PythagorasGoal/scripts/strategies/MR01_bollinger_fade.py

"""MR01 — Bollinger Fade (mean-reversion).

L'UNICA famiglia con edge netto reale dopo l'analisi out-of-sample fee-aware
(vedi scripts/analysis/strategy_research.py). Contrario della tesi squeeze:
i breakout RIENTRANO, quindi si fada l'estremo verso la media.

Logica:
    1. Bollinger Band (window n, k deviazioni) sul close
    2. ENTRY: close esce sotto la banda inferiore -> long (o sopra la superiore -> short)
    3. EXIT: take-profit alla media mobile (il rientro atteso),
       stop-loss a sl_atr*ATR oltre l'estremo, oppure time-limit max_bars
    4. ingresso a close[i] (eseguibile dal vivo, nessun look-ahead)

Validazione (netto, fee 0.10% RT reale Deribit, leva 3x, OOS = ultimo 30%):
    BTC 1h n=50 k=2.5: +201% OOS, DD 15%, ~tutti gli anni positivi
    ETH 1h n=50 k=2.0: +1238% OOS, DD 23%
    Robusto su TUTTA la griglia n in {14,20,30,50} x k in {2.0,2.5,3.0}
    e su tutte le fee 0.00-0.20% RT (margine di sicurezza ampio).

NOTA LIVE: usa TP alla media + SL ad ATR + max_bars. Lo StrategyWorker attuale
esce solo a hold_bars/stop -2% fisso: per tradarla come validata il worker deve
supportare gli exit TP/SL passati in metadata (vedi metadata di ogni Signal).
"""
from __future__ import annotations
import sys
sys.path.insert(0, ".")

import numpy as np
import pandas as pd

from src.strategies.base import Strategy, Signal, BacktestResult, YearlyStats, TF_MINUTES
from src.data.downloader import load_data


def _atr(df: pd.DataFrame, n: int = 14) -> np.ndarray:
    h, l, c = df["high"].values, df["low"].values, df["close"].values
    pc = np.roll(c, 1); pc[0] = c[0]
    tr = np.maximum(h - l, np.maximum(np.abs(h - pc), np.abs(l - pc)))
    return pd.Series(tr).rolling(n).mean().values


class BollingerFade(Strategy):
    name = "MR01_bollinger_fade"
    description = "Mean-reversion: fada la banda di Bollinger, TP alla media"
    default_assets = ["BTC", "ETH"]
    default_timeframes = ["1h"]
    fee_rt = 0.001          # Deribit perp realistico (taker 0.05%/lato)
    leverage = 3.0
    position_size = 0.15
    initial_capital = 1000.0

    def generate_signals(self, df: pd.DataFrame, ts: pd.DatetimeIndex,
                         **params) -> list[Signal]:
        c = df["close"].values
        n_len = len(c)
        bb_w = params.get("bb_window", 50)
        k = params.get("k", 2.5)
        sl_atr = params.get("sl_atr", 2.0)
        max_bars = params.get("max_bars", 24)
        trend_max = params.get("trend_max")          # None = filtro disattivo
        ema_long = params.get("ema_long", 200)
        # Edge minimo: salta i segnali il cui TP (la media) è più vicino dell'entry del
        # costo round-trip -> perdenti garantiti anche colpendo il TP. 0 = off.
        min_tp_frac = params.get("min_tp_frac", 0.0)

        ma = pd.Series(c).rolling(bb_w).mean().values
        sd = pd.Series(c).rolling(bb_w).std().values
        a = _atr(df, 14)
        up, lo = ma + k * sd, ma - k * sd
        el = pd.Series(c).ewm(span=ema_long, adjust=False).mean().values if trend_max is not None else None

