DOM.РФ API classifies euro-format flats (26-50м²) as rooms=2. _SUPPLY_BATCH_SQL now maps: rooms=2 + area<35 → 'euro-1' rooms=2 + area<50 → 'euro-2' before the generic rooms IN (1,2,3) branch. Audit: 4 140 units rooms=2 + area<35 in domrf_kn_flats were inflating the supply count for genuine 2-room apartments (median 57м²). euro buckets have no velocity counterpart in objective_corpus_room_month so they are filtered out of top_layouts by min_velocity. Also extends RoomBucket Literal and room_bucket_from_flat() in layout_signature.py with the new euro-1/euro-2 values. Closes #271 item 8
66 lines
2 KiB
Python
66 lines
2 KiB
Python
"""Layout signature extraction для Issue #113 (Phase 2.1 minimal).
|
|
|
|
Без `layout_type` / `balcony_count` — ждут B2B Объектив (#52).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Literal
|
|
|
|
RoomBucket = Literal["studio", "euro-1", "euro-2", "1", "2", "3", "4+"]
|
|
AreaBin = Literal["<25", "25-40", "40-60", "60-80", "80-100", "100+"]
|
|
|
|
|
|
def room_bucket_from_flat(
|
|
rooms: int | None,
|
|
flat_type: str | None,
|
|
is_studio: bool | None,
|
|
total_area: float | None = None,
|
|
) -> RoomBucket:
|
|
"""Determine room_bucket из kn_flats полей.
|
|
|
|
Priority:
|
|
1. is_studio=True OR flat_type='Квартира-студия' → "studio"
|
|
2. rooms=0 (без is_studio) → "studio"
|
|
3. Fix SF-08: rooms=2 + area<35 → "euro-1" (DOM.РФ маркирует малогабаритные как 2-комн)
|
|
4. Fix SF-08: rooms=2 + area<50 → "euro-2" (евро-двушки 35-50м²)
|
|
5. rooms IN (1, 2, 3) → str(rooms)
|
|
6. rooms >= 4 → "4+"
|
|
7. fallback на "1" (rooms is None и не studio)
|
|
"""
|
|
if is_studio is True or flat_type == "Квартира-студия":
|
|
return "studio"
|
|
if rooms is None:
|
|
return "1"
|
|
if rooms == 0:
|
|
return "studio"
|
|
if rooms == 2 and total_area is not None:
|
|
if total_area < 35.0:
|
|
return "euro-1"
|
|
if total_area < 50.0:
|
|
return "euro-2"
|
|
if rooms >= 4:
|
|
return "4+"
|
|
if rooms in (1, 2, 3):
|
|
return str(rooms) # type: ignore[return-value]
|
|
return "1"
|
|
|
|
|
|
def area_bin(area_m2: float) -> AreaBin:
|
|
"""Bucket площади per ARN-buckets (НСПД)."""
|
|
if area_m2 < 25.0:
|
|
return "<25"
|
|
if area_m2 < 40.0:
|
|
return "25-40"
|
|
if area_m2 < 60.0:
|
|
return "40-60"
|
|
if area_m2 < 80.0:
|
|
return "60-80"
|
|
if area_m2 < 100.0:
|
|
return "80-100"
|
|
return "100+"
|
|
|
|
|
|
def layout_signature(room_bucket_val: RoomBucket, area_bin_val: AreaBin) -> str:
|
|
"""Deterministic string-signature для группировки."""
|
|
return f"{room_bucket_val}__{area_bin_val}"
|