feat(tradein): estimator — Cian Valuation as on-demand evaluation source (Stage 9) #476

Merged
lekss361 merged 1 commit from feat/tradein-estimator-cian-clean into main 2026-05-23 14:29:53 +00:00
2 changed files with 285 additions and 1 deletions

View file

@ -39,6 +39,10 @@ from app.services.scrapers.avito_imv import (
evaluate_via_imv,
save_imv_evaluation,
)
from app.services.scrapers.cian_valuation import (
CianValuationResult,
estimate_via_cian_valuation,
)
from app.services.scrapers.yandex_valuation import (
YandexValuationResult,
YandexValuationScraper,
@ -546,6 +550,39 @@ async def estimate_quality(
len(yandex_val.history_items), saved_hist,
)
# ── Stage 9: Cian Valuation as 7th source (on-demand, 24h cached, graceful if no cookies) ──
cian_val: CianValuationResult | None = None
if (
geo is not None
and geo.full_address
and payload.rooms is not None
and payload.area_m2
and payload.floor is not None
and payload.total_floors is not None
):
try:
cian_val = await estimate_via_cian_valuation(
db,
address=geo.full_address,
total_area=payload.area_m2,
rooms_count=payload.rooms,
floor=payload.floor,
total_floors=payload.total_floors,
repair_type="cosmetic",
deal_type="sale",
use_cache=True,
)
if cian_val is not None and cian_val.sale_price_rub:
sources_used_pre = sorted(set(sources_used_pre) | {"cian_valuation"})
logger.info(
"cian_valuation: price=%s accuracy=%s house_id=%s",
cian_val.sale_price_rub,
cian_val.sale_accuracy,
cian_val.external_house_id,
)
except Exception as exc:
logger.warning("cian_valuation: lookup failed (graceful): %s", exc)
# 5. Deals — фактические сделки за период
deals = _fetch_deals(
db, lat=geo.lat, lon=geo.lon, rooms=payload.rooms, area=payload.area_m2,
@ -645,7 +682,7 @@ async def estimate_quality(
logger.warning("imv: failed to link estimate_id to evaluation: %s", e)
logger.info(
"estimate: id=%s addr=%s rooms=%d area=%.1f → median=%d (n=%d, conf=%s)%s",
"estimate: id=%s addr=%s rooms=%d area=%.1f → median=%d (n=%d, conf=%s)%s%s",
estimate_id,
geo.full_address[:60],
payload.rooms,
@ -654,6 +691,7 @@ async def estimate_quality(
n_analogs,
confidence,
f" imv={imv_eval.recommended_price}" if imv_eval else "",
f" cian={cian_val.sale_price_rub}" if cian_val and cian_val.sale_price_rub else "",
)
sources_used = sorted({lot.source for lot in analogs_lots if lot.source})
@ -661,6 +699,8 @@ async def estimate_quality(
sources_used = sorted(set(sources_used) | {"avito_imv"})
if yandex_val is not None:
sources_used = sorted(set(sources_used) | {"yandex_valuation"})
if cian_val is not None and cian_val.sale_price_rub:
sources_used = sorted(set(sources_used) | {"cian_valuation"})
freshness_min = _compute_freshness_minutes(listings_clean)
return AggregatedEstimate(

