"""Burst-candle frequency by UTC hour — the empirical "hedge fund hours".

Usage:
    python backtest/research/burst_profile.py PARQUET_GLOB

Per UTC bar-close hour of the given bars: % of bars whose range is
>= K x the PRIOR bar's Wilder ATR(14), for K in {3,4,5}; mean bar
range; and mean signed drift over the 6 bars following a >=4x burst
(does price continue or snap back?). Analysis tooling only.
"""
import glob
import sys

import pandas as pd


def burst_table(parquet_glob: str, bar_minutes: int = 5):
    files = sorted(glob.glob(parquet_glob))
    if not files:
        raise SystemExit(f"no parquet matches {parquet_glob}")
    df = pd.concat([pd.read_parquet(f) for f in files]).sort_index()
    df = df[~df.index.duplicated(keep="last")]
    h, l, c = df["High"], df["Low"], df["Close"]
    tr = pd.concat([h - l, (h - c.shift()).abs(), (l - c.shift()).abs()],
                   axis=1).max(axis=1)
    atr = tr.ewm(alpha=1 / 14, min_periods=14, adjust=False).mean()
    ratio = (h - l) / atr.shift(1)
    close_hour = (df.index + pd.Timedelta(minutes=bar_minutes)).hour
    fwd6 = c.shift(-6) - c  # signed move over the 6 bars after this one
    out = pd.DataFrame({
        "bars": ratio.groupby(close_hour).size(),
        **{f"pct_ge_{k}x": (ratio >= k).groupby(close_hour).mean() * 100
           for k in (3, 4, 5)},
        "mean_range": (h - l).groupby(close_hour).mean(),
        "post4x_drift6": fwd6[ratio >= 4].groupby(close_hour[ratio >= 4]).mean(),
    })
    return out.round(3)


if __name__ == "__main__":
    print(burst_table(sys.argv[1],
                      int(sys.argv[2]) if len(sys.argv) > 2 else 5).to_string())