From 5c0ccc693deeca46b9ca043d4056bafc8b00b3cc Mon Sep 17 00:00:00 2001 From: Tudor Date: Tue, 22 Sep 2026 11:58:36 +0100 Subject: [PATCH 1/3] fix: order nearby schools by distance, not by how alike they are MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reported from staging: a Catholic primary showed six Catholic primaries, none of them close enough to be a real option, and omitted the community school down the road. Three causes, compounding. Ranking put tier before distance, so a faith match at 2.9 miles outranked a community school at 0.3. The ENOUGH=3 stopping rule — added so a cap of six would not drag in weak distant matches — filled the row from the best tier before it ever widened, which is what made every card Catholic. And a 3-mile tier-1 radius is sane for a secondary and most of a city for a primary, whose catchments are routinely under a mile. The premise was backwards. For a parent, distance is a constraint and intake is a preference; a school beyond a primary catchment is not a weaker option, it is not an option. So distance now decides the order and nothing else does. The hard filters are untouched — they were always where the defensibility lived. Similarity survives as chips on the card: reported, so a reader applies their own weighting, rather than ranked, so we apply ours for them. Reach is capped per phase (primary 2, secondary 6, post-16 10) as a sanity bound, not a target: ordering already handles density, so the cap only decides what happens where an area is sparse. A primary with nothing inside two miles now renders no section, which is the honest answer. Deleted: the tier system, the stopping rule, the tier-dependent lede, the `tier` field, the tier-3 fallback chip and its style. select_similar also stops taking is_secondary — it reads the phase from the subject's own row, so no caller can hand it one that disagrees with the data. The heading is now "Other schools nearby". The hard filters still guarantee a comparable set, but nothing ranks on likeness, so the heading no longer says it does. Co-Authored-By: Claude Opus 5 --- backend/app.py | 25 +- backend/similar_schools.py | 160 +++++----- backend/tests/test_similar_schools.py | 285 +++++++++++------- e2e/tests/journeys.spec.ts | 12 +- .../components/SimilarSchoolsSection.test.tsx | 44 ++- .../__tests__/lib/schoolSections.test.ts | 20 +- .../app/(frontend)/school/[slug]/page.tsx | 2 +- .../school/SimilarSchools.module.css | 1 - .../school/SimilarSchoolsSection.tsx | 47 ++- nextjs-app/lib/schoolSections.ts | 12 +- nextjs-app/lib/types.ts | 13 +- 11 files changed, 343 insertions(+), 278 deletions(-) diff --git a/backend/app.py b/backend/app.py index 23826c2..e46aff9 100644 --- a/backend/app.py +++ b/backend/app.py @@ -41,7 +41,7 @@ from .data_loader import get_data_info as get_db_info from . import flags from .places import build_place_index, build_place_registry, places_for_urn from .schemas import METRIC_DEFINITIONS, PHASE_GROUPS, RANKING_COLUMNS, SCHOOL_COLUMNS -from .similar_schools import is_secondary_phase, select_similar +from .similar_schools import select_similar from .utils import clean_for_json, convert_to_native # Values to exclude from filter dropdowns (empty strings, non-applicable labels) @@ -266,20 +266,18 @@ def _places_payload(urn: int) -> list[dict]: return payload -def _similar_schools_payload(urn: int, phase: str | None) -> list[dict]: - """Nearby schools this page may offer as alternatives. +def _similar_schools_payload(urn: int) -> list[dict]: + """The nearest eligible schools this page may offer, closest first. + + Phase and reach are read from the school's own row inside select_similar, + so nothing here can hand it a phase that disagrees with the data. Wrapped: a failure in selection must never 500 a page that is otherwise complete, which is the posture get_supplementary_data already takes. The section simply does not render. """ try: - # Decided in similar_schools, beside the PHASE_GROUPS bucket it selects - # from, so the two cannot drift. A substring test for "secondary" here - # would miss "16 plus" and hand a sixth-form college the primary bucket. - return select_similar( - load_latest_school_data(), int(urn), is_secondary_phase(phase) - ) + return select_similar(load_latest_school_data(), int(urn)) except Exception: import logging @@ -999,11 +997,10 @@ async def get_school_details(request: Request, urn: int): # and authority both fall below the publish threshold has nowhere to # point, and the page renders without the module. "places": _places_payload(urn), - # Nearby schools of the same phase and a comparable intake. Always - # present on a build with this code; the frontend treats absent and - # empty identically, which is what lets the two images deploy - # independently. - "similar_schools": _similar_schools_payload(urn, latest.get("phase")), + # The nearest eligible schools, closest first. Always present on a + # build with this code; the frontend treats absent and empty + # identically, which is what lets the two images deploy independently. + "similar_schools": _similar_schools_payload(urn), "yearly_data": clean_for_json(school_data), # Supplementary data (null if not yet populated by Kestra) "ofsted": supplementary.get("ofsted"), diff --git a/backend/similar_schools.py b/backend/similar_schools.py index 0e75467..08a5966 100644 --- a/backend/similar_schools.py +++ b/backend/similar_schools.py @@ -1,17 +1,24 @@ """Which nearby schools a detail page may offer as alternatives. -Two kinds of rule, and they are not interchangeable. +HARD FILTERS decide eligibility, and encode claims the section is not allowed +to make. A selective school is not an alternative to a non-selective one, a +special school is not comparable to a mainstream one, and a Girls school is not +an option for a Boys school's reader. They never relax, at any distance, even +where that means the section does not render at all. -HARD FILTERS encode claims the section is not allowed to make. A selective -school is not an alternative to a non-selective one, a special school is not -comparable to a mainstream one, and a Girls school is not an option for a Boys -school's reader. These never relax, at any distance, even where that means the -section does not render at all. +DISTANCE decides the order, and nothing else does. -SOFT PREFERENCES describe how closely an intake resembles this school's. They -relax in tiers, and every card reports the tier that actually took it so the -page can say what is shared rather than implying more. They relax only far -enough to reach a usable set, never far enough to fill the last of the slots. +An earlier version ranked by intake similarity first and used distance only as +a tiebreak. That put a Catholic school 2.9 miles away above the community +school 0.3 miles down the road, and — because the row filled from the best tier +before widening — filled all six slots with faith matches while omitting every +school a parent could actually walk to. For a primary, a school that far is not +a weaker option; it is not an option. Distance is a constraint and intake is a +preference, and the ranking now says so. + +Similarity survives as `shared`: what a candidate genuinely has in common with +this school, reported on its card, so a reader applies their own weighting +instead of having ours applied for them. Pure functions over a DataFrame: no I/O, no FastAPI, no database. """ @@ -25,19 +32,21 @@ import pandas as pd from .schemas import PHASE_GROUPS -# A cap, not a quota: the section shows everything that qualified at the tiers -# it used, up to this many. Three fit the row; the rest are behind the arrows. +# Three fit the row; the rest are behind the carousel arrows. MAX_SCHOOLS = 6 -# Tiers stop relaxing once this many have been found. Without it, a cap of six -# would reliably drag in tier-3 schools ten miles away to fill a row that three -# good matches had already earned. -ENOUGH = 3 MINIMUM = 2 -# (tier, radius in miles). Faith relaxes before gender: a faith mismatch -# changes the character of a school, while a gender mismatch can mean the -# school is not available to this reader's child at all. -TIERS: tuple[tuple[int, float], ...] = ((1, 3.0), (2, 5.0), (3, 10.0)) +# How far the section will reach, in miles, when nothing closer exists. +# +# A sanity bound rather than a target: ordering by distance already handles +# density, so a school in a dense area fills all six slots inside a mile and +# never sees this. It decides one thing — what happens where the area is +# sparse — and the answer differs by phase because catchments do. Primary +# catchments are routinely under a mile; beyond two, a primary is not a weaker +# option but not an option, and no section is the honest answer. +PRIMARY_RADIUS_MILES = 2.0 +SECONDARY_RADIUS_MILES = 6.0 +POST16_RADIUS_MILES = 10.0 EARTH_RADIUS_MILES = 3958.8 @@ -80,15 +89,6 @@ def genders_compatible(a: str | None, b: str | None) -> bool: return not (left in single and right in single and left != right) -def phase_label(phase: str | None) -> str: - text = (phase or "").strip() - if not text: - return "School" - if text.lower() == "all-through": - return "All-through school" - return f"{text.capitalize()} school" - - def is_secondary_phase(phase: str | None) -> bool: """Whether this phase takes the secondary side: secondary group membership, minus all-through. @@ -107,6 +107,13 @@ def is_secondary_phase(phase: str | None) -> bool: return text != "all-through" and text in PHASE_GROUPS["secondary"] +def radius_miles(phase: str | None) -> float: + """How far this phase's section will reach when nothing closer exists.""" + if (phase or "").strip().lower() == "16 plus": + return POST16_RADIUS_MILES + return SECONDARY_RADIUS_MILES if is_secondary_phase(phase) else PRIMARY_RADIUS_MILES + + def _phase_group(is_secondary: bool) -> set[str]: return PHASE_GROUPS["secondary" if is_secondary else "primary"] @@ -144,26 +151,45 @@ def _mask(series: pd.Series, predicate) -> pd.Series: return pd.Series([predicate(value) for value in series], index=series.index, dtype=bool) -def _chips(subject: pd.Series, candidate: pd.Series, tier: int, is_secondary: bool) -> list[str]: - if tier >= 3: - return [phase_label(candidate.get("phase"))] +def _shared(subject: pd.Series, candidate: pd.Series, is_secondary: bool) -> list[str]: + """What this candidate genuinely has in common with the subject. + + Empty is a real answer, and renders no chips at all. A card claiming a + shared characteristic it does not have would be worse than a bare one — + and since these no longer affect the order, an empty list costs the school + nothing but its place in the row, which distance already decided. + """ + shared: list[str] = [] + + gender = str(subject.get("gender") or "").strip() + if gender and str(candidate.get("gender") or "").strip().lower() == gender.lower(): + shared.append(gender) - chips = [str(subject.get("gender") or "").strip()] if is_secondary: - policy = (candidate.get("admissions_policy") or "").strip() - if policy and policy.lower() not in {"not applicable", "unknown"}: - chips.append(policy) - if tier == 1: - chips.append(faith_label(candidate.get("religious_denomination"))) - return [chip for chip in chips if chip] + policy = str(candidate.get("admissions_policy") or "").strip() + subject_policy = str(subject.get("admissions_policy") or "").strip() + if ( + policy + and policy.lower() == subject_policy.lower() + and policy.lower() not in {"not applicable", "unknown"} + ): + shared.append(policy) + + if faith_key(candidate.get("religious_denomination")) == faith_key( + subject.get("religious_denomination") + ): + shared.append(faith_label(candidate.get("religious_denomination"))) + + return shared -def select_similar(frame: pd.DataFrame, urn: int, is_secondary: bool) -> list[dict]: - """Up to MAX_SCHOOLS nearby schools this page may