Model/tests/domain/epc_prediction/test_comparable_properties.py

"""Behaviour of Comparable Properties selection (ADR-0029): given a prediction
target's known inputs and the raw postcode cohort, choose + weight the
comparables EPC Prediction will synthesise from. Filter-then-relax ladder:
hard filters on identity (property type, built form) + known overrides while
enough remain, weighted by recency × similarity. Pure domain logic.
"""

from datetime import date
from typing import Optional, Union

from datatypes.epc.domain.epc_property_data import EpcPropertyData, SapBuildingPart
from domain.epc_prediction.comparable_properties import (
    Comparable,
    ComparableProperties,
    PredictionTarget,
    select_comparables,
)


def _comparable(
    *,
    property_type: str,
    certificate_number: str,
    built_form: str = "1",
    wall_construction: Optional[Union[int, str]] = None,
    address: Optional[str] = None,
    registration_date: Optional[date] = None,
) -> Comparable:
    """A Comparable carrying only the fields under test (opaque EpcPropertyData
    with property_type / built_form / main wall set — the partial-instance idiom)."""
    epc: EpcPropertyData = object.__new__(EpcPropertyData)
    epc.property_type = property_type
    epc.built_form = built_form
    main: SapBuildingPart = object.__new__(SapBuildingPart)
    if wall_construction is not None:
        main.wall_construction = wall_construction
    epc.sap_building_parts = [main]
    return Comparable(
        epc=epc,
        certificate_number=certificate_number,
        address=address,
        registration_date=registration_date,
    )


def test_selects_only_candidates_of_the_same_property_type() -> None:
    # Arrange — a target house (property_type "2"); cohort of 2 houses + 1 flat.
    target = PredictionTarget(postcode="LS6 1AA", property_type="2")
    candidates = [
        _comparable(property_type="2", certificate_number="A"),
        _comparable(property_type="2", certificate_number="B"),
        _comparable(property_type="1", certificate_number="C"),
    ]

    # Act
    result: ComparableProperties = select_comparables(target, candidates)

    # Assert — the flat is excluded; the two houses remain.
    assert {c.certificate_number for c in result.members} == {"A", "B"}


def test_dedupes_re_lodgements_to_the_latest_cert_per_address() -> None:
    # Arrange — a register cohort with one address (FLAT 3) lodged three times.
    # Comparables are one-per-real-neighbour, so a re-lodged address must not
    # count three times towards the mode; the latest cert is its current state.
    target = PredictionTarget(postcode="LS6 1AA", property_type="2")
    candidates = [
        _comparable(
            property_type="2",
            certificate_number="OLD",
            address="FLAT 3",
            registration_date=date(2020, 4, 6),
        ),
        _comparable(
            property_type="2",
            certificate_number="MID",
            address="FLAT 3",
            registration_date=date(2021, 2, 1),
        ),
        _comparable(
            property_type="2",
            certificate_number="NEW",
            address="FLAT 3",
            registration_date=date(2025, 1, 20),
        ),
        _comparable(
            property_type="2",
            certificate_number="OTHER",
            address="FLAT 5",
            registration_date=date(2024, 9, 27),
        ),
    ]

    # Act
    result: ComparableProperties = select_comparables(target, candidates)

    # Assert — FLAT 3 collapses to its latest cert; FLAT 5 is untouched.
    assert {c.certificate_number for c in result.members} == {"NEW", "OTHER"}


def test_filters_to_the_known_built_form_when_enough_remain() -> None:
    # Arrange — a mid-terrace target (built_form "4"); cohort of 5 mid-terraces
    # + 2 detached, all houses. The built form is known and leaves ≥ k, so it is
    # applied as a hard filter.
    target = PredictionTarget(
        postcode="LS6 1AA", property_type="2", built_form="4"
    )
    candidates = [
        _comparable(property_type="2", built_form="4", certificate_number=f"T{i}")
        for i in range(5)
    ] + [
        _comparable(property_type="2", built_form="1", certificate_number=f"D{i}")
        for i in range(2)
    ]

    # Act
    result: ComparableProperties = select_comparables(
        target, candidates, minimum_cohort=5
    )

    # Assert — only the five mid-terraces survive.
    assert {c.certificate_number for c in result.members} == {
        "T0", "T1", "T2", "T3", "T4"
    }


def test_known_wall_override_emphasises_matching_comparables() -> None:
    # Arrange — a mixed street: 5 solid-brick (code 2) + 3 cavity (code 1) houses.
    # We KNOW the target is solid brick (a Landlord Override), and the filter
    # leaves ≥ k, so cavity neighbours are dropped (the border-property case).
    target = PredictionTarget(
        postcode="LS6 1AA", property_type="2", wall_construction=2
    )
    candidates = [
        _comparable(property_type="2", wall_construction=2, certificate_number=f"S{i}")
        for i in range(5)
    ] + [
        _comparable(property_type="2", wall_construction=1, certificate_number=f"C{i}")
        for i in range(3)
    ]

    # Act
    result: ComparableProperties = select_comparables(
        target, candidates, minimum_cohort=5
    )

    # Assert — only the solid-brick comparables remain.
    assert {c.certificate_number for c in result.members} == {
        "S0", "S1", "S2", "S3", "S4"
    }


def test_known_wall_override_relaxes_when_too_few_match() -> None:
    # Arrange — only 2 solid-brick but 6 cavity houses; the override would leave
    # 2 (< k=5), so it relaxes to keep the full type cohort (graceful degradation).
    target = PredictionTarget(
        postcode="LS6 1AA", property_type="2", wall_construction=2
    )
    candidates = [
        _comparable(property_type="2", wall_construction=2, certificate_number=f"S{i}")
        for i in range(2)
    ] + [
        _comparable(property_type="2", wall_construction=1, certificate_number=f"C{i}")
        for i in range(6)
    ]

    # Act
    result: ComparableProperties = select_comparables(
        target, candidates, minimum_cohort=5
    )

    # Assert — relaxed: all eight houses retained.
    assert len(result.members) == 8