Model/tests/scripts/test_null_predicted_lodged_performance.py
Khalim Conn-Kowlessar 7e06aa63c6 Backfill the phantom Lodged Performance on predicted Properties to NULL 🟩
One-time script (dry-run default, --apply in a transaction, idempotent) that
NULLs the four lodged_* columns on every predicted-source baseline row — a
predicted EPC exists and no lodged one does — leaving Effective, the bill block,
and rebaseline_reason intact. Dry-run against the audited DB reports 12,236 rows.
Must run after the FE-owned Drizzle ALTER ... DROP NOT NULL lands.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 22:17:57 +00:00

120 lines
4 KiB
Python

"""The one-time backfill nulls a predicted Property's phantom Lodged Performance,
leaves a lodged Property's intact, and is idempotent (#1361 Class B)."""
from __future__ import annotations
import json
from pathlib import Path
from typing import Any
from sqlalchemy import Engine
from sqlmodel import Session
from datatypes.epc.domain.epc import Epc
from datatypes.epc.domain.epc_property_data import EpcPropertyData
from datatypes.epc.domain.mapper import EpcPropertyDataMapper
from domain.property_baseline.performance import Performance
from domain.property_baseline.property_baseline_performance import (
PropertyBaselinePerformance,
)
from repositories.epc.epc_postgres_repository import EpcPostgresRepository
from repositories.property_baseline.property_baseline_postgres_repository import (
PropertyBaselinePostgresRepository,
)
from scripts.null_predicted_lodged_performance import backfill
_JSON_SAMPLES = Path(__file__).resolve().parents[2] / "backend/epc_api/json_samples"
_PHANTOM_LODGED = Performance(
sap_score=14, epc_band=Epc.G, co2_emissions=5.0, primary_energy_intensity=400
)
_EFFECTIVE = Performance(
sap_score=57, epc_band=Epc.D, co2_emissions=1.5, primary_energy_intensity=160
)
def _epc() -> EpcPropertyData:
raw: dict[str, Any] = json.loads(
(_JSON_SAMPLES / "RdSAP-Schema-21.0.0" / "epc.json").read_text()
)
return EpcPropertyDataMapper.from_api_response(raw)
def _baseline(lodged: Performance) -> PropertyBaselinePerformance:
return PropertyBaselinePerformance(
lodged=lodged,
effective=_EFFECTIVE,
rebaseline_reason="physical_state_changed",
space_heating_kwh=4200.0,
water_heating_kwh=1600.0,
)
def _seed(db_engine: Engine) -> None:
"""A predicted Property (id 1, predicted EPC only, phantom lodged) and a
lodged Property (id 2, lodged EPC, real lodged) — both with a baseline row
carrying a populated lodged half (the pre-fix state)."""
epc = _epc()
with Session(db_engine) as session:
epc_repo = EpcPostgresRepository(session)
epc_repo.save(epc, property_id=1, source="predicted")
epc_repo.save(epc, property_id=2, source="lodged")
baseline_repo = PropertyBaselinePostgresRepository(session)
baseline_repo.save(_baseline(_PHANTOM_LODGED), property_id=1)
baseline_repo.save(_baseline(_PHANTOM_LODGED), property_id=2)
session.commit()
def test_apply_nulls_only_the_predicted_propertys_lodged_half(
db_engine: Engine,
) -> None:
# Arrange
_seed(db_engine)
# Act
with db_engine.begin() as conn:
found = backfill(conn, apply=True)
# Assert — one phantom found and nulled; the predicted Property loses its
# lodged half but keeps its Effective half, while the lodged Property is
# untouched.
assert found == 1
with Session(db_engine) as session:
repo = PropertyBaselinePostgresRepository(session)
predicted = repo.get_for_property(1)
lodged = repo.get_for_property(2)
assert predicted is not None
assert predicted.lodged is None
assert predicted.effective == _EFFECTIVE
assert lodged is not None
assert lodged.lodged == _PHANTOM_LODGED
def test_dry_run_reports_the_phantom_but_writes_nothing(db_engine: Engine) -> None:
# Arrange
_seed(db_engine)
# Act
with db_engine.begin() as conn:
found = backfill(conn, apply=False)
# Assert — the phantom is counted, but the row is left untouched.
assert found == 1
with Session(db_engine) as session:
predicted = PropertyBaselinePostgresRepository(session).get_for_property(1)
assert predicted is not None
assert predicted.lodged == _PHANTOM_LODGED
def test_re_running_apply_is_a_no_op(db_engine: Engine) -> None:
# Arrange — the first apply nulls the phantom.
_seed(db_engine)
with db_engine.begin() as conn:
backfill(conn, apply=True)
# Act — a second apply finds nothing left to null.
with db_engine.begin() as conn:
found = backfill(conn, apply=True)
# Assert
assert found == 0