Model/scripts/reclassify_water_heating.py

"""One-time re-classification of water-heating overrides funnelled into house coal.

#1376 / ADR-0043: with no biomass / wood / dual-fuel / biodiesel water fuel in the
taxonomy, the LLM classified those DHW descriptions (and the "no system / electric
immersion assumed" case) to ``"From main system, house coal"`` (fuel 33). On an
individual-main dwelling that scores hot water at ~14x the carbon of biomass; on a
community-main dwelling the score is already right but the stored value lies.

The live classifier now applies ``water_heating_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 immediate fix) unconditionally. The ``landlord_water_heating_overrides.value``
classifier cache is a ``water_heating`` **pgEnum**; the four new archetypes are
FE-owned values, so their cache writes are **deferred** until the Drizzle migration
adds them (the Class-A/B pattern). ``Electric immersion, electricity`` and
``From main system, house coal`` are existing enum members and update the cache.

DRY-RUN BY DEFAULT: prints the counts it would change and writes nothing. Pass
``--apply`` to execute inside a transaction. Idempotent — only rows whose stored
value differs from the target member are touched.
"""

from __future__ import annotations

import argparse
from collections.abc import Iterable

from sqlalchemy import Connection, text

from domain.epc.property_overrides.water_heating_guard import water_heating_guard
from scripts.e2e_common import build_engine, load_env


def water_heating_corrections(
    stored: Iterable[tuple[str, str]],
) -> dict[str, str]:
    """``(description, stored override_value)`` → the faithful archetype value, for
    the descriptions the water-heating guard resolves whose stored value differs.
    Descriptions the guard defers (mains gas, electricity, …), genuine house-coal
    rows, and rows already on the target are omitted, so re-running against
    corrected data is a no-op."""
    corrections: dict[str, str] = {}
    for description, value in stored:
        member = water_heating_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 = 'water_heating'
    """
)
_OVERRIDES_UPDATE = text(
    """
    UPDATE property_overrides
       SET override_value = :new_value
     WHERE override_component = 'water_heating'
       AND lower(original_spreadsheet_description) = :description
       AND override_value <> :new_value
    """
)
_OVERRIDES_COUNT = text(
    """
    SELECT count(*) FROM property_overrides
     WHERE override_component = 'water_heating'
       AND lower(original_spreadsheet_description) = :description
       AND override_value <> :new_value
    """
)
_CACHE_UPDATE = text(
    """
    UPDATE landlord_water_heating_overrides
       SET value = :new_value, updated_at = now()
     WHERE lower(description) = :description
       AND value::text <> :new_value
    """
)
_ENUM_VALUES = text(
    "SELECT e.enumlabel FROM pg_enum e JOIN pg_type t ON t.oid = e.enumtypid "
    "WHERE t.typname = 'water_heating'"
)


def reclassify(conn: Connection, *, apply: bool) -> tuple[int, set[str]]:
    """Re-map house-coal water-heating overrides onto their faithful archetypes.
    Returns the number of ``property_overrides`` rows found and the set of target
    values the live ``water_heating`` pgEnum does not yet carry (cache-deferred
    until the FE migration)."""
    stored = [(r.description, r.value) for r in conn.execute(_DISTINCT)]
    enum_values = {r[0] for r in conn.execute(_ENUM_VALUES)}
    total = 0
    deferred: set[str] = set()
    for description, new_value in water_heating_corrections(stored).items():
        params = {"description": description, "new_value": new_value}
        total += conn.execute(_OVERRIDES_COUNT, params).scalar() or 0
        in_enum = new_value in enum_values
        if not in_enum:
            deferred.add(new_value)
        if apply:
            conn.execute(_OVERRIDES_UPDATE, params)
            if in_enum:
                conn.execute(_CACHE_UPDATE, params)
    return total, deferred


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, deferred = reclassify(conn, apply=args.apply)

    verb = "re-classified" if args.apply else "would re-classify"
    print(
        f"{verb} {total} water-heating override row(s) off the house-coal dumping "
        "ground onto faithful biomass / wood / dual-fuel / biodiesel / immersion "
        "archetypes (property_overrides / TEXT — what the modelling reads)."
    )
    if deferred:
        print(
            f"\n{len(deferred)} target value(s) NOT yet in the water_heating "
            "pgEnum — their classifier-cache rows are deferred until the FE-repo "
            "enum migration adds these members (property_overrides was still "
            "updated, which is what the modelling reads):"
        )
        for value in sorted(deferred):
            print(f"    {value!r}")
    if not args.apply:
        print("\nDRY-RUN — nothing written. Re-run with --apply to execute.")


if __name__ == "__main__":
    main()