idk

pipeline/transform/test_crime.py

@@ -158,6 +158,53 @@ def test_transform_crime_writes_by_year_output(tmp_path):
     assert serious[2024] == 12.0
 
 
+def test_transform_crime_headline_is_mean_of_per_year_bars(tmp_path):
+    """The avg/yr headline must equal the average of the by-year chart bars, i.e.
+    the simple mean of each year's annualised count -- NOT a month-weighted pooled
+    rate. They diverge when years have uneven partial-month coverage."""
+    crime_dir = tmp_path / "crime"
+    jan23 = crime_dir / "2023-01"
+    jan24 = crime_dir / "2024-01"
+    feb24 = crime_dir / "2024-02"
+    for d in (jan23, jan24, feb24):
+        d.mkdir(parents=True)
+
+    header = "Crime ID,Month,Reported by,Falls within,Longitude,Latitude,Location,LSOA code,LSOA name,Crime type,Last outcome category,Context"
+    # 2023: 6 burglaries in 1 month -> 6 * 12 / 1 = 72/yr.
+    (jan23 / "2023-01-test-force-street.csv").write_text(
+        "\n".join(
+            [header]
+            + [
+                f"{i},2023-01,F,F,-0.1,51.5,X,E01000001,L,Burglary,U,"
+                for i in range(1, 7)
+            ]
+        )
+        + "\n"
+    )
+    # 2024: 2 burglaries across 2 months -> 2 * 12 / 2 = 12/yr.
+    (jan24 / "2024-01-test-force-street.csv").write_text(
+        "\n".join([header, "7,2024-01,F,F,-0.1,51.5,X,E01000001,L,Burglary,U,"]) + "\n"
+    )
+    (feb24 / "2024-02-test-force-street.csv").write_text(
+        "\n".join([header, "8,2024-02,F,F,-0.1,51.5,X,E01000001,L,Burglary,U,"]) + "\n"
+    )
+
+    output = tmp_path / "crime.parquet"
+    by_year_output = tmp_path / "crime_by_year.parquet"
+    transform_crime(crime_dir, output, by_year_output)
+
+    # Mean of per-year bars = (72 + 12) / 2 = 42.0.
+    # The old pooled rate (8 incidents / 3 months * 12 = 32.0) would be wrong.
+    avg = pl.read_parquet(output).to_dicts()[0]
+    assert avg["Burglary (avg/yr)"] == 42.0
+
+    by_year = pl.read_parquet(by_year_output).row(0, named=True)
+    burglary = {p["year"]: p["count"] for p in by_year["Burglary (by year)"]}
+    assert burglary == {2023: 72.0, 2024: 12.0}
+    # Headline equals the mean of the bars it summarises.
+    assert avg["Burglary (avg/yr)"] == sum(burglary.values()) / len(burglary)
+
+
 def test_transform_crime_fails_without_valid_months(tmp_path):
     crime_dir = tmp_path / "crime"
     month_dir = crime_dir / "2024-01"