Model/scripts/reclassify_party_ceiling_roofs.py

"""One-time re-classification of party-ceiling roof overrides mis-read as roofs.

#1376: a landlord roof description that is a **party-ceiling** marker ("another /
same dwelling or premises above") was occasionally classified by the LLM to an
external ``Pitched, N mm loft insulation`` value when it carried a trailing depth —
inventing roof heat loss where a party ceiling has ~0 (RdSAP 10 Table 18: "There
is no heat loss through the roof of a building part that has the same dwelling or
another dwelling above"). ~106 ``property_overrides`` rows (party-ceiling markers
on any non-party-ceiling value), inconsistent with the ~13k of the same family
already resolving to the party-ceiling member.

The live classifier now applies ``roof_party_ceiling_guard`` deterministically
(so new intakes are correct); this fixes the rows written before it. The **same
guard** decides the correction here, so the backfill and the live path cannot
drift.

Updates the TEXT ``property_overrides.override_value`` (what the modelling reads —
the actual fix) and the ``landlord_roof_type_overrides.value`` classifier cache.
The party-ceiling members already exist in the roof pgEnum (13k rows store them),
so no FE migration is needed.

DRY-RUN BY DEFAULT: prints the row count it would change and writes nothing. Pass
``--apply`` to execute inside a transaction. Idempotent — only rows whose stored
value differs from the guard's member are touched, so a second run is a no-op.
"""

from __future__ import annotations

import argparse
from collections.abc import Iterable

from sqlalchemy import Connection, text

from domain.epc.property_overrides.roof_party_ceiling_guard import (
    roof_party_ceiling_guard,
)
from scripts.e2e_common import build_engine, load_env


def party_ceiling_corrections(
    stored: Iterable[tuple[str, str]],
) -> dict[str, str]:
    """``(description, stored override_value)`` → the corrected value, for the
    descriptions the party-ceiling guard resolves whose stored value is not already
    the guard's member. Descriptions the guard leaves to the LLM (``None``) and
    rows already on the right member are omitted — so the result is exactly the set
    to fix, and re-running against corrected data yields an empty map (idempotent).
    """
    corrections: dict[str, str] = {}
    for description, value in stored:
        member = roof_party_ceiling_guard(description)
        if member is not None and value != member.value:
            corrections[description] = member.value
    return corrections


_DISTINCT = text(
    """
    SELECT DISTINCT lower(original_spreadsheet_description) AS description,
                    override_value AS value
    FROM property_overrides
    WHERE override_component = 'roof_type'
    """
)
_OVERRIDES_UPDATE = text(
    """
    UPDATE property_overrides
       SET override_value = :new_value
     WHERE override_component = 'roof_type'
       AND lower(original_spreadsheet_description) = :description
       AND override_value <> :new_value
    """
)
_CACHE_UPDATE = text(
    """
    UPDATE landlord_roof_type_overrides
       SET value = :new_value, updated_at = now()
     WHERE lower(description) = :description
       AND value::text <> :new_value
    """
)
_OVERRIDES_COUNT = text(
    """
    SELECT count(*) FROM property_overrides
     WHERE override_component = 'roof_type'
       AND lower(original_spreadsheet_description) = :description
       AND override_value <> :new_value
    """
)


def reclassify(conn: Connection, *, apply: bool) -> int:
    """NULL-free re-map: set every mis-classified party-ceiling roof override to the
    guard's member. Returns the number of ``property_overrides`` rows found (that
    ``--apply`` would / did correct)."""
    stored = [(r.description, r.value) for r in conn.execute(_DISTINCT)]
    total = 0
    for description, new_value in party_ceiling_corrections(stored).items():
        params = {"description": description, "new_value": new_value}
        total += conn.execute(_OVERRIDES_COUNT, params).scalar() or 0
        if apply:
            conn.execute(_OVERRIDES_UPDATE, params)
            conn.execute(_CACHE_UPDATE, params)
    return total


def main() -> None:
    load_env()
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        "--apply",
        action="store_true",
        help="execute the updates (default: dry-run, writes nothing)",
    )
    args = parser.parse_args()

    engine = build_engine()
    with engine.begin() as conn:
        conn.execute(text("SET statement_timeout = 120000"))
        total = reclassify(conn, apply=args.apply)

    verb = "re-classified" if args.apply else "would re-classify"
    print(
        f"{verb} {total} party-ceiling roof override row(s) from an external "
        "roof value to the party-ceiling member."
    )
    if not args.apply:
        print("\nDRY-RUN — nothing written. Re-run with --apply to execute.")


if __name__ == "__main__":
    main()