Fix Ofsted transitional inspections, phase tab exclusions, and FSM benchmark comparison

backend/data_loader.py

@@ -577,6 +577,7 @@ def compute_benchmarks(df: pd.DataFrame) -> dict:
             "eal_pct": _median(sub, "eal_pct"),
             "sen_support_pct": _median(sub, "sen_support_pct"),
             "disadvantaged_pct": _median(sub, "disadvantaged_pct"),
+            "fsm_pct": _median(sub, "fsm_pct"),
             "median_pupils": median_pupils,
         }
         if with_disadvantaged:

backend/tests/test_benchmarks.py

@@ -17,33 +17,33 @@ def _df():
         # 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),
+             sen_support_pct=10.0, disadvantaged_pct=20.0, fsm_pct=15.0, 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),
+             sen_support_pct=14.0, disadvantaged_pct=24.0, fsm_pct=17.0, 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),
+             sen_support_pct=18.0, disadvantaged_pct=30.0, fsm_pct=19.0, 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),
+             sen_support_pct=np.nan, disadvantaged_pct=np.nan, fsm_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),
+             sen_support_pct=20.0, disadvantaged_pct=40.0, fsm_pct=21.0, 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),
+             sen_support_pct=22.0, disadvantaged_pct=44.0, fsm_pct=23.0, 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),
+             sen_support_pct=12.0, disadvantaged_pct=22.0, fsm_pct=12.0, 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),
+             sen_support_pct=16.0, disadvantaged_pct=26.0, fsm_pct=14.0, 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),
+             sen_support_pct=99.0, disadvantaged_pct=99.0, fsm_pct=99.0, total_pupils=9999),
     ]
     return pd.DataFrame(rows)
 
@@ -59,6 +59,8 @@ def test_medians_ignore_nan_and_older_years():
     assert b["year"] == LATEST
     # eal medians over [10,20,30,40,50] = 30
     assert b["primary"]["eal_pct"] == 30.0
+    # fsm medians over [15,17,19,21,23] = 19
+    assert b["primary"]["fsm_pct"] == 19.0
     # median pupils over [200,280,300,350,400] = 300
     assert b["primary"]["median_pupils"] == 300
 
@@ -66,6 +68,7 @@ def test_medians_ignore_nan_and_older_years():
 def test_secondary_block_has_no_disadvantaged_rwm():
     b = compute_benchmarks(_df())
     assert "disadvantaged_rwm_expected_pct" not in b["secondary"]
+    assert b["secondary"]["fsm_pct"] == 13.0
     assert b["secondary"]["median_pupils"] == 1100