fix(data): official DfE KS4 national headline averages; drop mislabelled computed means

New ees_ks4_national stream ingests the EES 'National characteristics
summary data' series (England, state-funded, all pupils). The old mart's
unweighted school means were 7-15 points off every headline measure and
produced an impossible national Progress 8 (-0.27). The API's computed
fallback is gone too: the footnote calls these figures official, so an
unbuilt mart now yields an empty series, never a stand-in.

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

pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py

@@ -564,6 +564,74 @@ class EESKs2NationalStream(Stream):
             yield record
 
 
+# ── KS4 National Headlines (national level only — one row per year) ──────────
+# Dataset: "National characteristics summary data" (Key stage 4 performance).
+# Official England state-funded headline measures, 2018/19 → latest.
+# Suppressed values ('z', 'x') → NULL downstream. Progress 8 is legitimately
+# absent in years with no KS2 baseline (e.g. 2024/25) — that is DfE policy,
+# not missing data.
+
+_KS4_NATIONAL_CSV_URL = (
+    "https://explore-education-statistics.service.gov.uk/data-catalogue/"
+    "data-set/1b649e16-01e8-435b-a814-56be2faf9054/csv"
+)
+
+_KS4_NATIONAL_COL_MAP = {
+    "attainment8_average":    "attainment_8_score",
+    "progress8_average":      "progress_8_score",
+    "engmath_94_percent":     "english_maths_standard_pass_pct",
+    "engmath_95_percent":     "english_maths_strong_pass_pct",
+    "ebacc_entering_percent": "ebacc_entry_pct",
+    "ebacc_94_percent":       "ebacc_standard_pass_pct",
+    "ebacc_95_percent":       "ebacc_strong_pass_pct",
+    "ebacc_aps_average":      "ebacc_avg_score",
+}
+
+
+class EESKs4NationalStream(Stream):
+    """National KS4 headline averages — one row per academic year.
+
+    Filters to geographic_level == 'National', establishment_type_group ==
+    'All state-funded', breakdown_topic == 'Total', breakdown == 'Total'
+    so only the England-wide all-pupils row per year is emitted.
+    """
+
+    name = "ees_ks4_national"
+    primary_keys = ["time_period"]
+    replication_key = None
+
+    schema = th.PropertiesList(
+        th.Property("time_period", th.StringType, required=True),
+        *[th.Property(out, th.StringType) for out in _KS4_NATIONAL_COL_MAP.values()],
+    ).to_dict()
+
+    def get_records(self, context):
+        import pandas as pd
+
+        self.logger.info("Downloading KS4 national headlines: %s", _KS4_NATIONAL_CSV_URL)
+        resp = requests.get(_KS4_NATIONAL_CSV_URL, timeout=60)
+        resp.raise_for_status()
+
+        df = pd.read_csv(io.BytesIO(resp.content), dtype=str, keep_default_na=False)
+        df.columns = [c.strip().lower() for c in df.columns]
+
+        for col, want in [
+            ("geographic_level", "national"),
+            ("establishment_type_group", "all state-funded"),
+            ("breakdown_topic", "total"),
+            ("breakdown", "total"),
+        ]:
+            if col in df.columns:
+                df = df[df[col].str.strip().str.lower() == want]
+
+        self.logger.info("Emitting %d national KS4 rows", len(df))
+        for _, row in df.iterrows():
+            record = {"time_period": row.get("time_period", "").strip()}
+            for csv_col, field in _KS4_NATIONAL_COL_MAP.items():
+                record[field] = row.get(csv_col, "").strip()
+            yield record
+
+
 # ── Legacy KS2 (pre-COVID wide format from DfE performance tables) ────────────
 # The DfE "Compare School Performance" site published school-level KS2 CSVs
 # in a wide format (one row per school, ~300 columns).  EES only has school-level
@@ -903,6 +971,7 @@ class TapUKEES(Tap):
             LegacyKS2Stream(self),
             LegacyKS4Stream(self),
             EESKs2NationalStream(self),
+            EESKs4NationalStream(self),
         ]