foxhunt/scripts/surfer/phase1_signals.py

#!/usr/bin/env python3
"""Phase 1 — hunt & validate NEW crypto signals; build the linear-blend baseline RL must beat.

Each candidate is theoretically distinct from momentum (different driver), run through the same
gauntlet that killed carry/low-vol: PIT universe (top-50 by dollar-vol, dead coins in), death-excl,
~10bp cost, full/IS/OOS Sharpe, CPCV-median, coin-bootstrap (frac>0), and CORRELATION to momentum.
Survivors (CPCVmed>0 & OOS>0 & bootstrap frac>0>=0.8) -> linear blend = the baseline to beat.
"""
import math
import os
import sys

import numpy as np

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import pit_sweep  # noqa: E402
from signal_sweep import xs_weights, pnl_w, validate, sharpe_t  # noqa: E402
import torch  # noqa: E402

DEV = "cuda" if torch.cuda.is_available() else "cpu"
TOPK = 50


def roll(fn, X, L):
    out = np.full_like(X, np.nan)
    for t in range(L, len(X)):
        out[t] = fn(X[t - L:t], axis=0)
    return out


def trailing(lc, L):
    out = np.full_like(lc, np.nan); out[L:] = lc[L:] - lc[:-L]; return out


def main():
    syms, days, close, qv, fund = pit_sweep.load()
    T, N = close.shape
    lc = np.log(close)
    R = np.zeros((T, N)); R[1:] = lc[1:] - lc[:-1]; R = np.where(np.isfinite(R), R, 0.0)
    fund = np.where(np.isfinite(fund), fund, 0.0)
    qv = np.nan_to_num(qv)
    dv30 = roll(np.mean, qv, 30)
    tradeable = np.ones((T, N), bool)
    for j in range(N):
        idx = np.where(np.isfinite(close[:, j]))[0]
        if len(idx):
            tradeable[max(0, idx[-1] - 4):idx[-1] + 1, j] = False
    Reff = np.where(tradeable, R - fund, 0.0)
    univ = np.zeros((T, N), bool)
    for t in range(T):
        elig = np.where((dv30[t] > 0) & np.isfinite(close[t]))[0]
        if len(elig):
            univ[t, elig[np.argsort(-dv30[t, elig])[:TOPK]]] = True
    year = (1970 + days / 365.25).astype(int)

    # rolling BTC-beta -> residual returns (for residual momentum + IVOL)
    bj = syms.index("BTCUSDT")
    rb = R[:, bj]
    beta = np.zeros((T, N)); W = 60
    for t in range(W, T):
        rw = rb[t - W:t]; vb = rw.var() + 1e-12
        cov = (R[t - W:t] * rw[:, None]).mean(0) - R[t - W:t].mean(0) * rw.mean()
        beta[t] = cov / vb
    resid = R - beta * rb[:, None]
    resid_cum = np.cumsum(np.where(np.isfinite(resid), resid, 0.0), axis=0)

    def trail_arr(A, L):
        out = np.full_like(A, np.nan); out[L:] = A[L:] - A[:-L]; return out

    sigs = {
        "mom_30 (ref)": trailing(lc, 30),
        "resid_mom_30": trail_arr(resid_cum, 30),
        "MAX_lottery": -roll(np.max, R, 20),                       # short extreme-spike (lottery) coins
        "ivol_low": -roll(np.std, resid, 30),                      # low idiosyncratic vol
        "amihud_illiq": roll(np.mean, np.abs(R) / np.maximum(qv, 1.0), 30),  # illiquidity premium
        "accel": trailing(lc, 10) - trailing(lc, 30),             # momentum acceleration
    }

    def book(sig):
        s = sig.copy(); s[~univ] = np.nan
        return pnl_w(xs_weights(s), Reff, cost_bp=10)

    mom_pnl = book(sigs["mom_30 (ref)"])
    rng = np.random.default_rng(3)
    print(f"\n===== PHASE 1 — candidate crypto signals (PIT top{TOPK}, death-excl, 10bp) =====")
    print(f"{'signal':>16} {'full':>6} {'IS':>6} {'OOS':>6} {'CPCVmed':>8} {'boot>0':>7} {'corr_mom':>8}")
    pnls = {}
    for nm, sg in sigs.items():
        p = book(sg); pnls[nm] = p
        v = validate(p, days, 40)
        # coin-bootstrap
        sh = []
        for _ in range(80):
            cols = rng.choice(N, size=max(N // 2, 10), replace=False)
            sub = np.full((T, N), np.nan); sub[:, cols] = sg[:, cols]
            s = sharpe_t(torch.tensor(book(sub), device=DEV, dtype=torch.float64))
            if not math.isnan(s):
                sh.append(s)
        bootp = float(np.mean(np.array(sh) > 0)) if sh else float("nan")
        a, b = mom_pnl, p; m = np.isfinite(a) & np.isfinite(b)
        corr = float(np.corrcoef(a[m], b[m])[0, 1])
        print(f"{nm:>16} {v['full']:>+6.2f} {v['is_']:>+6.2f} {v['oos']:>+6.2f} {v['med']:>+8.2f} {bootp:>7.2f} {corr:>+8.2f}")
        v["_boot"] = bootp
        sigs[nm] = (sg, v)

    # survivors -> linear blend baseline (sum of cross-sectional z-scores)
    def zc(x):
        mu = np.nanmean(x, axis=1, keepdims=True); sd = np.nanstd(x, axis=1, keepdims=True)
        return np.nan_to_num((x - mu) / np.where(sd > 0, sd, 1))
    surv = [nm for nm, (sg, v) in sigs.items() if v["med"] > 0 and v["oos"] > 0 and v.get("_boot", 0) >= 0.8]
    print(f"\nSURVIVORS (CPCVmed>0 & OOS>0 & boot>0>=0.8): {surv}")
    if len(surv) >= 2:
        blend = sum(zc(sigs[nm][0]) for nm in surv)
        bp = book(blend)
        vb = validate(bp, days, 40)
        T_ = lambda x: torch.tensor(x, device=DEV, dtype=torch.float64)
        py = " ".join(f"{y}:{sharpe_t(T_(bp[year[1:]==y])):+.2f}" for y in range(2020, 2027) if (year[1:] == y).sum() > 30)
        print(f"LINEAR-BLEND BASELINE ({len(surv)} signals): full {vb['full']:+.2f}  OOS {vb['oos']:+.2f}  CPCVmed {vb['med']:+.2f}")
        print("  per-year: " + py)
        print("  -> this is the bar an RL combiner must BEAT out-of-sample (deflated) to justify itself.")
    else:
        print("Too few survivors for a blend — RL has no signal set to combine; momentum stays solo.")


if __name__ == "__main__":
    main()