42 lines
1.4 KiB
Python
42 lines
1.4 KiB
Python
|
# -*- coding: utf-8 -*-
|
||
|
|
"""Kalibrasi waktu training LSTM 2-lapis pd subset — ekstrapolasi utk gate/wf."""
|
||
|
|
import os
|
||
|
|
import sys
|
||
|
|
import time
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
HERE = os.path.dirname(os.path.abspath(__file__))
|
||
|
|
sys.path.insert(0, HERE)
|
||
|
|
import train_hybrid as TH
|
||
|
|
|
||
|
|
|
||
|
|
def time_run(n_train, n_ep, tag):
|
||
|
|
F, label, close, midx, split_pos, split_bar = TH.load_base()
|
||
|
|
X = F
|
||
|
|
mean = X[midx[:split_pos]].mean(0)
|
||
|
|
std = X[midx[:split_pos]].std(0)
|
||
|
|
std[std < 1e-9] = 1.0
|
||
|
|
Xs = (X - mean) / std
|
||
|
|
n = min(n_train, split_pos)
|
||
|
|
va2 = int(0.85 * n)
|
||
|
|
Xtr = TH.build_sequences(Xs, midx[:va2])
|
||
|
|
Xva = TH.build_sequences(Xs, midx[va2:n])
|
||
|
|
yl = (label[midx] == 1).astype(float)
|
||
|
|
ys = (label[midx] == -1).astype(float)
|
||
|
|
Ytr = np.column_stack([yl[:va2], ys[:va2]])
|
||
|
|
Yva = np.column_stack([yl[va2:n], ys[va2:n]])
|
||
|
|
t0 = time.time()
|
||
|
|
st, va, ep = TH.train_lstm2(Xtr, Ytr, Xva, Yva, seed=42, epoch_max=n_ep,
|
||
|
|
verbose=False)
|
||
|
|
dt_ = time.time() - t0
|
||
|
|
per_ep = dt_ / (ep + 1)
|
||
|
|
print(f"[{tag}] n_train={len(Xtr)} epochs={ep + 1} total={dt_:.0f}s "
|
||
|
|
f"({per_ep:.1f}s/ep) val_AUC={va:.4f}")
|
||
|
|
return per_ep
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
per = time_run(6000, 3, "probe-6k")
|
||
|
|
# ekstrapolasi gate: ~39k train, 5 seed, ~15 ep/seed
|
||
|
|
est_gate = per * (39000 / 6000) * 15 * 5
|
||
|
|
print(f"Estimasi GATE penuh (39k train, 5 seed, ~15 ep): ~{est_gate / 60:.0f} menit")
|