fix(api): serve DfE's LA averages for "vs LA avg" (H2)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

backend/app.py

@@ -1273,17 +1273,63 @@ async def get_filter_options(request: Request):
     }
 
 
+def _la_averages_payload(df: pd.DataFrame) -> dict:
+    """Per-LA Attainment 8 for the "vs LA avg" comparison: DfE's own LA
+    averages (fact_ks4_la_averages, all state-funded schools), never a mean of
+    the dataframe. That mean counted independent and special schools and put
+    most LAs about 7 points low (audit H2).
+
+    The year is the latest with any school Attainment 8, so the average and
+    the scores set against it are the same year. Figures are keyed by our LA
+    name through the LA code. An LA without a DfE figure for that year (City of
+    London) is absent; no figures for the year, or no mart, give an empty map,
+    so rows show no comparison, never another year's figure.
+    """
+    empty = {"year": 0, "secondary": {"attainment_8_by_la": {}}}
+    if df.empty or "attainment_8_score" not in df.columns:
+        return empty
+    scored = df[df["attainment_8_score"].notna()]
+    if scored.empty:
+        return empty
+    year = int(scored["year"].max())
+
+    la = (df[["local_authority_code", "local_authority"]]
+          .dropna()
+          .drop_duplicates("local_authority_code"))
+    name_by_code = {int(code): name for code, name in
+                    zip(la["local_authority_code"], la["local_authority"])}
+
+    from . import database
+    from .models import Ks4LaAverage
+
+    rows: list = []
+    db = None
+    try:
+        db = database.SessionLocal()
+        rows = db.query(Ks4LaAverage).filter(Ks4LaAverage.year == year).all()
+    except Exception:
+        import logging
+        logging.getLogger(__name__).warning(
+            "DfE LA averages unavailable for %s", year, exc_info=True)
+        if db is not None:
+            db.rollback()
+    finally:
+        if db is not None:
+            db.close()
+
+    by_la = {
+        name_by_code[row.la_code]: row.attainment_8_score
+        for row in rows
+        if row.attainment_8_score is not None and row.la_code in name_by_code
+    }
+    return {"year": year, "secondary": {"attainment_8_by_la": by_la}}
+
+
 @app.get("/api/la-averages")
 @limiter.limit(f"{settings.rate_limit_per_minute}/minute")
 async def get_la_averages(request: Request):
-    """Get per-LA average Attainment 8 score for secondary schools in the latest year."""
-    df = load_school_data()
-    if df.empty:
-        return {"year": 0, "secondary": {"attainment_8_by_la": {}}}
-    latest_year = int(df["year"].max())
-    sec_df = df[(df["year"] == latest_year) & df["attainment_8_score"].notna()]
-    la_avg = sec_df.groupby("local_authority")["attainment_8_score"].mean().round(1).to_dict()
-    return {"year": latest_year, "secondary": {"attainment_8_by_la": la_avg}}
+    """DfE's per-LA Attainment 8 averages for the latest year with results."""
+    return _la_averages_payload(load_school_data())
 
 
 _KS2_NATIONAL_METRICS = [