fix: purge ML validation label leakage

tests/test_ml_optimizer_validation.py

@@ -0,0 +1,74 @@
+from datetime import datetime, timedelta
+
+from ml import optimizer
+
+
+def _row(date, returns=10.0, score_200w=10, score_drawdown=0):
+    row = {
+        "date": date,
+        "price": 100.0,
+        "fwd_365d": returns,
+        "score_puell_multiple": 0,
+        "score_mvrv_zscore": 0,
+        "score_reserve_risk": 0,
+        "score_rhodl_ratio": 0,
+        "score_nupl": 0,
+        "score_fear_greed": 0,
+        "score_drawdown": score_drawdown,
+        "score_pct_above_200w_sma": score_200w,
+        "score_pct_above_lth_rp": 0,
+    }
+    return row
+
+
+def test_purged_time_series_splits_remove_overlapping_forward_label_windows():
+    start = datetime(2020, 1, 1)
+    rows = [_row((start + timedelta(days=i)).strftime("%Y-%m-%d")) for i in range(900)]
+
+    splits = list(
+        optimizer.purged_time_series_splits(
+            rows,
+            n_splits=3,
+            label_horizon_days=365,
+            embargo_days=0,
+        )
+    )
+
+    assert splits, "expected at least one viable split"
+    for train_idx, val_idx in splits:
+        val_start = datetime.strptime(rows[val_idx[0]]["date"], "%Y-%m-%d")
+        latest_allowed_train_date = val_start - timedelta(days=365)
+        assert len(train_idx) > 0, "purging should keep non-overlapping expanding-window training rows"
+        for idx in train_idx:
+            train_date = datetime.strptime(rows[idx]["date"], "%Y-%m-%d")
+            assert train_date <= latest_allowed_train_date
+
+
+def test_run_out_of_sample_comparison_scores_only_validation_rows_with_fold_weights():
+    rows = [
+        _row("2020-01-01", returns=-10, score_200w=0, score_drawdown=10),
+        _row("2020-01-02", returns=-5, score_200w=0, score_drawdown=10),
+        _row("2020-01-03", returns=100, score_200w=10, score_drawdown=10),
+        _row("2020-01-04", returns=120, score_200w=10, score_drawdown=10),
+    ]
+    fold_results = [
+        {
+            "fold": 1,
+            "val_idx": [2, 3],
+            "weights": {"pct_above_200w_sma": 1.0, "drawdown": 0.0},
+        }
+    ]
+
+    comparison = optimizer.run_out_of_sample_comparison(rows, fold_results)
+
+    assert comparison["validation_days"] == 2
+    assert comparison["folds"] == 1
+    assert sum(bucket["days"] for bucket in comparison["ml_weighted"]) == 2
+    assert sum(bucket["days"] for bucket in comparison["equal_weight"]) == 2
+
+    extreme_ml = next(bucket for bucket in comparison["ml_weighted"] if bucket["label"] == "Extreme Accumulation")
+    assert extreme_ml["days"] == 2
+    assert extreme_ml["avg_365d"] == 110.0
+
+    caution_equal = next(bucket for bucket in comparison["equal_weight"] if bucket["label"] == "Caution")
+    assert caution_equal["days"] == 2

tests/test_scoring_engine_ml.py

@@ -0,0 +1,63 @@
+import math
+
+from scoring import engine
+
+
+def _complete_metrics():
+    return {
+        "fear_greed": {"value": 10, "classification": "Extreme Fear"},
+        "puell_multiple": {"value": 0.3},
+        "mvrv_zscore": {"value": -0.1},
+        "drawdown": {"value": 60.0, "ath": 250.0},
+        "price": {"price": 100.0},
+        "200w_sma": {"value": 120.0},
+        "reserve_risk": {"value": 0.001},
+        "rhodl_ratio": {"value": 50.0},
+        "nupl": {"value": -0.1},
+        "lth_realized_price": {"value": 120.0},
+        "hash_ribbons": {"buy_signal": False},
+    }
+
+
+def test_score_all_ml_normalizes_displayed_weights_and_contributions(monkeypatch):
+    monkeypatch.setattr(
+        engine,
+        "load_ml_weights",
+        lambda: {
+            "fear_greed": 0.40,
+            "puell_multiple": 0.20,
+            "mvrv_zscore": 0.15,
+            "drawdown": 0.10,
+            "pct_above_200w_sma": 0.05,
+            "reserve_risk": 0.04,
+            "rhodl_ratio": 0.03,
+            "nupl": 0.02,
+            "pct_above_lth_rp": 0.01,
+        },
+    )
+
+    scored = engine.score_all_ml(_complete_metrics())
+
+    assert scored["ml_mode"] is True
+    valid_metrics = [m for m in scored["metrics"] if m["score"] is not None]
+    assert scored["ml_weight_total"] == 1.01  # trained weights + small hash-ribbons fallback
+    assert math.isclose(sum(m["ml_weight"] for m in valid_metrics), 1.0, abs_tol=0.001)
+    assert math.isclose(
+        sum(m["ml_contribution"] for m in valid_metrics),
+        scored["composite_score"],
+        abs_tol=0.05,
+    )
+
+    hash_ribbons = next(m for m in valid_metrics if m["key"] == "hash_ribbons")
+    assert hash_ribbons["ml_raw_weight"] == 0.01
+    assert hash_ribbons["ml_weight"] == round(0.01 / 1.01, 4)
+
+
+def test_score_all_ml_preserves_classic_fallback_when_weights_missing(monkeypatch):
+    monkeypatch.setattr(engine, "load_ml_weights", lambda: {})
+
+    scored = engine.score_all_ml(_complete_metrics())
+
+    assert scored["ml_mode"] is False
+    assert scored["ml_error"] == "ML weights not found — run ml/optimizer.py"
+    assert "classic_score" not in scored