"""Valida il PairsWorker: replay bar-per-bar sui dati storici == backtest pairs_sim?

Come validate_worker_mr01 per MR01: alimenta il PairsWorker con finestre trailing
crescenti (simula il feed live) e confronta trade/capitale finale col backtest di
riferimento scripts/analysis/pairs_research.pairs_sim. Se combaciano, la semantica
live (z-score causale, exit |z|<=z_exit o max_bars, fee 2 gambe) e' fedele.
"""
from __future__ import annotations

import shutil
import sys
import tempfile
from pathlib import Path

import pandas as pd

PROJECT_ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(PROJECT_ROOT))

from src.live.pairs_worker import PairsWorker
from scripts.analysis.pairs_research import aligned, pairs_sim
from scripts.strategies.PR01_pairs_reversion import PAIRS

WINDOW = 60         # finestra trailing minima (>= n+2): z[i] corretto, replay veloce


def replay(a: str, b: str, params: dict, data_dir: Path) -> PairsWorker:
    m = aligned(a, b)
    df_a = m[["timestamp"]].copy(); df_a["close"] = m["close_a"].values
    df_b = m[["timestamp"]].copy(); df_b["close"] = m["close_b"].values
    w = PairsWorker(a, b, "1h", params=params, fee_rt=0.001, data_dir=data_dir)
    # replay veloce: niente I/O su file / log / notifiche ad ogni tick (servono solo le metriche finali)
    w._save_state = lambda: None
    w._log = lambda *a, **k: None
    w._notify = lambda *a, **k: None
    n = w.n
    for k in range(n + 2, len(m) + 1):
        lo = max(0, k - WINDOW)
        w.tick(df_a.iloc[lo:k], df_b.iloc[lo:k])
    # chiudi eventuale posizione aperta a fine serie (come fa il backtest col troncamento)
    return w


def main():
    print("=" * 96)
    print("  VALIDAZIONE PairsWorker — replay live vs backtest pairs_sim (fee 0.20% RT/coppia)")
    print("=" * 96)
    print(f"  {'coppia':<10s}{'WORKER cap':>12s}{'trd':>5s}{'win%':>6s}  |  {'BACKTEST cap':>13s}{'trd':>5s}{'win%':>6s}  match?")
    print("  " + "-" * 88)
    # Sottoinsieme rappresentativo: il codice del worker e' identico per ogni coppia,
    # quindi 2 coppie con strutture diverse (alt/major e major/alt) bastano a provare
    # l'equivalenza. ~135s/coppia su 73k barre orarie. Per validarle tutte: usa PAIRS.
    subset = [pp for pp in PAIRS if (pp[0], pp[1]) in {("ETH", "BTC"), ("BTC", "LTC")}]
    tmp = Path(tempfile.mkdtemp(prefix="pairs_validate_"))
    try:
        for a, b, p in subset:
            w = replay(a, b, p, tmp)
            bt = pairs_sim(a, b, **p)
            bt_cap = 1000.0 * (1 + bt["ret"] / 100)
            cap_match = abs(w.capital - bt_cap) / bt_cap < 0.02 if bt_cap else False
            trd_match = abs(w.total_trades - bt["trades"]) <= max(2, bt["trades"] * 0.02)
            ok = "OK" if (cap_match and trd_match) else "DIFF"
            ww = w.total_wins / w.total_trades * 100 if w.total_trades else 0
            print(f"  {a+'/'+b:<10s}{w.capital:>12.0f}{w.total_trades:>5d}{ww:>6.1f}  |  "
                  f"{bt_cap:>13.0f}{bt['trades']:>5d}{bt['win']:>6.1f}  {ok}")
    finally:
        shutil.rmtree(tmp, ignore_errors=True)
    print("  " + "-" * 88)
    print("  match = capitale entro 2% e trade entro 2% del backtest. Differenze minime sono")
    print("  attese (gestione bar finale/troncamento), ma la semantica deve coincidere.")


if __name__ == "__main__":
    main()