import pandas as pd, numpy as np, glob
from scipy import stats

arm_a = pd.read_parquet('/mnt/d/Resonance_Engine/traj/tension_20260607T130445/arm_A_no_inject.parquet')
arm_t = pd.read_parquet('/mnt/d/Resonance_Engine/traj/tension_20260607T130445/arm_T_tension.parquet')

files = sorted(glob.glob('/mnt/d/PaperTrader/research/hl_data/minutes/202604*/*.parquet'))
pdf = pd.concat([pd.read_parquet(f) for f in files], ignore_index=True)
pdf = pdf[pdf.coin=='BTC'].sort_values('minute').reset_index(drop=True)
pdf['fwd_60']  = (pdf['mid_price'].shift(-60)/pdf['mid_price']-1)*10000
pdf['sign_60'] = pdf['fwd_60'].apply(lambda x: 1 if x>0 else -1)

for label, arm in [('ARM_A_freerun', arm_a), ('ARM_T_driven', arm_t)]:
    arm = arm.copy().sort_values('minute').reset_index(drop=True)
    arm['asym_d240'] = arm['asymmetry'].diff(240)
    arm['coh_d240']  = arm['coherence'].diff(240)
    arm['vel_d60']   = arm['vel_max'].diff(60)
    merged = arm.merge(pdf[['minute','fwd_60','sign_60']], on='minute', how='inner')
    merged = merged.dropna(subset=['asym_d240','fwd_60'])
    n = len(merged)
    test = merged.iloc[int(n*0.7):]
    for feat in ['asym_d240','coh_d240','vel_d60']:
        if feat not in test.columns: continue
        t2 = test.dropna(subset=[feat])
        pred = t2[feat].apply(lambda x: 1 if x>0 else -1)
        acc = (pred == t2['sign_60']).mean()
        r, p = stats.spearmanr(t2[feat], t2['fwd_60'])
        print(f'{label} {feat}: dacc={acc*100:.1f}%  r={r:+.4f}  p={p:.2e}  n={len(t2)}')
    print()