"""Test log_0.5 vs head-aggressive boost curve.

log_0.5:         boost = 1.0 + 0.5 * ln(1+s)  → s=2: 1.55x, s=2.5: 1.63x, s=3: 1.69x
head_aggressive:  s>=3: 2.5x, s>=2.5: 1.97x, else log_0.5
"""
import sys, time, math
from pathlib import Path
import numpy as np
import pandas as pd

sys.path.insert(0, str(Path(__file__).parent))

print("Compiling numba kernels...")
t_jit = time.time()
from nautilus_dolphin.nautilus.alpha_asset_selector import compute_irp_nb, compute_ars_nb, rank_assets_irp_nb
from nautilus_dolphin.nautilus.alpha_bet_sizer import compute_sizing_nb
from nautilus_dolphin.nautilus.alpha_signal_generator import check_dc_nb
_p = np.array([1.0, 2.0, 3.0], dtype=np.float64)
compute_irp_nb(_p, -1); compute_ars_nb(1.0, 0.5, 0.01)
rank_assets_irp_nb(np.ones((10, 2), dtype=np.float64), 8, -1, 5, 500.0, 20, 0.20)
compute_sizing_nb(-0.03, -0.02, -0.05, 3.0, 0.5, 5.0, 0.20, True, True, 0.0,
                  np.zeros(4, dtype=np.int64), np.zeros(4, dtype=np.int64),
                  np.zeros(5, dtype=np.float64), 0, -1, 0.01, 0.04)
check_dc_nb(_p, 3, 1, 0.75)
print(f"  JIT: {time.time() - t_jit:.1f}s")

from nautilus_dolphin.nautilus.alpha_orchestrator import NDAlphaEngine
from nautilus_dolphin.nautilus.adaptive_circuit_breaker import AdaptiveCircuitBreaker

VBT_DIR = Path(r"C:\Users\Lenovo\Documents\- DOLPHIN NG HD HCM TSF Predict\vbt_cache")
META_COLS = {'timestamp', 'scan_number', 'v50_lambda_max_velocity', 'v150_lambda_max_velocity',
             'v300_lambda_max_velocity', 'v750_lambda_max_velocity', 'vel_div',
             'instability_50', 'instability_150'}
ENGINE_KWARGS = dict(
    initial_capital=25000.0, vel_div_threshold=-0.02, vel_div_extreme=-0.05,
    min_leverage=0.5, max_leverage=5.0, leverage_convexity=3.0,
    fraction=0.20, fixed_tp_pct=0.0099, stop_pct=1.0, max_hold_bars=120,
    use_direction_confirm=True, dc_lookback_bars=7, dc_min_magnitude_bps=0.75,
    dc_skip_contradicts=True, dc_leverage_boost=1.0, dc_leverage_reduce=0.5,
    use_asset_selection=True, min_irp_alignment=0.45,
    use_sp_fees=True, use_sp_slippage=True,
    sp_maker_entry_rate=0.62, sp_maker_exit_rate=0.50,
    use_ob_edge=True, ob_edge_bps=5.0, ob_confirm_rate=0.40,
    lookback=100, use_alpha_layers=True, use_dynamic_leverage=True, seed=42,
)

acb = AdaptiveCircuitBreaker()
parquet_files = sorted(VBT_DIR.glob("*.parquet"))
acb_signals = {pf.stem: acb.get_cut_for_date(pf.stem)['signals'] for pf in parquet_files}

# Vol percentiles
all_vols = []
for pf in parquet_files[:2]:
    df = pd.read_parquet(pf)
    if 'BTCUSDT' not in df.columns: continue
    for i in range(60, len(df['BTCUSDT'].values)):
        seg = df['BTCUSDT'].values[max(0,i-50):i]
        if len(seg) < 10: continue
        rets = np.diff(seg)/seg[:-1]; v = float(np.std(rets))
        if v > 0: all_vols.append(v)
vol_p60 = float(np.percentile(all_vols, 60))

# Pre-load data
pq_data = {}
for pf in parquet_files:
    df = pd.read_parquet(pf)
    ac = [c for c in df.columns if c not in META_COLS]
    bp = df['BTCUSDT'].values if 'BTCUSDT' in df.columns else None
    dv = np.full(len(df), np.nan)
    if bp is not None:
        for i in range(50, len(bp)):
            seg = bp[max(0,i-50):i]
            if len(seg)<10: continue
            dv[i] = float(np.std(np.diff(seg)/seg[:-1]))
    pq_data[pf.stem] = (df, ac, dv)

# Boost curves
def log05(s):
    return 1.0 + 0.5 * math.log1p(s) if s >= 1.0 else 1.0

def head_aggressive(s):
    if s >= 3.0:   return 2.50
    elif s >= 2.5: return 1.97
    else:          return log05(s)