offer, or [] below MINIMUM. +def select_similar(frame: pd.DataFrame, urn: int) -> list[dict]: + """The nearest eligible schools, closest first — at most MAX_SCHOOLS, and + none at all below MINIMUM. - Selected by tier, displayed by distance: the tier decides which schools - earn a slot, and the render order is then closest-first, because "nearby" - is the promise in the heading. + The phase is read from the subject's own row rather than passed in, so a + caller cannot hand this a phase that disagrees with the data it selects + from. """ subject_rows = frame[frame["urn"] == urn] if subject_rows.empty: @@ -174,6 +200,9 @@ def select_similar(frame: pd.DataFrame, urn: int, is_secondary: bool) -> list[di if lat is None or lon is None: return [] + phase = subject.get("phase") + is_secondary = is_secondary_phase(phase) + reach = radius_miles(phase) metric_key = "attainment_8_score" if is_secondary else "rwm_expected_pct" candidates = frame[frame["urn"] != urn].copy() @@ -208,42 +237,12 @@ def select_similar(frame: pd.DataFrame, urn: int, is_secondary: bool) -> list[di lat, lon, candidates["latitude"].values, candidates["longitude"].values ).round(1) - # ── Soft preferences, in tiers ────────────────────────────────────── - subject_faith = faith_key(subject.get("religious_denomination")) - subject_gender_key = (subject_gender or "").strip().lower() - same_gender = candidates["gender"].fillna("").str.strip().str.lower() == subject_gender_key - same_faith = _mask( - candidates["religious_denomination"], lambda d: faith_key(d) == subject_faith - ) - - tier_masks = { - 1: same_gender & same_faith, - 2: same_gender, - 3: pd.Series(True, index=candidates.index), - } - - # Descend the tiers only until the set reaches ENOUGH. The tier that gets - # there is the last one opened, and the remaining slots up to MAX_SCHOOLS - # are filled from the tiers already used — never by widening again. - picked: dict[int, tuple[int, pd.Series]] = {} - for tier, radius in TIERS: - within = candidates[tier_masks[tier] & (candidates["distance_miles"] <= radius)] - for _, row in within.sort_values("distance_miles").iterrows(): - candidate_urn = int(row["urn"]) - if candidate_urn in picked: - continue - picked[candidate_urn] = (tier, row) - if len(picked) >= MAX_SCHOOLS: - break - if len(picked) >= ENOUGH: - break - - if len(picked) < MINIMUM: + # ── Nearest first, and nothing else has a say ─────────────────────── + within = candidates[candidates["distance_miles"] <= reach] + if len(within) < MINIMUM: return [] - selected = sorted( - picked.values(), key=lambda pair: float(pair[1]["distance_miles"]) - )[:MAX_SCHOOLS] + selected = within.sort_values(["distance_miles", "urn"]).head(MAX_SCHOOLS) return [ { "urn": int(row["urn"]), @@ -251,11 +250,10 @@ def select_similar(frame: pd.DataFrame, urn: int, is_secondary: bool) -> list[di "distance_miles": float(row["distance_miles"]), "school_type": _native(row.get("school_type")), "age_range": _native(row.get("age_range")), - "shared": _chips(subject, row, tier, is_secondary), - "tier": tier, + "shared": _shared(subject, row, is_secondary), "metric_value": _native(row.get(metric_key)), "metric_key": metric_key, "metric_year": _native(row.get("year")), } - for tier, row in selected + for _, row in selected.iterrows() ] diff --git a/backend/tests/test_similar_schools.py b/backend/tests/test_similar_schools.py index ad4aca7..874ed4b 100644 --- a/backend/tests/test_similar_schools.py +++ b/backend/tests/test_similar_schools.py @@ -1,19 +1,26 @@ -"""Selection rules for the "similar schools nearby" section. +"""Selection rules for the nearby-schools section. -The hard filters encode claims the section is not allowed to make — that a +Hard filters encode claims the section is not allowed to make — that a selective school is an alternative to a non-selective one, that a special school is comparable to a mainstream one, or that a Girls school is an option -for a Boys school's reader. They never relax. The soft preferences describe -how close the intake is, and they do — but only far enough to reach a usable -set, never far enough to fill the last of the six slots. +for a Boys school's reader. They decide who is eligible. + +Distance decides the order, and nothing else does. An earlier version ranked by +intake similarity first, which put a Catholic school 2.9 miles away above the +community school 0.3 miles down the road — for a primary, a school that far is +not a weaker option, it is not an option. Similarity is now reported on the +card and never reorders the row. """ import numpy as np import pandas as pd -from backend.similar_schools import is_secondary_phase, select_similar +from backend.similar_schools import ( + is_secondary_phase, + radius_miles, + select_similar, +) -# Roughly 0.7 miles apart in latitude at this longitude. BASE_LAT, BASE_LON = 51.5000, -0.1000 @@ -48,16 +55,68 @@ def _at(miles): return BASE_LAT + miles / 69.0 -def test_returns_nearest_same_phase_schools(): +# --------------------------------------------------------------------------- +# Order: distance, and only distance +# --------------------------------------------------------------------------- + +def test_returns_nearest_first(): frame = _frame( _row(100001, "Subject"), - _row(100002, "Near", latitude=_at(0.5)), - _row(100003, "Mid", latitude=_at(1.0)), - _row(100004, "Far", latitude=_at(2.0)), + _row(100002, "Mid", latitude=_at(1.0)), + _row(100003, "Near", latitude=_at(0.4)), + _row(100004, "Far", latitude=_at(1.8)), ) - result = select_similar(frame, 100001, is_secondary=False) - assert [s["urn"] for s in result] == [100002, 100003, 100004] - assert result[0]["distance_miles"] == 0.5 + result = select_similar(frame, 100001) + assert [s["urn"] for s in result] == [100003, 100002, 100004] + assert result[0]["distance_miles"] == 0.4 + + +def test_a_faith_match_never_outranks_a_closer_school(): + """The reported defect. A Catholic primary surrounded by Catholic primaries + showed six of them and omitted the community school down the road.""" + frame = _frame( + _row(100001, "St Jude's RC Primary", religious_denomination="Roman Catholic"), + _row(100002, "Elm Grove Primary", religious_denomination="None", latitude=_at(0.3)), + _row(100003, "Holy Cross RC", religious_denomination="Roman Catholic", latitude=_at(0.8)), + _row(100004, "Sacred Heart RC", religious_denomination="Roman Catholic", latitude=_at(1.2)), + _row(100005, "St Peter's RC", religious_denomination="Roman Catholic", latitude=_at(1.6)), + ) + result = select_similar(frame, 100001) + assert result[0]["urn"] == 100002, "the nearest school leads, whatever its intake" + assert [s["distance_miles"] for s in result] == sorted(s["distance_miles"] for s in result) + + +def test_the_nearest_eligible_school_is_always_shown(): + """Whatever else changes, a section titled "nearby" cannot omit the nearest + school while listing one four times further away.""" + frame = _frame( + _row(100001, "Subject", gender="Boys", religious_denomination="Roman Catholic"), + _row(100002, "Nearest", gender="Mixed", religious_denomination="None", latitude=_at(0.2)), + *[ + _row(100010 + n, f"Match {n}", gender="Boys", + religious_denomination="Roman Catholic", latitude=_at(0.9 + n * 0.1)) + for n in range(6) + ], + ) + assert select_similar(frame, 100001)[0]["urn"] == 100002 + + +def test_caps_at_six_taking_the_nearest(): + frame = _frame( + _row(100001, "Subject"), + *[_row(100010 + n, f"Peer {n}", latitude=_at(0.1 * (n + 1))) for n in range(7)], + ) + result = select_similar(frame, 100001) + assert len(result) == 6 + assert 100016 not in {s["urn"] for s in result}, "the seventh-nearest is the one dropped" + + +def test_fewer_than_two_matches_returns_empty(): + frame = _frame( + _row(100001, "Subject"), + _row(100002, "Only neighbour", latitude=_at(0.5)), + ) + assert select_similar(frame, 100001) == [] def test_excludes_the_subject_school(): @@ -66,19 +125,66 @@ def test_excludes_the_subject_school(): _row(100002, "A", latitude=_at(0.5)), _row(100003, "B", latitude=_at(0.6)), ) - assert 100001 not in {s["urn"] for s in select_similar(frame, 100001, is_secondary=False)} + assert 100001 not in {s["urn"] for s in select_similar(frame, 100001)} +def test_a_school_is_never_listed_twice(): + frame = _frame( + _row(100001, "Subject"), + _row(100002, "A", latitude=_at(0.5)), + _row(100003, "B", latitude=_at(0.6)), + ) + result = select_similar(frame, 100001) + assert len(result) == len({s["urn"] for s in result}) + + +# --------------------------------------------------------------------------- +# Reach: a sanity bound, not a target +# --------------------------------------------------------------------------- + +def test_primary_does_not_reach_past_two_miles(): + frame = _frame( + _row(100001, "Subject"), + _row(100002, "Just inside", latitude=_at(1.9)), + _row(100003, "Just outside", latitude=_at(2.4)), + _row(100004, "Miles away", latitude=_at(4.0)), + ) + # One inside the cap is below the minimum, so nothing renders at all — + # a primary with nothing within two miles has no nearby schools. + assert select_similar(frame, 100001) == [] + + +def test_secondary_reaches_further_than_primary(): + frame = _frame( + _row(100001, "Subject", phase="Secondary"), + _row(100002, "A", phase="Secondary", latitude=_at(3.0)), + _row(100003, "B", phase="Secondary", latitude=_at(5.5)), + ) + assert {s["urn"] for s in select_similar(frame, 100001)} == {100002, 100003} + + +def test_the_cap_follows_the_phase(): + assert radius_miles("Primary") == 2.0 + assert radius_miles("Middle deemed primary") == 2.0 + assert radius_miles("All-through") == 2.0 + assert radius_miles("Secondary") == 6.0 + assert radius_miles("Middle deemed secondary") == 6.0 + # Post-16 is the phase people travel furthest for. + assert radius_miles("16 plus") == 10.0 + + +# --------------------------------------------------------------------------- +# Hard filters: eligibility, never order +# --------------------------------------------------------------------------- + def test_selective_never_meets_non_selective(): frame = _frame( _row(100001, "Grammar", phase="Secondary", admissions_policy="Selective"), _row(100002, "Comp A", phase="Secondary", admissions_policy="Non-selective", latitude=_at(0.5)), _row(100003, "Comp B", phase="Secondary", admissions_policy="Non-selective", latitude=_at(0.6)), ) - assert select_similar(frame, 100001, is_secondary=True) == [] - - reverse = select_similar(frame, 100002, is_secondary=True) - assert 100001 not in {s["urn"] for s in reverse} + assert select_similar(frame, 100001) == [] + assert 100001 not in {s["urn"] for s in select_similar(frame, 100002)} def test_special_schools_match_only_each_other(): @@ -87,8 +193,8 @@ def test_special_schools_match_only_each_other(): _row(100002, "Mainstream A", latitude=_at(0.5)), _row(100003, "Mainstream B", latitude=_at(0.6)), ) - assert select_similar(frame, 100001, is_secondary=False) == [] - assert select_similar(frame, 100002, is_secondary=False) == [] + assert select_similar(frame, 100001) == [] + assert select_similar(frame, 100002) == [] def test_boys_never_meets_girls(): @@ -98,7 +204,7 @@ def test_boys_never_meets_girls(): _row(100003, "Mixed School", gender="Mixed", latitude=_at(0.6)), _row(100004, "Another Mixed", gender="Mixed", latitude=_at(0.7)), ) - urns = {s["urn"] for s in select_similar(frame, 100001, is_secondary=False)} + urns = {s["urn"] for s in select_similar(frame, 100001)} assert 100002 not in urns assert urns == {100003, 100004} @@ -111,80 +217,7 @@ def test_closed_schools_and_missing_coordinates_are_dropped(): _row(100004, "Good A", latitude=_at(0.6)), _row(100005, "Good B", latitude=_at(0.7)), ) - assert {s["urn"] for s in select_similar(frame, 100001, is_secondary=False)} == {100004, 100005} - - -def test_tiers_relax_faith_before_gender(): - frame = _frame( - _row(100001, "Subject", gender="Boys", religious_denomination="Roman