feat(tradein/backtest): full-spine prediction via _price_from_inputs + range-coverage/calibration/segment metrics (#1966)

tradein-mvp/backend/tests/test_backtest_estimator.py

@@ -217,9 +217,8 @@ def _rows_for_bucket(
 def test_derive_ratios_per_bucket_exact() -> None:
     # Each bucket ≥ MIN_BUCKET deals so every bucket gets its OWN ratio.
     # bucket 1: sold/ask = 80k/100k = 0.80 ; bucket 2: 150k/200k = 0.75.
-    rows = (
+    rows = _rows_for_bucket(1, n=bt.MIN_BUCKET, ask=100_000.0, sold=80_000.0) + _rows_for_bucket(
-        _rows_for_bucket(1, n=bt.MIN_BUCKET, ask=100_000.0, sold=80_000.0)
+        2, n=bt.MIN_BUCKET, ask=200_000.0, sold=150_000.0
-        + _rows_for_bucket(2, n=bt.MIN_BUCKET, ask=200_000.0, sold=150_000.0)
     )
     ratios, meta = bt._derive_room_ratios(rows)
     assert ratios[1] == pytest.approx(0.80)
@@ -328,9 +327,7 @@ def test_corrected_metrics_cancel_plus_30_pct_bias_to_zero() -> None:
     # in-sample and re-applying it MUST collapse the corrected bias to ~0.
     rows: list[tuple[float, float, int]] = []
     for bucket, sold in ((0, 80_000.0), (1, 100_000.0), (2, 150_000.0)):
-        rows += _rows_for_bucket(
+        rows += _rows_for_bucket(bucket, n=bt.MIN_BUCKET, ask=1.30 * sold, sold=sold)
-            bucket, n=bt.MIN_BUCKET, ask=1.30 * sold, sold=sold
-        )
 
     # sanity: the ASKING block really is +30%.
     asking = bt._compute_metrics(rows)
@@ -346,9 +343,7 @@ def test_corrected_metrics_cancel_plus_30_pct_bias_to_zero() -> None:
     assert corrected["overall"]["median_bias_pct"] == pytest.approx(0.0, abs=1e-6)
     assert corrected["overall"]["mape_pct"] == pytest.approx(0.0, abs=1e-6)
     for bucket in (0, 1, 2):
-        assert corrected["per_rooms"][bucket]["median_bias_pct"] == pytest.approx(
+        assert corrected["per_rooms"][bucket]["median_bias_pct"] == pytest.approx(0.0, abs=1e-6)
-            0.0, abs=1e-6
-        )
 
 
 def test_corrected_metrics_global_fallback_cancels_uniform_bias() -> None:
@@ -469,8 +464,18 @@ def test_argparse_defaults() -> None:
 
 def test_argparse_overrides() -> None:
     ns = bt._parse_args(
-        ["--sample", "50", "--since", "2024-01-01", "--radius", "2000",
+        [
-         "--rooms-tolerance", "1", "--holdout-split", "--json"]
+            "--sample",
+            "50",
+            "--since",
+            "2024-01-01",
+            "--radius",
+            "2000",
+            "--rooms-tolerance",
+            "1",
+            "--holdout-split",
+            "--json",
+        ]
     )
     assert ns.sample == 50
     assert ns.since == "2024-01-01"
@@ -478,3 +483,328 @@ def test_argparse_overrides() -> None:
     assert ns.rooms_tolerance == 1
     assert ns.holdout_split is True
     assert ns.json is True
+
+
+# --------------------------------------------------------------------------- #
+# #1966 full spine — --engine flag.
+# --------------------------------------------------------------------------- #
+
+
+def test_argparse_engine_defaults_to_full() -> None:
+    assert bt._parse_args([]).engine == "full"
+
+
+def test_argparse_engine_asking_core_override() -> None:
+    assert bt._parse_args(["--engine", "asking-core"]).engine == "asking-core"
+    assert bt._parse_args(["--engine", "full"]).engine == "full"
+
+
+def test_argparse_engine_rejects_unknown() -> None:
+    with pytest.raises(SystemExit):
+        bt._parse_args(["--engine", "bogus"])
+
+
+# --------------------------------------------------------------------------- #
+# #1966 _bucketize_confidence / _segment_label — pure bucketing.
+# --------------------------------------------------------------------------- #
+
+
+def test_bucketize_confidence_canonical_passthrough() -> None:
+    assert bt._bucketize_confidence("high") == "high"
+    assert bt._bucketize_confidence("medium") == "medium"
+    assert bt._bucketize_confidence("low") == "low"
+
+
+def test_bucketize_confidence_unknown_maps_to_other() -> None:
+    assert bt._bucketize_confidence("weird") == "other"
+    assert bt._bucketize_confidence("") == "other"
+
+
+def test_segment_label_bands_and_boundaries() -> None:
+    # Boundaries are upper-exclusive: 120k falls into комфорт, not эконом.
