PythagorasGoal/scripts/analysis/shape_ml_validate.py

"""Validazione DURA del solo edge sopravvissuto alla ricerca shape: ML walk-forward
(LogisticRegression) sulle feature di FORMA. Tutto il resto della famiglia shape e' rumore.

Candidato: BTC logit W24H12 th0.58 (FULL +219% / OOS +42% / Sharpe 2.72 / 8-9 anni+,
regge fee 0.20% RT). Prima di promuoverlo a strategia serve (metodologia obbligatoria):
  1. ROBUSTEZZA MULTI-ASSET: stessa config su BTC/ETH/LTC/SOL/ADA/XRP 1h.
  2. WALK-FORWARD ROLLING (train fisso 2y) oltre all'expanding -> niente "memoria infinita".
  3. STRESS leva 2x + slippage doppio (fee 0.20% RT) -> regge in condizioni realistiche?
  4. ROBUSTEZZA SU GRIGLIA (th, W, H) -> plateau, non picco.
  5. CORRELAZIONE col MASTER + integrazione -> e' un diversificatore (free-lunch)?

Tutto netto-fee, OOS = ultimo 30%. Conta il PnL netto, non l'accuracy (lezione squeeze).

Run:  uv run python scripts/analysis/shape_ml_validate.py
"""
from __future__ import annotations

import sys
import time
import warnings
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))

warnings.filterwarnings("ignore")

from scripts.analysis.explore_lab import get_df, evaluate, robust, FEE_RT, LEV, POS, OOS_FRAC
from scripts.analysis.shape_ml_research import ml_wf_entries, acc_oos

ASSETS = ["BTC", "ETH", "LTC", "SOL", "ADA", "XRP"]
TWO_YEARS_1H = 24 * 365 * 2          # ~17520 barre = finestra rolling 2 anni


# ---------------------------------------------------------------------------
def line(name, ents, df, fees=(0.0, 0.001, 0.002)):
    """Riga evaluate + accuracy OOS, ritorna (res, robusto?)."""
    res = evaluate(name, ents, df)
    ac = acc_oos(ents, df)
    rb = (res["full"]["ret"] > 0 and res["oos"]["ret"] > 0
          and res["sweep"][0.002] > 0 and res["sweep_oos"][0.002] > 0)
    print(f"      ^ accOOS={ac:4.1f}%  {'[ROBUST fee0.2%]' if rb else ''}")
    return res, rb


# ---------------------------------------------------------------------------
def sec_multi_asset(W=24, H=12, th=0.58):
    print("\n[1] MULTI-ASSET — logit W%dH%d th%.2f, walk-forward EXPANDING (1h):" % (W, H, th))
    ok = []
    dfs = {}
    for a in ASSETS:
        df = get_df(a, "1h"); dfs[a] = df
        ents = ml_wf_entries(df, W=W, H=H, model="logit", thresh=th)
        _, rb = line(f"{a} exp", ents, df)
        if rb:
            ok.append(a)
    print(f"    -> EXPANDING robusti (fee0.2%): {ok if ok else 'NESSUNO'}")
    return dfs, ok


def sec_rolling(dfs, W=24, H=12, th=0.58, tw=TWO_YEARS_1H):
    print("\n[2] WALK-FORWARD ROLLING — train fisso ~2 anni (%d barre), stessa config:" % tw)
    ok = []
    for a in ASSETS:
        ents = ml_wf_entries(dfs[a], W=W, H=H, model="logit", thresh=th, train_window=tw)
        _, rb = line(f"{a} roll2y", ents, dfs[a])
        if rb:
            ok.append(a)
    print(f"    -> ROLLING robusti (fee0.2%): {ok if ok else 'NESSUNO'}")
    return ok


def sec_stress(dfs, W=24, H=12, th=0.58):
    print("\n[3] STRESS — leva 2x + slippage doppio (fee 0.20% RT) su BTC/ETH:")
    print("    (la config nominale e' leva 3x fee 0.10%; qui peggioro entrambe)")
    from scripts.analysis.explore_lab import simulate
    for a in ["BTC", "ETH"]:
        ents = ml_wf_entries(dfs[a], W=W, H=H, model="logit", thresh=th)
        df = dfs[a]
        split = int(len(df) * (1 - OOS_FRAC))
        base = simulate(ents, df, fee_rt=0.001, lev=3.0)
        stress_f = simulate(ents, df, fee_rt=0.002, lev=2.0)
        stress_o = simulate(ents, df, fee_rt=0.002, lev=2.0, split=split)
        print(f"  {a}: base(3x,0.1%) FULL={base['ret']:+.0f}% Shrp={base['sharpe']:.2f} | "
              f"STRESS(2x,0.2%) FULL={stress_f['ret']:+.0f}% OOS={stress_o['ret']:+.0f}% "
              f"DD={stress_f['dd']:.0f}% Shrp={stress_f['sharpe']:.2f} "
              f"{'OK' if stress_f['ret'] > 0 and stress_o['ret'] > 0 else 'KO'}")


def sec_grid(dfs, asset="BTC"):
    print(f"\n[4] ROBUSTEZZA GRIGLIA su {asset} (plateau, non picco):")
    rob = tot = 0
    for W in (16, 24, 32):
        for H in (8, 12, 16):
            for th in (0.56, 0.58, 0.60):
                ents = ml_wf_entries(dfs[asset], W=W, H=H, model="logit", thresh=th)
                _, rb = line(f"{asset} W{W}H{H}th{th}", ents, dfs[asset])
                tot += 1; rob += rb
    print(f"    -> {asset}: {rob}/{tot} celle robuste a fee 0.2% (plateau se alta frazione)")


# ---------------------------------------------------------------------------
def shape_daily_equity(asset, IDX, W=24, H=12, th=0.58):
    """Equity giornaliera dello sleeve shape-ML (time-exit a H, non-overlap, pos 0.15,
    leva 3x, fee 0.10% RT), normalizzata sull'indice comune dei portafogli."""
    from src.data.downloader import load_data
    df = get_df(asset, "1h")
    c = df["close"].values
    ts = pd.to_datetime(df["timestamp"], unit="ms", utc=True)
    ents = ml_wf_entries(df, W=W, H=H, model="logit", thresh=th)
    n = len(c); eq = np.full(n, 1000.0); cap = 1000.0; last_exit = -1
    fee = FEE_RT * LEV
    for e in sorted(ents, key=lambda x: x["i"]):
        i, d, mb = e["i"], e["d"], e["max_bars"]
        if i <= last_exit or i + mb >= n:
            continue
        j = i + mb
        ret = (c[j] - c[i]) / c[i] * d * LEV - fee
        cap = max(cap + cap * POS * ret, 10.0)
        eq[j:] = cap; last_exit = j
    s = pd.Series(eq, index=ts).resample("1D").last().reindex(IDX).ffill().bfill()
    return s / s.iloc[0]


def sec_master_integration():
    print("\n[5] CORRELAZIONE + INTEGRAZIONE COL MASTER:")
    from scripts.analysis.combine_portfolio import (
        build_all_sleeves, port_returns, metrics, IDX, SPLIT,
    )
    sleeves = build_all_sleeves()
    # sleeve shape: BTC + ETH (i due con piu' storia/edge)
    shape = {}
    for a in ("BTC", "ETH"):
        shape[f"SH_{a}"] = shape_daily_equity(a, IDX)
    dr_master = port_returns(sleeves)                         # MASTER equal-weight attuale
    dr_shape = port_returns(shape)
    corr = float(dr_master.corr(dr_shape))
    print(f"    correlazione daily MASTER vs sleeve-shape: {corr:+.3f}")
    # correlazione media shape vs ogni sleeve esistente
    cs = {k: float(port_returns({k: v}).corr(dr_shape)) for k, v in sleeves.items()}
    print("    corr shape vs singole sleeve: " + ", ".join(f"{k}={v:+.2f}" for k, v in cs.items()))

    base = {**sleeves}
    ext = {**sleeves, **shape}
    fb, ob = metrics(port_returns(base)), metrics(port_returns(base), lo=SPLIT)
    fe, oe = metrics(port_returns(ext)), metrics(port_returns(ext), lo=SPLIT)
    print("    %-22s %9s %6s %6s %6s | %9s %6s %6s %6s" %
          ("portafoglio", "FULLret", "CAGR", "DD", "Shrp", "OOSret", "CAGR", "DD", "Shrp"))
    print("    %-22s %+9.0f %6.0f %6.1f %6.2f | %+9.0f %6.0f %6.1f %6.2f" %
          ("MASTER (9 sleeve)", fb["ret"], fb["cagr"], fb["dd"], fb["sharpe"],
           ob["ret"], ob["cagr"], ob["dd"], ob["sharpe"]))
    print("    %-22s %+9.0f %6.0f %6.1f %6.2f | %+9.0f %6.0f %6.1f %6.2f" %
          ("MASTER + shape", fe["ret"], fe["cagr"], fe["dd"], fe["sharpe"],
           oe["ret"], oe["cagr"], oe["dd"], oe["sharpe"]))
    better = oe["sharpe"] > ob["sharpe"] and oe["dd"] <= ob["dd"] + 1
    print(f"    -> aggiungere shape MIGLIORA il MASTER OOS (Sharpe up, DD ~stabile)? "
          f"{'SI' if better else 'NO'}")


def run():
    t0 = time.time()
    print("=" * 100)
    print("  VALIDAZIONE DURA — shape-ML (LogisticRegression walk-forward sulle feature di forma)")
    print("=" * 100)
    dfs, _ = sec_multi_asset()
    sec_rolling(dfs)
    sec_stress(dfs)
    sec_grid(dfs, "BTC")
    sec_master_integration()
    print(f"\n  tempo totale: {time.time() - t0:.0f}s")
    print("=" * 100)


if __name__ == "__main__":
    run()