TudorandClaude Opus 5
b650df8d93
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 <noreply@anthropic.com>
384 lines
15 KiB
Python
384 lines
15 KiB
Python
"""Selection rules for the nearby-schools section.
|
|
|
|
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 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.nearby_schools import (
|
|
is_secondary_phase,
|
|
radius_miles,
|
|
select_nearby,
|
|
)
|
|
|
|
BASE_LAT, BASE_LON = 51.5000, -0.1000
|
|
|
|
|
|
def _row(urn, name, **overrides):
|
|
base = {
|
|
"urn": urn,
|
|
"school_name": name,
|
|
"local_authority": "Testshire",
|
|
"school_type": "Community school",
|
|
"phase": "Primary",
|
|
"age_range": "4-11",
|
|
"status": "Open",
|
|
"gender": "Mixed",
|
|
"religious_denomination": "None",
|
|
"admissions_policy": "Not applicable",
|
|
"latitude": BASE_LAT,
|
|
"longitude": BASE_LON,
|
|
"year": 202425,
|
|
"rwm_expected_pct": 70.0,
|
|
"attainment_8_score": np.nan,
|
|
}
|
|
base.update(overrides)
|
|
return base
|
|
|
|
|
|
def _frame(*rows):
|
|
return pd.DataFrame(list(rows))
|
|
|
|
|
|
def _at(miles):
|
|
"""A latitude `miles` north of BASE_LAT."""
|
|
return BASE_LAT + miles / 69.0
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Order: distance, and only distance
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_returns_nearest_first():
|
|
frame = _frame(
|
|
_row(100001, "Subject"),
|
|
_row(100002, "Mid", latitude=_at(1.0)),
|
|
_row(100003, "Near", latitude=_at(0.4)),
|
|
_row(100004, "Far", latitude=_at(1.8)),
|
|
)
|
|
result = select_nearby(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_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)
|
|
|
|
|
|
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_nearby(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_nearby(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_nearby(frame, 100001) == []
|
|
|
|
|
|
def test_excludes_the_subject_school():
|
|
frame = _frame(
|
|
_row(100001, "Subject"),
|
|
_row(100002, "A", latitude=_at(0.5)),
|
|
_row(100003, "B", latitude=_at(0.6)),
|
|
)
|
|
assert 100001 not in {s["urn"] for s in select_nearby(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_nearby(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_nearby(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_nearby(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_nearby(frame, 100001) == []
|
|
assert 100001 not in {s["urn"] for s in select_nearby(frame, 100002)}
|
|
|
|
|
|
def test_special_schools_match_only_each_other():
|
|
frame = _frame(
|
|
_row(100001, "Special", school_type="Community special school"),
|
|
_row(100002, "Mainstream A", latitude=_at(0.5)),
|
|
_row(100003, "Mainstream B", latitude=_at(0.6)),
|
|
)
|
|
assert select_nearby(frame, 100001) == []
|
|
assert select_nearby(frame, 100002) == []
|
|
|
|
|
|
def test_boys_never_meets_girls():
|
|
frame = _frame(
|
|
_row(100001, "Boys School", gender="Boys"),
|
|
_row(100002, "Girls School", gender="Girls", latitude=_at(0.5)),
|
|
_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_nearby(frame, 100001)}
|
|
assert 100002 not in urns
|
|
assert urns == {100003, 100004}
|
|
|
|
|
|
def test_closed_schools_and_missing_coordinates_are_dropped():
|
|
frame = _frame(
|
|
_row(100001, "Subject"),
|
|
_row(100002, "Closed", status="Closed", latitude=_at(0.5)),
|
|
_row(100003, "No coords", latitude=np.nan, longitude=np.nan),
|
|
_row(100004, "Good A", latitude=_at(0.6)),
|
|
_row(100005, "Good B", latitude=_at(0.7)),
|
|
)
|
|
assert {s["urn"] for s in select_nearby(frame, 100001)} == {100004, 100005}
|
|
|
|
|
|
def test_all_through_is_offered_on_both_phase_sides():
|
|
frame = _frame(
|
|
_row(100001, "Primary subject", phase="Primary"),
|
|
_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_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_nearby(secondary, 100010)}
|
|
|
|
|
|
def test_sixteen_plus_is_matched_against_secondary_not_primary():
|
|
"""GIAS phase 6 is "16 plus", and PHASE_GROUPS puts it in the secondary
|
|
group — a sixth-form college's peers are secondaries and other colleges,
|
|
never primary schools. A substring test for "secondary" misses it silently:
|
|
no crash, just a page offering infant schools to a sixth form."""
|
|
frame = _frame(
|
|
_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)),
|
|
_row(100004, "Nearby Primary", phase="Primary", latitude=_at(0.1)),
|
|
)
|
|
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}
|
|
assert all(s["metric_key"] == "attainment_8_score" for s in result)
|
|
|
|
|
|
def test_is_secondary_phase_agrees_with_the_phase_groups_it_selects_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 phase side.
|
|
assert is_secondary_phase("All-through") is False
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 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"),
|
|
_row(100002, "Full match", phase="Secondary", gender="Mixed",
|
|
religious_denomination="None", admissions_policy="Non-selective", latitude=_at(0.5)),
|
|
_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_nearby(frame, 100001)}
|
|
assert by_urn[100002]["shared"] == ["Mixed", "Non-selective", "No religious character"]
|
|
assert by_urn[100003]["shared"] == ["Mixed", "Non-selective"]
|
|
|
|
|
|
def test_a_shared_faith_is_named():
|
|
frame = _frame(
|
|
_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)),
|
|
)
|
|
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"]
|
|
|
|
|
|
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_nearby(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_nearby(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_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
|
|
assert by_urn[100003]["metric_value"] is None
|
|
|
|
|
|
def test_values_are_json_safe_native_types():
|
|
frame = _frame(
|
|
_row(100001, "Subject"),
|
|
_row(100002, "A", latitude=_at(0.5)),
|
|
_row(100003, "B", latitude=_at(0.6)),
|
|
)
|
|
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)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# The endpoint
|
|
# ---------------------------------------------------------------------------
|
|
|
|
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
|
|
def _endpoint_frame():
|
|
return _frame(
|
|
_row(100001, "Subject Primary"),
|
|
_row(100002, "Neighbour A", latitude=_at(0.5)),
|
|
_row(100003, "Neighbour B", latitude=_at(0.6)),
|
|
)
|
|
|
|
|
|
@pytest.fixture()
|
|
def client(monkeypatch):
|
|
from backend import app as app_module
|
|
|
|
monkeypatch.setattr(app_module, "load_latest_school_data", _endpoint_frame)
|
|
monkeypatch.setattr(app_module, "load_school_data", _endpoint_frame)
|
|
monkeypatch.setattr(app_module, "get_supplementary_data", lambda db, urn: {})
|
|
return TestClient(app_module.app, raise_server_exceptions=False)
|
|
|
|
|
|
def test_detail_payload_carries_nearby_schools(client):
|
|
resp = client.get("/api/schools/100001")
|
|
assert resp.status_code == 200, resp.text
|
|
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"
|
|
|
|
|
|
def test_a_failure_in_selection_does_not_break_the_page(client, monkeypatch):
|
|
from backend import app as app_module
|
|
|
|
def _explode(*args, **kwargs):
|
|
raise ValueError("selection blew up")
|
|
|
|
monkeypatch.setattr(app_module, "select_nearby", _explode)
|
|
resp = client.get("/api/schools/100001")
|
|
assert resp.status_code == 200, resp.text
|
|
assert resp.json()["nearby_schools"] == []
|