Merge pull request 'perf(api): batch supplementary queries — /api/compare stops scaling per school' (#38) from perf/batch-supplementary into main

Reviewed-on: #38

backend/app.py

@@ -30,6 +30,7 @@ from .data_loader import (
     load_latest_school_data,
     geocode_single_postcode,
     get_supplementary_data,
+    get_supplementary_data_batch,
     search_schools_typesense,
 )
 from .data_loader import get_data_info as get_db_info
@@ -679,8 +680,10 @@ async def compare_schools(
     db = None
     try:
         db = database.SessionLocal()
+        # One query per table for all schools, not ~5 queries per school.
+        batch = get_supplementary_data_batch(db, urn_list)
         for urn in urn_list:
-            supp = get_supplementary_data(db, urn)
+            supp = batch.get(urn, {})
             supplementary_by_urn[urn] = {
                 key: supp.get(key, default)
                 for key, default in _EMPTY_SUPPLEMENTARY.items()

backend/data_loader.py

@@ -662,92 +662,150 @@ def _admissions_row_dict(a) -> dict:
     }
 
 
-def get_supplementary_data(db: Session, urn: int) -> dict:
-    """Fetch all supplementary data for a single school URN."""
-    result = {}
+def _census_dict(pc) -> dict:
+    return {
+        "year": pc.year,
+        "total_pupils": pc.total_pupils,
+        "female_pupils": pc.female_pupils,
+        "male_pupils": pc.male_pupils,
+        "fsm_pct": pc.fsm_pct,
+        "eal_pct": pc.eal_pct,
+    }
 
-    def safe_query(model, pk_field, latest_field=None):
+
+def _deprivation_dict(d) -> dict:
+    return {
+        "lsoa_code": d.lsoa_code,
+        "idaci_score": d.idaci_score,
+        "idaci_decile": d.idaci_decile,
+    }
+
+
+def _finance_dict(f) -> dict:
+    return {
+        "year": f.year,
+        "per_pupil_spend": f.per_pupil_spend,
+        "staff_cost_pct": f.staff_cost_pct,
+        "teacher_cost_pct": f.teacher_cost_pct,
+        "support_staff_cost_pct": f.support_staff_cost_pct,
+        "premises_cost_pct": f.premises_cost_pct,
+    }
+
+
+def _empty_supplementary() -> dict:
+    return {
+        "ofsted": None,
+        "census": None,
+        "admissions": None,
+        "admissions_history": [],
+        "sen_detail": None,
+        "phonics": None,
+        "deprivation": None,
+        "finance": None,
+    }
+
+
+def get_supplementary_data_batch(db: Session, urns: list[int]) -> dict:
+    """Fetch supplementary data for many URNs with one query per table
+    (WHERE urn IN (...)) instead of ~5 queries per school, collapsing the
+    per-request round-trips from 5*N to a constant 5. Returns {urn: block}
+    with the same shape get_supplementary_data produces per URN.
+
+    Each table is queried independently and failures degrade that table to
+    empty for every URN — a missing mart never blanks the others.
+    """
+    urns = [int(u) for u in urns]
+    result = {urn: _empty_supplementary() for urn in urns}
+    if not urns:
+        return result
+
+    def _safe(fn):
         try:
-            q = db.query(model).filter(getattr(model, pk_field) == urn)
-            if latest_field:
-                q = q.order_by(getattr(model, latest_field).desc())
-            return q.first()
+            fn()
         except Exception as e:
             import logging
-            logging.getLogger(__name__).error("safe_query failed for %s: %s", model.__name__, e)
+            logging.getLogger(__name__).error("batch supplementary query failed: %s", e)
             db.rollback()
-            return None
 
-    # Latest Ofsted inspection
-    o = safe_query(FactOfstedInspection, "urn", "inspection_date")
-    result["ofsted"] = _ofsted_block(o, urn) if o else None
-
-    # Census (latest year of fact_pupil_characteristics)
-    pc = safe_query(FactPupilCharacteristics, "urn", "year")
-    result["census"] = (
-        {
-            "year": pc.year,
-            "total_pupils": pc.total_pupils,
-            "female_pupils": pc.female_pupils,
-            "male_pupils": pc.male_pupils,
-            "fsm_pct": pc.fsm_pct,
-            "eal_pct": pc.eal_pct,
-        }
-        if pc
-        else None
-    )
-
-    # Admissions — all years, oldest first (for the multi-year trend view).
-    try:
-        admissions_rows = (
-            db.query(FactAdmissions)
-            .filter(FactAdmissions.urn == urn)
-            .order_by(FactAdmissions.year.asc())
+    # Ofsted — latest inspection per URN. Ordered so the first row seen per
+    # URN is the most recent.
+    def _ofsted():
+        rows = (
+            db.query(FactOfstedInspection)
+            .filter(FactOfstedInspection.urn.in_(urns))
+            .order_by(FactOfstedInspection.urn, FactOfstedInspection.inspection_date.desc())
             .all()
         )
-    except Exception as e:
-        import logging
-        logging.getLogger(__name__).error("admissions history query failed: %s", e)
-        db.rollback()
-        admissions_rows = []
+        seen = set()
+        for o in rows:
+            if o.urn in seen:
+                continue
+            seen.add(o.urn)
+            result[o.urn]["ofsted"] = _ofsted_block(o, o.urn)
+    _safe(_ofsted)
 
