Improve data pipeline

pipeline/transform/test_school_proximity.py

@@ -0,0 +1,82 @@
+import polars as pl
+
+from pipeline.transform.school_proximity import classify_good_plus_schools
+
+
+def _school(phase, oeif, ungraded, postcode="AA1 1AA"):
+    return {
+        "Postcode": postcode,
+        "Ofsted phase": phase,
+        "Latest OEIF overall effectiveness": oeif,
+        "Ungraded inspection overall outcome": ungraded,
+    }
+
+
+def _classify(rows):
+    result = classify_good_plus_schools(pl.DataFrame(rows))
+    return {(r["postcode"], r["category"]) for r in result.to_dicts()}
+
+
+def test_legacy_oeif_grades_1_and_2_are_kept():
+    rows = [
+        _school("Primary", "1", None, "AA1 1AA"),
+        _school("Primary", "2", None, "AA1 1AB"),
+        _school("Secondary", "1", None, "AA1 1AC"),
+        _school("Secondary", "2", None, "AA1 1AD"),
+    ]
+    assert _classify(rows) == {
+        ("AA1 1AA", "outstanding_primary"),
+        ("AA1 1AB", "good_primary"),
+        ("AA1 1AC", "outstanding_secondary"),
+        ("AA1 1AD", "good_secondary"),
+    }
+
+
+def test_grades_3_and_4_are_excluded():
+    rows = [_school("Primary", "3", None), _school("Primary", "4", None)]
+    assert _classify(rows) == set()
+
+
+def test_ungraded_remains_good_is_recovered_when_no_graded_result():
+    # Null and "Not judged" OEIF fall back to the ungraded outcome.
+    rows = [
+        _school("Primary", None, "School remains Good", "AA1 1AA"),
+        _school("Secondary", "Not judged", "School remains Outstanding", "AA1 1AB"),
+        # "(Concerns)"/"(Improving)" variants are still good+.
+        _school("Primary", None, "School remains Good (Concerns) - S5 Next", "AA1 1AC"),
+        _school(
+            "Secondary",
+            None,
+            "School remains Outstanding (Concerns) - S5 Next",
+            "AA1 1AD",
+        ),
+    ]
+    assert _classify(rows) == {
+        ("AA1 1AA", "good_primary"),
+        ("AA1 1AB", "outstanding_secondary"),
+        ("AA1 1AC", "good_primary"),
+        ("AA1 1AD", "outstanding_secondary"),
+    }
+
+
+def test_ungraded_non_good_outcomes_are_excluded():
+    rows = [
+        _school("Primary", None, "Some aspects not as strong"),
+        _school("Primary", None, "Standards maintained"),
+        _school("Primary", None, None),
+    ]
+    assert _classify(rows) == set()
+
+
+def test_genuine_grade_3_is_not_overridden_by_stale_remains_good():
+    # A real grade 3 must not be promoted by an ungraded "remains Good".
+    rows = [_school("Primary", "3", "School remains Good")]
+    assert _classify(rows) == set()
+
+
+def test_non_primary_secondary_phases_excluded():
+    rows = [
+        _school("Nursery", "1", None),
+        _school("Not applicable", "2", None),
+    ]
+    assert _classify(rows) == set()