View file

@ -0,0 +1,244 @@
"""Tests for Cian Valuation integration in estimator.py (Stage 9)."""
import os
# Settings requires DATABASE_URL at init time. Set dummy DSN before any app import.
os.environ.setdefault("DATABASE_URL", "postgresql://test:test@localhost/test_db")
from unittest.mock import AsyncMock, MagicMock, patch
import anyio
from app.services.scrapers.cian_valuation import CianValuationResult
def _fake_cian_result(**kwargs) -> CianValuationResult:
result = CianValuationResult()
result.sale_price_rub = kwargs.get("sale_price_rub", 7_500_000.0)
result.sale_accuracy = kwargs.get("sale_accuracy", 85.0)
result.sale_price_from = kwargs.get("sale_price_from", 7_000_000.0)
result.sale_price_to = kwargs.get("sale_price_to", 8_000_000.0)
result.chart = kwargs.get("chart", [{"month_date": "2026-05-01", "price": 145_000}])
result.chart_change_pct = kwargs.get("chart_change_pct", 1.5)
result.chart_change_direction = kwargs.get("chart_change_direction", "increase")
result.external_house_id = kwargs.get("external_house_id", 12345)
result.is_authenticated = kwargs.get("is_authenticated", True)
return result
# ── Cache-layer unit tests ────────────────────────────────────────────────────
def test_cian_valuation_cache_key_deterministic() -> None:
"""compute_cache_key produces same hash for identical inputs."""
from app.services.scrapers.cian_valuation import compute_cache_key
k1 = compute_cache_key("ЕКБ, ул. Учителей, 18", 38.8, 1, 4, "cosmetic", "sale")
k2 = compute_cache_key("ЕКБ, ул. Учителей, 18", 38.8, 1, 4, "cosmetic", "sale")
assert k1 == k2
assert len(k1) == 64
def test_cian_valuation_cache_key_differs_for_different_inputs() -> None:
from app.services.scrapers.cian_valuation import compute_cache_key
a = compute_cache_key("addr A", 38.8, 1, 4, "cosmetic", "sale")
b = compute_cache_key("addr B", 38.8, 1, 4, "cosmetic", "sale")
c = compute_cache_key("addr A", 50.0, 1, 4, "cosmetic", "sale")
d = compute_cache_key("addr A", 38.8, 2, 4, "cosmetic", "sale")
assert len({a, b, c, d}) == 4
# ── estimate_via_cian_valuation graceful-degradation tests ───────────────────
def test_estimate_via_cian_returns_none_when_no_cookies() -> None:
"""estimate_via_cian_valuation returns None when no cookies in DB (graceful)."""
db = MagicMock()
# cache miss
db.execute.return_value.mappings.return_value.first.return_value = None
async def _run() -> None:
with patch(
"app.services.scrapers.cian_valuation.load_session",
return_value=None, # no cookies stored
):
from app.services.scrapers.cian_valuation import estimate_via_cian_valuation
result = await estimate_via_cian_valuation(
db,
address="ЕКБ, ул. Учителей, 18",
total_area=38.8,
rooms_count=1,
floor=4,
total_floors=16,
use_cache=True,
)
assert result is None
anyio.run(_run)
# ── Estimator integration tests ───────────────────────────────────────────────
def _make_fake_geo():
"""Return GeocodeResult with provider field (not source)."""
from app.services.geocoder import GeocodeResult
return GeocodeResult(
lat=56.838,
lon=60.595,
full_address="Свердловская обл., Екатеринбург, ул. Учителей, 18",
provider="nominatim",
)
def _make_payload():
from app.schemas.trade_in import TradeInEstimateInput
return TradeInEstimateInput(
address="ЕКБ, ул. Учителей, 18",
area_m2=38.8,
rooms=1,
floor=4,
total_floors=16,
)
def _common_patches(cian_mock):
"""Return list of context managers for all sources except cian_valuation."""
return [
patch("app.services.estimator.geocode", new=AsyncMock(return_value=_make_fake_geo())),
patch("app.services.estimator.get_house_metadata", new=AsyncMock(return_value=None)),
patch("app.services.estimator._fetch_analogs", return_value=([], False)),
patch("app.services.estimator._fetch_deals", return_value=[]),
patch(
"app.services.estimator._get_or_fetch_imv_cached",
new=AsyncMock(return_value=None),
),
patch(
"app.services.estimator._get_or_fetch_yandex_valuation_cached",
new=AsyncMock(return_value=None),
),
patch(
"app.services.estimator.estimate_via_cian_valuation",
new=cian_mock,
),
]
def test_estimator_includes_cian_valuation_when_available() -> None:
