Warrior_EA/research/test_context3.py

"""Settling the context score with nine instruments instead of four.

On the honest engine the Wyckoff context slope landed at +0.0239 R/trace, t +1.37, sign held
in 6 of 8 cells - too weak to trade, too consistent to dismiss. `sqxbars.py` has since made
five more instruments readable, sharing no data path with the original four: FTSE100, UK100,
WTI (two independent feeds) and USDCAD.

The test is unchanged and was fixed before any of this ran: the ORIGINAL LPS configuration
(market entry at the next bar's open, stop at the retest extreme, 2R target), scored by the
five traces of book 2 2.3 / 7.1, with the single pre-specified prediction that expR rises
monotonically with the number of agreeing traces. Nothing is tuned per instrument.

WHAT WOULD SETTLE IT EITHER WAY
-------------------------------
  real    the pooled slope holds near +0.024 with t comfortably past 2, and the new
          instruments - which had no hand in choosing anything - carry their share of it
  nothing the slope drifts toward zero as power rises, and the new instruments split evenly

The second is what a small sample of noisy cells looks like when it is finally given enough
data to speak. The five new instruments are the honest out-of-sample here: every parameter in
this test was set on the original four.

Bases on the breadth instruments use a SYNTHESISED spread and are approximate; the slope is
not, because cost is nearly uncorrelated with the context score (measured: +0.0008 R/trace).
"""
import numpy as np, sys, time
sys.stdout.reconfigure(encoding='utf-8', errors='replace')
import fills, book, breadth, test_lps2

NATIVE = ('EURUSD', 'USDJPY', 'XAUUSD', 'SP500')


def cells(tfs=('M15', 'H1')):
    for tf in tfs:
        for s in NATIVE:
            bk = fills.Book(s)
            yield s, tf, bk, book.frame(s, tf, bk), 'original'
        for s in breadth.SPREAD_BP:
            bk, f = breadth.get(s, tf)
            yield breadth.NICE[s], tf, bk, f, 'new'


if __name__ == '__main__':
    tfs = tuple(a for a in sys.argv[1:] if a in ('M15', 'H1', 'H4')) or ('M15', 'H1')
    print("=== CONTEXT SLOPE: NINE INSTRUMENTS ===")
    print("    same LPS configuration, unchanged. The five 'new' instruments had no hand")
    print("    in choosing any parameter, so they are the out-of-sample arm.\n")
    print(f"  {'sym':>9}{'tf':>5}{'set':>10}{'n':>7}   "
          + "".join(f"{k:>12}" for k in range(5)) + f"{'slope':>9}{'t':>7}{'base':>9}")
    PR, PA, PT, tag = [], [], [], []
    for s, tf, bk, f, kind in cells(tfs):
        try:
            a = test_lps2.events(s, tf, bk=bk, f=f)
        except Exception as ex:
            print(f"  {s:>9}{tf:>5}{kind:>10}   failed: {ex}")
            continue
        if a is None:
            print(f"  {s:>9}{tf:>5}{kind:>10}   - too few")
            continue
        R, ag = a['R'], a['ag']
        txt = [f"{R[ag==k].mean():+6.3f}({int((ag==k).sum()):>4})"
               if (ag == k).sum() >= 25 else f"{'-':>12}" for k in range(5)]
        sl, tt = book.slope_t(R, ag)
        print(f"  {s:>9}{tf:>5}{kind:>10}{a['n']:>7}   " + "".join(txt)
              + f"{sl:>+9.4f}{tt:>+7.2f}{R.mean():>+9.4f}")
        PR.append(R); PA.append(ag); PT.append(a['t']); tag.append((kind, sl, R.mean()))
    if not PR:
        sys.exit()

    def pooled(sel, label):
        R = np.concatenate([r for r, k in zip(PR, tag) if sel(k)])
        A = np.concatenate([a for a, k in zip(PA, tag) if sel(k)])
        sl, tt = book.slope_t(R, A)
        pos = sum(1 for k in tag if sel(k) and k[1] > 0)
        tot = sum(1 for k in tag if sel(k))
        print(f"  {label:<26} n={len(R):>7,}  slope {sl:>+8.4f}  t {tt:>+6.2f}"
              f"  base {R.mean():>+8.4f}   positive-slope cells {pos}/{tot}")
        return R, A

    print()
    Rn, An = pooled(lambda k: k[0] == 'original', 'ORIGINAL four')
    Rb, Ab = pooled(lambda k: k[0] == 'new', 'NEW five (out of sample)')
    R, A = pooled(lambda k: True, 'ALL nine')
    print()
    for k in range(6):
        m = A == k
        if m.sum() < 25:
            continue
        se = R[m].std(ddof=1) / np.sqrt(m.sum())
        print(f"    {k} agree  n={int(m.sum()):>6}  expR {R[m].mean():+7.4f} +/- {se:.4f}"
              f"   t {book.tstat(R[m]):+6.2f}")
    print("\n  The out-of-sample line is the one that matters: those five instruments")
    print("  had no hand in choosing the trigger, the traces, or any threshold.")