-    history = [_admissions_row_dict(a) for a in admissions_rows]
-    result["admissions_history"] = history
-    # Keep the single latest-year object for backwards-compatible consumers
-    # (hero chips, etc.).
-    result["admissions"] = history[-1] if history else None
+    # Census — latest year per URN.
+    def _census():
+        rows = (
+            db.query(FactPupilCharacteristics)
+            .filter(FactPupilCharacteristics.urn.in_(urns))
+            .order_by(FactPupilCharacteristics.urn, FactPupilCharacteristics.year.desc())
+            .all()
+        )
+        seen = set()
+        for pc in rows:
+            if pc.urn in seen:
+                continue
+            seen.add(pc.urn)
+            result[pc.urn]["census"] = _census_dict(pc)
+    _safe(_census)
 
-    # SEN detail — not available in current marts
-    result["sen_detail"] = None
+    # Admissions — all years per URN, oldest first (multi-year trend view).
+    def _admissions():
+        rows = (
+            db.query(FactAdmissions)
+            .filter(FactAdmissions.urn.in_(urns))
+            .order_by(FactAdmissions.urn, FactAdmissions.year.asc())
+            .all()
+        )
+        history: dict = {urn: [] for urn in urns}
+        for a in rows:
+            history[a.urn].append(_admissions_row_dict(a))
+        for urn, rows_for_urn in history.items():
+            result[urn]["admissions_history"] = rows_for_urn
+            result[urn]["admissions"] = rows_for_urn[-1] if rows_for_urn else None
+    _safe(_admissions)
 
-    # Phonics — no school-level data on EES
-    result["phonics"] = None
+    # Deprivation — one row per URN.
+    def _deprivation():
+        rows = (
+            db.query(FactDeprivation)
+            .filter(FactDeprivation.urn.in_(urns))
+            .all()
+        )
+        for d in rows:
+            result[d.urn]["deprivation"] = _deprivation_dict(d)
+    _safe(_deprivation)
 
-    # Deprivation
-    d = safe_query(FactDeprivation, "urn")
-    result["deprivation"] = (
-        {
-            "lsoa_code": d.lsoa_code,
-            "idaci_score": d.idaci_score,
-            "idaci_decile": d.idaci_decile,
-        }
-        if d
-        else None
-    )
-
-    # Finance (latest year)
-    f = safe_query(FactFinance, "urn", "year")
-    result["finance"] = (
-        {
-            "year": f.year,
-            "per_pupil_spend": f.per_pupil_spend,
-            "staff_cost_pct": f.staff_cost_pct,
-            "teacher_cost_pct": f.teacher_cost_pct,
-            "support_staff_cost_pct": f.support_staff_cost_pct,
-            "premises_cost_pct": f.premises_cost_pct,
-        }
-        if f
-        else None
-    )
+    # Finance — latest year per URN.
+    def _finance():
+        rows = (
+            db.query(FactFinance)
+            .filter(FactFinance.urn.in_(urns))
+            .order_by(FactFinance.urn, FactFinance.year.desc())
+            .all()
+        )
+        seen = set()
+        for f in rows:
+            if f.urn in seen:
+                continue
+            seen.add(f.urn)
+            result[f.urn]["finance"] = _finance_dict(f)
+    _safe(_finance)
 
     return result
+
+
+def get_supplementary_data(db: Session, urn: int) -> dict:
+    """Supplementary data for a single URN (thin wrapper over the batch)."""
+    return get_supplementary_data_batch(db, [urn])[int(urn)]

backend/tests/test_compare_enrichment.py

@@ -67,7 +67,9 @@ def client(monkeypatch):
 
     monkeypatch.setattr(app_module, "load_school_data", _two_primary_schools_df)
     monkeypatch.setattr(
-        app_module, "get_supplementary_data", lambda db, urn: dict(CANNED_SUPPLEMENTARY)
+        app_module,
+        "get_supplementary_data_batch",
+        lambda db, urns: {int(u): dict(CANNED_SUPPLEMENTARY) for u in urns},
     )
     monkeypatch.setattr(database_module, "SessionLocal", _StubSession)
     return TestClient(app_module.app, raise_server_exceptions=False)
@@ -102,10 +104,10 @@ def test_top_level_national_averages_and_benchmarks(client):
 def test_supplementary_failure_degrades_not_500(client, monkeypatch):
     from backend import app as app_module
 
-    def _boom(db, urn):
+    def _boom(db, urns):
         raise RuntimeError("marts unavailable")
 
