# -*- coding: utf-8 -*-
"""Diagnosa fit GARCH pada return padat-train XAUUSD M15."""
import os
import sys
import numpy as np
import datetime as dt

HERE = os.path.dirname(os.path.abspath(__file__))
SRC = os.path.normpath(os.path.join(HERE, "..", "..", "SniperGold_ML"))
sys.path.insert(0, SRC)
import train_regime as TR

BASE = os.path.normpath(os.path.join(HERE, "..", "..", "..", "Files", "AlgoForge", "Data"))
z = np.load(os.path.join(BASE, "XAUUSD_M15.npz"))
t = z["time"].astype(np.int64)
c = z["close"].astype(np.float64)
r = np.zeros(len(c))
r[1:] = np.log(np.maximum(c[1:], 1e-12) / np.maximum(c[:-1], 1e-12))

# window padat-train: 2018-01-01 .. 2024-07-30
lo = int(np.argmax(t >= dt.datetime(2018, 1, 1).timestamp()))
hi = int(np.argmax(t > dt.datetime(2024, 7, 30).timestamp()))
rr = r[lo:hi]
print(f"fit window: n={len(rr)} | {dt.datetime.fromtimestamp(int(t[lo]), dt.timezone.utc)} "
      f".. {dt.datetime.fromtimestamp(int(t[hi-1]), dt.timezone.utc)}")
print(f"std={rr.std():.6f} | nol-return: {int((rr == 0).sum())} "
      f"({100*(rr == 0).mean():.2f}%) | |r|max={np.abs(rr).max():.4f}")
for lag in (1, 2, 5, 10, 24):
    ac = np.corrcoef(rr[lag:] ** 2, rr[:-lag] ** 2)[0, 1]
    print(f"  ac(r^2, lag={lag:2d}) = {ac:+.4f}")

print("\nfit default (bounds train_regime):")
try:
    w, a, b, nu = TR.fit_garch_t(rr)
    print(f"  omega={w:.3e} alpha={a:.4f} beta={b:.4f} persist={a+b:.4f} nu={nu:.2f}")
except Exception as e:
    print("  GAGAL:", e)

print("\nfit dgn bounds longgar + init lain:")
from scipy.optimize import minimize
import math
rl = [float(x) for x in rr]
n = len(rl)
var0 = float(np.var(rr) + 1e-12)

def negll_p(p, init_s2=None):
    w, a, b, nu = p
    if w <= 0 or a < 0 or b < 0 or a + b >= 0.999 or nu <= 2.05:
        return 1e12
    l1 = math.log(math.pi * (nu - 2.0))
    l2 = 2.0 * math.lgamma(nu / 2.0) - 2.0 * math.lgamma((nu + 1.0) / 2.0)
    s2 = var0 if init_s2 is None else init_s2
    ll = 0.0
    for rv in rl:
        s2 = w + a * rv * rv + b * s2
        if s2 < 1e-12:
            s2 = 1e-12
        e2 = rv * rv / s2
        ll += math.log(s2) + (nu + 1.0) * math.log1p(e2 / (nu - 2.0))
    return 0.5 * (ll + n * (l1 + l2))

for tag, x0, bnd in [
    ("init klasik (0.06/0.92/7)", [1e-7, 0.06, 0.92, 7.0],
     [(1e-12, 1e-4), (0.001, 0.5), (0.40, 0.995), (2.1, 50.0)]),
    ("init netral (0.1/0.85/10)", [1e-7, 0.10, 0.85, 10.0],
     [(1e-12, 1e-4), (0.001, 0.5), (0.40, 0.995), (2.1, 50.0)]),
    ("init ekstrem-vol (0.05/0.9/5)", [1e-7, 0.05, 0.90, 5.0],
     [(1e-12, 1e-4), (0.001, 0.5), (0.40, 0.995), (2.1, 50.0)]),
]:
    res = minimize(negll_p, x0, method="L-BFGS-B", bounds=bnd,
                   options=dict(maxiter=3000))
    w, a, b, nu = res.x
    print(f"  [{tag}] omega={w:.3e} alpha={a:.4f} beta={b:.4f} "
          f"persist={a+b:.4f} nu={nu:.2f} nfev={res.nfev} fun={res.fun:.1f}")

# subset 2018-2020 (periode vol lebih tenang) sbg kontrol
lo2 = int(np.argmax(t >= dt.datetime(2018, 1, 1).timestamp()))
hi2 = int(np.argmax(t > dt.datetime(2020, 12, 31).timestamp()))
rr2 = r[lo2:hi2]
print(f"\nkontrol subset 2018-2020: n={len(rr2)} std={rr2.std():.6f}")
w, a, b, nu = TR.fit_garch_t(rr2)
print(f"  fit default: omega={w:.3e} alpha={a:.4f} beta={b:.4f} "
      f"persist={a+b:.4f} nu={nu:.2f}")