Catholic"), - # Tier 1: same gender and same faith. - _row(100002, "Tier one", gender="Boys", religious_denomination="Roman Catholic", latitude=_at(2.0)), - # Tier 2: same gender, different faith — closer, but a weaker match. - _row(100003, "Tier two", gender="Boys", religious_denomination="None", latitude=_at(0.5)), - # Tier 3: mixed gender, different faith. - _row(100004, "Tier three", gender="Mixed", religious_denomination="None", latitude=_at(0.6)), - ) - result = select_similar(frame, 100001, is_secondary=False) - tier_by_urn = {s["urn"]: s["tier"] for s in result} - assert tier_by_urn == {100002: 1, 100003: 2, 100004: 3} - # Selected by tier, displayed by distance. - assert [s["urn"] for s in result] == [100003, 100004, 100002] - - -def test_caps_at_six_taking_the_nearest(): - frame = _frame( - _row(100001, "Subject"), - *[_row(100010 + n, f"Peer {n}", latitude=_at(0.1 * (n + 1))) for n in range(7)], - ) - result = select_similar(frame, 100001, is_secondary=False) - assert len(result) == 6 - # The seventh-nearest is the one dropped, not an arbitrary one. - assert 100016 not in {s["urn"] for s in result} - - -def test_tiers_stop_once_enough_are_found(): - """Four tier-1 matches are a usable set, so tier 2 is never opened — even - though it holds a school that is closer than any of them.""" - frame = _frame( - _row(100001, "Subject", religious_denomination="Roman Catholic"), - _row(100002, "RC one", religious_denomination="Roman Catholic", latitude=_at(0.5)), - _row(100003, "RC two", religious_denomination="Roman Catholic", latitude=_at(0.6)), - _row(100004, "RC three", religious_denomination="Roman Catholic", latitude=_at(0.7)), - _row(100005, "RC four", religious_denomination="Roman Catholic", latitude=_at(0.8)), - # Closer than every one of them, but only a tier-2 match. - _row(100006, "Secular and nearer", religious_denomination="None", latitude=_at(0.2)), - ) - result = select_similar(frame, 100001, is_secondary=False) - assert 100006 not in {s["urn"] for s in result} - assert len(result) == 4 - assert all(s["tier"] == 1 for s in result) - - -def test_a_school_is_never_taken_twice(): - frame = _frame( - _row(100001, "Subject"), - _row(100002, "A", latitude=_at(0.5)), - _row(100003, "B", latitude=_at(0.6)), - ) - result = select_similar(frame, 100001, is_secondary=False) - assert len(result) == len({s["urn"] for s in result}) - - -def test_fewer_than_two_matches_returns_empty(): - frame = _frame( - _row(100001, "Subject"), - _row(100002, "Only neighbour", latitude=_at(0.5)), - ) - assert select_similar(frame, 100001, is_secondary=False) == [] - - -def test_beyond_the_widest_radius_is_not_offered(): - frame = _frame( - _row(100001, "Subject"), - _row(100002, "A", latitude=_at(11.0)), - _row(100003, "B", latitude=_at(12.0)), - ) - assert select_similar(frame, 100001, is_secondary=False) == [] + assert {s["urn"] for s in select_similar(frame, 100001)} == {100004, 100005} def test_all_through_is_offered_on_both_phase_sides(): @@ -193,14 +226,14 @@ def test_all_through_is_offered_on_both_phase_sides(): _row(100002, "All through", phase="All-through", latitude=_at(0.5)), _row(100003, "Primary peer", phase="Primary", latitude=_at(0.6)), ) - assert 100002 in {s["urn"] for s in select_similar(frame, 100001, is_secondary=False)} + assert 100002 in {s["urn"] for s in select_similar(frame, 100001)} secondary = _frame( _row(100010, "Secondary subject", phase="Secondary"), _row(100002, "All through", phase="All-through", latitude=_at(0.5)), _row(100011, "Secondary peer", phase="Secondary", latitude=_at(0.6)), ) - assert 100002 in {s["urn"] for s in select_similar(secondary, 100010, is_secondary=True)} + assert 100002 in {s["urn"] for s in select_similar(secondary, 100010)} def test_sixteen_plus_is_matched_against_secondary_not_primary(): @@ -212,11 +245,10 @@ def test_sixteen_plus_is_matched_against_secondary_not_primary(): _row(100001, "Sixth Form College", phase="16 plus", age_range="16-19"), _row(100002, "Nearby Secondary", phase="Secondary", latitude=_at(0.5), attainment_8_score=52.0), - _row(100003, "Nearby College", phase="16 plus", latitude=_at(0.6), - attainment_8_score=np.nan), + _row(100003, "Nearby College", phase="16 plus", latitude=_at(0.6)), _row(100004, "Nearby Primary", phase="Primary", latitude=_at(0.1)), ) - result = select_similar(frame, 100001, is_secondary=is_secondary_phase("16 plus")) + result = select_similar(frame, 100001) urns = {s["urn"] for s in result} assert 100004 not in urns, "a primary school is not a peer for a sixth form" assert urns == {100002, 100003} @@ -224,18 +256,20 @@ def test_sixteen_plus_is_matched_against_secondary_not_primary(): def test_is_secondary_phase_agrees_with_the_phase_groups_it_selects_from(): - """The two must not drift: whatever this calls secondary decides which - PHASE_GROUPS bucket the candidates come from.""" for phase in ("Secondary", "Middle deemed secondary", "16 plus"): assert is_secondary_phase(phase) is True, phase for phase in ("Primary", "Middle deemed primary", "Nursery", "", None): assert is_secondary_phase(phase) is False, phase # In PHASE_GROUPS an all-through school is on both sides, but it renders - # with the primary template, and the metric follows the template. + # with the primary template, and the metric follows the phase side. assert is_secondary_phase("All-through") is False -def test_chips_state_only_what_the_tier_earned(): +# --------------------------------------------------------------------------- +# What the card reports +# --------------------------------------------------------------------------- + +def test_shared_lists_only_what_is_actually_shared(): frame = _frame( _row(100001, "Subject", phase="Secondary", gender="Mixed", religious_denomination="None", admissions_policy="Non-selective"), @@ -244,28 +278,47 @@ def test_chips_state_only_what_the_tier_earned(): _row(100003, "Faith differs", phase="Secondary", gender="Mixed", religious_denomination="Church of England", admissions_policy="Non-selective", latitude=_at(0.6)), ) - by_urn = {s["urn"]: s for s in select_similar(frame, 100001, is_secondary=True)} + by_urn = {s["urn"]: s for s in select_similar(frame, 100001)} assert by_urn[100002]["shared"] == ["Mixed", "Non-selective", "No religious character"] assert by_urn[100003]["shared"] == ["Mixed", "Non-selective"] -def test_tier_three_chip_is_the_plain_phase(): +def test_a_shared_faith_is_named(): frame = _frame( - _row(100001, "Subject", gender="Boys"), - _row(100002, "A", gender="Mixed", latitude=_at(0.5)), - _row(100003, "B", gender="Mixed", latitude=_at(0.6)), + _row(100001, "Subject", religious_denomination="Roman Catholic"), + _row(100002, "Also RC", religious_denomination="Roman Catholic", latitude=_at(0.4)), + _row(100003, "Secular", religious_denomination="None", latitude=_at(0.5)), ) - result = select_similar(frame, 100001, is_secondary=False) - assert all(s["shared"] == ["Primary school"] for s in result) + by_urn = {s["urn"]: s for s in select_similar(frame, 100001)} + assert "Roman Catholic" in by_urn[100002]["shared"] + assert by_urn[100003]["shared"] == ["Mixed"] -def test_metric_follows_the_template_not_the_neighbour(): +def test_shared_is_empty_when_nothing_is_shared(): + frame = _frame( + _row(100001, "Subject", gender="Boys", religious_denomination="Roman Catholic"), + _row(100002, "A", gender="Mixed", religious_denomination="None", latitude=_at(0.4)), + _row(100003, "B", gender="Mixed", religious_denomination="Church of England", latitude=_at(0.5)), + ) + assert all(s["shared"] == [] for s in select_similar(frame, 100001)) + + +def test_no_tier_is_reported_because_there_are_no_tiers(): + frame = _frame( + _row(100001, "Subject"), + _row(100002, "A", latitude=_at(0.4)), + _row(100003, "B", latitude=_at(0.5)), + ) + assert all("tier" not in s for s in select_similar(frame, 100001)) + + +def test_metric_follows_the_phase_side_not_the_neighbour(): frame = _frame( _row(100001, "Subject", phase="Secondary", attainment_8_score=50.0), _row(100002, "A", phase="Secondary", attainment_8_score=52.8, latitude=_at(0.5)), _row(100003, "B", phase="Secondary", attainment_8_score=np.nan, latitude=_at(0.6)), ) - by_urn = {s["urn"]: s for s in select_similar(frame, 100001, is_secondary=True)} + by_urn = {s["urn"]: s for s in select_similar(frame, 100001)} assert by_urn[100002]["metric_key"] == "attainment_8_score" assert by_urn[100002]["metric_value"] == 52.8 assert by_urn[100002]["metric_year"] == 202425 @@ -278,7 +331,7 @@ def test_values_are_json_safe_native_types(): _row(100002, "A", latitude=_at(0.5)), _row(100003, "B", latitude=_at(0.6)), ) - for school in select_similar(frame, 100001, is_secondary=False): + for school in select_similar(frame, 100001): assert isinstance(school["urn"], int) assert isinstance(school["distance_miles"], float) assert not isinstance(school["metric_value"], np.generic) @@ -310,7 +363,7 @@ def client(monkeypatch): return TestClient(app_module.app, raise_server_exceptions=False) -def test_detail_payload_carries_similar_schools(client): +def test_detail_payload_carries_nearby_schools(client): resp = client.get("/api/schools/100001") assert resp.status_code == 200, resp.text similar = resp.json()["similar_schools"] diff --git a/e2e/tests/journeys.spec.ts b/e2e/tests/journeys.spec.ts index 23ac1bb..4de2c6f 100644 --- a/e2e/tests/journeys.spec.ts +++ b/e2e/tests/journeys.spec.ts @@ -2736,7 +2736,7 @@ test('the content sitemap lists the about page and is advertised in robots', asy }); /** - * Similar schools nearby. + * Other schools nearby. * * The section is absent by design where fewer than two schools qualify, and the * arrows are absent where three cards fit, so this asserts each part of the @@ -2746,12 +2746,12 @@ test('the content sitemap lists the about page and is advertised in robots', asy * which jsdom cannot measure because it has no layout, and the scroll position * surviving a selection, which is DOM state rather than React state. */ -test('similar schools link on to other schools and into compare', async ({ page }) => { +test('nearby schools link on to other schools and into compare', async ({ page }) => { await searchByName(page, 'Primary'); await schoolLinks(page).first().click(); await page.waitForURL(/\/school\//); - const section = page.locator('#similar'); + const section = page.locator('#nearby'); if ((await section.count()) === 0) { test.skip(true, 'No qualifying similar schools for this school'); } @@ -2793,7 +2793,7 @@ test('similar schools link on to other schools and into compare', async ({ page }); /** - * The section at MOBILE.md's three reference widths. + * The nearby-schools section at MOBILE.md's three reference widths. * * MOBILE.md asks for exactly this check and records that it was not written * because "Playwright isn't currently in the project dependency set". That is @@ -2801,13 +2801,13 @@ test('similar schools link on to other schools and into compare', async ({ page * to the page this feature touches. */ for (const width of [360, 390, 430]) { - test(`similar schools survives a ${width}px viewport`, async ({ page }) => { + test(`nearby schools survives a ${width}px viewport`, async ({ page }) => { await page.setViewportSize({ width, height: 800 }); await searchByName(page, 'Primary'); await schoolLinks(page).first().click(); await page.waitForURL(/\/school\//); - const section = page.locator('#similar'); + const section = page.locator('#nearby'); if ((await section.count()) === 0) { test.skip(true, 'No qualifying similar schools for this school'); } diff --git a/nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx b/nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx index 646ad89..3e381b3 100644 --- a/nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx +++ b/nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx @@ -1,8 +1,8 @@ /** - * The section's job is to be