"""Merge per-pair hourly parquets into a single wide multipair parquet.

Each pair contributes two features: {pair}_ret and {pair}_rv (realized vol).
The merge is an INNER JOIN on datetime — only hours present in ALL pairs are kept.
The target for train.py remains eurusd_rv.

Output: data/processed/eurusd_multipair.parquet

    python scripts/prepare_multipair.py
    PROCESSED=data/processed python scripts/prepare_multipair.py
"""
import os
import pandas as pd

PAIRS = ["eurusd", "gbpusd", "usdjpy", "usdchf", "audusd"]

PROCESSED_DEFAULT = "data/processed"
OUT_DEFAULT       = "data/processed/eurusd_multipair.parquet"


def merge_pair_parquets(pair_dfs: dict) -> pd.DataFrame:
    """Inner-join hourly DataFrames from multiple pairs on datetime.

    Args:
        pair_dfs: dict mapping pair name (e.g. "eurusd") to hourly DataFrame
                  with columns [datetime, close, ret, realized_vol, ...].
    Returns:
        Wide DataFrame with columns:
          datetime, {pair}_ret, {pair}_rv  for each pair.
    """
    merged = None
    for pair, df in pair_dfs.items():
        sub = df[["datetime", "ret", "realized_vol"]].copy()
        sub = sub.rename(columns={"ret": f"{pair}_ret", "realized_vol": f"{pair}_rv"})
        sub = sub.set_index("datetime")
        if merged is None:
            merged = sub
        else:
            merged = merged.join(sub, how="inner")

    return merged.reset_index()


def build_multipair_parquet(
    processed_dir: str = PROCESSED_DEFAULT,
    out_path: str = OUT_DEFAULT,
    pairs: list = None,
) -> None:
    if pairs is None:
        pairs = PAIRS
    pair_dfs = {}
    for pair in pairs:
        path = os.path.join(processed_dir, f"{pair}_hourly.parquet")
        if not os.path.exists(path):
            raise FileNotFoundError(
                f"{pair}_hourly.parquet not found at {path} — run prepare_hourly.py for this pair first"
            )
        df = pd.read_parquet(path)
        pair_dfs[pair] = df

    merged = merge_pair_parquets(pair_dfs)
    merged.to_parquet(out_path, index=False)
    n_pairs = len(pairs)
    n_ch    = n_pairs * 2
    print(f"Multipair parquet: {len(merged):,} rows × {n_ch} feature channels ({n_pairs} pairs)")
    print(f"Date range: {merged['datetime'].min()} → {merged['datetime'].max()}")
    print(f"Written: {out_path}")


if __name__ == "__main__":
    processed_dir = os.environ.get("PROCESSED", PROCESSED_DEFAULT)
    build_multipair_parquet(processed_dir=processed_dir)