Add ML prediction pipeline — LightGBM, calibration fix, ensemble disagreement

Tier 1 ML enhancements:
- Feature engineering (37 features across 5 groups: thermal, dynamic,
  moisture, temporal, interaction) from NWP model output
- 7 LightGBM probability models for rain/temp/wind thresholds
- Temperature-scaled probabilities to prevent overconfidence on bootstrap data
- MLPredictor: unified inference pipeline replacing heuristic sigmoids
- Ensemble disagreement signals (composite spread → edge amplification)
- Fixed calibration loop: update_calibration() now functional (EMA of errors)
- record_outcome() wired for post-resolution feedback
- Nautilus strategy updated: ML predictions take priority, heuristics as fallback
- Historical backtest engine with Sharpe/ROI/max-DD simulation
- Bootstrap training data generator from HK climate normals

Run: python ml/train.py && python ml/backtest.py --edge 50

ml/__init__.py

@@ -0,0 +1,20 @@
+"""ML prediction pipeline for HK weather.
+
+Usage:
+    from ml import MLPredictor
+    predictor = MLPredictor()
+    predictor.fetch_and_predict()
+    signal = predictor.generate_signal("temp_gt_30c_24h", market_probability=45.0)
+"""
+
+from ml.predictor import MLPredictor
+from ml.model import ModelEnsemble, WeatherModel, TARGET_DEFINITIONS
+from ml.features import FeatureEngine
+
+__all__ = [
+    "MLPredictor",
+    "ModelEnsemble",
+    "WeatherModel",
+    "FeatureEngine",
+    "TARGET_DEFINITIONS",
+]