PythagorasGoal/scripts/analysis/fade_tf_sweep.py

"""FADE TF SWEEP — i fade MR01/02/07 su 1m/2m/5m/10m/30m (oltre a 15m live e 1h).

Ricerca 2026-06-12 (post-swap 15m). Diario: docs/diary/2026-06-12-fade-tf-sweep.md.

Due banchi di prova:
  A. STORIA COMPLETA (parquet locale; 10m = resample dal 5m): engine canonico
     build_trades, daily equity su IDX comune, OOS da 2024-10, fee 0.10% e 2x.
  B. FINESTRA COMUNE RECENTE (2026-02-12 -> 06-12): 1m/2m (fetch Cerbero, non
     esiste storia locale 1m: il refresh la esclude per costo) vs 5m/15m sugli
     STESSI 120 giorni — confronto apples-to-apples sul regime corrente.

Esiti:
  - La frontiera Sharpe e' MONOTONA al scendere del tf per MR01/MR07 (full
    history OOS: 5m > 10m > 15m > 30m > 1h)... ma il margine fee si assottiglia
    insieme: a fee 2x MR02_BTC muore a 5m (-1.70) e resta fragile a 10m (0.32).
  - MR02 (donchian, 3-6x i trade degli altri) sotto i 15m muore di fee nel
    regime corrente: 1m -64%, 2m -44%, 5m -22% sulla finestra recente.
  - 1m/2m: SCARTATI. MR01 a 1m brilla sulla finestra recente (ETH +60%, Sh 5.7)
    ma muore a fee 2x, il flat-share 1m e' alto (ETH 25.6%, BTC 13.3% -> rischio
    stale-print) e la validazione full-history e' impraticabile (storia 1m non
    mantenuta). Il regime recente e' CALMO: anche il 5m vi e' fiacco — i tf
    veloci pagano nella volatilita', non nella calma.
  - 10m: il miglior candidato OLTRE il 15m (quasi l'edge del 5m con piu' margine
    fee; corr daily col 15m live 0.53 media). Eventuale ADD da gateare in
    futuro, NON ora: il 15m e' appena andato live (v1.1.30), un cambio alla volta.
  - VERDETTO: tenere il 15m (ginocchio della frontiera margine-fee/rendimento);
    10m in watchlist; 1m/2m chiusi; 5m no-swap (fee-fragile su MR02_BTC).

    uv run python scripts/analysis/fade_tf_sweep.py
"""
from __future__ import annotations

import sys
from pathlib import Path

import numpy as np
import pandas as pd

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

from src.data.downloader import load_data
from scripts.analysis.risk_management import strats_for, build_trades, INIT, POS
from scripts.analysis.combine_portfolio import IDX, SPLIT, _norm, metrics

EPOCH = pd.Timestamp(0, tz="UTC")
WINDOW_START = "2026-02-12"          # finestra comune del banco B
RECENT_1M = {a: Path(f"/tmp/{a.lower()}_1m_recent.parquet") for a in ("BTC", "ETH")}


def resample_ohlcv(df: pd.DataFrame, minutes: int) -> pd.DataFrame:
    """Resample OHLCV unit-safe (pandas 2.x conserva datetime64[ms]: niente
    aritmetica diretta su .view int64 — il //10**6 doppio manda i ts nel 1970)."""
    ts = pd.to_datetime(df["timestamp"], unit="ms", utc=True)
    g = df.set_index(ts).resample(f"{minutes}min")
    out = pd.DataFrame({"open": g["open"].first(), "high": g["high"].max(),
                        "low": g["low"].min(), "close": g["close"].last(),
                        "volume": g["volume"].sum()}).dropna()
    out["timestamp"] = (out.index - EPOCH) // pd.Timedelta(milliseconds=1)
    return out.reset_index(drop=True)


def daily_eq(df: pd.DataFrame, fn, params, fee_rt: float = 0.001) -> tuple[pd.Series, int]:
    ts = pd.to_datetime(df["timestamp"], unit="ms", utc=True)
    trades = build_trades(fn(df, **params), df, fee_rt=fee_rt, trend_max=3.0)
    n = len(df)
    eq = np.full(n, INIT)
    cap = INIT
    for i, j, ret in sorted(trades, key=lambda t: t[1]):
        cap = max(cap + cap * POS * ret, 10.0)
        eq[j:] = cap
    s = pd.Series(eq, index=ts).resample("1D").last().reindex(IDX).ffill().bfill()
    return _norm(s), len(trades)


def full_history() -> None:
    print("=== A. STORIA COMPLETA (OOS da 2024-10, fee 0.10% RT; f2x = OOS Sharpe a fee 2x) ===")
    print(f"{'tf':<5} {'sleeve':<10} {'FULL%':>10} {'DD%':>6} {'Sh':>6} | {'OOS%':>8} {'oDD%':>6} {'oSh':>6} | {'f2x_oSh':>7} {'n':>6}")
    for tf in ("5m", "10m", "15m", "30m"):
        for asset in ("BTC", "ETH"):
            df = resample_ohlcv(load_data(asset, "5m"), 10) if tf == "10m" else load_data(asset, tf)
            for nm, (fn, params) in strats_for(asset).items():
                eq, n = daily_eq(df, fn, params)
                r = eq.pct_change().fillna(0.0)
                f, o = metrics(r), metrics(r, lo=SPLIT)
                eq2, _ = daily_eq(df, fn, params, fee_rt=0.002)
                o2 = metrics(eq2.pct_change().fillna(0.0), lo=SPLIT)
                print(f"{tf:<5} {nm + '_' + asset:<10} {f['ret']:>10.0f} {f['dd']:>6.1f} {f['sharpe']:>6.2f}"
                      f" | {o['ret']:>8.0f} {o['dd']:>6.1f} {o['sharpe']:>6.2f} | {o2['sharpe']:>7.2f} {n:>6}")
        print()


def trade_stats(df: pd.DataFrame, fn, params, fee_rt: float = 0.001) -> dict:
    trades = build_trades(fn(df, **params), df, fee_rt=fee_rt, trend_max=3.0)
    cap = peak = INIT
    dd = 0.0
    rets = []
    wins = 0
    for i, j, ret in sorted(trades, key=lambda t: t[1]):
        cap = max(cap + cap * POS * ret, 10.0)
        peak = max(peak, cap)
        dd = max(dd, (peak - cap) / peak)
        rets.append(ret * POS)
        wins += ret > 0
    n = len(trades)
    sh = float(np.mean(rets) / np.std(rets) * np.sqrt(n)) if n > 1 and np.std(rets) > 0 else 0.0
    return dict(ret=(cap / INIT - 1) * 100, dd=dd * 100, n=n,
                wr=wins / n * 100 if n else 0.0, sh=sh)


def recent_window() -> None:
    if not all(p.exists() for p in RECENT_1M.values()):
        print("\n=== B. saltato: manca il parquet 1m recente (fetch Cerbero, vedi diario) ===")
        return
    start_ms = int(pd.Timestamp(WINDOW_START, tz="UTC").timestamp() * 1000)
    data: dict[tuple[str, str], pd.DataFrame] = {}
    for asset in ("BTC", "ETH"):
        m1 = pd.read_parquet(RECENT_1M[asset]).sort_values("timestamp").reset_index(drop=True)
        data[(asset, "1m")] = m1
        data[(asset, "2m")] = resample_ohlcv(m1, 2)
        for tf in ("5m", "15m"):
            df = load_data(asset, tf)
            data[(asset, tf)] = df[df["timestamp"] >= start_ms].reset_index(drop=True)

    print(f"\n=== B. FINESTRA COMUNE {WINDOW_START} -> oggi (regime corrente) ===")
    print("flat share (O=H=L=C):")
    for (asset, tf), df in sorted(data.items()):
        fl = ((df["open"] == df["high"]) & (df["high"] == df["low"]) & (df["low"] == df["close"])).mean() * 100
        print(f"  {asset} {tf:>3}: {fl:5.1f}%")
    print(f"\n{'tf':<4} {'sleeve':<10} {'ret%':>8} {'DD%':>6} {'n':>5} {'WR%':>5} {'Sh_tr':>6} | {'fee2x_ret%':>10}")
    for tf in ("1m", "2m", "5m", "15m"):
        for asset in ("BTC", "ETH"):
            for nm, (fn, params) in strats_for(asset).items():
                r1 = trade_stats(data[(asset, tf)], fn, params)
                r2 = trade_stats(data[(asset, tf)], fn, params, fee_rt=0.002)
                print(f"{tf:<4} {nm + '_' + asset:<10} {r1['ret']:>8.1f} {r1['dd']:>6.1f} {r1['n']:>5}"
                      f" {r1['wr']:>5.1f} {r1['sh']:>6.2f} | {r2['ret']:>10.1f}")
        print()


def correlations() -> None:
    print("=== C. corr daily (storia completa) vs twin 15m LIVE ===")
    c5s, c10s = [], []
    for asset in ("BTC", "ETH"):
        d15, d5 = load_data(asset, "15m"), load_data(asset, "5m")
        d10 = resample_ohlcv(d5, 10)
        for nm, (fn, params) in strats_for(asset).items():
            e15 = daily_eq(d15, fn, params)[0].pct_change()
            c5 = daily_eq(d5, fn, params)[0].pct_change().corr(e15)
            c10 = daily_eq(d10, fn, params)[0].pct_change().corr(e15)
            c5s.append(c5)
            c10s.append(c10)
            print(f"  {nm}_{asset:<4} 5m-15m {c5:.2f}  10m-15m {c10:.2f}")
    print(f"  media: 5m-15m {np.mean(c5s):.2f} | 10m-15m {np.mean(c10s):.2f}")


if __name__ == "__main__":
    full_history()
    recent_window()
    correlations()