+    assert bt._segment_label(100_000) == "эконом"
+    assert bt._segment_label(119_999) == "эконом"
+    assert bt._segment_label(120_000) == "комфорт"
+    assert bt._segment_label(150_000) == "комфорт"
+    assert bt._segment_label(160_000) == "бизнес"
+    assert bt._segment_label(219_999) == "бизнес"
+    assert bt._segment_label(220_000) == "элит"
+    assert bt._segment_label(300_000) == "премиум"
+    assert bt._segment_label(2_000_000) == "премиум"  # +inf tail catches the top
+
+
+# --------------------------------------------------------------------------- #
+# #1966 _segment_metrics — per-price-segment signed error (band by SOLD ppm²).
+# --------------------------------------------------------------------------- #
+
+
+def test_segment_metrics_buckets_by_sold_price() -> None:
+    rows = [
+        (110_000.0, 100_000.0),  # sold эконом, +10
+        (132_000.0, 110_000.0),  # sold эконом, +20  → median эконом bias +15
+        (165_000.0, 150_000.0),  # sold комфорт, +10
+        (330_000.0, 300_000.0),  # sold премиум, +10
+    ]
+    seg = bt._segment_metrics(rows)
+    assert set(seg.keys()) == {label for label, _ in bt.PRICE_SEGMENTS_PPM2}
+    assert seg["эконом"]["n"] == 2
+    assert seg["эконом"]["median_bias_pct"] == pytest.approx(15.0)
+    assert seg["комфорт"]["n"] == 1
+    assert seg["комфорт"]["median_bias_pct"] == pytest.approx(10.0)
+    assert seg["премиум"]["n"] == 1
+    # bands with no rows are still present with n=0.
+    assert seg["бизнес"]["n"] == 0
+    assert seg["элит"]["n"] == 0
+
+
+def test_segment_metrics_drops_nonpositive_sold() -> None:
+    seg = bt._segment_metrics([(100_000.0, 0.0), (100_000.0, -1.0)])
+    assert all(seg[label]["n"] == 0 for label, _ in bt.PRICE_SEGMENTS_PPM2)
+
+
+# --------------------------------------------------------------------------- #
+# #1966 _range_coverage — inside / outside / boundary inclusive.
+# --------------------------------------------------------------------------- #
+
+
+def test_range_coverage_inside_outside_and_boundary_inclusive() -> None:
+    rows = [
+        (100.0, 90.0, 110.0),  # inside
+        (80.0, 90.0, 110.0),  # below low → outside
+        (120.0, 90.0, 110.0),  # above high → outside
+        (90.0, 90.0, 110.0),  # exactly on low → covered (inclusive)
+        (110.0, 90.0, 110.0),  # exactly on high → covered (inclusive)
+    ]
+    cov = bt._range_coverage(rows)
+    assert cov["n"] == 5
+    assert cov["n_covered"] == 3
+    assert cov["coverage_pct"] == pytest.approx(60.0)
+
+
+def test_range_coverage_empty_returns_none_pct() -> None:
+    cov = bt._range_coverage([])
+    assert cov["n"] == 0
+    assert cov["n_covered"] == 0
+    assert cov["coverage_pct"] is None
+
+
+def test_range_coverage_full_and_zero() -> None:
+    assert bt._range_coverage([(100.0, 50.0, 150.0)])["coverage_pct"] == pytest.approx(100.0)
+    assert bt._range_coverage([(10.0, 50.0, 150.0)])["coverage_pct"] == pytest.approx(0.0)
+
+
+# --------------------------------------------------------------------------- #
+# #1966 _sharpness — median relative range width (guards coverage gaming).
+# --------------------------------------------------------------------------- #
+
+
+def test_sharpness_median_relative_width() -> None:
+    rows = [
+        (100.0, 90.0, 110.0),  # width 20 / point 100 = 0.20
+        (200.0, 150.0, 250.0),  # width 100 / point 200 = 0.50
+    ]
+    sh = bt._sharpness(rows)
+    assert sh["n"] == 2
+    assert sh["median_rel_width"] == pytest.approx(0.35)  # median(0.20, 0.50)
+
+
+def test_sharpness_drops_nonpositive_point_and_empty() -> None:
+    assert bt._sharpness([(0.0, 1.0, 2.0)])["median_rel_width"] is None
+    assert bt._sharpness([(-5.0, 1.0, 2.0)])["n"] == 0
+    assert bt._sharpness([])["median_rel_width"] is None
+
+
+# --------------------------------------------------------------------------- #
+# #1966 _calibration_metrics — per-confidence n / coverage% / MAPE%.