honest about what it matched. These tests pin the - * ways it could lie: rendering below the minimum, claiming a similar intake at - * tier 3, showing a missing figure as a number, or hiding a card behind an - * arrow where a crawler cannot reach it. + * The section's job is to be honest about what it is showing. These tests pin + * the ways it could mislead: rendering below the minimum, claiming a likeness + * it does not rank on, showing a missing figure as a number, or hiding a card + * behind an arrow where a crawler cannot reach it. */ import { render, screen } from '@testing-library/react'; @@ -34,7 +34,6 @@ function school(overrides: Partial = {}): SimilarSchool { school_type: 'Community school', age_range: '4-11', shared: ['Mixed', 'No religious character'], - tier: 1, metric_value: 74, metric_key: 'rwm_expected_pct', metric_year: 202425, @@ -74,15 +73,36 @@ describe('render gates', () => { }); }); -describe('the claim the lede makes', () => { - it('claims a similar intake when every card is tier 1 or 2', () => { - renderSection([school({ tier: 1 }), school({ urn: 100003, tier: 2 })]); - expect(screen.getByText(/with a similar intake/i)).toBeInTheDocument(); +describe('what the section claims', () => { + it('never claims a similar intake, because it does not rank on one', () => { + renderSection([school(), school({ urn: 100003, shared: [] })]); + expect(screen.queryByText(/similar intake/i)).not.toBeInTheDocument(); }); - it('drops the claim when any card is tier 3', () => { - renderSection([school({ tier: 1 }), school({ urn: 100003, tier: 3, shared: ['Primary school'] })]); - expect(screen.queryByText(/with a similar intake/i)).not.toBeInTheDocument(); + it('is headed "Other schools nearby", not "similar"', () => { + renderSection([school(), school({ urn: 100003 })]); + expect(screen.getByRole('heading', { name: 'Other schools nearby' })).toBeInTheDocument(); + }); + + it('shows chips for what is shared', () => { + renderSection([school({ shared: ['Mixed', 'Roman Catholic'] }), school({ urn: 100003 })]); + expect(screen.getAllByText('Roman Catholic').length).toBe(1); + }); + + it('shows no chips at all when nothing is shared, rather than inventing one', () => { + const { container } = render( + , + ); + // The card still carries its distance, name, type and figure — just no + // claim of likeness. + expect(container.querySelectorAll('li ul').length).toBe(0); + expect(screen.getAllByText(/miles away/).length).toBe(2); }); }); diff --git a/nextjs-app/__tests__/lib/schoolSections.test.ts b/nextjs-app/__tests__/lib/schoolSections.test.ts index fdd807a..6bff0d3 100644 --- a/nextjs-app/__tests__/lib/schoolSections.test.ts +++ b/nextjs-app/__tests__/lib/schoolSections.test.ts @@ -173,7 +173,7 @@ describe('buildSecondaryNavItems', () => { }); }); -describe('the similar-schools nav item', () => { +describe('the nearby-schools nav item', () => { const navInput = { ofsted: null, admissions: null, admissionDistance: null, hasLocation: true, yearlyDataLength: 1, @@ -182,29 +182,29 @@ describe('the similar-schools nav item', () => { it('appears on both templates when the section renders', () => { const primary = computeSchoolFlags(primaryFixture); const secondary = computeSecondaryFlags(secondaryFixture); - const input = { ...navInput, hasSimilarSchools: true }; + const input = { ...navInput, hasNearbySchools: true }; - expect(buildNavItems(primary, input).map((i) => i.id)).toContain('similar'); - expect(buildSecondaryNavItems(secondary, input).map((i) => i.id)).toContain('similar'); + expect(buildNavItems(primary, input).map((i) => i.id)).toContain('nearby'); + expect(buildSecondaryNavItems(secondary, input).map((i) => i.id)).toContain('nearby'); }); it('is absent when the section does not render', () => { const primary = computeSchoolFlags(primaryFixture); const secondary = computeSecondaryFlags(secondaryFixture); - const input = { ...navInput, hasSimilarSchools: false }; + const input = { ...navInput, hasNearbySchools: false }; - expect(buildNavItems(primary, input).map((i) => i.id)).not.toContain('similar'); - expect(buildSecondaryNavItems(secondary, input).map((i) => i.id)).not.toContain('similar'); + expect(buildNavItems(primary, input).map((i) => i.id)).not.toContain('nearby'); + expect(buildSecondaryNavItems(secondary, input).map((i) => i.id)).not.toContain('nearby'); }); it('is absent when nothing says either way', () => { const primary = computeSchoolFlags(primaryFixture); - expect(buildNavItems(primary, navInput).map((i) => i.id)).not.toContain('similar'); + expect(buildNavItems(primary, navInput).map((i) => i.id)).not.toContain('nearby'); }); it('comes last, because the section renders last', () => { const primary = computeSchoolFlags(primaryFixture); - const ids = buildNavItems(primary, { ...navInput, hasSimilarSchools: true }).map((i) => i.id); - expect(ids[ids.length - 1]).toBe('similar'); + const ids = buildNavItems(primary, { ...navInput, hasNearbySchools: true }).map((i) => i.id); + expect(ids[ids.length - 1]).toBe('nearby'); }); }); diff --git a/nextjs-app/app/(frontend)/school/[slug]/page.tsx b/nextjs-app/app/(frontend)/school/[slug]/page.tsx index 23b98e8..1a2f040 100644 --- a/nextjs-app/app/(frontend)/school/[slug]/page.tsx +++ b/nextjs-app/app/(frontend)/school/[slug]/page.tsx @@ -189,7 +189,7 @@ export default async function SchoolPage({ params }: SchoolPageProps) { admissions: admissions ?? null, admissionDistance: admission_distance ?? null, hasLocation: school_info.latitude != null && school_info.longitude != null, - hasSimilarSchools: shouldRenderSimilar(similarSchools), + hasNearbySchools: shouldRenderSimilar(similarSchools), yearlyDataLength: yearly_data.length, }; const primaryNavItems = buildNavItems(primaryFlags, navInput); diff --git a/nextjs-app/components/school/SimilarSchools.module.css b/nextjs-app/components/school/SimilarSchools.module.css index 2427b7a..82bad54 100644 --- a/nextjs-app/components/school/SimilarSchools.module.css +++ b/nextjs-app/components/school/SimilarSchools.module.css @@ -39,7 +39,6 @@ .shared { display: flex; flex-wrap: wrap; gap: 0.35rem; list-style: none; margin: 0 0 0.85rem; padding: 0; } .chip { font-size: 0.72rem; line-height: 1.4; padding: 0.25rem 0.5rem; border-radius: 999px; background: var(--brand-bg); color: var(--brand); border: 1px solid transparent; } -.chipLoose { font-size: 0.72rem; line-height: 1.4; padding: 0.25rem 0.5rem; border-radius: 999px; background: transparent; color: var(--text-muted); border: 1px solid var(--border); } .metric { margin-top: auto; padding-top: 0.8rem; border-top: 1px solid var(--border); } /* No valence colour here, deliberately: green and terracotta mean "against the diff --git a/nextjs-app/components/school/SimilarSchoolsSection.tsx b/nextjs-app/components/school/SimilarSchoolsSection.tsx index 76db7e1..ec0334e 100644 --- a/nextjs-app/components/school/SimilarSchoolsSection.tsx +++ b/nextjs-app/components/school/SimilarSchoolsSection.tsx @@ -1,12 +1,16 @@ /** - * SimilarSchoolsSection — nearby schools of the same phase and a comparable - * intake. Server component; only the carousel, the compare bar and the - * add-to-compare button are client-side. + * NearbySchoolsSection — the nearest eligible schools, closest first. Server + * component; only the carousel, the compare bar and the add-to-compare button + * are client-side. * - * The section is allowed to say exactly what the backend matched and no more. - * The lede only claims a similar intake when no card came from tier 3, and a - * card's chips list what that school actually shares rather than a match it - * did not earn. + * "Other schools nearby", not "similar" ones: the order is distance and only + * distance. The hard filters upstream still guarantee the set is comparable — + * same phase, same selectivity, mainstream never beside special — but nothing + * here ranks by how alike two schools are, so the heading does not say it does. + * + * The chips report what a school shares, and may be absent entirely. That is + * information for the reader to weigh, not a verdict this section has already + * reached on their behalf. * * There is deliberately no "how these are chosen" panel: the method is already * visible in the lede, the chips and the distances. The single caption line is @@ -78,25 +82,20 @@ export function SimilarSchoolsSection({ // One card matched on phase alone, so the section may not claim the set // shares an intake with this school. - const loosest = Math.max(...schools.map((s) => s.tier)); const metricKey = schools[0].metric_key; const noun = nearbyNoun(phase); return ( -
+
-

- Similar schools nearby +

+ Other schools nearby

-

- {loosest >= 3 - ? `Other ${noun} near ${schoolName}.` - : `Other ${noun} near ${schoolName}, with a similar intake.`} -

+

{`Other ${noun} near ${schoolName}.`}

} > @@ -113,13 +112,13 @@ export function SimilarSchoolsSection({ .filter(Boolean) .join(' · ')}

-
    - {school.shared.map((label) => ( -
  • = 3 ? styles.chipLoose : styles.chip}> - {label} -
    • - ))} -
+ {school.shared.length > 0 && ( +
    + {school.shared.map((label) => ( +
  • {label}
    • + ))} +
+ )}

Date: Tue, 22 Sep 2026 11:59:27 +0100 Subject: [PATCH 2/3] =?UTF-8?q?refactor:=20rename=20similar=20=E2=86=92=20?= =?UTF-8?q?nearby,=20so=20the=20code=20says=20what=20the=20section=20does?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The section ranks on distance and is headed "Other schools nearby", but every identifier still called it "similar" — the exact drift that leaves a later reader trusting a name over the behaviour. Mechanical: files, the module, the payload key, the type, the components, the prop. No behaviour change; the suites are unchanged in count and still green. Free to do now because #150 has not merged, so the payload key rename needs no lockstep deploy. Uses of "similar" that are ordinary English — progress measures compared to similar pupils, and unrelated comments — are untouched. Co-Authored-By: Claude Opus 5 --- backend/app.py | 12 ++-- .../{similar_schools.py => nearby_schools.py} | 2 +- backend/schemas.py | 2 +- ...ilar_schools.py => test_nearby_schools.py} | 58 +++++++++---------- docs/ARCHITECTURE.md | 12 ++-- ...test.tsx => NearbySchoolsSection.test.tsx} | 34 +++++------ .../app/(frontend)/school/[slug]/page.tsx | 10 ++-- .../components/school/AddToCompareButton.tsx | 6 +- ...ls.module.css => NearbySchools.module.css} | 0 ...Carousel.tsx => NearbySchoolsCarousel.tsx} | 4 +- ...areBar.tsx => NearbySchoolsCompareBar.tsx} | 8 +-- ...lsSection.tsx => NearbySchoolsSection.tsx} | 28 ++++----- .../school/PrimarySchoolSections.tsx | 12 ++-- .../school/SecondarySchoolSections.tsx | 12 ++-- nextjs-app/lib/types.ts | 4 +- 15 files changed, 102 insertions(+), 102 deletions(-) rename backend/{similar_schools.py => nearby_schools.py} (99%) rename backend/tests/{test_similar_schools.py => test_nearby_schools.py} (89%) rename nextjs-app/__tests__/components/{SimilarSchoolsSection.test.tsx => NearbySchoolsSection.test.tsx} (87%) rename nextjs-app/components/school/{SimilarSchools.module.css => NearbySchools.module.css} (100%) rename nextjs-app/components/school/{SimilarSchoolsCarousel.tsx => NearbySchoolsCarousel.tsx} (97%) rename nextjs-app/components/school/{SimilarSchoolsCompareBar.tsx => NearbySchoolsCompareBar.tsx} (90%) rename nextjs-app/components/school/{SimilarSchoolsSection.tsx => NearbySchoolsSection.tsx} (88%) diff --git a/backend/app.py b/backend/app.py index e46aff9..9cfb87d 100644 --- a/backend/app.py +++ b/backend/app.py @@ -41,7 +41,7 @@ from .data_loader import get_data_info as get_db_info from . import flags from .places import build_place_index, build_place_registry, places_for_urn from .schemas import METRIC_DEFINITIONS, PHASE_GROUPS, RANKING_COLUMNS, SCHOOL_COLUMNS -from .similar_schools import select_similar +from .nearby_schools import