model_filename = \
os.path.join(output_dir, 'models',
'%s_%s_exp%d_bs%d_nep%d_nla%d_nno%d_'
% (survival_estimator_name, dataset,
experiment_idx, batch_size, n_epochs,
n_layers, n_nodes)
+
'lr%f_nd%d_cv%d.pt'
% (lr, num_durations, cross_val_idx))
time_elapsed_filename = model_filename[:-3] + '_time.txt'
if not os.path.isfile(model_filename):
print('*** Fitting with hyperparam:', hyperparam,
'-- cross val index:', cross_val_idx, flush=True)
if num_durations > 0:
surv_model.fit(fold_X_train_std,
fold_y_train_discrete,
batch_size, n_epochs, verbose=False)
else:
surv_model.fit(fold_X_train_std,
(fold_y_train[:, 0],
fold_y_train[:, 1]), batch_size,
n_epochs, verbose=False)
elapsed = time.time() - tic
print('Time elapsed: %f second(s)' % elapsed)
np.savetxt(time_elapsed_filename,
np.array(elapsed).reshape(1, -1))
surv_model.save_net(model_filename)
else:
print('*** Loading ***', flush=True)
surv_model.load_net(model_filename)
elapsed = float(np.loadtxt(time_elapsed_filename))
y_train_discrete = labtrans.fit_transform(*y_train.T)
surv_model = NKSDiscrete(net, optimizer,
duration_index=labtrans.cuts)
else:
surv_model = NKS(net, optimizer)
model_filename = \
os.path.join(output_dir, 'models',
'%s_%s_exp%d_bs%d_nep%d_nla%d_nno%d_lr%f_nd%d_test.pt'
% (survival_estimator_name, dataset, experiment_idx,
batch_size, n_epochs, n_layers, n_nodes, lr, num_durations))
assert os.path.isfile(model_filename)
if not os.path.isfile(model_filename):
print('*** Fitting with hyperparam:', hyperparam, flush=True)
if num_durations > 0:
surv_model.fit(X_train_std, y_train_discrete,
batch_size, n_epochs, verbose=True)
else:
surv_model.fit(X_train_std, (y_train[:, 0], y_train[:, 1]),
batch_size, n_epochs, verbose=True)
surv_model.save_net(model_filename)
else:
print('*** Loading ***', flush=True)
surv_model.load_net(model_filename)
if num_durations > 0:
surv_df = surv_model.interpolate(10).predict_surv_df(X_test_std)
else:
surv_df = surv_model.predict_surv_df(X_test_std)
surv = surv_df.to_numpy().T
print()
'lr%f_nd%d_fold%d.pt'
% (lr, num_durations, fold_idx))
time_elapsed_filename = model_filename[:-3] + '_time.txt'
if not os.path.isfile(model_filename):
if use_cross_val:
print('*** Fitting with hyperparam:', hyperparam,
'-- cross val index:', fold_idx, flush=True)
else:
print('*** Fitting with hyperparam:', hyperparam,
flush=True)
if num_durations > 0:
if use_early_stopping and not use_cross_val:
surv_model.fit(fold_X_train_std,
fold_y_train_discrete,
batch_size, n_epochs,
[tt.callbacks.EarlyStopping()],
val_data=(fold_X_val_std,
fold_y_val_discrete),
verbose=False)
else:
surv_model.fit(fold_X_train_std,
fold_y_train_discrete,
batch_size, n_epochs,
verbose=False)
else:
if use_early_stopping and not use_cross_val:
surv_model.fit(fold_X_train_std,
(fold_y_train[:, 0],
fold_y_train[:, 1]), batch_size,
n_epochs,
[tt.callbacks.EarlyStopping()],