k_ratios_test_low = 1.2
k_ratios_test_high = 3.8
diff_coef_ratios_test_low = 4.2
diff_coef_ratios_test_high = 6.8
# simulate two beads
print("simulating data for training")
for n_data in n_datas:
file_name_data = siu.sim_two_beads(data_len, k_ratios=k_ratios, diff_coef_ratios=diff_coef_ratios, dt=dt, n_data=n_data, n_steps_initial=10000, save_file=True, root_dir=root_dir)
file_names_data.append(file_name_data)
for avg_len in avg_lens:
for n_filter_octave in n_filter_octaves:
try:
print("scat transforming n_data:{} with parameters avg_len:{}, n_filter_octave:{}".format(n_data, avg_len, n_filter_octave))
file_name_scat = scu.scat_transform(file_name_data, avg_len, log_transform=False, n_filter_octave=n_filter_octave, save_file=True, root_dir=root_dir)
file_names_scat.append(file_name_scat)
except:
print("exception occurred during scat transformation for n_data:{} with parameters avg_len:{}, n_filter_octave:{}".format(n_data, avg_len, n_filter_octave))
# simulate data for testing performance
print("simulating data for evaluation for randomly sampled labels")
k_ratios_test = (k_ratios_test_high - k_ratios_test_low) * np.random.random(n_data_test,) + k_ratios_test_low
diff_coef_ratios_test = (diff_coef_ratios_test_high - diff_coef_ratios_test_low) * np.random.random(n_data_test,) + diff_coef_ratios_test_low
k_ratios_diff_coef_ratios_test = np.stack([k_ratios_test, diff_coef_ratios_test], axis=1)
data_tests = []
for k_ratio_test, diff_coef_ratio_test in k_ratios_diff_coef_ratios_test:
data_test = siu.sim_two_beads(data_len, k_ratios=k_ratio_test, diff_coef_ratios=diff_coef_ratio_test, dt=dt, n_data=1, n_steps_initial=10000, save_file=False)
data_tests.append(data_test)
processes = np.concatenate(data_tests, axis=2) # shaped (1, 1, n_data_test, n_channels, data_len)
}
torch.save(samples_train, os.path.join(root_dir, 'obd_exp_0.pt'))
torch.save(samples_test, os.path.join(root_dir, 'obd_exp_1.pt'))
# create scat transformed versions
for avg_len in avg_lens:
for n_filter_octave in n_filter_octaves:
try:
print(
"scat transforming data_len:{} with parameters avg_len:{}, n_filter_octave:{}"
.format(data_len, avg_len, n_filter_octave))
file_name_scat = scu.scat_transform(
'obd_exp_0.pt',
avg_len,
log_transform=False,
n_filter_octave=n_filter_octave,
save_file=True,
root_dir=root_dir)
file_name_test_scat = scu.scat_transform(
'obd_exp_1.pt',
avg_len,
log_transform=False,
n_filter_octave=n_filter_octave,
save_file=True,
root_dir=root_dir)
file_names_scat.append(file_name_scat)
except:
print(
"exception occurred during scat transformation for data_len:{} with parameters avg_len:{}, n_filter_octave:{}"
.format(data_len, avg_len, n_filter_octave))