# Print boost levels
print("\nBoost levels:")
for s in [0, 0.5, 1.0, 1.5, 2.0, 2.5, 3.0]:
    print(f"  signals={s:.1f}: log05={log05(s):.2f}x  head_agg={head_aggressive(s):.2f}x")

def run(boost_fn):
    engine = NDAlphaEngine(**ENGINE_KWARGS)
    bar_idx = 0; ph = {}; peak = engine.capital; max_dd = 0.0; dstats = []
    for pf in parquet_files:
        ds = pf.stem; cs = engine.capital; ts = len(engine.trade_history)
        engine.regime_direction = -1
        engine.regime_size_mult = boost_fn(acb_signals[ds])
        engine.regime_dd_halt = False
        df, acols, dvol = pq_data[ds]
        bid = 0
        for ri in range(len(df)):
            row = df.iloc[ri]; vd = row.get("vel_div")
            if vd is None or not np.isfinite(vd): bar_idx+=1; bid+=1; continue
            prices = {}
            for ac in acols:
                p = row[ac]
                if p and p > 0 and np.isfinite(p):
                    prices[ac] = float(p)
                    if ac not in ph: ph[ac] = []
                    ph[ac].append(float(p))
            if not prices: bar_idx+=1; bid+=1; continue
            vrok = False if bid < 100 else (np.isfinite(dvol[ri]) and dvol[ri] > vol_p60)
            engine.process_bar(bar_idx=bar_idx, vel_div=float(vd), prices=prices,
                               vol_regime_ok=vrok, price_histories=ph)
            bar_idx+=1; bid+=1
        ce = engine.capital; peak = max(peak, ce)
        dd = (peak-ce)/peak*100 if peak>0 else 0; max_dd = max(max_dd, dd)
        dstats.append({'date':ds,'pnl':ce-cs,'cap':ce,'dd':dd,
                       'mult':engine.regime_size_mult,'trades':len(engine.trade_history)-ts})
    tr = engine.trade_history
    w = [t for t in tr if t.pnl_absolute>0]; l = [t for t in tr if t.pnl_absolute<=0]
    gw = sum(t.pnl_absolute for t in w) if w else 0
    gl = abs(sum(t.pnl_absolute for t in l)) if l else 0
    dr = [s['pnl']/25000*100 for s in dstats]
    return {
        'roi':(engine.capital-25000)/25000*100, 'pf':gw/gl if gl>0 else 999,
        'dd':max_dd, 'sharpe':np.mean(dr)/np.std(dr)*np.sqrt(365) if np.std(dr)>0 else 0,
        'trades':len(tr), 'wr':len(w)/len(tr)*100 if tr else 0,
        'cap':engine.capital, 'fees':engine.total_fees,
    }, dstats

# Run all 3
t0 = time.time()
print("\n=== Running baseline ===")
r_base, s_base = run(lambda s: 1.0)
print(f"  {time.time()-t0:.0f}s")

print("=== Running log_0.5 ===")
t1 = time.time()
r_log, s_log = run(log05)
print(f"  {time.time()-t1:.0f}s")

print("=== Running head_aggressive ===")
t2 = time.time()
r_head, s_head = run(head_aggressive)
print(f"  {time.time()-t2:.0f}s")

# Results
print(f"\n{'='*80}")
print(f"{'STRATEGY':<20} {'ROI%':>7} {'PF':>6} {'DD%':>6} {'SHARPE':>7} {'TRADES':>7} {'WR%':>6} {'CAPITAL':>10}")
print(f"{'='*80}")
for name, r in [("baseline", r_base), ("log_0.5", r_log), ("head_aggressive", r_head)]:
    print(f"{name:<20} {r['roi']:>+7.2f} {r['pf']:>6.3f} {r['dd']:>6.2f} {r['sharpe']:>7.2f} "
          f"{r['trades']:>7} {r['wr']:>6.1f} {r['cap']:>10.2f}")

# Per-date comparison for boost days only
print(f"\n--- BOOST DAYS COMPARISON ---")
print(f"{'DATE':<12} {'SIG':>4} {'BASE PnL':>10} {'LOG PnL':>10} {'HEAD PnL':>10} {'LOG mult':>9} {'HEAD mult':>10}")
for sb, sl, sh in zip(s_base, s_log, s_head):
    if sl['mult'] > 1.0 or sh['mult'] > 1.0:
        print(f"{sb['date']:<12} {acb_signals[sb['date']]:>4.1f} {sb['pnl']:>+10.2f} {sl['pnl']:>+10.2f} "
              f"{sh['pnl']:>+10.2f} {sl['mult']:>8.2f}x {sh['mult']:>9.2f}x")

# Overfitting: half split
mid = len(parquet_files) // 2
print(f"\n--- OVERFITTING CHECK ---")
for name, fn in [("baseline", lambda s:1.0), ("log_0.5", log05), ("head_aggressive", head_aggressive)]:
    # Just use full run stats split
    h1_pnl = sum(s['pnl'] for s in (s_base if name=="baseline" else s_log if name=="log_0.5" else s_head)[:mid])
    h2_pnl = sum(s['pnl'] for s in (s_base if name=="baseline" else s_log if name=="log_0.5" else s_head)[mid:])
    print(f"  {name:<20} H1=${h1_pnl:>+8.2f}  H2=${h2_pnl:>+8.2f}  ratio={h2_pnl/h1_pnl:.2f}" if h1_pnl != 0 else f"  {name}: H1=0")

print(f"\nDelta log_0.5:        ROI {r_base['roi']:+.2f}% -> {r_log['roi']:+.2f}% ({r_log['roi']-r_base['roi']:+.2f}%)")
print(f"Delta head_aggressive: ROI {r_base['roi']:+.2f}% -> {r_head['roi']:+.2f}% ({r_head['roi']-r_base['roi']:+.2f}%)")
print(f"Total time: {time.time()-t0:.0f}s")