feat(ml): relax training thresholds for 5-10x more training samples

Add TRAIN_* constants (signal_threshold=2, adx=15, vol_mult=1.5, neg_ratio=3)
as dataset_builder defaults. Remove hardcoded negative_ratio=5 from all callers.
Bot entry conditions unchanged (config.py strict values).

WF 5-fold results (all symbols AUC 0.91+):
- XRPUSDT: 0.9216 ± 0.0052
- SOLUSDT:  0.9174 ± 0.0063
- DOGEUSDT: 0.9222 ± 0.0085

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/train_mlx_model.py

@@ -59,7 +59,7 @@ def train_mlx(data_path: str, time_weight_decay: float = 2.0, atr_sl_mult: float
     print("\n데이터셋 생성 중...")
     t0 = time.perf_counter()
     dataset = generate_dataset_vectorized(df, btc_df=btc_df, eth_df=eth_df, time_weight_decay=time_weight_decay,
-                                          atr_sl_mult=atr_sl_mult, atr_tp_mult=atr_tp_mult, negative_ratio=5)
+                                          atr_sl_mult=atr_sl_mult, atr_tp_mult=atr_tp_mult)
     t1 = time.perf_counter()
     print(f"데이터셋 생성 완료: {t1 - t0:.1f}초, {len(dataset)}개 샘플")
 
@@ -175,7 +175,7 @@ def walk_forward_auc(
 
     dataset = generate_dataset_vectorized(
         df, btc_df=btc_df, eth_df=eth_df, time_weight_decay=time_weight_decay,
-        atr_sl_mult=atr_sl_mult, atr_tp_mult=atr_tp_mult, negative_ratio=5,
+        atr_sl_mult=atr_sl_mult, atr_tp_mult=atr_tp_mult,
     )
     missing = [c for c in FEATURE_COLS if c not in dataset.columns]
     for col in missing:

scripts/train_model.py

@@ -222,7 +222,7 @@ def train(data_path: str, time_weight_decay: float = 2.0, tuned_params_path: str
     dataset = generate_dataset_vectorized(
         df, btc_df=btc_df, eth_df=eth_df,
         time_weight_decay=time_weight_decay,
-        negative_ratio=5,
+
         atr_sl_mult=atr_sl_mult,
         atr_tp_mult=atr_tp_mult,
     )
@@ -367,7 +367,7 @@ def walk_forward_auc(
     dataset = generate_dataset_vectorized(
         df, btc_df=btc_df, eth_df=eth_df,
         time_weight_decay=time_weight_decay,
-        negative_ratio=5,
+
         atr_sl_mult=atr_sl_mult,
         atr_tp_mult=atr_tp_mult,
     )
@@ -459,7 +459,7 @@ def compare(data_path: str, time_weight_decay: float = 2.0, tuned_params_path: s
     dataset = generate_dataset_vectorized(
         df, btc_df=btc_df, eth_df=eth_df,
         time_weight_decay=time_weight_decay,
-        negative_ratio=5,
+
         atr_sl_mult=atr_sl_mult,
         atr_tp_mult=atr_tp_mult,
     )

scripts/tune_hyperparams.py

@@ -64,7 +64,7 @@ def load_dataset(data_path: str, atr_sl_mult: float = 2.0, atr_tp_mult: float =
     df = df_raw[base_cols].copy()
 
     print("\n데이터셋 생성 중 (1회만 실행)...")
-    dataset = generate_dataset_vectorized(df, btc_df=btc_df, eth_df=eth_df, time_weight_decay=0.0, negative_ratio=5,
+    dataset = generate_dataset_vectorized(df, btc_df=btc_df, eth_df=eth_df, time_weight_decay=0.0,
                                           atr_sl_mult=atr_sl_mult, atr_tp_mult=atr_tp_mult)
 
     if dataset.empty or "label" not in dataset.columns: