mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
Addresses PR #1402 review: the guard only claimed dominant-single, leaving the symmetric bug open — the LLM can flatten a dominant-double/triple split onto its minority single (e.g. "96% Double glazing 2002 or later, 4% Single"). A dominant double/triple whose era is explicit ("pre-2002" / "2002 or later") is just as fully determined as era-free single, so the guard now claims it via _DOMINANT_MEMBER. Only a genuinely ambiguous era ("unknown age", unstated) still defers to the LLM — the "96% double -> None" contract now holds solely for the era-unknown case, not the era-stated one. Backfill script reuses the same guard, so it now corrects any dominant split; renamed reclassify_dominant_single_glazing.py -> reclassify_dominant_glazing.py to match. Tests cover double/triple x pre-2002/2002-or-later and the still- deferred unknown-age case; 14 green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
125 lines
4.7 KiB
Python
125 lines
4.7 KiB
Python
"""Backfill glazing overrides where a dominant (>= 90%) split was flattened onto
|
|
its *minority* type.
|
|
|
|
Sibling to ``scripts/reclassify_mixed_glazing.py``. That script rescued genuine
|
|
mixes (no type >= 90%) to ``MIXED``; it deliberately left near-uniform rows to the
|
|
LLM classifier. But for a dominant split the LLM sometimes latched onto the
|
|
minority type — a dominant-*single* dwelling ("4% Double glazing 2002 or later,
|
|
96% Single Glazing") written as "Double glazing…", or the symmetric dominant-double
|
|
case written as "Single glazing". ``glazing_mix_guard`` now resolves any
|
|
era-unambiguous dominant split deterministically — SINGLE (era-free), or a
|
|
double/triple whose era is stated — so this backfill fixes the rows written before
|
|
that guard change.
|
|
|
|
Uses the SAME guard as the live path, so the backfill and the classifier cannot
|
|
drift. SCOPED TO ONE PORTFOLIO (``--portfolio``, default 796 = Hyde) and only
|
|
touches ``property_overrides.override_value`` (TEXT — what the modelling reads);
|
|
the global ``landlord_glazing_overrides`` classifier cache is left alone.
|
|
|
|
DRY-RUN BY DEFAULT: prints what it would change and writes nothing. Pass
|
|
``--apply`` to execute inside a transaction; it also writes an audit CSV of every
|
|
row changed (property_id, uprn, old value, new value) so the change is reversible.
|
|
Idempotent — only rows whose stored value differs from the guard's target member
|
|
are touched.
|
|
|
|
python -m scripts.lisasrequest.reclassify_dominant_glazing # dry run
|
|
python -m scripts.lisasrequest.reclassify_dominant_glazing --apply # write
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import csv
|
|
import sys
|
|
from collections import Counter
|
|
from pathlib import Path
|
|
|
|
from sqlalchemy import text
|
|
|
|
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
sys.path.insert(0, str(_REPO_ROOT))
|
|
|
|
from domain.epc.property_overrides.glazing_mix_guard import glazing_mix_guard # noqa: E402
|
|
from scripts.e2e_common import ENV_PATH, build_engine, load_env # noqa: E402
|
|
|
|
_SELECT = text(
|
|
"""
|
|
SELECT po.property_id, pr.uprn,
|
|
po.original_spreadsheet_description AS description,
|
|
po.override_value AS value
|
|
FROM property_overrides po
|
|
JOIN property pr ON pr.id = po.property_id
|
|
WHERE po.portfolio_id = :portfolio
|
|
AND po.override_component = 'glazing'
|
|
"""
|
|
)
|
|
_UPDATE = text(
|
|
"""
|
|
UPDATE property_overrides
|
|
SET override_value = :new_value
|
|
WHERE portfolio_id = :portfolio
|
|
AND override_component = 'glazing'
|
|
AND property_id = :property_id
|
|
AND override_value <> :new_value
|
|
"""
|
|
)
|
|
|
|
|
|
def main() -> int:
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument("--portfolio", type=int, default=796)
|
|
parser.add_argument(
|
|
"--apply",
|
|
action="store_true",
|
|
help="execute the updates (default: dry-run, writes nothing)",
|
|
)
|
|
args = parser.parse_args()
|
|
|
|
load_env(ENV_PATH)
|
|
engine = build_engine()
|
|
|
|
audit: list[tuple[int, object, str, str, str]] = [] # pid, uprn, descr, old, new
|
|
tally: Counter[str] = Counter()
|
|
with engine.begin() as conn:
|
|
conn.execute(text("SET statement_timeout = 120000"))
|
|
for property_id, uprn, description, value in conn.execute(
|
|
_SELECT, {"portfolio": args.portfolio}
|
|
):
|
|
member = glazing_mix_guard(description or "")
|
|
if member is None or value == member.value:
|
|
continue
|
|
tally[f"{value!r} -> {member.value!r}"] += 1
|
|
audit.append((property_id, uprn, description, value, member.value))
|
|
if args.apply:
|
|
conn.execute(
|
|
_UPDATE,
|
|
{
|
|
"portfolio": args.portfolio,
|
|
"property_id": property_id,
|
|
"new_value": member.value,
|
|
},
|
|
)
|
|
if not args.apply:
|
|
conn.rollback()
|
|
|
|
verb = "re-classified" if args.apply else "would re-classify"
|
|
print(f"portfolio {args.portfolio}: {verb} {len(audit)} glazing override row(s)")
|
|
for change, n in tally.most_common():
|
|
print(f" {n:5d} {change}")
|
|
|
|
if args.apply and audit:
|
|
out = _REPO_ROOT / "scripts" / "lisasrequest" / (
|
|
f"reclassify_dominant_glazing_{args.portfolio}_audit.csv"
|
|
)
|
|
with out.open("w", newline="") as fh:
|
|
w = csv.writer(fh)
|
|
w.writerow(["property_id", "uprn", "description", "old_value", "new_value"])
|
|
w.writerows(audit)
|
|
print(f"\naudit trail: {out}")
|
|
if not args.apply:
|
|
print("\nDRY-RUN — nothing written. Re-run with --apply to execute.")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|