select_nearby from .utils import clean_for_json, convert_to_native # Values to exclude from filter dropdowns (empty strings, non-applicable labels) @@ -266,10 +266,10 @@ def _places_payload(urn: int) -> list[dict]: return payload -def _similar_schools_payload(urn: int) -> list[dict]: +def _nearby_schools_payload(urn: int) -> list[dict]: """The nearest eligible schools this page may offer, closest first. - Phase and reach are read from the school's own row inside select_similar, + Phase and reach are read from the school's own row inside select_nearby, so nothing here can hand it a phase that disagrees with the data. Wrapped: a failure in selection must never 500 a page that is otherwise @@ -277,12 +277,12 @@ def _similar_schools_payload(urn: int) -> list[dict]: section simply does not render. """ try: - return select_similar(load_latest_school_data(), int(urn)) + return select_nearby(load_latest_school_data(), int(urn)) except Exception: import logging logging.getLogger(__name__).exception( - "Similar schools selection failed for urn=%s", urn + "Nearby schools selection failed for urn=%s", urn ) return [] @@ -1000,7 +1000,7 @@ async def get_school_details(request: Request, urn: int): # The nearest eligible schools, closest first. Always present on a # build with this code; the frontend treats absent and empty # identically, which is what lets the two images deploy independently. - "similar_schools": _similar_schools_payload(urn), + "nearby_schools": _nearby_schools_payload(urn), "yearly_data": clean_for_json(school_data), # Supplementary data (null if not yet populated by Kestra) "ofsted": supplementary.get("ofsted"), diff --git a/backend/similar_schools.py b/backend/nearby_schools.py similarity index 99% rename from backend/similar_schools.py rename to backend/nearby_schools.py index 08a5966..c4f22bd 100644 --- a/backend/similar_schools.py +++ b/backend/nearby_schools.py @@ -183,7 +183,7 @@ def _shared(subject: pd.Series, candidate: pd.Series, is_secondary: bool) -> lis return shared -def select_similar(frame: pd.DataFrame, urn: int) -> list[dict]: +def select_nearby(frame: pd.DataFrame, urn: int) -> list[dict]: """The nearest eligible schools, closest first — at most MAX_SCHOOLS, and none at all below MINIMUM. diff --git a/backend/schemas.py b/backend/schemas.py index 8d49c3c..5dbec05 100644 --- a/backend/schemas.py +++ b/backend/schemas.py @@ -536,7 +536,7 @@ RANKING_COLUMNS = [ # include. All-through schools appear in both primary and secondary results, # which is why this is a set per phase rather than a single string comparison. # -# Lives here rather than in app.py because similar_schools.py needs it too, and +# Lives here rather than in app.py because nearby_schools.py needs it too, and # importing app from there would be a cycle. PHASE_GROUPS: dict[str, set[str]] = { "primary": {"primary", "middle deemed primary", "all-through"}, diff --git a/backend/tests/test_similar_schools.py b/backend/tests/test_nearby_schools.py similarity index 89% rename from backend/tests/test_similar_schools.py rename to backend/tests/test_nearby_schools.py index 874ed4b..a096d9b 100644 --- a/backend/tests/test_similar_schools.py +++ b/backend/tests/test_nearby_schools.py @@ -15,10 +15,10 @@ card and never reorders the row. import numpy as np import pandas as pd -from backend.similar_schools import ( +from backend.nearby_schools import ( is_secondary_phase, radius_miles, - select_similar, + select_nearby, ) BASE_LAT, BASE_LON = 51.5000, -0.1000 @@ -66,7 +66,7 @@ def test_returns_nearest_first(): _row(100003, "Near", latitude=_at(0.4)), _row(100004, "Far", latitude=_at(1.8)), ) - result = select_similar(frame, 100001) + result = select_nearby(frame, 100001) assert [s["urn"] for s in result] == [100003, 100002, 100004] assert result[0]["distance_miles"] == 0.4 @@ -81,7 +81,7 @@ def test_a_faith_match_never_outranks_a_closer_school(): _row(100004, "Sacred Heart RC", religious_denomination="Roman Catholic", latitude=_at(1.2)), _row(100005, "St Peter's RC", religious_denomination="Roman Catholic", latitude=_at(1.6)), ) - result = select_similar(frame, 100001) + result = select_nearby(frame, 100001) assert result[0]["urn"] == 100002, "the nearest school leads, whatever its intake" assert [s["distance_miles"] for s in result] == sorted(s["distance_miles"] for s in result) @@ -98,7 +98,7 @@ def test_the_nearest_eligible_school_is_always_shown(): for n in range(6) ], ) - assert select_similar(frame, 100001)[0]["urn"] == 100002 + assert select_nearby(frame, 100001)[0]["urn"] == 100002 def test_caps_at_six_taking_the_nearest(): @@ -106,7 +106,7 @@ def test_caps_at_six_taking_the_nearest(): _row(100001, "Subject"), *[_row(100010 + n, f"Peer {n}", latitude=_at(0.1 * (n + 1))) for n in range(7)], ) - result = select_similar(frame, 100001) + result = select_nearby(frame, 100001) assert len(result) == 6 assert 100016 not in {s["urn"] for s in result}, "the seventh-nearest is the one dropped" @@ -116,7 +116,7 @@ def test_fewer_than_two_matches_returns_empty(): _row(100001, "Subject"), _row(100002, "Only neighbour", latitude=_at(0.5)), ) - assert select_similar(frame, 100001) == [] + assert select_nearby(frame, 100001) == [] def test_excludes_the_subject_school(): @@ -125,7 +125,7 @@ def test_excludes_the_subject_school(): _row(100002, "A", latitude=_at(0.5)), _row(100003, "B", latitude=_at(0.6)), ) - assert 100001 not in {s["urn"] for s in select_similar(frame, 100001)} + assert 100001 not in {s["urn"] for s in select_nearby(frame, 100001)} def test_a_school_is_never_listed_twice(): @@ -134,7 +134,7 @@ def test_a_school_is_never_listed_twice(): _row(100002, "A", latitude=_at(0.5)), _row(100003, "B", latitude=_at(0.6)), ) - result = select_similar(frame, 100001) + result = select_nearby(frame, 100001) assert len(result) == len({s["urn"] for s in result}) @@ -151,7 +151,7 @@ def test_primary_does_not_reach_past_two_miles(): ) # One inside the cap is below the minimum, so nothing renders at all — # a primary with nothing within two miles has no nearby schools. - assert select_similar(frame, 100001) == [] + assert select_nearby(frame, 100001) == [] def test_secondary_reaches_further_than_primary(): @@ -160,7 +160,7 @@ def test_secondary_reaches_further_than_primary(): _row(100002, "A", phase="Secondary", latitude=_at(3.0)), _row(100003, "B", phase="Secondary", latitude=_at(5.5)), ) - assert {s["urn"] for s in select_similar(frame, 100001)} == {100002, 100003} + assert {s["urn"] for s in select_nearby(frame, 100001)} == {100002, 100003} def test_the_cap_follows_the_phase(): @@ -183,8 +183,8 @@ def test_selective_never_meets_non_selective(): _row(100002, "Comp A", phase="Secondary", admissions_policy="Non-selective", latitude=_at(0.5)), _row(100003, "Comp B", phase="Secondary", admissions_policy="Non-selective", latitude=_at(0.6)), ) - assert select_similar(frame, 100001) == [] - assert 100001 not in {s["urn"] for s in select_similar(frame, 100002)} + assert select_nearby(frame, 100001) == [] + assert 100001 not in {s["urn"] for s in select_nearby(frame, 100002)} def test_special_schools_match_only_each_other(): @@ -193,8 +193,8 @@ def test_special_schools_match_only_each_other(): _row(100002, "Mainstream A", latitude=_at(0.5)), _row(100003, "Mainstream B", latitude=_at(0.6)), ) - assert select_similar(frame, 100001) == [] - assert select_similar(frame, 100002) == [] + assert select_nearby(frame, 100001) == [] + assert select_nearby(frame, 100002) == [] def test_boys_never_meets_girls(): @@ -204,7 +204,7 @@ def test_boys_never_meets_girls(): _row(100003, "Mixed School", gender="Mixed", latitude=_at(0.6)), _row(100004, "Another Mixed", gender="Mixed", latitude=_at(0.7)), ) - urns = {s["urn"] for s in select_similar(frame, 100001)} + urns = {s["urn"] for s in select_nearby(frame, 100001)} assert 100002 not in urns assert urns == {100003, 100004} @@ -217,7 +217,7 @@ def test_closed_schools_and_missing_coordinates_are_dropped(): _row(100004, "Good A", latitude=_at(0.6)), _row(100005, "Good B", latitude=_at(0.7)), ) - assert {s["urn"] for s in select_similar(frame, 100001)} == {100004, 100005} + assert {s["urn"] for s in select_nearby(frame, 100001)} == {100004, 100005} def test_all_through_is_offered_on_both_phase_sides(): @@ -226,14 +226,14 @@ def test_all_through_is_offered_on_both_phase_sides(): _row(100002, "All through", phase="All-through", latitude=_at(0.5)), _row(100003, "Primary peer", phase="Primary", latitude=_at(0.6)), ) - assert 100002 in {s["urn"] for s in select_similar(frame, 100001)} + assert 100002 in {s["urn"] for s in select_nearby(frame, 100001)} secondary = _frame( _row(100010, "Secondary subject", phase="Secondary"), _row(100002, "All through", phase="All-through", latitude=_at(0.5)), _row(100011, "Secondary peer", phase="Secondary", latitude=_at(0.6)), ) - assert 100002 in {s["urn"] for s in select_similar(secondary, 100010)} + assert 100002 in {s["urn"] for s in select_nearby(secondary, 100010)} def test_sixteen_plus_is_matched_against_secondary_not_primary(): @@ -248,7 +248,7 @@ def test_sixteen_plus_is_matched_against_secondary_not_primary(): _row(100003, "Nearby College", phase="16 plus", latitude=_at(0.6)), _row(100004, "Nearby Primary", phase="Primary", latitude=_at(0.1)), ) - result = select_similar(frame, 100001) + result = select_nearby(frame, 100001) urns = {s["urn"] for s in result} assert 100004 not in urns, "a primary school is not a peer for a sixth form" assert urns == {100002, 100003} @@ -278,7 +278,7 @@ def test_shared_lists_only_what_is_actually_shared(): _row(100003, "Faith differs", phase="Secondary", gender="Mixed", religious_denomination="Church of England", admissions_policy="Non-selective", latitude=_at(0.6)), ) - by_urn = {s["urn"]: s for s in select_similar(frame, 100001)} + by_urn = {s["urn"]: s for s in select_nearby(frame, 100001)} assert by_urn[100002]["shared"] == ["Mixed", "Non-selective", "No religious character"] assert by_urn[100003]["shared"] == ["Mixed", "Non-selective"] @@ -289,7 +289,7 @@ def test_a_shared_faith_is_named(): _row(100002, "Also RC", religious_denomination="Roman Catholic", latitude=_at(0.4)), _row(100003, "Secular", religious_denomination="None", latitude=_at(0.5)), ) - by_urn = {s["urn"]: s for s in select_similar(frame, 100001)} + by_urn = {s["urn"]: s for s in select_nearby(frame, 100001)} assert "Roman Catholic" in by_urn[100002]["shared"] assert by_urn[100003]["shared"] == ["Mixed"] @@ -300,7 +300,7 @@ def test_shared_is_empty_when_nothing_is_shared(): _row(100002, "A", gender="Mixed", religious_denomination="None", latitude=_at(0.4)), _row(100003, "B", gender="Mixed", religious_denomination="Church of England", latitude=_at(0.5)), ) - assert all(s["shared"] == [] for s in select_similar(frame, 100001)) + assert all(s["shared"] == [] for s in select_nearby(frame, 100001)) def test_no_tier_is_reported_because_there_are_no_tiers(): @@ -309,7 +309,7 @@ def test_no_tier_is_reported_because_there_are_no_tiers(): _row(100002, "A", latitude=_at(0.4)), _row(100003, "B", latitude=_at(0.5)), ) - assert all("tier" not in s for s in select_similar(frame, 100001)) + assert all("tier" not in s for s in select_nearby(frame, 100001)) def test_metric_follows_the_phase_side_not_the_neighbour(): @@ -318,7 +318,7 @@ def test_metric_follows_the_phase_side_not_the_neighbour(): _row(100002, "A", phase="Secondary", attainment_8_score=52.8, latitude=_at(0.5)), _row(100003, "B", phase="Secondary", attainment_8_score=np.nan, latitude=_at(0.6)), ) - by_urn = {s["urn"]: s for s in select_similar(frame, 100001)} + by_urn = {s["urn"]: s for s in select_nearby(frame, 100001)} assert by_urn[100002]["metric_key"] == "attainment_8_score" assert by_urn[100002]["metric_value"] == 52.8 assert by_urn[100002]["metric_year"] == 202425 @@ -331,7 +331,7 @@ def test_values_are_json_safe_native_types(): _row(100002, "A", latitude=_at(0.5)), _row(100003, "B", latitude=_at(0.6)), ) - for