-    monkeypatch.setattr(app_module, "get_supplementary_data", _boom)
+    monkeypatch.setattr(app_module, "get_supplementary_data_batch", _boom)
     resp = client.get("/api/compare?urns=100140")
     assert resp.status_code == 200
     school = resp.json()["comparison"]["100140"]

backend/tests/test_supplementary_batch.py

@@ -0,0 +1,111 @@
+"""get_supplementary_data_batch fetches one query per table for all URNs
+(not ~5 per school) and returns the same per-URN block shape as the
+single-URN function, picking the latest row per URN where relevant."""
+
+import types
+
+from backend import data_loader
+from backend.data_loader import get_supplementary_data_batch
+
+
+class _FakeQuery:
+    """Records that a query ran and serves canned rows filtered by an in-list."""
+
+    def __init__(self, recorder, model_name, rows):
+        self._rec = recorder
+        self._model = model_name
+        self._rows = rows
+
+    def filter(self, *args, **kwargs):
+        return self
+
+    def order_by(self, *args, **kwargs):
+        return self
+
+    def all(self):
+        self._rec.append(self._model)
+        return self._rows
+
+    def first(self):
+        self._rec.append(self._model)
+        return self._rows[0] if self._rows else None
+
+
+class _FakeSession:
+    def __init__(self, rows_by_model):
+        self.rows_by_model = rows_by_model
+        self.queries: list[str] = []
+
+    def query(self, model):
+        name = model.__name__
+        return _FakeQuery(self.queries, name, self.rows_by_model.get(name, []))
+
+    def rollback(self):
+        pass
+
+
+def _ofsted_row(urn, date, oe):
+    base = {f: None for f in (
+        "framework", "inspection_type", "quality_of_education", "behaviour_attitudes",
+        "personal_development", "leadership_management", "early_years_provision",
+        "sixth_form_provision", "ungraded_outcome", "ungraded_grade",
+        "rc_safeguarding_met", "rc_inclusion", "rc_curriculum_teaching", "rc_achievement",
+        "rc_attendance_behaviour", "rc_personal_development", "rc_leadership_governance",
+        "rc_early_years", "rc_sixth_form", "report_url",
+    )}
+    base.update(urn=urn, inspection_date=types.SimpleNamespace(isoformat=lambda: date),
+                overall_effectiveness=oe, grade_source=None)
+    return types.SimpleNamespace(**base)
+
+
+def _adm_row(urn, year):
+    return types.SimpleNamespace(
+        urn=urn, year=year, school_phase="Primary", places_offered=100,
+        total_applications=200, first_preference_applications=150,
+        first_preference_offers=140, first_preference_offer_pct=93.3,
+        oversubscription_ratio=1.5, oversubscribed=True,
+        total_offers=100, second_preference_offers=5, third_preference_offers=2,
+        cross_la_applications=10, cross_la_offers=3,
+    )
+
+
+def test_one_query_per_table_and_latest_row_per_urn():
+    rows = {
+        # URN 1 has two Ofsted rows; the batch must keep the most recent (2023).
+        "FactOfstedInspection": [
+            _ofsted_row(1, "2023-01-01", 2),
+            _ofsted_row(1, "2019-01-01", 3),
+            _ofsted_row(2, "2021-06-01", 1),
+        ],
+        "FactAdmissions": [_adm_row(1, 202526), _adm_row(1, 202627), _adm_row(2, 202627)],
+        "FactPupilCharacteristics": [],
+        "FactDeprivation": [],
+        "FactFinance": [],
+    }
+    session = _FakeSession(rows)
+    out = get_supplementary_data_batch(session, [1, 2])
+
+    # Exactly one query per table — five total, regardless of two URNs.
+    assert sorted(session.queries) == [
+        "FactAdmissions", "FactDeprivation", "FactFinance",
+        "FactOfstedInspection", "FactPupilCharacteristics",
+    ]
+
+    # Latest Ofsted kept per URN
+    assert out[1]["ofsted"]["overall_effectiveness"] == 2
+    assert out[2]["ofsted"]["overall_effectiveness"] == 1
+
+    # Admissions history grouped per URN, latest exposed as `admissions`
+    assert [r["year"] for r in out[1]["admissions_history"]] == [202526, 202627]
+    assert out[1]["admissions"]["year"] == 202627
+    assert out[2]["admissions_history"] == [{**out[2]["admissions_history"][0]}]
+
+    # Empty tables degrade to the null block, not a crash
+    assert out[1]["census"] is None and out[1]["deprivation"] is None
+
+
+def test_single_wrapper_matches_batch(monkeypatch):
+    session = _FakeSession({"FactOfstedInspection": [_ofsted_row(5, "2022-01-01", 2)]})
+    single = data_loader.get_supplementary_data(session, 5)
+    assert single["ofsted"]["overall_effectiveness"] == 2
+    assert single["admissions_history"] == []