Rerun data pipelines

pipeline/transform/test_merge.py

@@ -0,0 +1,33 @@
+import polars as pl
+
+from pipeline.transform.merge import (
+    _is_dynamic_poi_metric_column,
+    _less_deprived_percentile_expr,
+)
+
+
+def test_less_deprived_percentile_expr_preserves_direction_and_nulls() -> None:
+    df = pl.DataFrame({"Income Score (rate)": [1.0, 2.0, 3.0, None]})
+
+    result = df.lazy().with_columns(
+        _less_deprived_percentile_expr("Income Score (rate)")
+    ).collect()
+
+    assert result["Income Score (rate)"].to_list() == [100.0, 50.0, 0.0, None]
+
+
+def test_less_deprived_percentile_expr_uses_exact_scale_endpoints() -> None:
+    df = pl.DataFrame({"Income Score (rate)": [1.0, 1.0, 2.0, 3.0, 3.0]})
+
+    result = df.lazy().with_columns(
+        _less_deprived_percentile_expr("Income Score (rate)")
+    ).collect()
+
+    assert result["Income Score (rate)"].to_list() == [100.0, 100.0, 50.0, 0.0, 0.0]
+
+
+def test_dynamic_poi_metric_columns_are_area_level() -> None:
+    assert _is_dynamic_poi_metric_column("Distance to nearest Cafe POI (km)")
+    assert _is_dynamic_poi_metric_column("Number of Cafe POIs within 2km")
+    assert _is_dynamic_poi_metric_column("Number of Cafe POIs within 5km")
+    assert not _is_dynamic_poi_metric_column("Number of restaurants within 2km")