SPlit up

pipeline/transform/test_crime.py

@@ -275,6 +275,51 @@ def test_transform_crime_applies_lsoa_2011_to_2021_lookup(tmp_path):
     assert burglaries["E01000099"] == [{"year": 2024, "count": 12.0}]
 
 
+def test_transform_crime_sums_mixed_weights_within_a_target_lsoa(tmp_path):
+    """Irregular (M:N) recodes can land rows with DIFFERENT `_weight`s in the
+    same (lsoa21, year, type) group: here E01000050 receives 0.5-weighted
+    incidents from split E01000001 alongside a 1.0-weighted incident from
+    E01000099. The aggregation must sum per-incident weights; the old
+    `_weight.first() * len` applied one row's weight to all three
+    (nondeterministically 1.5 or 3.0 instead of 2.0)."""
+    crime_dir = tmp_path / "crime"
+    month_dir = crime_dir / "2024-01"
+    month_dir.mkdir(parents=True)
+
+    header = "Crime ID,Month,Reported by,Falls within,Longitude,Latitude,Location,LSOA code,LSOA name,Crime type,Last outcome category,Context"
+    (month_dir / "2024-01-test-force-street.csv").write_text(
+        "\n".join(
+            [
+                header,
+                "1,2024-01,F,F,-0.1,51.5,X,E01000001,L,Burglary,U,",
+                "2,2024-01,F,F,-0.1,51.5,X,E01000001,L,Burglary,U,",
+                "3,2024-01,F,F,-0.1,51.5,X,E01000099,L,Burglary,U,",
+            ]
+        )
+        + "\n"
+    )
+
+    lookup_path = tmp_path / "lookup.parquet"
+    pl.DataFrame(
+        {
+            "lsoa11": ["E01000001", "E01000001", "E01000099"],
+            "lsoa21": ["E01000050", "E01000051", "E01000050"],
+        }
+    ).write_parquet(lookup_path)
+
+    output = tmp_path / "crime.parquet"
+    by_year_output = tmp_path / "by_year.parquet"
+    transform_crime(crime_dir, output, by_year_output, lookup_path)
+
+    # E01000050: 0.5 + 0.5 + 1.0 = 2.0 incidents -> 24/yr annualised.
+    # E01000051: 0.5 + 0.5 = 1.0 incident -> 12/yr.
+    avg = pl.read_parquet(output).sort("LSOA code").to_dicts()
+    assert avg == [
+        {"LSOA code": "E01000050", "Burglary (avg/yr)": 24.0},
+        {"LSOA code": "E01000051", "Burglary (avg/yr)": 12.0},
+    ]
+
+
 def test_transform_crime_maps_legacy_crime_types(tmp_path):
     """Pre-2014 police.uk type names are aliased to current equivalents instead
     of being dropped."""