feat: add OI derived features (oi_change_ma5, oi_price_spread) to dataset builder and ML features

Add two new OI-derived features to improve ML model's market microstructure
understanding:
- oi_change_ma5: 5-candle moving average of OI change rate (short-term trend)
- oi_price_spread: z-scored OI minus z-scored price return (divergence signal)

Both features use 96-candle rolling z-score window. FEATURE_COLS expanded from
24 to 26. Existing tests updated to reflect new feature counts.

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

src/dataset_builder.py

@@ -287,8 +287,18 @@ def _calc_features_vectorized(
     else:
         fr_raw = np.full(len(d), np.nan)
 
-    result["oi_change"]    = _rolling_zscore(oi_raw.astype(np.float64))
-    result["funding_rate"] = _rolling_zscore(fr_raw.astype(np.float64))
+    oi_z = _rolling_zscore(oi_raw.astype(np.float64), window=96)
+    result["oi_change"]    = oi_z
+    result["funding_rate"] = _rolling_zscore(fr_raw.astype(np.float64), window=96)
+
+    # --- OI 파생 피처 ---
+    # 1. oi_change_ma5: OI 변화율의 5캔들 이동평균 (단기 추세)
+    oi_series = pd.Series(oi_raw.astype(np.float64))
+    oi_ma5_raw = oi_series.rolling(window=5, min_periods=1).mean().values
+    result["oi_change_ma5"] = _rolling_zscore(oi_ma5_raw, window=96)
+
+    # 2. oi_price_spread: z-scored OI - z-scored 가격 수익률 (연속값)
+    result["oi_price_spread"] = oi_z - ret_1_z
 
     return result
 
@@ -384,7 +394,7 @@ def generate_dataset_vectorized(
     feat_all   = _calc_features_vectorized(d, signal_arr, btc_df=btc_df, eth_df=eth_df)
 
     # 신호 발생 + NaN 없음 + 미래 데이터 충분한 인덱스만
-    OPTIONAL_COLS = {"oi_change", "funding_rate"}
+    OPTIONAL_COLS = {"oi_change", "funding_rate", "oi_change_ma5", "oi_price_spread"}
     available_cols_for_nan_check = [
         c for c in FEATURE_COLS
         if c in feat_all.columns and c not in OPTIONAL_COLS

src/ml_features.py

@@ -9,8 +9,9 @@ FEATURE_COLS = [
     "eth_ret_1", "eth_ret_3", "eth_ret_5",
     "xrp_btc_rs", "xrp_eth_rs",
     # 시장 미시구조: OI 변화율(z-score), 펀딩비(z-score)
-    # parquet에 oi_change/funding_rate 컬럼이 없으면 dataset_builder에서 0으로 채움
     "oi_change", "funding_rate",
+    # OI 파생 피처
+    "oi_change_ma5", "oi_price_spread",
     "adx",
 ]
 
@@ -37,12 +38,14 @@ def build_features(
     eth_df: pd.DataFrame | None = None,
     oi_change: float | None = None,
     funding_rate: float | None = None,
+    oi_change_ma5: float | None = None,
+    oi_price_spread: float | None = None,
 ) -> pd.Series:
     """
     기술 지표가 계산된 DataFrame의 마지막 행에서 ML 피처를 추출한다.
-    btc_df, eth_df가 제공되면 24개 피처를, 없으면 16개 피처를 반환한다.
+    btc_df, eth_df가 제공되면 26개 피처를, 없으면 18개 피처를 반환한다.
     signal: "LONG" | "SHORT"
-    oi_change, funding_rate: 실제 값이 제공되면 사용, 없으면 0.0으로 채운다.
+    oi_change, funding_rate, oi_change_ma5, oi_price_spread: 실제 값이 제공되면 사용, 없으면 0.0으로 채운다.
     """
     last = df.iloc[-1]
     close = last["close"]
@@ -132,8 +135,10 @@ def build_features(
         })
 
     # 실시간에서 실제 값이 제공되면 사용, 없으면 0으로 채운다
-    base["oi_change"]    = float(oi_change)    if oi_change    is not None else 0.0
-    base["funding_rate"] = float(funding_rate) if funding_rate is not None else 0.0
+    base["oi_change"]       = float(oi_change)       if oi_change       is not None else 0.0
+    base["funding_rate"]    = float(funding_rate)    if funding_rate    is not None else 0.0
+    base["oi_change_ma5"]   = float(oi_change_ma5)   if oi_change_ma5   is not None else 0.0
+    base["oi_price_spread"] = float(oi_price_spread) if oi_price_spread is not None else 0.0
     base["adx"] = float(last.get("adx", 0))
 
     return pd.Series(base)