl.Float32
+
+
+def test_tree_density_by_postcode_requires_postcode_and_density_columns(
+    tmp_path,
+) -> None:
+    path = tmp_path / "tree_density_by_postcode.parquet"
+    pl.DataFrame({"postcode": ["AB1 2CD"], "unrelated": [1.0]}).write_parquet(path)
+
+    with pytest.raises(ValueError, match="must contain column"):
+        _tree_density_by_postcode(path)
+
+    missing_postcode_path = tmp_path / "missing_postcode.parquet"
+    pl.DataFrame({"Tree canopy density percentile within 50m": [12.5]}).write_parquet(
+        missing_postcode_path
+    )
+
+    with pytest.raises(ValueError, match="missing required column: postcode"):
+        _tree_density_by_postcode(missing_postcode_path)