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_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,
     )