import kit, numpy as np, sys, datetime as dt
sys.stdout.reconfigure(encoding='utf-8',errors='replace')
from sklearn.ensemble import HistGradientBoostingClassifier

def run(sym,tf,sl,tp,H,label,min_year=None):
    t,o,h,l,c,v,sp=kit.load_rates(sym,tf)
    if min_year:
        k=np.array([dt.datetime.fromtimestamp(x,dt.UTC).year for x in t])>=min_year
        t,o,h,l,c,v,sp=[a[k] for a in (t,o,h,l,c,v,sp)]
    X,names,a=kit.features(t,o,h,l,c,v)
    diffs=np.abs(np.diff(np.unique(np.round(c,6)))); tick=np.median(diffs[diffs>0])
    spread=np.median(sp)*tick
    y,valid=kit.barrier_vec(h,l,c,a,sl,tp,H,spread)
    n=len(y); idx=np.arange(n)
    be=100*sl/(sl+tp)
    prob=np.full((n,3),np.nan); fold=np.full(n,-1)
    bounds=np.linspace(int(n*0.35),n,6).astype(int)
    for f in range(5):
        te0,te1=bounds[f],bounds[f+1]
        te=(idx>=te0)&(idx<te1)&valid; tr=(idx<te0-H)&valid
        if tr.sum()<8000 or te.sum()<1000: continue
        m=HistGradientBoostingClassifier(max_iter=200,learning_rate=0.06,max_depth=6,
                                         l2_regularization=1.0,random_state=0).fit(X[tr],y[tr])
        prob[te]=m.predict_proba(X[te]); fold[te]=f
    best=None
    for thr in (0.40,0.45,0.50,0.55):
        tr_i=[]; j=0
        while j<n:
            if fold[j]<0 or not np.isfinite(prob[j,0]): j+=1; continue
            p=prob[j]; pr=int(np.argmax(p))
            if pr==2 or float(np.max(p))<thr: j+=1; continue
            tr_i.append((pr==y[j],fold[j])); j+=H
        if len(tr_i)<60: continue
        w=np.array([x[0] for x in tr_i]); fo=np.array([x[1] for x in tr_i])
        wr=100*w.mean(); nT=len(w)
        se=100*np.sqrt((be/100)*(1-be/100)/nT); sig=(wr-be)/se
        pf=[100*w[fo==f].mean() for f in range(5) if (fo==f).sum()>=15]
        pos=sum(1 for x in pf if x>be)
        if best is None or sig>best[0]:
            best=(sig,thr,nT,wr,be,pf,pos,len(pf))
    if best is None: print(f"  {label:<26} too few trades"); return
    sig,thr,nT,wr,be,pf,pos,nf=best
    exp=(wr/100)*tp-(1-wr/100)*sl
    print(f"  {label:<26} thr{thr:.2f} {nT:5d} trades  win {wr:5.2f}% vs {be:5.2f}%  "
          f"edge {wr-be:+5.2f}pp ({sig:+.2f}s)  exp {exp:+.3f} ATR  folds+{pos}/{nf}")

print("=== PURGED WALK-FORWARD, SEQUENTIAL NON-OVERLAPPING TRADES ===")
print("(best-of-4 confidence thresholds shown; 'folds+' = test folds above break-even)\n")
for sym,tf,mn in (("EURUSD","16385",1999),("USDJPY","16385",1999),
                  ("XAUUSD","16385",None),("SP500","16385",None)):
    print(f"{sym} H1:")
    for sl,tp,H in ((2,2,32),(2,3,48),(2,6,128)):
        run(sym,tf,sl,tp,H,f"{sl}:{tp} h{H}",mn)
    print()