perf(api): persist KS4 national averages as a mart; stop per-request aggregation

fact_ks4_national_averages is computed once at dbt build time (covered by
the EES DAG's stg_ees_ks4+ selector). _national_averages_payload now reads
both national-averages marts instead of scanning the performance dataframe
per year on every /api/compare request (~250ms saved per call). Fallback
for the deploy-before-DAG window computes the latest year only.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0146VHeLAWjDVE2B5uU67jCB

backend/tests/test_national_averages_marts.py

@@ -0,0 +1,93 @@
+"""_national_averages_payload reads persisted marts (computed at import
+time) — it must never loop the dataframe per year. The only dataframe work
+allowed is the single-latest-year KS4 fallback for the window between a
+deploy and the next DAG run."""
+
+import numpy as np
+import pandas as pd
+import pytest
+
+LATEST = 202425
+
+
+def _df():
+    return pd.DataFrame(
+        [
+            dict(year=202324, attainment_8_score=40.0, rwm_expected_pct=np.nan),
+            dict(year=LATEST, attainment_8_score=50.0, rwm_expected_pct=np.nan),
+            dict(year=LATEST, attainment_8_score=30.0, rwm_expected_pct=np.nan),
+            dict(year=LATEST, attainment_8_score=np.nan, rwm_expected_pct=80.0),
+        ]
+    )
+
+
+class _Ks2Row:
+    year = LATEST
+    rwm_expected_pct = 62.1
+    gps_expected_pct = 72.0
+
+
+class _Ks4Row:
+    year = LATEST
+    attainment_8_score = 46.5
+    progress_8_score = -0.02
+
+
+class _StubSession:
+    """Returns KS2 rows for the first query and KS4 rows for the second —
+    mirroring the payload's query order."""
+
+    def __init__(self):
+        self.calls = 0
+
+    def query(self, model):
+        self._model = model.__name__
+        return self
+
+    def order_by(self, *a):
+        return self
+
+    def all(self):
+        return [_Ks2Row()] if self._model == "Ks2NationalAverage" else [_Ks4Row()]
+
+    def close(self):
+        pass
+
+
+class _Ks4MissingSession(_StubSession):
+    def all(self):
+        if self._model == "Ks4NationalAverage":
+            raise RuntimeError("relation does not exist")
+        return [_Ks2Row()]
+
+    def rollback(self):
+        pass
+
+
+@pytest.fixture()
+def payload(monkeypatch):
+    from backend import app as app_module
+    from backend import database as database_module
+
+    def _run(session_cls):
+        monkeypatch.setattr(database_module, "SessionLocal", session_cls)
+        return app_module._national_averages_payload(_df())
+
+    return _run
+
+
+def test_ks4_averages_come_from_the_mart_not_the_dataframe(payload):
+    body = payload(_StubSession)
+    # Mart value (46.5), NOT the dataframe mean of (50+30)/2 = 40.0
+    assert body["secondary"]["attainment_8_score"] == 46.5
+    assert body["primary"]["rwm_expected_pct"] == 62.1
+    assert body["by_year"][-1]["secondary"]["progress_8_score"] == -0.02
+
+
+def test_missing_ks4_mart_falls_back_to_latest_year_only(payload):
+    body = payload(_Ks4MissingSession)
+    # Fallback computes the latest year from the df: mean(50, 30) = 40.0
+    assert body["secondary"]["attainment_8_score"] == 40.0
+    # ...and only the latest year — no historical KS4 loop
+    ks4_years = [e["year"] for e in body["by_year"] if e["secondary"]]
+    assert ks4_years == [LATEST]