Improve data

pipeline/transform/test_school_proximity.py

@@ -42,7 +42,20 @@ def test_ungraded_remains_good_is_recovered_when_no_graded_result():
     rows = [
         _school("Primary", None, "School remains Good", "AA1 1AA"),
         _school("Secondary", "Not judged", "School remains Outstanding", "AA1 1AB"),
-        # "(Concerns)"/"(Improving)" variants are still good+.
+        # "(Improving)" is still good+ ...
+        _school("Primary", None, "School remains Good (Improving) - S5 Next", "AA1 1AE"),
+    ]
+    assert _classify(rows) == {
+        ("AA1 1AA", "good_primary"),
+        ("AA1 1AB", "outstanding_secondary"),
+        ("AA1 1AE", "good_primary"),
+    }
+
+
+def test_ungraded_concerns_are_not_good_plus():
+    # "(Concerns)" outcomes signal issues warranting earlier re-inspection and
+    # must NOT be counted as good+ schools.
+    rows = [
         _school("Primary", None, "School remains Good (Concerns) - S5 Next", "AA1 1AC"),
         _school(
             "Secondary",
@@ -51,12 +64,7 @@ def test_ungraded_remains_good_is_recovered_when_no_graded_result():
             "AA1 1AD",
         ),
     ]
-    assert _classify(rows) == {
-        ("AA1 1AA", "good_primary"),
-        ("AA1 1AB", "outstanding_secondary"),
-        ("AA1 1AC", "good_primary"),
-        ("AA1 1AD", "outstanding_secondary"),
-    }
+    assert _classify(rows) == set()
 
 
 def test_ungraded_non_good_outcomes_are_excluded():
@@ -80,3 +88,52 @@ def test_non_primary_secondary_phases_excluded():
         _school("Not applicable", "2", None),
     ]
     assert _classify(rows) == set()
+
+
+def _aged_school(phase, oeif, low, high, postcode="AA1 1AA"):
+    return {
+        "Postcode": postcode,
+        "Ofsted phase": phase,
+        "Latest OEIF overall effectiveness": oeif,
+        "Ungraded inspection overall outcome": None,
+        "URN": 100000,
+        "Statutory lowest age": low,
+        "Statutory highest age": high,
+    }
+
+
+def test_all_through_school_counts_toward_both_primary_and_secondary():
+    # An all-through school (age 3-18) is labelled "Secondary" by Ofsted phase but
+    # serves primary-age children too, so it must count in BOTH metrics.
+    rows = [_aged_school("Secondary", "2", 3, 18, "AA1 1AA")]
+    assert _classify(rows) == {
+        ("AA1 1AA", "good_primary"),
+        ("AA1 1AA", "good_secondary"),
+    }
+
+
+def test_age_ranges_assign_single_phase_for_standard_schools():
+    rows = [
+        _aged_school("Primary", "1", 4, 11, "AA1 1AA"),  # primary only
+        _aged_school("Secondary", "2", 11, 16, "AA1 1AB"),  # secondary only
+        _aged_school("Secondary", "1", 9, 13, "AA1 1AC"),  # middle -> both
+    ]
+    assert _classify(rows) == {
+        ("AA1 1AA", "outstanding_primary"),
+        ("AA1 1AB", "good_secondary"),
+        ("AA1 1AC", "outstanding_primary"),
+        ("AA1 1AC", "outstanding_secondary"),
+    }
+
+
+def test_closed_schools_excluded_when_open_register_given():
+    rows = [
+        _aged_school("Primary", "1", 4, 11, "AA1 1AA"),
+        _aged_school("Secondary", "2", 11, 16, "AA1 1AB"),
+    ]
+    rows[0]["URN"] = 111
+    rows[1]["URN"] = 222
+    result = classify_good_plus_schools(pl.DataFrame(rows), open_urns={111})
+    pairs = {(r["postcode"], r["category"]) for r in result.to_dicts()}
+    # URN 222 is not in the open register, so it is dropped.
+    assert pairs == {("AA1 1AA", "outstanding_primary")}