foxhunt/scripts/surfer/crypto_trend_sizing.py

#!/usr/bin/env python3
"""Crypto TS-trend sizing — reconfirm the validated return engine + find the deployable CAGR.

The TSMOM crypto sleeve is VALIDATED (memory: Sharpe ~1.23, CAGR 75.7% @ 61% vol, corr~0 to funding).
The 76% CAGR is just 61%-vol sizing, not a free lunch. This re-runs the SAME pre-registered config
(LONG/FLAT, lookbacks 20/60/120, on crypto_pit daily close, liquidity floor on qvol) and sweeps a
vol-target overlay to answer the #2 question: at a SANE vol target, what is the deployable CAGR and
does the Sharpe hold (it should — vol-target is a rescale, but per-period sizing adds timing).

NOT a search: the 20/60/120 long/flat config is replicated verbatim from the validated harness.
"""
import glob
import math

import numpy as np

PIT = "data/surfer/crypto_pit"
LOOKBACKS = [20, 60, 120]
COST_BP = 5.0
ADV_FLOOR = 5e6          # $5M trailing quote-volume liquidity floor
VOL_TARGETS = [0.10, 0.15, 0.20]
LEV_CAP = 3.0
PPY = 365                # crypto trades every day


def build():
    days = set()
    raw = {}
    for f in sorted(glob.glob(f"{PIT}/*.npz")):
        d = np.load(f)
        if len(d["day"]) < 130:
            continue
        sym = f.split("/")[-1][:-4]
        raw[sym] = {int(dd): (c, q) for dd, c, q in zip(d["day"], d["close"], d["qvol"])}
        days.update(int(x) for x in d["day"])
    days = sorted(days)
    di = {d: i for i, d in enumerate(days)}
    syms = sorted(raw)
    C = np.full((len(days), len(syms)), np.nan)
    V = np.full((len(days), len(syms)), np.nan)
    for j, s in enumerate(syms):
        for dd, (c, q) in raw[s].items():
            C[di[dd], j] = c; V[di[dd], j] = q
    return np.array(days), syms, C, V


def maxdd(equity):
    peak = np.maximum.accumulate(equity)
    return float((equity / peak - 1).min())


def run():
    days, syms, C, V = build()
    T, N = C.shape
    logC = np.log(C)
    ret = np.full((T, N), np.nan)
    ret[1:] = C[1:] / C[:-1] - 1.0
    # long/flat signal = mean over lookbacks of 1[trailing-L log return > 0]
    sig = np.zeros((T, N))
    cnt = np.zeros((T, N))
    for L in LOOKBACKS:
        tr = np.full((T, N), np.nan)
        tr[L:] = logC[L:] - logC[:-L]
        on = np.where(np.isfinite(tr), (tr > 0).astype(float), np.nan)
        m = np.isfinite(on)
        sig[m] += on[m]; cnt[m] += 1
    sig = np.where(cnt > 0, sig / np.maximum(cnt, 1), 0.0)   # 0..1 long/flat conviction

    print(f"\n===== CRYPTO TS-TREND SIZING (long/flat {LOOKBACKS}, ${ADV_FLOOR/1e6:.0f}M ADV floor, {COST_BP}bp/leg) =====")
    print(f"panel: {T} days x {N} coins  (survivorship-free incl. dead)\n")

    # base book (gross 1, daily rebalance, equal-weight by conviction among liquid+on coins)
    w_prev = np.zeros(N)
    book = np.zeros(T)
    for t in range(1, T):
        eligible = np.isfinite(ret[t]) & np.isfinite(V[t - 1]) & (V[t - 1] > ADV_FLOOR)
        s = sig[t - 1] * eligible
        g = s.sum()
        w = s / g if g > 0 else np.zeros(N)
        turn = np.abs(w - w_prev).sum()
        book[t] = float(np.nansum(w * ret[t])) - turn * COST_BP / 1e4
        w_prev = w

    valid = np.arange(T) > max(LOOKBACKS)
    base = book[valid]
    base_sr = base.mean() / base.std() * math.sqrt(PPY) if base.std() > 0 else float("nan")
    base_vol = base.std() * math.sqrt(PPY)
    base_cagr = float(np.prod(1 + base) ** (PPY / len(base)) - 1)
    print(f"BASE (un-vol-targeted): Sharpe {base_sr:+.2f}  vol {base_vol*100:.0f}%  CAGR {base_cagr*100:+.1f}%  maxDD {maxdd(np.cumprod(1+base))*100:.1f}%")
    print(f"  (memory reference: Sharpe ~1.23, CAGR ~76% @ ~61% vol — replicating)\n")

    print(f"{'vol_tgt':>8} {'Sharpe':>7} {'CAGR':>7} {'real_vol':>9} {'maxDD':>7} {'avg_lev':>8} {'per-year SR':>30}")
    print("-" * 86)
    # vol-target overlay on the base book (trailing 30d realized, lagged, leverage-capped)
    rv = np.full(T, np.nan)
    for t in range(31, T):
        w = book[t - 30:t]
        rv[t] = w.std() * math.sqrt(PPY)
    yrs = 1970 + days // 365
    for vt in VOL_TARGETS:
        lev = np.where(np.isfinite(rv) & (rv > 0), np.clip(vt / rv, 0, LEV_CAP), 0.0)
        tgt = book * np.concatenate([[0], lev[:-1]])   # lag leverage by 1 day
        s = tgt[valid]
        sr = s.mean() / s.std() * math.sqrt(PPY) if s.std() > 0 else float("nan")
        vol = s.std() * math.sqrt(PPY)
        cagr = float(np.prod(1 + s) ** (PPY / len(s)) - 1)
        dd = maxdd(np.cumprod(1 + s))
        avglev = float(np.mean(lev[valid]))
        yv = {}
        for r, y in zip(s, yrs[valid]):
            yv.setdefault(int(y), []).append(r)
        ystr = " ".join(f"{y}:{(np.mean(v)/(np.std(v)+1e-12)*math.sqrt(PPY)):+.1f}"
                        for y, v in sorted(yv.items()) if len(v) >= 30)
        print(f"{vt*100:>6.0f}% {sr:>+7.2f} {cagr*100:>+6.1f}% {vol*100:>8.0f}% {dd*100:>+6.1f}% {avglev:>8.2f}   {ystr}")
    print("-" * 86)
    print("Deployable read: pick the vol target whose maxDD you can stomach; Sharpe should ~hold across targets.")


if __name__ == "__main__":
    run()