perf(api): batch supplementary queries — one per table, not five per school

get_supplementary_data ran ~5 sequential DB round-trips per URN, so
/api/compare scaled at ~37ms/school (measured on staging: 1 school 155ms,
3 schools 220ms, 6 schools 340ms). get_supplementary_data_batch fetches
each table once with WHERE urn IN (...) and groups in Python, collapsing
5*N round-trips to a constant 5. get_supplementary_data is now a thin
wrapper so the detail endpoint is unchanged; the compare endpoint makes
one batched call. Each table degrades independently on failure.

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

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)]