scripts/01_prepare_data.py

"""Phase 1 entrypoint: load -> clean -> split -> save processed parquet files.

Usage:
    python scripts/01_prepare_data.py
Outputs train/val/test parquet files + a cleaning_funnel.csv into data/processed/.
"""
from __future__ import annotations

import sys
from pathlib import Path

sys.path.append(str(Path(__file__).resolve().parents[1]))
from src.config import load_config
from src.data.clean import clean, split
from src.data.load import load_raw


def main():
    cfg = load_config()
    print("=" * 60)
    print("PHASE 1: DATA PREPARATION")
    print("=" * 60)

    raw = load_raw(cfg)
    cleaned, funnel = clean(raw, cfg)

    print("\nCleaning funnel:")
    print(funnel.to_string(index=False))

    splits = split(cleaned, cfg)
    out = Path(cfg.paths.processed_dir)
    for name, part in splits.items():
        path = out / f"{name}.parquet"
        part.to_parquet(path, index=False)
        print(f"  saved {name}: {len(part):,} rows -> {path}")

    funnel.to_csv(out / "cleaning_funnel.csv", index=False)
    print(f"\nDone. Processed data in {out}")


if __name__ == "__main__":
    main()