school in select_similar(frame, 100001): + for school in select_nearby(frame, 100001): assert isinstance(school["urn"], int) assert isinstance(school["distance_miles"], float) assert not isinstance(school["metric_value"], np.generic) @@ -366,7 +366,7 @@ def client(monkeypatch): def test_detail_payload_carries_nearby_schools(client): resp = client.get("/api/schools/100001") assert resp.status_code == 200, resp.text - similar = resp.json()["similar_schools"] + similar = resp.json()["nearby_schools"] assert [s["school_name"] for s in similar] == ["Neighbour A", "Neighbour B"] assert similar[0]["metric_key"] == "rwm_expected_pct" @@ -377,7 +377,7 @@ def test_a_failure_in_selection_does_not_break_the_page(client, monkeypatch): def _explode(*args, **kwargs): raise ValueError("selection blew up") - monkeypatch.setattr(app_module, "select_similar", _explode) + monkeypatch.setattr(app_module, "select_nearby", _explode) resp = client.get("/api/schools/100001") assert resp.status_code == 200, resp.text - assert resp.json()["similar_schools"] == [] + assert resp.json()["nearby_schools"] == [] diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md index e5ca4cc..6d72959 100644 --- a/docs/ARCHITECTURE.md +++ b/docs/ARCHITECTURE.md @@ -73,12 +73,12 @@ There is no SWR dependency. Leaflet maps are loaded through dynamic wrappers; Chart.js renders performance and comparison charts. `components/school/` contains detail sections, with section decisions and data -preparation in `lib/schoolSections.ts`. The similar-schools section is selected -in `backend/similar_schools.py` — hard filters that never relax (phase, -provision, selectivity, gender) and soft preferences that do (religious -character, then gender exactness) — and served on `/api/schools/{urn}`. Its -rules are presentation logic, deliberately kept out of `marts.*` so they can be -tuned by deploy rather than by pipeline run. `lib/types.ts` contains manually maintained +preparation in `lib/schoolSections.ts`. The nearby-schools section is selected in +`backend/nearby_schools.py` — hard filters decide eligibility (phase, provision, +selectivity, gender) and distance alone decides the order, capped per phase — +and served on `/api/schools/{urn}`. Its rules are presentation logic, +deliberately kept out of `marts.*` so they can be tuned by deploy rather than by +pipeline run. `lib/types.ts` contains manually maintained API types. `payload-types.ts` and the Payload import map are generated artifacts. ## Publication and caching today diff --git a/nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx b/nextjs-app/__tests__/components/NearbySchoolsSection.test.tsx similarity index 87% rename from nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx rename to nextjs-app/__tests__/components/NearbySchoolsSection.test.tsx index 3e381b3..0f042d8 100644 --- a/nextjs-app/__tests__/components/SimilarSchoolsSection.test.tsx +++ b/nextjs-app/__tests__/components/NearbySchoolsSection.test.tsx @@ -9,24 +9,24 @@ import { render, screen } from '@testing-library/react'; import { nearbyNoun, - SimilarSchoolsSection, - shouldRenderSimilar, -} from '@/components/school/SimilarSchoolsSection'; -import type { SimilarSchool } from '@/lib/types'; + NearbySchoolsSection, + shouldRenderNearby, +} from '@/components/school/NearbySchoolsSection'; +import type { NearbySchool } from '@/lib/types'; jest.mock('@/components/school/AddToCompareButton', () => ({ - AddToCompareButton: ({ school }: { school: SimilarSchool }) => ( + AddToCompareButton: ({ school }: { school: NearbySchool }) => ( ), })); -jest.mock('@/components/school/SimilarSchoolsCompareBar', () => ({ - SimilarSchoolsCompareBar: ({ thisUrn }: { thisUrn: number }) => ( +jest.mock('@/components/school/NearbySchoolsCompareBar', () => ({ + NearbySchoolsCompareBar: ({ thisUrn }: { thisUrn: number }) => (

bar for {thisUrn}
), })); -function school(overrides: Partial = {}): SimilarSchool { +function school(overrides: Partial = {}): NearbySchool { return { urn: 100002, school_name: 'Willow Lane Primary School', @@ -41,14 +41,14 @@ function school(overrides: Partial = {}): SimilarSchool { }; } -function renderSection(similar: SimilarSchool[]) { +function renderSection(nearby: NearbySchool[]) { return render( - , ); } @@ -60,11 +60,11 @@ describe('render gates', () => { ['empty', []], ['a single school', [school()]], ])('renders nothing for %s', (_label, value) => { - expect(shouldRenderSimilar(value as SimilarSchool[] | null | undefined)).toBe(false); + expect(shouldRenderNearby(value as NearbySchool[] | null | undefined)).toBe(false); }); it('renders for two or more schools', () => { - expect(shouldRenderSimilar([school(), school({ urn: 100003 })])).toBe(true); + expect(shouldRenderNearby([school(), school({ urn: 100003 })])).toBe(true); }); it('returns null rather than an empty shell below the minimum', () => { @@ -91,12 +91,12 @@ describe('what the section claims', () => { it('shows no chips at all when nothing is shared, rather than inventing one', () => { const { container } = render( - , ); // The card still carries its distance, name, type and figure — just no @@ -124,12 +124,12 @@ describe('what the lede calls the set', () => { it('never calls a sixth form college\'s neighbours primary schools', () => { render( - , ); expect(screen.getByText(/Other schools and colleges near Barnet Sixth Form College/)).toBeInTheDocument(); diff --git a/nextjs-app/app/(frontend)/school/[slug]/page.tsx b/nextjs-app/app/(frontend)/school/[slug]/page.tsx index 1a2f040..838ab67 100644 --- a/nextjs-app/app/(frontend)/school/[slug]/page.tsx +++ b/nextjs-app/app/(frontend)/school/[slug]/page.tsx @@ -8,7 +8,7 @@ import { APIFetchError, fetchSchoolDetails, fetchSchools, fetchNationalAverages import { notFound, redirect } from 'next/navigation'; import { SchoolDetailShell } from '@/components/school/SchoolDetailShell'; import { NearbyPlaces } from '@/components/school/NearbyPlaces'; -import { shouldRenderSimilar } from '@/components/school/SimilarSchoolsSection'; +import { shouldRenderNearby } from '@/components/school/NearbySchoolsSection'; import { schoolBreadcrumbJsonLd, type SchoolPlace } from '@/lib/jsonld'; import { PrimarySchoolSections } from '@/components/school/PrimarySchoolSections'; import { SecondarySchoolSections } from '@/components/school/SecondarySchoolSections'; @@ -157,7 +157,7 @@ export default async function SchoolPage({ params }: SchoolPageProps) { // lockstep deploy of the two images. const places: SchoolPlace[] = data.places ?? []; // Absent on an older API build, exactly like `places` above. - const similarSchools = data.similar_schools ?? []; + const nearbySchools = data.nearby_schools ?? []; // Redirect bare URN to canonical slug URL const canonicalSlug = schoolUrl(urn, school_info.school_name).replace('/school/', ''); @@ -189,7 +189,7 @@ export default async function SchoolPage({ params }: SchoolPageProps) { admissions: admissions ?? null, admissionDistance: admission_distance ?? null, hasLocation: school_info.latitude != null && school_info.longitude != null, - hasNearbySchools: shouldRenderSimilar(similarSchools), + hasNearbySchools: shouldRenderNearby(nearbySchools), yearlyDataLength: yearly_data.length, }; const primaryNavItems = buildNavItems(primaryFlags, navInput); @@ -266,7 +266,7 @@ export default async function SchoolPage({ params }: SchoolPageProps) { finance={finance ?? null} nationalAvg={nationalAvg} destinations={destinations ?? null} - similarSchools={similarSchools} + nearbySchools={nearbySchools} flags={secondaryFlags} /> @@ -289,7 +289,7 @@ export default async function SchoolPage({ params }: SchoolPageProps) { deprivation={deprivation ?? null} finance={finance ?? null} nationalAvg={nationalAvg} - similarSchools={similarSchools} + nearbySchools={nearbySchools} flags={primaryFlags} /> diff --git a/nextjs-app/components/school/AddToCompareButton.tsx b/nextjs-app/components/school/AddToCompareButton.tsx index b263969..dd519ea 100644 --- a/nextjs-app/components/school/AddToCompareButton.tsx +++ b/nextjs-app/components/school/AddToCompareButton.tsx @@ -9,10 +9,10 @@ */ import { useComparisonContext } from '@/context/ComparisonContext'; -import type { School, SimilarSchool } from '@/lib/types'; -import styles from './SimilarSchools.module.css'; +import type { School, NearbySchool } from '@/lib/types'; +import styles from './NearbySchools.module.css'; -export function AddToCompareButton({ school }: { school: SimilarSchool }) { +export function AddToCompareButton({ school }: { school: NearbySchool }) { const { addSchool, removeSchool, selectedSchools } = useComparisonContext(); const selected = selectedSchools.some((s) => s.urn === school.urn); diff --git a/nextjs-app/components/school/SimilarSchools.module.css b/nextjs-app/components/school/NearbySchools.module.css similarity index 100% rename from nextjs-app/components/school/SimilarSchools.module.css rename to nextjs-app/components/school/NearbySchools.module.css diff --git a/nextjs-app/components/school/SimilarSchoolsCarousel.tsx b/nextjs-app/components/school/NearbySchoolsCarousel.tsx similarity index 97% rename from nextjs-app/components/school/SimilarSchoolsCarousel.tsx rename to nextjs-app/components/school/NearbySchoolsCarousel.tsx index 8b748a4..ccc59fd 100644 --- a/nextjs-app/components/school/SimilarSchoolsCarousel.tsx +++ b/nextjs-app/components/school/NearbySchoolsCarousel.tsx @@ -14,7 +14,7 @@ */ import { useCallback, useEffect, useRef, useState, type ReactNode } from 'react'; -import styles from './SimilarSchools.module.css'; +import styles from './NearbySchools.module.css'; /** Three cards fit the row, so fewer than four has nowhere to scroll to. * Below 640px the arrows are not rendered at all — see the stylesheet. */ @@ -31,7 +31,7 @@ const VISIBLE = 3; */ const EDGE = 8; -export function SimilarSchoolsCarousel({ +export function NearbySchoolsCarousel({ count, labelledBy, header, diff --git a/nextjs-app/components/school/SimilarSchoolsCompareBar.tsx b/nextjs-app/components/school/NearbySchoolsCompareBar.tsx similarity index 90% rename from nextjs-app/components/school/SimilarSchoolsCompareBar.tsx rename to nextjs-app/components/school/NearbySchoolsCompareBar.tsx index 8e0050b..ff99478 100644 --- a/nextjs-app/components/school/SimilarSchoolsCompareBar.tsx +++ b/nextjs-app/components/school/NearbySchoolsCompareBar.tsx @@ -11,15 +11,15 @@ import Link from 'next/link'; import { useComparisonContext } from '@/context/ComparisonContext'; -import type { SimilarSchool } from '@/lib/types'; -import styles from './SimilarSchools.module.css'; +import type { NearbySchool } from '@/lib/types'; +import styles from './NearbySchools.module.css'; -export function SimilarSchoolsCompareBar({ +export function NearbySchoolsCompareBar({ thisUrn, candidates, }: { thisUrn: number; - candidates: SimilarSchool[]; + candidates: NearbySchool[]; }) { const { selectedSchools } = useComparisonContext(); diff --git a/nextjs-app/components/school/SimilarSchoolsSection.tsx b/nextjs-app/components/school/NearbySchoolsSection.tsx similarity index 88% rename from nextjs-app/components/school/SimilarSchoolsSection.tsx rename to nextjs-app/components/school/NearbySchoolsSection.tsx index ec0334e..07d4bba 100644 --- a/nextjs-app/components/school/SimilarSchoolsSection.tsx +++ b/nextjs-app/components/school/NearbySchoolsSection.tsx @@ -18,18 +18,18 @@ */ import Link from 'next/link'; -import type { SimilarSchool } from '@/lib/types'; +import type { NearbySchool } from '@/lib/types'; import { schoolUrl } from '@/lib/utils'; import { AddToCompareButton } from './AddToCompareButton'; -import { SimilarSchoolsCarousel } from './SimilarSchoolsCarousel'; -import { SimilarSchoolsCompareBar } from './SimilarSchoolsCompareBar'; +import { NearbySchoolsCarousel } from './NearbySchoolsCarousel'; +import { NearbySchoolsCompareBar } from './NearbySchoolsCompareBar'; import { Section } from './sectionShared'; -import styles from './SimilarSchools.module.css'; +import styles from './NearbySchools.module.css'; const MINIMUM = 2; -export function shouldRenderSimilar(similar?: SimilarSchool[] | null): boolean { - return (similar?.length ?? 0) >= MINIMUM; +export function shouldRenderNearby(nearby?: NearbySchool[] | null): boolean { + return (nearby?.length ?? 0) >= MINIMUM; } /** @@ -63,22 +63,22 @@ function formatMetric(value: number | null, key: string): string { return key === 'attainment_8_score' ? value.toFixed(1) : `${Math.round(value)}%`; } -export function SimilarSchoolsSection({ +export function NearbySchoolsSection({ urn, schoolName, phase, thisMetricValue, - similar, + nearby, }: { urn: number; schoolName: string; /** The school's own GIAS phase, not the template it renders with. */ phase: string | null | undefined; thisMetricValue: number | null; - similar?: SimilarSchool[] | null; + nearby?: NearbySchool[] | null; }) { - if (!shouldRenderSimilar(similar)) return null; - const schools = similar as SimilarSchool[]; + if (!shouldRenderNearby(nearby)) return null; + const schools = nearby as NearbySchool[]; // One card matched on phase alone, so the section may not claim the set // shares an intake with this school. @@ -87,7 +87,7 @@ export function SimilarSchoolsSection({ return (