+# --------------------------------------------------------------------------- #
+
+
+def test_calibration_metrics_per_confidence_n_coverage_mape() -> None:
+    rows = [
+        ("high", 5.0, True),
+        ("high", 15.0, True),  # high: n=2, covered 2/2=100%, mape median(5,15)=10
+        ("low", 40.0, False),
+        ("low", 60.0, True),  # low: n=2, covered 1/2=50%, mape median(40,60)=50
+    ]
+    cal = bt._calibration_metrics(rows)
+    # canonical buckets always present.
+    assert set(("high", "medium", "low")).issubset(cal.keys())
+    assert cal["high"]["n"] == 2
+    assert cal["high"]["coverage_pct"] == pytest.approx(100.0)
+    assert cal["high"]["mape_pct"] == pytest.approx(10.0)
+    assert cal["low"]["n"] == 2
+    assert cal["low"]["coverage_pct"] == pytest.approx(50.0)
+    assert cal["low"]["mape_pct"] == pytest.approx(50.0)
+    # empty canonical bucket renders with n=0 / None metrics, not missing.
+    assert cal["medium"]["n"] == 0
+    assert cal["medium"]["coverage_pct"] is None
+    assert cal["medium"]["mape_pct"] is None
+
+
+def test_calibration_metrics_handles_none_signed_and_covered() -> None:
+    # A prediction with no expected_sold (signed None) and no range (covered None)
+    # still counts toward n but not toward coverage/MAPE.
+    rows: list[tuple[str, float | None, bool | None]] = [
+        ("high", None, None),
+        ("high", 10.0, True),
+    ]
+    cal = bt._calibration_metrics(rows)
+    assert cal["high"]["n"] == 2
+    assert cal["high"]["coverage_pct"] == pytest.approx(100.0)  # only the 1 with covered
+    assert cal["high"]["mape_pct"] == pytest.approx(10.0)  # only the 1 with signed
+
+
+def test_calibration_metrics_appends_other_bucket() -> None:
+    cal = bt._calibration_metrics([("exotic", 5.0, True)])
+    assert "other" in cal
+    assert cal["other"]["n"] == 1
+    # canonical three still present even though empty.
+    assert cal["high"]["n"] == 0
+
+
+# --------------------------------------------------------------------------- #
+# #1966 Prediction + _compute_full_metrics — integration of the new blocks.
+# --------------------------------------------------------------------------- #
+
+
+def _pred(
+    *,
+    rooms: int = 2,
+    area: float = 50.0,
+    sold_ppm2: float = 100_000.0,
+    median_ppm2: float = 120_000.0,
+    confidence: str = "high",
+    es_ppm2: float | None = 100_000.0,
+    es_price: float | None = 5_000_000.0,
+    range_low: float | None = 4_500_000.0,
+    range_high: float | None = 5_500_000.0,
+    anchor_tier: str | None = None,
+    deal_id: int = 1,
+) -> bt.Prediction:
+    return bt.Prediction(
+        deal_id=deal_id,
+        rooms=rooms,
+        area_m2=area,
+        sold_ppm2=sold_ppm2,
+        median_ppm2=median_ppm2,
+        confidence=confidence,
+        anchor_tier=anchor_tier,
+        expected_sold_ppm2=es_ppm2,
+        expected_sold_price=es_price,
+        range_low=range_low,
+        range_high=range_high,
+    )
+
+
+def test_prediction_sold_total_property() -> None:
+    p = _pred(sold_ppm2=100_000.0, area=50.0)
+    assert p.sold_total == pytest.approx(5_000_000.0)
+
+
+def test_compute_full_metrics_structure_and_blocks() -> None:
+    preds = [
+        # sold_total = 100k*50 = 5.0M, range [4.5M, 5.5M] → covered; es +0%
+        _pred(deal_id=1, confidence="high", es_ppm2=100_000.0, sold_ppm2=100_000.0),
+        # sold_total = 200k*50 = 10.0M, range [4.5M,5.5M] → NOT covered; es -50%
+        _pred(
+            deal_id=3,
+            confidence="low",
+            es_ppm2=100_000.0,
+            sold_ppm2=200_000.0,
+            median_ppm2=120_000.0,
+        ),
+    ]
+    m = bt._compute_full_metrics(preds, n_no_prediction=4, per_rooms_no_prediction={2: 4})
+
+    # expected_sold block: overall + per_rooms + per_segment, carries no-pred count.