        signals: list[Signal] = []
        for i in range(bb_w + 14, n_len):
            if np.isnan(up[i]) or np.isnan(a[i]):
                continue
            if el is not None and (a[i] == 0 or np.isnan(el[i]) or abs(c[i] - el[i]) / a[i] > trend_max):
                continue
            if c[i] < lo[i] and c[i - 1] >= lo[i - 1]:
                d, sl = 1, c[i] - sl_atr * a[i]
            elif c[i] > up[i] and c[i - 1] <= up[i - 1]:
                d, sl = -1, c[i] + sl_atr * a[i]
            else:
                continue
            if min_tp_frac > 0 and abs(ma[i] - c[i]) / c[i] <= min_tp_frac:
                continue                              # TP entro le fee -> non eseguibile in utile
            signals.append(Signal(
                idx=i, direction=d, entry_price=c[i],
                metadata={"tp": float(ma[i]), "sl": float(sl), "max_bars": max_bars},
            ))
        return signals

    def backtest(self, asset: str, tf: str = "1h", hold: int = 3,
                 **params) -> BacktestResult | None:
        """Backtest fedele: TP alla media / SL ad ATR / time-limit, fee+leva nette."""
        df = load_data(asset, tf)
        ts = pd.to_datetime(df["timestamp"], unit="ms", utc=True)
        signals = self.generate_signals(df, ts, **params)
        if not signals:
            return None

        h, l, c = df["high"].values, df["low"].values, df["close"].values
        n = len(c)
        fee = self.fee_rt * self.leverage
        capital = peak = float(self.initial_capital)
        max_dd = 0.0
        total_bars = 0
        last_exit = -1
        yearly: dict[int, dict] = {}

        for sig in signals:
            i, d = sig.idx, sig.direction
            if i <= last_exit or i + 1 >= n:
                continue
            entry = c[i]
            tp, sl, mb = sig.metadata["tp"], sig.metadata["sl"], sig.metadata["max_bars"]
            exit_p = c[min(i + mb, n - 1)]
            j = min(i + mb, n - 1)
            for step in range(1, mb + 1):
                j = i + step
                if j >= n:
                    j = n - 1; exit_p = c[j]; break
                hit_sl = (d == 1 and l[j] <= sl) or (d == -1 and h[j] >= sl)
                hit_tp = (d == 1 and h[j] >= tp) or (d == -1 and l[j] <= tp)
                if hit_sl:
                    exit_p = sl; break
                if hit_tp:
                    exit_p = tp; break
                if step == mb:
                    exit_p = c[j]

            ret = (exit_p - entry) / entry * d * self.leverage - fee
            capital = max(capital + capital * self.position_size * ret, 10.0)
            if capital > peak:
                peak = capital
            max_dd = max(max_dd, (peak - capital) / peak)
            total_bars += (j - i)
            last_exit = j

            year = ts.iloc[i].year
            yr = yearly.setdefault(year, {"w": 0, "t": 0, "pnl": 0.0})
            yr["t"] += 1
            if ret > 0:
                yr["w"] += 1
            yr["pnl"] += ret * self.initial_capital

        all_t = sum(v["t"] for v in yearly.values())
        all_w = sum(v["w"] for v in yearly.values())
        if all_t == 0:
            return None

        yearly_stats = [YearlyStats(y, v["t"], v["w"], v["pnl"]) for y, v in sorted(yearly.items())]
        return BacktestResult(
            strategy_name=self.name, asset=asset, timeframe=tf, params=params,
            trades=all_t, wins=all_w, pnl=sum(v["pnl"] for v in yearly.values()),
            capital=capital, initial_capital=self.initial_capital,
            max_dd=max_dd * 100, time_in_market_pct=total_bars / n * 100,
            avg_trade_duration_h=total_bars / all_t * TF_MINUTES.get(tf, 60) / 60,
            years_active=len(yearly), yearly=yearly_stats,
        )


if __name__ == "__main__":
    strat = BollingerFade()
    print(f"{'=' * 110}")
    print(f"  MR01 BOLLINGER FADE — netto fee {strat.fee_rt*100:.2f}% RT, leva {strat.leverage:.0f}x")
    print(f"{'=' * 110}")
    results = []
    for asset in ["BTC", "ETH"]:
        for k in [2.0, 2.5]:
            r = strat.backtest(asset, "1h", bb_window=50, k=k, sl_atr=2.0, max_bars=24)
            if r:
                r.strategy_name = f"MR01 {asset} 1h n50 k{k}"
                results.append(r)
    for r in results:
        r.print_summary()
    if results:
        results[0].print_yearly()