import sys, os
import numpy as np
import warnings; warnings.filterwarnings('ignore')

from backtesting.framework.config import STRATEGY_NAME, ACTIVE_STRATEGY_FN, ACTIVE_PARAMS, REBAL_PARAM_NAME, load_data

try:
    from backtesting.engines.v30_causal_engine import evaluate_slice
except ImportError:
    from backtesting.engines.v30_causal_engine import evaluate_slice

def run_test_2_2():
    print("=" * 80)
    print(f" TEST 2.2: START DATE SENSITIVITY - {STRATEGY_NAME}")
    print("=" * 80)

    dc, spy, vf, daily_ret = load_data()
    
    rebal = ACTIVE_PARAMS.get(REBAL_PARAM_NAME, 60)
    # Ensure strictly ~20 offsets
    step = max(1, rebal // 20)
    offsets = list(range(0, rebal, step))[:20]
    
    print(f"Running {len(offsets)} start date offsets to sample path dependency...")
    sharpes = []
    cagrs = []
    mdds = []
    
    for off in offsets:
        c_off = ACTIVE_STRATEGY_FN(dc.iloc[off:], spy.iloc[off:], vf, daily_ret.iloc[off:], **ACTIVE_PARAMS)
        if isinstance(c_off, dict) and 'curve' in c_off:
            c_off = c_off['curve']
            
        m = evaluate_slice(c_off, "2008-01-01", "2025-12-31")
        sharpes.append(m['sharpe'])
        cagrs.append(m['cagr'])
        mdds.append(m['mdd'])
        print(".", end="", flush=True)
    print()
    
    s_mean = np.mean(sharpes)
    s_max = np.max(sharpes)
    s_min = np.min(sharpes)
    s_range = s_max - s_min
    
    c_mean = np.mean(cagrs)
    d_mean = np.mean(mdds)
    
    print(f"  Mean Sharpe: {s_mean:.4f}")
    print(f"  Mean CAGR:   {c_mean:.1f}%")
    print(f"  Mean MaxDD:  {d_mean:.1f}%")
    print(f"  Min Sharpe:  {s_min:.4f}")
    print(f"  Max Sharpe:  {s_max:.4f}")
    print(f"  Range:       {s_range:.4f}")
    
    print("-" * 80)
    if s_range < 0.20:
        print("  VERDICT: PASS (Low path dependency, structurally robust)")
    else:
        print("  VERDICT: FAIL (High path dependency, unreliable variance)")

if __name__ == "__main__":
    run_test_2_2()