fix(places): a phase page needs results, not merely publishable schools

Asked where schools with no results should sit in an alphabetical list, and
found that some pages were almost entirely made of them.

The per-phase threshold counted schools that were publishable — a result OR
an Ofsted grade — while a phase page exists for its results column.
/schools/kent/primary published with none of its five rows carrying a result;
Minehead had one of seven, Buntingford one of five. Forty-four phase pages
were majority-blank.

It is the same rule as "no page without a local average", which was written
into the spec as a thin-page control and never extended per phase.

The threshold now counts schools with a result for that phase. It gates
whether the page exists; it does not filter rows — a page that publishes still
lists every school of the phase, because someone looking up a school by name
has to find it whether or not it published results.

126 of 1,012 variant pages stop publishing: 62 primary, 64 secondary. Every
one of them was a table with too little in it to be worth a page.

The ordering itself is unchanged: pure A-Z, blanks interleaved. A school sits
where its name says it does, and at roughly a tenth of rows that reads fine.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015mWQnpye9F299NVRCCSRvj

backend/places.py

@@ -59,18 +59,51 @@ def _publishable_urns(df) -> set[int]:
     return set(df.loc[df[cols].notna().any(axis=1), "urn"].astype(int))
 
 
+# The measure a phase page is built around. A page with no results in this
+# column has nothing a list of school names does not already give.
+_PHASE_METRIC = {
+    "primary": "rwm_expected_pct",
+    "secondary": "attainment_8_score",
+}
+
+
 def _phase_urns(group, publishable: set[int]) -> dict[str, tuple[int, ...]]:
-    """URNs per phase. All-through schools count toward both, matching the
-    PHASE_GROUPS mapping the search filters already use."""
+    """URNs per phase, counting only schools with a result for that phase.
+
+    Not merely "publishable". A school with an Ofsted grade and no results is
+    worth a page of its own and belongs in the place list, but it cannot
+    populate a phase page's results column — and the threshold is there to ask
+    whether that column will have anything in it.
+
+    Counting publishable schools instead let /schools/kent/primary publish
+    with none of its five rows carrying a result, and left 44 phase pages
+    majority-blank. It is the same rule as "no page without a local average",
+    which was never extended per phase.
+
+    All-through schools count toward both phases, matching the PHASE_GROUPS
+    mapping the search filters already use.
+    """
     from backend.app import PHASE_GROUPS
 
     if "phase" not in group.columns:
         return {}
     lowered = group["phase"].fillna("").str.lower()
+
     out: dict[str, tuple[int, ...]] = {}
     for phase in ("primary", "secondary"):
         wanted = PHASE_GROUPS.get(phase, set())
         subset = group[lowered.isin(wanted)]
+
+        # The page lists every school of the phase; the threshold counts only
+        # those carrying a result, so a mostly-empty table never publishes.
+        metric = _PHASE_METRIC[phase]
+        with_result = (
+            {int(u) for u in subset.loc[subset[metric].notna(), "urn"]}
+            if metric in subset.columns else set()
+        )
+        if len(with_result & publishable) < MIN_SCHOOLS:
+            continue
+
         urns = tuple(sorted({int(u) for u in subset["urn"]} & publishable))
         if urns:
             out[phase] = urns

backend/tests/test_places.py

@@ -343,3 +343,49 @@ def test_the_merged_place_takes_its_most_common_spelling():
             + _town(5, "NEWCASTLE-UNDER-LYME", "Staffordshire", start=400000))
     reg = build_place_registry(_df(rows))
     assert reg["town:newcastle-under-lyme"].name == "Newcastle-under-Lyme"
+
+
+def test_a_phase_page_needs_results_not_merely_publishable_schools():
+    """/schools/kent/primary published with none of its five rows scored.
+
+    The threshold counted schools that were publishable — a result OR an
+    Ofsted grade — while the page exists for its results column. Forty-four
+    phase pages were majority-blank; one had no results at all.
+    """
+    rows = _town(MIN_SCHOOLS, "Kent", "Kent")
+    for r in rows:
+        r["rwm_expected_pct"] = np.nan     # Ofsted only, no results
+    reg = build_place_registry(_df(rows))
+
+    assert "town:kent" in reg               # the place still publishes
+    assert not reg["town:kent"].publishes_phase("primary")
+
+
+def test_a_phase_page_publishes_once_enough_schools_carry_a_result():
+    rows = _town(MIN_SCHOOLS, "Beccles", "Suffolk")
+    reg = build_place_registry(_df(rows))
+    assert reg["town:beccles"].publishes_phase("primary")
+
+
+def test_a_publishing_phase_page_still_lists_its_unscored_schools():
+    """The threshold gates whether the page exists; it does not filter rows.
+
+    A parent looking up a school by name has to find it whether or not it
+    published results.
+    """
+    scored = _town(MIN_SCHOOLS, "Beccles", "Suffolk", start=300000)
+    unscored = _town(2, "Beccles", "Suffolk", start=400000)
+    for r in unscored:
+        r["rwm_expected_pct"] = np.nan
+    reg = build_place_registry(_df(scored + unscored))
+
+    place = reg["town:beccles"]
+    assert place.publishes_phase("primary")
+    assert len(place.phase_urns["primary"]) == MIN_SCHOOLS + 2
+
+
+def test_the_secondary_threshold_counts_its_own_metric():
+    # A town full of scored primaries must not thereby publish a secondary page.
+    rows = _town(MIN_SCHOOLS, "Brentwood", "Essex")
+    reg = build_place_registry(_df(rows))
+    assert not reg["town:brentwood"].publishes_phase("secondary")