fix: remove leakage from legacy ML evaluation

tests/test_legacy_ml_validation.py

@@ -0,0 +1,103 @@
+import numpy as np
+import pandas as pd
+
+import orchestrator
+from ml_engine import train_and_backtest as legacy
+from ml_engine.train_and_backtest import create_accumulation_target
+
+
+def _frame(prices):
+    return pd.DataFrame({"close": prices})
+
+
+def test_accumulation_target_for_existing_row_is_invariant_to_unrelated_future_rows():
+    config = {
+        "timeframe": "4h",
+        "target": {
+            "forward_periods_4h": [1, 2, 3],
+            "weights": [0.2, 0.3, 0.5],
+            "return_scales_pct": [5, 10, 20],
+        },
+    }
+    base = _frame([100, 102, 104, 106, 108, 110, 112, 114])
+    extended = _frame([100, 102, 104, 106, 108, 110, 112, 114, 1000, 1, 2000])
+
+    base_target = create_accumulation_target(base, config)
+    extended_target = create_accumulation_target(extended, config)
+
+    assert np.isclose(base_target.iloc[0], extended_target.iloc[0])
+    assert 0 <= base_target.iloc[0] <= 100
+
+
+def test_rolling_validation_purges_forward_label_horizon_at_train_boundaries(monkeypatch):
+    rows = 200
+    frame = pd.DataFrame({
+        "feature": np.linspace(0, 1, rows),
+        "target": np.arange(rows, dtype=float) % 100,
+        "close": np.linspace(10_000, 20_000, rows),
+    })
+    observed = []
+
+    def fake_train(X_train, y_train, X_val, y_val, X_test, *args):
+        observed.append((len(X_train), len(X_val), len(X_test)))
+        return np.full(len(X_test), 50.0), np.array([1.0])
+
+    monkeypatch.setattr(legacy, "_train_and_predict_window", fake_train)
+    config = {
+        "model_type": "xgboost",
+        "target": {"forward_periods_4h": [1, 2, 3]},
+        "training": {
+            "rolling_train_size": 120,
+            "rolling_test_size": 40,
+            "validation_pct": 0.25,
+        },
+        "features": {"use_scaler": False, "use_pca": False},
+        "strategy": {},
+    }
+
+    legacy.rolling_window_train_test(frame, ["feature"], config)
+
+    assert observed[0] == (87, 27, 40)
+
+
+def test_periodic_accumulation_compares_equal_contributions_and_retains_cash():
+    result = legacy.simulate_periodic_accumulation(
+        predicted_scores=np.array([90, 10, 90, 10], dtype=float),
+        close_prices=np.array([100, 300, 100, 200], dtype=float),
+        buy_threshold=70,
+        contribution=100,
+    )
+
+    assert np.isclose(result["dca_contributed"], 400)
+    assert np.isclose(result["model_contributed"], 400)
+    assert np.isclose(result["model_cash"], 100)
+    assert np.isclose(result["model_btc"], 3)
+    assert result["model_terminal_value"] > result["dca_terminal_value"]
+
+
+def test_compiled_results_publish_equal_capital_terminal_wealth_metric():
+    predictions = [
+        {"predicted": score, "actual": 50.0, "close": price}
+        for score, price in zip([90, 10, 90, 10], [100, 300, 100, 200])
+    ]
+
+    result = legacy.compile_results(
+        predictions,
+        per_window_cost_improvement=[],
+        fi_sum=np.array([1.0]),
+        fi_count=1,
+        feature_cols=["feature"],
+        config={"model_type": "xgboost", "strategy": {"good_buy_threshold": 70}},
+    )
+
+    assert result["terminal_wealth_improvement_pct"] > 0
+    assert result["backtest_objective"] == "equal_periodic_contribution_terminal_wealth"
+
+
+def test_orchestrator_selects_models_by_terminal_wealth_not_cost_basis():
+    results = {
+        "terminal_wealth_improvement_pct": 4.5,
+        "cost_basis_improvement_pct": 99.0,
+    }
+
+    assert orchestrator.objective_score(results) == 4.5