- ))} - + - + {/* The one caveat the cards cannot make on their own: a reader who takes "0.6 miles away" for the walk has been misled, and nothing else here diff --git a/nextjs-app/components/school/PrimarySchoolSections.tsx b/nextjs-app/components/school/PrimarySchoolSections.tsx index 18bf76c..b7dd319 100644 --- a/nextjs-app/components/school/PrimarySchoolSections.tsx +++ b/nextjs-app/components/school/PrimarySchoolSections.tsx @@ -14,7 +14,7 @@ import type { School, SchoolResult, AbsenceData, OfstedInspection, SchoolCensus, SchoolAdmissions, SchoolAdmissionDistance, SchoolDeprivation, SchoolFinance, NationalAverages, - SimilarSchool, + NearbySchool, } from '@/lib/types'; import { ofstedLegacyAreas } from '@/lib/utils'; import type { SchoolFlags } from '@/lib/schoolSections'; @@ -27,7 +27,7 @@ import { HistorySection } from './HistorySection'; import { SchoolLifeSection } from './SchoolLifeSection'; import { LocalAreaSection } from './LocalAreaSection'; import { FinancesSection } from './FinancesSection'; -import { SimilarSchoolsSection } from './SimilarSchoolsSection'; +import { NearbySchoolsSection } from './NearbySchoolsSection'; export interface PrimarySchoolSectionsProps { schoolInfo: School; @@ -42,14 +42,14 @@ export interface PrimarySchoolSectionsProps { finance: SchoolFinance | null; nationalAvg: NationalAverages | null; /** Nearby schools of a comparable intake. Absent on an older API build. */ - similarSchools?: SimilarSchool[]; + nearbySchools?: NearbySchool[]; flags: SchoolFlags; } export function PrimarySchoolSections({ schoolInfo, yearlyData, absenceData, ofsted, census, admissions, admissionsHistory, admissionDistance, - deprivation, finance, nationalAvg, similarSchools, flags, + deprivation, finance, nationalAvg, nearbySchools, flags, }: PrimarySchoolSectionsProps) { const primaryAvg = nationalAvg?.primary ?? {}; const secondaryAvg = nationalAvg?.secondary ?? {}; @@ -152,12 +152,12 @@ export function PrimarySchoolSections({ {flags.hasFinance && finance && } {/* Last: it is where the reader goes next, not part of this school. */} - ); diff --git a/nextjs-app/components/school/SecondarySchoolSections.tsx b/nextjs-app/components/school/SecondarySchoolSections.tsx index a660e1f..697dfaa 100644 --- a/nextjs-app/components/school/SecondarySchoolSections.tsx +++ b/nextjs-app/components/school/SecondarySchoolSections.tsx @@ -14,7 +14,7 @@ import type { School, SchoolResult, AbsenceData, OfstedInspection, SchoolCensus, SchoolAdmissions, SchoolAdmissionDistance, SchoolDeprivation, SchoolFinance, NationalAverages, - SchoolDestinations, SimilarSchool, + SchoolDestinations, NearbySchool, } from '@/lib/types'; import { ofstedLegacyAreas } from '@/lib/utils'; import type { SecondaryFlags } from '@/lib/schoolSections'; @@ -27,7 +27,7 @@ import { DistanceSection } from './DistanceSection'; import { SecondaryHistorySection } from './SecondaryHistorySection'; import { WellbeingSection } from './WellbeingSection'; import { FinancesSection } from './FinancesSection'; -import { SimilarSchoolsSection } from './SimilarSchoolsSection'; +import { NearbySchoolsSection } from './NearbySchoolsSection'; import styles from './schoolSections.module.css'; export interface SecondarySchoolSectionsProps { @@ -49,14 +49,14 @@ export interface SecondarySchoolSectionsProps { nationalAvg: NationalAverages | null; destinations: SchoolDestinations | null; /** Nearby schools of a comparable intake. Absent on an older API build. */ - similarSchools?: SimilarSchool[]; + nearbySchools?: NearbySchool[]; flags: SecondaryFlags; } export function SecondarySchoolSections({ schoolInfo, yearlyData, ofsted, census, admissions, admissionsHistory, admissionDistance, - deprivation, finance, nationalAvg, destinations, similarSchools, flags, + deprivation, finance, nationalAvg, destinations, nearbySchools, flags, }: SecondarySchoolSectionsProps) { const secondaryAvg = nationalAvg?.secondary ?? {}; @@ -146,12 +146,12 @@ export function SecondarySchoolSections({ )} {/* Last: it is where the reader goes next, not part of this school. */} -
); diff --git a/nextjs-app/lib/types.ts b/nextjs-app/lib/types.ts index 425369a..d2fdc97 100644 --- a/nextjs-app/lib/types.ts +++ b/nextjs-app/lib/types.ts @@ -354,7 +354,7 @@ export interface SchoolsResponse { * version ordered by it and buried the school down the road under faith * matches three times further away. */ -export interface SimilarSchool { +export interface NearbySchool { urn: number; school_name: string; distance_miles: number; @@ -384,7 +384,7 @@ export interface SchoolDetailsResponse { * API that serves this must render without it. Absent and empty mean the * same thing here — no section. */ - similar_schools?: SimilarSchool[]; + nearby_schools?: NearbySchool[]; yearly_data: SchoolResult[]; absence_data: AbsenceData | null; // Supplementary data (null until Kestra populates) -- 2.54.0 From cd1c5d1e1ac041e73d1fd2ce3c8910446d392fcf Mon Sep 17 00:00:00 2001 From: Tudor Date: Tue, 22 Sep 2026 12:00:21 +0100 Subject: [PATCH 3/3] docs: revise the spec to the design that survived staging The spec described the tier system as the design of record. It is gone, so the document was describing something the code deliberately does not do. The revision note and the "why not, having built it the other way first" passage are kept rather than overwritten. The mistake is the instructive part: treating a preference as a constraint inverted the ranking, and the stopping rule added to prevent weak distant matches is what guaranteed six Catholic schools and no community school down the road. A spec that quietly presents the second design as the plan teaches nobody why the first one failed. The mockup link is annotated as one revision behind rather than silently left to look current. Co-Authored-By: Claude Opus 5 --- ...026-09-21-similar-schools-nearby-design.md | 187 ++++++++++-------- 1 file changed, 101 insertions(+), 86 deletions(-) diff --git a/docs/superpowers/specs/2026-09-21-similar-schools-nearby-design.md b/docs/superpowers/specs/2026-09-21-similar-schools-nearby-design.md index 6f87035..2d5f9cd 100644 --- a/docs/superpowers/specs/2026-09-21-similar-schools-nearby-design.md +++ b/docs/superpowers/specs/2026-09-21-similar-schools-nearby-design.md @@ -1,9 +1,16 @@ -# Similar Schools Nearby — Design +# Other Schools Nearby — Design -**Date:** 2026-09-21 -**Status:** awaiting review +**Date:** 2026-09-21, revised 2026-09-22 +**Status:** revised after staging review **Scope:** school detail pages, both phase templates +> **Revision, 2026-09-22.** The first build ranked by intake similarity and used +> distance as a tiebreak. On staging a Catholic primary showed six Catholic +> primaries, none of them close enough to be a real option, and omitted the +> community school down the road. Distance now decides the order and nothing +> else does; the tier system is gone. The reasoning is kept below rather than +> quietly overwritten, because the mistake is the instructive part. + ## Goal Give a school detail page an answer to the question every reader arrives with @@ -15,7 +22,8 @@ school. This section adds that edge — up to six nearby schools of the same pha and a comparable intake, three at a time in a carousel, each a crawlable link and each addable to the comparison basket in one click. -Mockup, with all three tier states live in both themes: +Mockup, in both themes (drawn against the original tiered design, so its ledes +and chip fallbacks are one revision behind the copy specified below): Source of the same page in the repo: `mockups/similar-schools-nearby.html`. @@ -37,19 +45,23 @@ alternative, and there are three ways that claim goes wrong: 3. A **single-sex** school of the opposite sex. Not a weak match — not an option at all. -So the design separates two kinds of rule, and never confuses them: +So the design separates two kinds of fact, and never confuses them: -- **Hard filters** encode the claims above. They are never relaxed, at any - distance, even if that means the section does not render. -- **Soft preferences** describe how closely the intake resembles this school's. - They relax in tiers, and the card's own text always states what survived. +- **Hard filters** encode the claims above. They decide eligibility, and are + never relaxed at any distance, even if that means the section does not render. +- **Shared characteristics** — gender, religious character, selectivity — + describe how closely an intake resembles this school's. They are *reported on + the card and never ranked on*, so the reader weighs them rather than having + them weighed for them. -Everything below follows from that split. +Everything below follows from that split. The revision at the top of this +document is what happens when the second kind is treated as the first. ## Selection algorithm -A backend helper, `_similar_schools_payload(urn)` in `backend/app.py`, modelled -on the existing `_places_payload(urn)` and operating on the cached +A backend helper, `_nearby_schools_payload(urn)` in `backend/app.py`, modelled +on the existing `_places_payload(urn)` and delegating to +`backend/nearby_schools.select_nearby(frame, urn)`, which operates on the cached `load_latest_school_data()` frame — one row per URN, already carrying `latitude`, `longitude`, `phase`, `gender`, `religious_denomination`, `admissions_policy`, `school_type` and `status`. @@ -77,64 +89,63 @@ school the frontend treats as special for benchmarking but the backend treats as mainstream for matching would be dropped from its own England comparison and then offered as a peer to a mainstream school on the next page along. -**Up to six cards, three visible.** Six is a cap, not a quota: the section shows -every school that qualifies at the tiers it used, up to six. Three fit the row, -and the rest are reached with the carousel arrows. Two is the minimum that -renders at all. +**Up to six cards, three visible.** Three fit the row; the rest are reached with +the carousel arrows. Two is the minimum that renders at all. -### Soft preferences, relaxed in tiers +### Order: distance, and nothing else -| Tier | Additionally requires | Radius | -|---|---|---| -| 1 | exact gender equality **and** same religious character | 3 miles | -| 2 | exact gender equality | 5 miles | -| 3 | nothing beyond the hard filters | 10 miles | +The nearest eligible schools, closest first. Similarity does not enter the +ranking at any point. -**Tiers relax to reach a usable set, never to fill the last slots.