"""
Offline training script.

Run once to build bucket assignments and train continuation models:

    cd /mnt/dolphinng5_predict
    siloqy-env python adaptive_exit/train.py

Artifacts written:
    adaptive_exit/models/bucket_assignments.pkl
    adaptive_exit/models/continuation_models.pkl
    adaptive_exit/models/training_data.parquet   (optional, for audit)
"""
import argparse
import os
import sys

sys.path.insert(0, "/mnt/dolphinng5_predict")

from adaptive_exit.bucket_engine import build_buckets
from adaptive_exit.continuation_model import ContinuationModelBank
from adaptive_exit.data_pipeline import build_training_data

_MODELS_DIR = os.path.join(os.path.dirname(__file__), "models")
_TRAIN_DATA_PATH = os.path.join(_MODELS_DIR, "training_data.parquet")


def main():
    parser = argparse.ArgumentParser(description="Train adaptive exit models")
    parser.add_argument("--k", type=int, default=None, help="Force bucket count (default: auto)")
    parser.add_argument("--save-data", action="store_true", help="Save training parquet for audit")
    parser.add_argument("--force-rebuild", action="store_true", help="Rebuild buckets even if cached")
    parser.add_argument("--vbt-dir", default="/mnt/dolphinng5_predict/vbt_cache",
                        help="VBT parquet dir for training data generation")
    parser.add_argument("--klines-dir", default="/mnt/dolphin_training/data/vbt_cache_klines",
                        help="1m klines dir for asset bucketing")
    args = parser.parse_args()

    os.makedirs(_MODELS_DIR, exist_ok=True)

    # ── Step 1: Build asset buckets ──────────────────────────────────────────
    print("\n=== STEP 1: Asset Bucketing ===")
    bucket_data = build_buckets(
        klines_dir=args.klines_dir,
        k_override=args.k,
        force_rebuild=args.force_rebuild,
    )
    print(f"Buckets: {bucket_data['n_buckets']} | Assets: {len(bucket_data['assignments'])}")

    # ── Step 2: Build training data from price series ────────────────────────
    print("\n=== STEP 2: Generate MAE/MFE Training Data ===")
    df = build_training_data(
        bucket_assignments=bucket_data["assignments"],
        vbt_dir=args.vbt_dir,
        use_obf_ch=False,   # OBF is live-only (13 days); zero-fill training, bolt on at Phase 2
    )
    print(f"Training data shape: {df.shape}")
    print(f"Bucket distribution:\n{df.groupby('bucket_id').size().describe()}")
    print(f"Continuation rate: {df['continuation'].mean():.3f}")

    if args.save_data:
        df.to_parquet(_TRAIN_DATA_PATH)
        print(f"Training data saved → {_TRAIN_DATA_PATH}")

    # ── Step 3: Train continuation models ────────────────────────────────────
    print("\n=== STEP 3: Train Continuation Models ===")
    bank = ContinuationModelBank()
    bank.train(df)
    bank.save()
    print(f"\nModel summary: {bank.summary()}")
    print("\nDone.")


if __name__ == "__main__":
    main()