feat(parcels): layout signature schemas + extractor (#113 PR A) (#193)

backend/app/schemas/parcel.py

@@ -1,3 +1,4 @@
+import datetime as dt
 from typing import Any, Literal
 
 from pydantic import BaseModel, Field
@@ -132,3 +133,83 @@ class CompetitorsSummary(BaseModel):
 class CompetitorsResponse(BaseModel):
     competitors: list[Competitor]
     summary: CompetitorsSummary
+
+
+# ── Layout analysis (Issue #113) ───────────────────────────────────────────
+
+
+class LayoutSignature(BaseModel):
+    """Минимальная сигнатура планировки = (room_bucket, area_bin).
+
+    Phase 2.1: layout_type/balcony_count в БД нет, ждут B2B Объектив (#52).
+    """
+
+    room_bucket: Literal["studio", "1", "2", "3", "4+"]
+    area_bin: Literal["<25", "25-40", "40-60", "60-80", "80-100", "100+"]
+
+
+class BestLayoutsRequest(BaseModel):
+    """Параметры запроса top-планировок в радиусе вокруг участка."""
+
+    radius_km: float = Field(default=1.0, ge=0.1, le=1.5)
+    time_window: Literal["last_month", "last_quarter", "last_year"] = "last_quarter"
+    filter_competitor_obj_ids: list[int] | None = None
+    exclude_competitor_obj_ids: list[int] = Field(default_factory=list)
+    min_velocity_per_month: float = Field(default=0.5, ge=0.0, le=100.0)
+    obj_class_filter: Literal["economy", "comfort", "business"] | None = None
+    target_total_flats: int | None = Field(default=None, ge=1, le=10000)
+
+
+class TopLayoutRow(BaseModel):
+    """Одна строка top-planirovok ranking'а."""
+
+    rank: int
+    room_bucket: str
+    area_bin: str
+    signature: str
+    competitor_obj_ids: list[int]
+    competitor_count: int
+    total_sold_in_window: int
+    velocity_per_month: float
+    avg_price_per_m2_rub: float | None  # NULL если objective не покрывает obj
+    avg_area_m2: float
+    supply_units_in_radius: int
+    sold_pct_of_supply: float | None  # NULL если supply=0
+
+
+class LayoutTzMixRow(BaseModel):
+    """Строка рекомендации unit-mix для ТЗ."""
+
+    room_bucket: str
+    pct: int  # 0..100, sum total = 100
+    abs_units: int | None  # NULL если target_total_flats не задан
+    avg_target_area_m2: float | None
+
+
+class LayoutTzRecommendation(BaseModel):
+    """Рекомендация для ТЗ на проектирование."""
+
+    rationale_text: str
+    mix: list[LayoutTzMixRow]
+    weighted_avg_price_per_m2_rub: float | None
+    based_on_obj_count: int
+    based_on_total_deals: int
+    data_window_start: dt.date
+    data_window_end: dt.date
+
+
+class LayoutDataQuality(BaseModel):
+    """Метаданные качества данных (coverage)."""
+
+    objects_with_velocity_data: int
+    objects_total_in_radius: int
+    velocity_coverage_pct: float
+    confidence: Literal["high", "medium", "low"]
+
+
+class BestLayoutsResponse(BaseModel):
+    """Ответ /best-layouts endpoint'а."""
+
+    top_layouts: list[TopLayoutRow]
+    recommendation_for_tz: LayoutTzRecommendation
+    data_quality: LayoutDataQuality

backend/app/services/site_finder/layout_signature.py

@@ -0,0 +1,58 @@
+"""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", "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,
+) -> RoomBucket:
+    """Determine room_bucket из kn_flats полей.
+
+    Priority:
+    1. is_studio=True OR flat_type='Квартира-студия' → "studio"
+    2. rooms IN (1, 2, 3) → str(rooms)
+    3. rooms >= 4 → "4+"
+    4. rooms = 0 (без is_studio) → "studio"
+    5. 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 >= 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}"

backend/tests/test_layout_signature.py

@@ -0,0 +1,97 @@
+"""Тесты для layout_signature helpers (Issue #113, Phase 2.1).
+
+Pure-Python, без БД и external calls.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from app.services.site_finder.layout_signature import (
+    area_bin,
+    layout_signature,
+    room_bucket_from_flat,
+)
+
+
+@pytest.mark.parametrize(
+    "rooms, flat_type, is_studio, expected",
+    [
+        (None, None, True, "studio"),
+        (0, "Квартира-студия", False, "studio"),
+        (0, "Квартира", None, "studio"),
+        (1, "Квартира", None, "1"),
+        (2, "Квартира", None, "2"),
+        (3, "Квартира", False, "3"),
+        (4, "Квартира", False, "4+"),
+        (5, "Квартира", None, "4+"),
+        (None, "Квартира", None, "1"),  # fallback
+    ],
+)
+def test_room_bucket(
+    rooms: int | None, flat_type: str | None, is_studio: bool | None, expected: str
+) -> None:
+    assert room_bucket_from_flat(rooms, flat_type, is_studio) == expected
+
+
+@pytest.mark.parametrize(
+    "area, expected",
+    [
+        (0.5, "<25"),
+        (24.9, "<25"),
+        (25.0, "25-40"),
+        (39.99, "25-40"),
+        (40.0, "40-60"),
+        (59.99, "40-60"),
+        (60.0, "60-80"),
+        (79.99, "60-80"),
+        (80.0, "80-100"),
+        (99.99, "80-100"),
+        (100.0, "100+"),
+        (250.0, "100+"),
+    ],
+)
+def test_area_bin(area: float, expected: str) -> None:
+    assert area_bin(area) == expected
+
+
+def test_layout_signature_deterministic() -> None:
+    assert layout_signature("studio", "<25") == "studio__<25"
+    assert layout_signature("4+", "100+") == "4+__100+"
+    # Same input → same output
+    sig1 = layout_signature("2", "40-60")
+    sig2 = layout_signature("2", "40-60")
+    assert sig1 == sig2
+
+
+def test_room_bucket_is_studio_overrides_rooms() -> None:
+    """is_studio=True beats any rooms value."""
+    assert room_bucket_from_flat(3, "Квартира", True) == "studio"
+
+
+def test_room_bucket_flat_type_studio_overrides_rooms() -> None:
+    """flat_type='Квартира-студия' beats rooms=2."""
+    assert room_bucket_from_flat(2, "Квартира-студия", None) == "studio"
+
+
+def test_room_bucket_large_rooms() -> None:
+    """rooms=10 → '4+'."""
+    assert room_bucket_from_flat(10, "Квартира", False) == "4+"
+
+
+def test_area_bin_boundary_exact() -> None:
+    """Граничные значения попадают в правильный бакет (включение левой границы)."""
+    assert area_bin(25.0) == "25-40"
+    assert area_bin(40.0) == "40-60"
+    assert area_bin(60.0) == "60-80"
+    assert area_bin(80.0) == "80-100"
+    assert area_bin(100.0) == "100+"
+
+
+def test_layout_signature_format() -> None:
+    """Сигнатура всегда содержит двойное подчёркивание-разделитель."""
+    sig = layout_signature("1", "25-40")
+    assert "__" in sig
+    parts = sig.split("__")
+    assert parts[0] == "1"
+    assert parts[1] == "25-40"