+    assert m["expected_sold"]["overall"]["n"] == 2
+    assert m["expected_sold"]["overall"]["n_no_analogs"] == 4  # repurposed = no_pred
+    assert "per_segment" in m["expected_sold"]
+    assert set(m["expected_sold"]["per_segment"].keys()) == {
+        label for label, _ in bt.PRICE_SEGMENTS_PPM2
+    }
+
+    # range coverage: 1 of 2 inside → 50% overall.
+    assert m["range_coverage"]["overall"]["n"] == 2
+    assert m["range_coverage"]["overall"]["n_covered"] == 1
+    assert m["range_coverage"]["overall"]["coverage_pct"] == pytest.approx(50.0)
+    # per-confidence: high covered 100%, low covered 0%.
+    assert m["range_coverage"]["per_confidence"]["high"]["coverage_pct"] == pytest.approx(100.0)
+    assert m["range_coverage"]["per_confidence"]["low"]["coverage_pct"] == pytest.approx(0.0)
+
+    # calibration: high tighter/accurate, low not.
+    assert m["calibration"]["high"]["n"] == 1
+    assert m["calibration"]["high"]["coverage_pct"] == pytest.approx(100.0)
+    assert m["calibration"]["high"]["mape_pct"] == pytest.approx(0.0)
+    assert m["calibration"]["low"]["coverage_pct"] == pytest.approx(0.0)
+    assert m["calibration"]["low"]["mape_pct"] == pytest.approx(50.0)
+
+    # sharpness present.
+    assert m["sharpness"]["n"] == 2
+    assert m["sharpness"]["median_rel_width"] is not None
+
+    # confidence order: canonical three first.
+    assert m["confidence_order"][:3] == ["high", "medium", "low"]
+
+
+def test_compute_full_metrics_empty_is_safe() -> None:
+    m = bt._compute_full_metrics([])
+    assert m["expected_sold"]["overall"]["n"] == 0
+    assert m["range_coverage"]["overall"]["coverage_pct"] is None
+    assert m["calibration"]["high"]["n"] == 0
+    assert m["sharpness"]["median_rel_width"] is None
+
+
+def test_compute_full_metrics_no_expected_sold_counts_in_calibration_only() -> None:
+    # A priced deal with no expected_sold (ratio unresolved) and no range:
+    # counts in calibration n but contributes nothing to expected_sold / coverage.
+    preds = [
+        _pred(
+            deal_id=1,
+            confidence="medium",
+            es_ppm2=None,
+            es_price=None,
+            range_low=None,
+            range_high=None,
+        )
+    ]
+    m = bt._compute_full_metrics(preds)
+    assert m["expected_sold"]["overall"]["n"] == 0  # no es row
+    assert m["range_coverage"]["overall"]["n"] == 0  # no range row
+    assert m["calibration"]["medium"]["n"] == 1  # still counted
+    assert m["calibration"]["medium"]["coverage_pct"] is None
+
+
+# --------------------------------------------------------------------------- #
+# #1966 _render_full_table — smoke (must not crash, renders all blocks).
+# --------------------------------------------------------------------------- #
+
+
+def test_render_full_table_runs_on_real_metrics() -> None:
+    preds = [
+        _pred(deal_id=1, confidence="high", es_ppm2=100_000.0, sold_ppm2=100_000.0),
+        _pred(deal_id=3, confidence="low", es_ppm2=100_000.0, sold_ppm2=200_000.0),
+    ]
+    m = bt._compute_full_metrics(preds, n_no_prediction=1, per_rooms_no_prediction={2: 1})
+    m["headline"] = {
+        "deal_median_ppm2": 100_000.0,
+        "ask_median_ppm2": 120_000.0,
+        "spread_pct": 20.0,
+    }
+    out = bt._render_full_table(m)
+    assert "full spine" in out
+    assert "EXPECTED_SOLD" in out
+    assert "RANGE COVERAGE" in out
+    assert "CONFIDENCE CALIBRATION" in out
+    assert "SHARPNESS" in out
+    assert "per price-segment" in out
+    assert "эконом" in out  # segment band rendered
+    assert "regression baseline" in out  # caveat present
+
+
+def test_render_full_table_handles_empty_sample() -> None:
+    m = bt._compute_full_metrics([])
+    m["headline"] = {"deal_median_ppm2": None, "ask_median_ppm2": None, "spread_pct": None}
+    out = bt._render_full_table(m)
+    assert "n/a" in out  # None metrics render as n/a, no crash
+    assert "BACKTEST" in out