def test(model_save_path, root_dir, p_r_root, day, test_log_dir, args, layer, dim):
# load test dataset
dataset = DataSet(os.path.join(root_dir, day)) # TODO: 测试不同的数据
# load model
running_context = torch.device("cuda:1")
model = GCN(args, running_context, layer, dim).to(running_context)
model.load_state_dict(torch.load(model_save_path))
model.eval()
# test log
test_log_list = [[] for _ in range(24)]
test_count = 0
print("\n" + "+" * 20 + " Test on day {} layer {} dim {} ".format(day, layer, dim) + "+" * 20)
for hour in range(0, 24):
data = dataset[hour]
edge_index = data.edge_index.to(running_context)
mask = data.mask.to(running_context)
logit = model(data.inputs, edge_index)
label = data.label.to(running_context, non_blocking=True)
acc, tn, fp, fn, tp, white_p, white_r, white_incorrect, black_p, black_r, black_incorrect, macro_f1, micro_f1 = evaluate(logit[mask].max(1)[1], label)
test_log_list[test_count].append(float(acc))
test_log_list[test_count].append(float(white_p))
test_log_list[test_count].append(float(white_r))
test_log_list[test_count].append(float(white_incorrect))
test_log_list[test_count].append(float(black_p))
test_log_list[test_count].append(float(black_r))
test_log_list[test_count].append(float(black_incorrect))
test_log_list[test_count].append(float(macro_f1))
test_log_list[test_count].append(float(micro_f1))
test_count += 1
test_log = "hour:{:3d}, acc: {:.4f}" \
"TN={:6d}, FP={:6d}, FN={:6d}, TP={:6d}, " \
"white_p={:.4f}, white_r={:.4f}, " \
"black_p={:.4f}, black_r={:.4f}, " \
"macro_f1: {:.4f}, micro_f1: {:.4f}"
print(test_log.format(hour, acc, tn, fp, fn, tp, white_p, white_r, black_p, black_r, macro_f1, micro_f1))
logit = np.array(norm(torch.sigmoid(logit[mask]).cpu().detach().numpy()))
label = np.array(label.cpu().detach().numpy()).reshape(-1, 1)
p_r = np.concatenate((logit, label), axis=1)
p_r_cols = ["neg_pro", "pos_pro", "label"]
p_r_df = pd.DataFrame(np.array(p_r), columns=p_r_cols)
p_r_dir = os.path.join(p_r_root, "test_{}_hour_{}_layer_{}_dim_{}_pr.csv" \
.format(day.split("-")[-1], hour, layer, dim))
p_r_df.to_csv(p_r_dir, index=None, columns=p_r_cols)
# save test logs to csv file
print("Start to save test log of {}.".format(day))
test_log_cols = ["acc", "white_p", "white_r", "white_incorrect", "black_p", "black_r", "black_incorrect", "macro_f1", "micro_f1"]
test_log_df = pd.DataFrame(np.array(test_log_list), columns=test_log_cols)
test_log_df.to_csv(test_log_dir, float_format="%.4f", index=None, columns=test_log_cols)
print("Save test log of day {} layer {} dim {} successfully.".format(day, layer, dim))
torch.cuda.empty_cache()
class GCNTrainer(Trainer):
def __init__(self, parameter, emb_matrix=None):
self.parameter = parameter
self.emb_matrix = emb_matrix
self.model = GCN(parameter, emb_matrix=emb_matrix)
self.criterion = nn.CrossEntropyLoss()
self.parameters = [
p for p in self.model.parameters() if p.requires_grad
]
self.optimizer = torch.optim.SGD(self.parameters,
lr=0.5,
weight_decay=0)
def update(self, batch):
inputs, labels = unpack_batch(batch)
self.model.train() #开启dropout
self.optimizer.zero_grad()
logits, pooling_output = self.model(inputs)
loss = self.criterion(logits, labels)
#正则化项
loss += 0.003 * (pooling_output**2).sum(1).mean()
loss_val = loss.item()
# 反向传播
loss.backward()
torch.nn.utils.clip_grad_norm_(self.model.parameters(), 5)
self.optimizer.step()
return loss_val
def predict(self, batch):
inputs, labels = unpack_batch(batch)
self.model.eval() #关闭dropout
orig_idx = batch[-1]
logits, _ = self.model(inputs)
probs = F.softmax(logits, 1).data.cpu().numpy().tolist()
predictions = np.argmax(logits.data.cpu().numpy(), axis=1).tolist()
_, predictions, probs = [list(t) for t in zip(*sorted(zip(orig_idx,\
predictions, probs)))]
return predictions