"""
Full dataset comparison: old-ACT (broken) vs FIX (gidx increment for NaN rows).
Verifies FIX produces T=2155.
"""
import sys, math, pathlib
import numpy as np
import pandas as pd

sys.path.insert(0, '/mnt/dolphinng5_predict')
sys.path.insert(0, '/mnt/dolphinng5_predict/nautilus_dolphin')

print("Importing...", flush=True)
from nautilus_dolphin.nautilus.proxy_boost_engine import create_boost_engine
print("Import done.", flush=True)

PARQUET_DIR = pathlib.Path('/mnt/dolphinng5_predict/vbt_cache')
VOL_P60_INWINDOW = 0.00009868

ENG_KWARGS = dict(
    max_hold_bars=120, min_irp_alignment=0.45, max_leverage=8.0,
    vel_div_threshold=-0.02, vel_div_extreme=-0.05,
    min_leverage=0.5, leverage_convexity=3.0,
    fraction=0.20, fixed_tp_pct=0.0095, stop_pct=1.0,
    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, 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,
)

def make_engine(cap=25000.0):
    return create_boost_engine(mode='d_liq', initial_capital=cap, **ENG_KWARGS)

def compute_vol_ok(df):
    btc_f = df['BTCUSDT'].values.astype('float64')
    n = len(btc_f)
    vol_ok = np.zeros(n, dtype=bool)
    for j in range(50, n):
        seg = btc_f[max(0, j-50):j]
        diffs = np.diff(seg)
        denom = seg[:-1]
        if np.any(denom == 0):
            continue
        v = float(np.std(diffs / denom))
        if math.isfinite(v) and v > 0:
            vol_ok[j] = v > VOL_P60_INWINDOW
    return vol_ok

def run_day(df, date_str, eng, fix_nan_gidx):
    """fix_nan_gidx=True → increment _global_bar_idx for NaN rows (correct behavior)."""
    eng.begin_day(date_str)
    btc_f = df['BTCUSDT'].values.astype('float64')
    vol_ok = compute_vol_ok(df)
    trades = 0
    data_arr = df.values
    cols = df.columns.tolist()

    usdt_cols = [c for c in cols if c.endswith('USDT')]
    vd_idx = cols.index('vel_div') if 'vel_div' in cols else -1
    v50_idx = cols.index('v50_lambda_max_velocity') if 'v50_lambda_max_velocity' in cols else -1
    v750_idx = cols.index('v750_lambda_max_velocity') if 'v750_lambda_max_velocity' in cols else -1
    i50_idx = cols.index('instability_50') if 'instability_50' in cols else -1
    usdt_idxs = [(c, cols.index(c)) for c in usdt_cols]

    for i in range(len(df)):
        row_vals = data_arr[i]

        vd_raw = float(row_vals[vd_idx]) if vd_idx != -1 else float('nan')
        if not math.isfinite(vd_raw):
            if fix_nan_gidx:
                eng._global_bar_idx += 1
            continue

        v750 = float(row_vals[v750_idx]) if v750_idx != -1 and math.isfinite(float(row_vals[v750_idx])) else 0.0
        inst50 = float(row_vals[i50_idx]) if i50_idx != -1 and math.isfinite(float(row_vals[i50_idx])) else 0.0
        v50 = float(row_vals[v50_idx]) if v50_idx != -1 and math.isfinite(float(row_vals[v50_idx])) else 0.0
        prices = {}
        for sym, ci in usdt_idxs:
            p = float(row_vals[ci])
            if math.isfinite(p) and p > 0:
                prices[sym] = p

        prev_pos = eng.position

        if hasattr(eng, 'pre_bar_proxy_update'):
            eng.pre_bar_proxy_update(inst50, v750)

        eng.step_bar(
            bar_idx=i,
            vel_div=vd_raw,
            prices=prices,
            v50_vel=v50,
            v750_vel=v750,
            vol_regime_ok=bool(vol_ok[i]),
        )

        if prev_pos is not None and eng.position is None:
            trades += 1

    eng.end_day()
    return trades

def main():
    files = sorted(PARQUET_DIR.glob('*.parquet'))
    print(f"Days: {len(files)}", flush=True)

    act_eng = make_engine()
    fix_eng = make_engine()
    act_T = fix_T = 0

    for pf in files:
        date_str = pf.stem
        df = pd.read_parquet(pf)

        ta = run_day(df, date_str, act_eng, fix_nan_gidx=False)
        tf = run_day(df, date_str, fix_eng, fix_nan_gidx=True)
        act_T += ta; fix_T += tf

        gap = fix_T - act_T
        print(f"{date_str}: ACT+{ta:3d}(cum={act_T:4d} ${act_eng.capital:8.0f})  "
              f"FIX+{tf:3d}(cum={fix_T:4d} ${fix_eng.capital:8.0f})  gap={gap:+d}", flush=True)

    ic = 25000.0
    print(f"\nACT: T={act_T}, cap=${act_eng.capital:.2f}, ROI={100*(act_eng.capital/ic-1):.2f}%", flush=True)
    print(f"FIX: T={fix_T}, cap=${fix_eng.capital:.2f}, ROI={100*(fix_eng.capital/ic-1):.2f}%", flush=True)

if __name__ == '__main__':
    main()