def run(filename):
"""실험할 세팅을 불러오고, 그에 따라서 실험을 수행한다."""
info = TrainInformation(filename)
np.random.seed(info.SEED)
torch.manual_seed(info.SEED)
fold = info.FOLD
test_AUCs_by_split = []
for split in range(fold):
#if split % 3 > 0:
# print("Skipping split %d" % split)
# continue
if False:
train_logisticregressoin(info, split, fold)
continue
result = train(info, split, fold)
test_AUCs = [float(auc) for auc in result.test_AUC_list]
test_AUCs_by_split.append(test_AUCs)
with open("result.txt", "a") as f:
test_AUCs_by_split = np.array(test_AUCs_by_split)
test_AUCs_by_epoch = test_AUCs_by_split.mean(axis=0)
best_test_epoch = np.argmax(test_AUCs_by_epoch)
best_test_AUC = test_AUCs_by_epoch[best_test_epoch]
#f.write(str(info) + "/n")
f.write("Name: %s\n" % info.NAME)
f.write("average test AUC: %f %d\n" % (best_test_AUC, best_test_epoch))
def train(info: TrainInformation, split, fold):
"""주어진 split에 대한 학습과 테스트를 진행한다."""
bs = info.BS
init_lr = info.INIT_LR
lr_decay = info.LR_DECAY
momentum = info.MOMENTUM
weight_decay = info.WEIGHT_DECAY
optimizer_method = info.OPTIMIZER_METHOD
epoch = info.EPOCH
nchs = info.NCHS
filename = info.FILENAME
model_name = info.MODEL_NAME
exp_name = info.NAME
print("Using File {}".format(filename))
train_dataset = Dataset(split=split, fold=fold, phase="train", filename=filename, use_data_dropout=info.USE_DATA_DROPOUT)
#val_dataset = Dataset(split=split, fold=fold, phase="val", filename=filename)
test_dataset = Dataset(split=split, fold=fold, phase="test", filename=filename, use_data_dropout=False)
model = get_classifier_model(model_name, train_dataset.feature_size, nchs, info.ACTIVATION)
print(model)
# Optimizer 설정
optimizer = set_optimizer(
optimizer_method, model, init_lr, weight_decay, momentum=momentum
)
data_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=bs, shuffle=True, num_workers=0, drop_last=True
)
bce_loss = torch.nn.BCEWithLogitsLoss().cuda()
train_result = TrainResult()
train_result.set_sizes(
len(train_dataset.data), 0, len(test_dataset.data)
)
for ep in range(epoch):
global prev_plot
prev_plot = 0
train_step(
exp_name,
ep,
model,
train_dataset,
test_dataset,
optimizer,
init_lr,
lr_decay,
data_loader,
bce_loss,
train_result,
)
savedir = "/content/drive/My Drive/research/frontiers/checkpoints/%s" % exp_name
best_test_epoch = train_result.best_test_epoch #25
savepath = "%s/epoch_%04d_fold_%02d.pt" % (savedir, best_test_epoch, train_dataset.split)
#model.load_state_dict(torch.load(savepath))
model = torch.load(savepath)
model.eval()
test_preds = train_utils.get_preds(test_dataset.data[:, 1:], model)
test_AUC = train_utils.compute_AUC(test_dataset.data[:, :1], test_preds)
test_PRAUC = train_utils.compute_PRAUC(test_dataset.data[:, :1], test_preds)
train_utils.plot_AUC(test_dataset, test_preds, test_AUC, savepath=savepath.replace(".pt", "_AUC.tiff"))
contributing_variables = compute_contributing_variables(model, test_dataset)
with open(os.path.join(savedir, "contributing_variables_epoch_%04d_fold_%02d.txt" % (best_test_epoch, train_dataset.split)), "w") as f:
for (v, auc) in contributing_variables:
f.write("%s %f\n" % (v, auc))
info.split_index = split
info.result_dict = train_result
info.save_result()
return train_result