'loss_function': 'mae', # 'mse' or 'mae'
'lr': 0.001,
'batch_size': 2560,
'shuffle': False,
'normalization':
'standard_positive', # 'min_max', 'standard', None
'epochs': 250
}
utrain.train_and_test(params)
ufig.plot_train_test(ids_attempt[-1], [3, 8, 13, 17],
lim_nr_samples=2000)
ufig.plot_multi_boxplots(ids=ids_attempt,
x='patient_id',
y='correlation',
hue='brain_state',
save_name=pre + 'corr' + post)
ufig.plot_multi_boxplots(ids=ids_attempt,
x='patient_id',
y='mae',
hue='brain_state',
save_name=pre + 'mae' + post)
ufig.plot_multi_boxplots(ids=ids_attempt,
x='patient_id',
y='mse',
hue='brain_state',
save_name=pre + 'mse' + post)
ufig.mean_weights(ids=ids_all, save_name=pre)
for i in range(3):
ids.append('batch_size_' + str(val) + '_' + pre + '_ID07_32h07m_' + str(i))
if custom_set:
custom_test_set = {'time_begin': [32, 7, 20],
'duration': 10,
'batch_size': 50}
utrain.predict(ids[-1], custom_test_set=custom_test_set)
utrain.distance(ids[-1])
print('0')
ids.append('batch_size_' + str(val) + '_' + pre + '_ID07_35h15m_' + str(i))
if custom_set:
custom_test_set = {'time_begin': [35, 15, 20],
'duration': 10,
'batch_size': 50}
utrain.predict(ids[-1], custom_test_set=custom_test_set)
utrain.distance(ids[-1])
print('1')
ids.append('batch_size_' + str(val) + '_' + pre + '_ID07_38h22m_' + str(i))
if custom_set:
custom_test_set = {'time_begin': [38, 22, 20],
'duration': 10,
'batch_size': 50}
utrain.predict(ids[-1], custom_test_set=custom_test_set)
utrain.distance(ids[-1])
print('2')
print('---------------------------------------------')
ufig.plot_multi_boxplots(ids=ids, x='batch_size', y='correlation', hue='brain_state',
save_name='batch_size_' + pre, ylim=(0, 1))
ufig.mean_weights(ids=ids, save_name='batch_size_' + pre, hidden=True, diagonal=True)