** +**Why not, having built it the other way first.** The original design ranked by +tiers — same gender and faith within 3 miles, then same gender within 5, then +anything within 10 — and used distance only to order the result. Two things +followed, and both showed up on the first Catholic primary anyone looked at: -Work down the tiers until the schools found so far reach three. Call the tier -that got there T. The section then shows up to six schools drawn from tiers 1 -to T, nearest first — and does not open tier T+1 merely because six slots are -not yet full. +- A faith match at 2.9 miles outranked a community school at 0.3 miles. For a + primary, whose catchment is routinely under a mile, the far school is not a + weaker option; it is not an option. +- Because the row filled from the best tier before widening, three Catholic + schools within 3 miles were enough to fill all six slots with Catholic + schools. The stopping rule that produced this had been added to prevent the + *opposite* failure — padding a row with weak distant matches — and made this + one certain. -Worked through: +The premise was backwards. **Distance is a constraint and intake is a +preference.** A parent cannot act on a school outside their reach however well +it matches, and they are perfectly capable of noticing a shared denomination +for themselves if we show it to them. So similarity moved from the ranking to +the card: `shared` reports what a school genuinely has in common, and the reader +applies their own weighting. -| Qualifying | T | Shown | -|---|---|---| -| 14 at tier 1 | 1 | the 6 nearest tier-1 schools | -| 4 at tier 1 | 1 | all 4 — tier 2 is never opened | -| 2 at tier 1, 7 more at tier 2 | 2 | the 6 nearest of those 9 | -| 2 at tier 1, 1 at tier 2 | 2 | all 3 | -| 2 across all three tiers | 3 | both, since 2 is the minimum | +The hard filters above were always where the defensibility lived. They are +untouched. -Without that stopping rule, a cap of six would reliably drag in tier-3 schools -ten miles away to fill a row that three good matches had already earned. The old -cap of three hid this; six exposes it, which is why the rule is stated rather -than left to the loop. +### Reach: a sanity bound, not a target -**Faith relaxes before gender.** A faith mismatch changes the character of a -school; a gender mismatch can mean the school is not available to the reader's -child at all. Ordering them the other way would fill the section with schools -that cannot be applied to. +| Phase | Reach | +|---|---| +| Primary, middle deemed primary, all-through | 2 miles | +| Secondary, middle deemed secondary | 6 miles | +| 16 plus | 10 miles | -### Two decisions that are easy to get wrong later +Ordering by distance already handles density — a school in inner London fills +all six slots inside a mile and never approaches the cap. The cap decides one +thing: what happens where the area is sparse. It differs by phase because +catchments do, and because people travel furthest for post-16. -**Selected by tier, displayed by distance.** Tier decides *which* three schools -earn a slot. The rendered order is then distance ascending, because "nearby" is -the promise in the heading and a reader scanning the row reads the first card as -the closest. A tier-2 school at 0.4 miles therefore appears above a tier-1 -school at 2.9 miles, and the chips explain the difference in match quality. +**A primary with nothing inside two miles renders no section**, and that is the +intended answer rather than a gap. The alternative is a section headed "nearby" +listing a school four miles from a five-year-old. -**Past the sixth school, the rest are dropped without a count.** In inner -London dozens clear tier 1, and a parent there will notice three is not the -neighbourhood — hence six. Beyond that the section does not try to be the list: -`NearbyPlaces` sits directly beneath and already leads to the place pages, which -are built for browsing a full set and which the school page exists to feed. +**Past the sixth school, the rest are dropped without a count.** The section +does not try to be the list: `NearbyPlaces` sits directly beneath and already +leads to the place pages, which are built for browsing a full set and which the +school page exists to feed. **Fewer than two results renders nothing.** Not an empty state, not a single -lonely card, not padding with schools that failed the hard filters. The section -is absent, the nav item is absent, and the page is unchanged from today. A page -with one weak match is better off without the section than with it. +lonely card. The section is absent, the nav item is absent, and the page is +unchanged from before it existed. ### Distance @@ -157,14 +168,13 @@ reader to assume otherwise. | `distance_miles` | one decimal place | | `school_type` | GIAS type, translated, for the card's meta line | | `age_range` | for the meta line | -| `shared` | the chip strings the tier actually justifies — see below | -| `tier` | 1, 2 or 3 — drives the lede's wording and the chip styling | +| `shared` | what this school genuinely shares with the subject; may be empty | | `metric_value` | the phase-appropriate headline figure, or null | | `metric_key` | `rwm_expected_pct` or `attainment_8_score` — see below | | `metric_year` | the year the figure is from | -The metric follows the phase side the school was *matched* on, not the -neighbour's own phase, so a row of cards never mixes two scales. The secondary +The metric follows the subject school's phase side, not the neighbour's own +phase, so a row of cards never mixes two scales. The secondary side uses `attainment_8_score`; the primary side uses `rwm_expected_pct`. Where the neighbour has no value for that key, the card reads "Not published" rather than falling back to the other key. @@ -183,12 +193,6 @@ correctly — against secondaries. The section therefore takes its lede noun fro the school's own phase rather than from its template, or it would print "Other primary schools near " above a row of secondaries. -`tier` is carried explicitly rather than inferred from the contents of -`shared`, because the frontend needs it for two separate decisions — whether the -lede may claim a similar intake, and whether a chip renders as a brand-tinted -fill or a muted outline — and inferring it from chip count would couple those -decisions to the copy. - Up to six rows of roughly 130 bytes each. It rides in the existing detail payload rather than a new endpoint because the page already makes exactly one server fetch for its data, and `/school/[slug]` regenerates at most weekly @@ -199,9 +203,11 @@ week. frontend treats absent and empty identically, which is what allowed `NearbyPlaces` to ship without a lockstep deploy of the two images. -`shared` is computed on the backend beside the tier that produced it, not -re-derived on the frontend. Deriving it twice is how a card comes to claim a -match the selection did not actually make. +`shared` is computed on the backend, beside the data it is derived from, not +re-derived on the frontend. Deriving it twice is how a card comes to claim +something the selection never established. An empty list is a real answer and +renders no chips: a bare card costs a school nothing but the likeness it does +not have, since the order was already settled by distance. ## Frontend @@ -308,16 +314,21 @@ shows. ## Copy, and what the section is allowed to claim -**The lede tracks the deepest tier shown.** At tiers 1–2 it reads "Other primary -schools near X, with a similar intake." Where any card came from tier 3 it drops -"with a similar intake", because for at least one of the cards that is not what -was matched. Six cards make this more likely to fire than three did, which is -correct: a wider net is exactly when the claim needs dropping. +**The lede never claims an intake.** It reads "Other primary schools near X." — +one sentence, no variants. The earlier version varied the wording by tier, which +only existed to soften a claim the section should not have been making. -**Chips state only what is shared.** A tier-2 card carries fewer chips rather -than a chip it has not earned; a tier-3 card falls back to the plain phase name, -styled as a muted outline rather than a brand-tinted fill so the difference is -visible at a glance. +**The heading is "Other schools nearby", not "Similar schools nearby".** The +hard filters do guarantee a comparable set — same phase, same selectivity, +mainstream never beside special — but nothing ranks on likeness, so the heading +does not say it does. The nav item reads "Nearby schools" and the section id is +`nearby`. + +**Chips state only what is shared, and may be absent entirely.** A card with +nothing in common renders no chip row rather than falling back to a filler. +Since chips no longer affect the order, an empty one costs that school nothing +except a claim it cannot support — and a Catholic parent scanning the row still +spots "Roman Catholic" on the card that carries it, and weighs it themselves. **The neighbour's metric carries no valence colour.** Green and terracotta are reserved site-wide for comparison against the England average. Colouring a @@ -364,9 +375,11 @@ synthetic frame rather than live marts: - a special school returns only special schools; a mainstream school returns none - a Boys school never returns a Girls school; Mixed matches both - closed schools and schools without coordinates are never returned -- tier relaxation fills in order, and a school taken at tier 1 is not repeated -- tiers stop relaxing once three are found: four tier-1 matches never open tier 2 +- results are ordered by distance ascending, always +- a faith match never outranks a closer school (the staging defect, pinned) +- the nearest eligible school is always present - more than six qualifying schools returns the six nearest +- reach is capped per phase, and a primary beyond two miles returns `[]` - an all-through school is offered on both phase sides - a `16 plus` school is matched against secondaries and colleges, never primaries - `is_secondary_phase` and `PHASE_GROUPS` agree on every GIAS phase value @@ -376,7 +389,8 @@ synthetic frame rather than live marts: **Frontend**, in `nextjs-app/__tests__`: - the section renders nothing for absent, empty and single-row inputs -- the lede drops "with a similar intake" when any card is tier 3 +- the lede never claims a similar intake +- an empty `shared` renders no chips rather than a filler - a null metric renders "Not published" - the nav item appears only alongside the section - every card is in the DOM, including the ones scrolled out of view @@ -408,10 +422,11 @@ journeys are confirmed on the post-merge staging run. - Autoplay, dots, or an infinite loop on the carousel. It is a short list a reader scans deliberately, not a banner competing for attention, and a row that moves on its own is a row that moves while someone is reading it. -- Statistical neighbours on deprivation, size or cohort profile. If the tiers - prove too coarse, that is the trigger to move this computation into a dbt mart - — `_similar_schools_payload` is a deliberate seam for exactly that swap. +- Statistical neighbours on deprivation, size or cohort profile. If plain + distance proves too blunt, that is the trigger to move this computation into a + dbt mart — `select_nearby` is a deliberate seam for exactly that swap. - Precomputing neighbours in `marts.*`. Rejected for now: a new mart is inert until Airflow runs, so the feature would ship dark, and every tuning change to - the tiers would become a pipeline round-trip instead of a deploy. + the rules would become a pipeline round-trip instead of a deploy. The revision + at the top of this document is the argument for keeping that loop short. - Any change to `/api/compare`, the compare page, or the comparison basket. -- 2.54.0