"""Trade-book diff: relaxed/gated run vs its control.

Usage:
    python backtest/research/book_diff.py CONTROL.csv CANDIDATE.csv BAR_MINUTES

Decision numbers are RUN-LEVEL (ΔtotalR, ΔPF, ΔmaxDD, Δtrades) — never
the added-trade bucket alone: the 5-bar entry cooldown means new
entries displace existing ones. The added/removed decomposition and the
per-decision-hour histogram of added trades are diagnostics.

Shifted trades = removed+added pairs in the same direction within
±5 bars (cooldown displacement, not a genuinely new/lost signal).
"""
import sys

import pandas as pd


def _metrics(df):
    r = df["r_multiple"]
    gains, losses = r[r > 0].sum(), -r[r <= 0].sum()
    cum = r.cumsum()
    return dict(trades=len(df), total_r=r.sum(),
                pf=gains / max(losses, 1e-9),
                wr=(r > 0).mean() * 100 if len(df) else 0.0,
                max_dd=(cum.cummax() - cum).max() if len(cum) else 0.0)


def diff_books(control_csv, candidate_csv, bar_minutes, split="2026-01-29"):
    ctrl, cand = pd.read_csv(control_csv), pd.read_csv(candidate_csv)
    for df in (ctrl, cand):
        df["_t"] = pd.to_datetime(df["entry_time"], utc=True, format="mixed")
        df["_key"] = df["entry_time"].astype(str) + "|" + df["direction"]

    added = cand[~cand["_key"].isin(ctrl["_key"])].copy()
    removed = ctrl[~ctrl["_key"].isin(cand["_key"])].copy()

    # cooldown displacement: same-direction removed/added within ±5 bars
    tol = pd.Timedelta(minutes=5 * bar_minutes)
    shifted = 0
    rem_pool = removed.copy()
    for _, a in added.iterrows():
        m = rem_pool[(rem_pool["direction"] == a["direction"])
                     & ((rem_pool["_t"] - a["_t"]).abs() <= tol)]
        if len(m):
            shifted += 1
            rem_pool = rem_pool.drop(m.index[0])

    mc, mk = _metrics(ctrl), _metrics(cand)
    split_ts = pd.Timestamp(split, tz="UTC")
    halves = (cand[cand["_t"] < split_ts]["r_multiple"].sum(),
              cand[cand["_t"] >= split_ts]["r_multiple"].sum())
    hour_hist = None
    if len(added):
        added["dec_hour"] = (added["_t"]
                             - pd.Timedelta(minutes=bar_minutes)).dt.hour
        hour_hist = added.groupby("dec_hour")["r_multiple"] \
                         .agg(["count", "sum"]).round(2)
    return dict(
        control=mc, candidate=mk,
        delta_r=mk["total_r"] - mc["total_r"],
        delta_pf=mk["pf"] - mc["pf"],
        delta_dd=mk["max_dd"] - mc["max_dd"],
        delta_trades=mk["trades"] - mc["trades"],
        added_n=len(added), added_r=added["r_multiple"].sum(),
        removed_n=len(removed), removed_r=removed["r_multiple"].sum(),
        shifted=shifted, halves=halves, added_by_hour=hour_hist,
    )


if __name__ == "__main__":
    d = diff_books(sys.argv[1], sys.argv[2], int(sys.argv[3]))
    c, k = d["control"], d["candidate"]
    print(f"control  : {c['trades']:4d} trades  {c['total_r']:+7.1f}R  "
          f"PF {c['pf']:.2f}  WR {c['wr']:.1f}%  DD {c['max_dd']:.1f}")
    print(f"candidate: {k['trades']:4d} trades  {k['total_r']:+7.1f}R  "
          f"PF {k['pf']:.2f}  WR {k['wr']:.1f}%  DD {k['max_dd']:.1f}")
    print(f"ΔR {d['delta_r']:+.1f}  ΔPF {d['delta_pf']:+.2f}  "
          f"ΔDD {d['delta_dd']:+.1f}  Δtrades {d['delta_trades']:+d}")
    print(f"added {d['added_n']} ({d['added_r']:+.1f}R)  "
          f"removed {d['removed_n']} ({d['removed_r']:+.1f}R)  "
          f"shifted≈{d['shifted']}")
    print(f"candidate halves: H1 {d['halves'][0]:+.1f}R  H2 {d['halves'][1]:+.1f}R")
    if d["added_by_hour"] is not None:
        print("\nadded trades by decision hour:")
        print(d["added_by_hour"].to_string())