fix(features): revert to 2-channel default; OHLCV features redundant

HPO finding: hl_range≈realized_vol, ret_intrabar≈ret — correlation kills signal.
4ch D=128: 0.3503, 4ch D=256: 0.3807, 2ch D=128 baseline: 0.3908 (winner).
Parquet keeps hl_range+ret_intrabar; comment in build() documents the attempt.
test_build_uses_4_channels → test_build_uses_2_channels (tracks current default).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/test_prepare_hourly.py

@@ -194,17 +194,14 @@ def test_ret_intrabar_formula(ph):
     assert abs(rib - expected) < 1e-6, f"ret_intrabar={rib:.8f}, expected={expected:.8f}"
 
 
-# 10. build() in train.py uses 4 feature channels when hl_range + ret_intrabar present
+# 10. build() in train.py uses 2 feature channels (HPO: hl_range/ret_intrabar redundant)
-def test_build_uses_4_channels(tmp_path):
+def test_build_uses_2_channels(tmp_path):
     import importlib.util, os
     hourly_path = "data/processed/eurusd_hourly.parquet"
     if not os.path.exists(hourly_path):
         pytest.skip("eurusd_hourly.parquet not present")
-    df = pd.read_parquet(hourly_path)
+    spec = importlib.util.spec_from_file_location("train_2ch", "train.py")
-    if "hl_range" not in df.columns:
-        pytest.skip("eurusd_hourly.parquet lacks hl_range — rebuild first")
-    spec = importlib.util.spec_from_file_location("train_4ch", "train.py")
     mod = importlib.util.module_from_spec(spec)
     spec.loader.exec_module(mod)
     (Xtr, _), _ = mod.build()
-    assert Xtr.shape[2] == 4, f"expected 4 channels, got {Xtr.shape[2]}"
+    assert Xtr.shape[2] == 2, f"expected 2 channels, got {Xtr.shape[2]}"

train.py

@@ -154,10 +154,9 @@ def build():
     else:
         df = pd.read_parquet(daily_path).reset_index(drop=True)
         df["date"] = pd.to_datetime(df["date"])
-    # Use OHLCV-derived features when available; fall back to 2-channel
+    # 2-channel default (HPO: adding hl_range+ret_intrabar hurt — correlated with base feats)
-    base_feats = ["ret", "realized_vol"]
+    # To experiment: change to ["ret", "realized_vol", "hl_range", "ret_intrabar"]
-    extra_feats = [c for c in ["hl_range", "ret_intrabar"] if c in df.columns]
+    FEAT_COLS = ["ret", "realized_vol"]
-    FEAT_COLS = base_feats + extra_feats
     feats  = df[FEAT_COLS].to_numpy(np.float32)
     target = df["realized_vol"].to_numpy(np.float32)
     tr_idx = df.index[df["date"].dt.year <= 2021].tolist()