"""When cian_valuation returns result with sale_price_rub, sources_used includes it."""
from app.services.estimator import estimate_quality
db = MagicMock()
payload = _make_payload()
fake_cian = _fake_cian_result()
cian_mock = AsyncMock(return_value=fake_cian)
async def _run() -> None:
with (
patch("app.services.estimator.geocode",
new=AsyncMock(return_value=_make_fake_geo())),
patch("app.services.estimator.get_house_metadata",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._fetch_analogs", return_value=([], False)),
patch("app.services.estimator._fetch_deals", return_value=[]),
patch("app.services.estimator._get_or_fetch_imv_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._get_or_fetch_yandex_valuation_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator.estimate_via_cian_valuation",
new=cian_mock),
):
result = await estimate_quality(payload, db)
assert "cian_valuation" in result.sources_used
anyio.run(_run)
def test_estimator_graceful_when_cian_returns_none() -> None:
"""When estimate_via_cian_valuation returns None (no cookies), estimator continues."""
from app.services.estimator import estimate_quality
db = MagicMock()
payload = _make_payload()
cian_mock = AsyncMock(return_value=None)
async def _run() -> None:
with (
patch("app.services.estimator.geocode",
new=AsyncMock(return_value=_make_fake_geo())),
patch("app.services.estimator.get_house_metadata",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._fetch_analogs", return_value=([], False)),
patch("app.services.estimator._fetch_deals", return_value=[]),
patch("app.services.estimator._get_or_fetch_imv_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._get_or_fetch_yandex_valuation_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator.estimate_via_cian_valuation",
new=cian_mock),
):
result = await estimate_quality(payload, db)
assert "cian_valuation" not in result.sources_used
assert result.estimate_id is not None # estimator still returned a result
anyio.run(_run)
def test_estimator_graceful_when_cian_raises() -> None:
"""When estimate_via_cian_valuation raises, estimator logs warning and continues."""
from app.services.estimator import estimate_quality
db = MagicMock()
payload = _make_payload()
cian_mock = AsyncMock(side_effect=RuntimeError("network timeout"))
async def _run() -> None:
with (
patch("app.services.estimator.geocode",
new=AsyncMock(return_value=_make_fake_geo())),
patch("app.services.estimator.get_house_metadata",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._fetch_analogs", return_value=([], False)),
patch("app.services.estimator._fetch_deals", return_value=[]),
patch("app.services.estimator._get_or_fetch_imv_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._get_or_fetch_yandex_valuation_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator.estimate_via_cian_valuation",
new=cian_mock),
):
result = await estimate_quality(payload, db)
assert "cian_valuation" not in result.sources_used
assert result.estimate_id is not None
anyio.run(_run)
def test_estimator_cian_result_no_sale_price_not_added() -> None:
"""When cian_valuation returns result with sale_price_rub=None, not added to sources."""
from app.services.estimator import estimate_quality
db = MagicMock()
payload = _make_payload()
# Result returned but no sale price (e.g. partial parse)
fake_cian_no_price = _fake_cian_result(sale_price_rub=None)
cian_mock = AsyncMock(return_value=fake_cian_no_price)
async def _run() -> None:
with (
patch("app.services.estimator.geocode",
new=AsyncMock(return_value=_make_fake_geo())),
patch("app.services.estimator.get_house_metadata",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._fetch_analogs", return_value=([], False)),
patch("app.services.estimator._fetch_deals", return_value=[]),
patch("app.services.estimator._get_or_fetch_imv_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator._get_or_fetch_yandex_valuation_cached",
new=AsyncMock(return_value=None)),
patch("app.services.estimator.estimate_via_cian_valuation",
new=cian_mock),
):
result = await estimate_quality(payload, db)
assert "cian_valuation" not in result.sources_used
anyio.run(_run)