backend/data_loader.py

@@ -525,6 +525,72 @@ def get_data_info(db: Session = None) -> dict:
 # SUPPLEMENTARY DATA — per-school detail page
 # =============================================================================
 
+def compute_benchmarks(df: pd.DataFrame) -> dict:
+    """State-school benchmarks computed from our dataset (spec §5/§8.6).
+
+    NOT official DfE figures — consumers must label them
+    "state-school average (computed from our dataset)". The disadvantaged
+    attainment average is weighted by cohort size (eligible_pupils) so
+    small schools don't dominate; context measures are medians.
+    """
+    if df.empty or "year" not in df.columns:
+        return {}
+    latest_year = df["year"].max()
+    if pd.isna(latest_year):
+        return {}
+    d = df[df["year"] == latest_year]
+    if d.empty:
+        return {}
+    is_secondary = (
+        d["attainment_8_score"].notna()
+        if "attainment_8_score" in d.columns
+        else pd.Series(False, index=d.index)
+    )
+    prim, sec = d[~is_secondary], d[is_secondary]
+
+    def _median(sub, col):
+        if col not in sub.columns:
+            return None
+        v = sub[col].median()
+        return round(float(v), 1) if pd.notna(v) else None
+
+    def _weighted_disadvantaged(sub):
+        needed = {"rwm_expected_disadvantaged_pct", "eligible_pupils"}
+        if not needed <= set(sub.columns):
+            return None
+        s = sub.dropna(subset=list(needed))
+        if s.empty or s["eligible_pupils"].sum() == 0:
+            return None
+        w = (
+            (s["rwm_expected_disadvantaged_pct"] * s["eligible_pupils"]).sum()
+            / s["eligible_pupils"].sum()
+        )
+        return round(float(w), 1)
+
+    def _block(sub, with_disadvantaged):
+        median_pupils = None
+        if "total_pupils" in sub.columns:
+            mp = sub["total_pupils"].median()
+            if pd.notna(mp):
+                median_pupils = int(mp)
+        block = {
+            "eal_pct": _median(sub, "eal_pct"),
+            "sen_support_pct": _median(sub, "sen_support_pct"),
+            "disadvantaged_pct": _median(sub, "disadvantaged_pct"),
+            "median_pupils": median_pupils,
+        }
+        if with_disadvantaged:
+            block["disadvantaged_rwm_expected_pct"] = _weighted_disadvantaged(sub)
+        return block
+
+    return {
+        "source": "state-school average (computed from our dataset)",
+        "year": int(latest_year),
+        "primary": _block(prim, with_disadvantaged=True),
+        "secondary": _block(sec, with_disadvantaged=False),
+    }
+
+
 def _ofsted_block(o, urn: int) -> dict:
     """Serialize the latest Ofsted inspection row for API responses.
 

backend/tests/test_benchmarks.py

@@ -0,0 +1,78 @@
+"""compute_benchmarks: state-school benchmarks computed from our dataset
+(spec §5/§8.6). The disadvantaged average must be weighted by cohort size,
+medians must ignore NaN, and only the latest year counts."""
+
+import numpy as np
+import pandas as pd
+
+from backend.data_loader import compute_benchmarks
+
+LATEST = 202425
+
+
+def _df():
+    rows = [
+        # Six primary schools, latest year. Disadvantaged RWM chosen so the
+        # weighted average differs clearly from the unweighted mean:
+        # weighted = (40*100 + 60*300) / 400 = 55.0 ; unweighted mean = 50.0
+        dict(year=LATEST, attainment_8_score=np.nan, eligible_pupils=100,
+             rwm_expected_disadvantaged_pct=40.0, eal_pct=10.0,
+             sen_support_pct=10.0, disadvantaged_pct=20.0, total_pupils=200),
+        dict(year=LATEST, attainment_8_score=np.nan, eligible_pupils=300,
+             rwm_expected_disadvantaged_pct=60.0, eal_pct=20.0,
+             sen_support_pct=14.0, disadvantaged_pct=24.0, total_pupils=280),
+        dict(year=LATEST, attainment_8_score=np.nan, eligible_pupils=np.nan,
+             rwm_expected_disadvantaged_pct=99.0, eal_pct=30.0,
+             sen_support_pct=18.0, disadvantaged_pct=30.0, total_pupils=300),
+        dict(year=LATEST, attainment_8_score=np.nan, eligible_pupils=50,
+             rwm_expected_disadvantaged_pct=np.nan, eal_pct=np.nan,
+             sen_support_pct=np.nan, disadvantaged_pct=np.nan, total_pupils=np.nan),
+        dict(year=LATEST, attainment_8_score=np.nan, eligible_pupils=40,
+             rwm_expected_disadvantaged_pct=np.nan, eal_pct=40.0,
+             sen_support_pct=20.0, disadvantaged_pct=40.0, total_pupils=350),
+        dict(year=LATEST, attainment_8_score=np.nan, eligible_pupils=60,
+             rwm_expected_disadvantaged_pct=np.nan, eal_pct=50.0,
+             sen_support_pct=22.0, disadvantaged_pct=44.0, total_pupils=400),
+        # Two secondary schools (attainment_8 non-null)
+        dict(year=LATEST, attainment_8_score=45.0, eligible_pupils=180,
+             rwm_expected_disadvantaged_pct=np.nan, eal_pct=15.0,
+             sen_support_pct=12.0, disadvantaged_pct=22.0, total_pupils=1000),
+        dict(year=LATEST, attainment_8_score=50.0, eligible_pupils=200,
+             rwm_expected_disadvantaged_pct=np.nan, eal_pct=25.0,
+             sen_support_pct=16.0, disadvantaged_pct=26.0, total_pupils=1200),
+        # An older-year primary row that must NOT influence anything
+        dict(year=202324, attainment_8_score=np.nan, eligible_pupils=500,
+             rwm_expected_disadvantaged_pct=1.0, eal_pct=99.0,
+             sen_support_pct=99.0, disadvantaged_pct=99.0, total_pupils=9999),
+    ]
+    return pd.DataFrame(rows)
+
+
+def test_weighted_disadvantaged_average():
+    b = compute_benchmarks(_df())
+    # Row 3 has NaN eligible_pupils and must be excluded from the weighting.
+    assert b["primary"]["disadvantaged_rwm_expected_pct"] == 55.0
+
+
+def test_medians_ignore_nan_and_older_years():
+    b = compute_benchmarks(_df())
+    assert b["year"] == LATEST
+    # eal medians over [10,20,30,40,50] = 30
+    assert b["primary"]["eal_pct"] == 30.0
+    # median pupils over [200,280,300,350,400] = 300
+    assert b["primary"]["median_pupils"] == 300
+
+
+def test_secondary_block_has_no_disadvantaged_rwm():
+    b = compute_benchmarks(_df())
+    assert "disadvantaged_rwm_expected_pct" not in b["secondary"]
+    assert b["secondary"]["median_pupils"] == 1100
+
+
+def test_provenance_string():
+    b = compute_benchmarks(_df())
+    assert b["source"] == "state-school average (computed from our dataset)"
+
+
+def test_empty_df():
+    assert compute_benchmarks(pd.DataFrame()) == {}