|
|
@ -118,48 +118,48 @@ eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)
|
|
|
|
|
|
|
|
|
|
|
|
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(device) # 导入模型并设置模型的参数输入输出层、隐藏层等
|
|
|
|
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(device) # 导入模型并设置模型的参数输入输出层、隐藏层等
|
|
|
|
|
|
|
|
|
|
|
|
loss_function = nn.MSELoss()
|
|
|
|
# loss_function = nn.MSELoss()
|
|
|
|
optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
|
|
|
|
# optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
|
|
|
|
|
|
|
|
#
|
|
|
|
min_loss = 1
|
|
|
|
# min_loss = 1
|
|
|
|
for i in range(2500):
|
|
|
|
# for i in range(2500):
|
|
|
|
model.train()
|
|
|
|
# model.train()
|
|
|
|
out = model(train_x)
|
|
|
|
# out = model(train_x)
|
|
|
|
loss = loss_function(out, train_y)
|
|
|
|
# loss = loss_function(out, train_y)
|
|
|
|
loss.backward()
|
|
|
|
# loss.backward()
|
|
|
|
optimizer.step()
|
|
|
|
# optimizer.step()
|
|
|
|
optimizer.zero_grad()
|
|
|
|
# optimizer.zero_grad()
|
|
|
|
|
|
|
|
#
|
|
|
|
model.eval()
|
|
|
|
# model.eval()
|
|
|
|
with torch.no_grad():
|
|
|
|
# with torch.no_grad():
|
|
|
|
pred = model(eval_x)
|
|
|
|
# pred = model(eval_x)
|
|
|
|
eval_loss = loss_function(pred,eval_y)
|
|
|
|
# eval_loss = loss_function(pred,eval_y)
|
|
|
|
if eval_loss <= min_loss:
|
|
|
|
# if eval_loss <= min_loss:
|
|
|
|
min_loss = eval_loss
|
|
|
|
# min_loss = eval_loss
|
|
|
|
best_param = model.state_dict()
|
|
|
|
# best_param = model.state_dict()
|
|
|
|
|
|
|
|
#
|
|
|
|
if (i+1) % 100 == 0:
|
|
|
|
# if (i+1) % 100 == 0:
|
|
|
|
print(f'epoch {i+1}/1500 loss:{round(loss.item(),5)}')
|
|
|
|
# print(f'epoch {i+1}/1500 loss:{round(loss.item(),5)}')
|
|
|
|
|
|
|
|
#
|
|
|
|
# 保存模型
|
|
|
|
# # 保存模型
|
|
|
|
torch.save(best_param,'best_dy3.pth')
|
|
|
|
# torch.save(best_param,'best_dy3.pth')
|
|
|
|
|
|
|
|
|
|
|
|
# for test
|
|
|
|
# for test
|
|
|
|
model = model.eval()
|
|
|
|
# model = model.eval()
|
|
|
|
|
|
|
|
#
|
|
|
|
dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN) # (seq_size, batch_size, feature_size)
|
|
|
|
# dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN) # (seq_size, batch_size, feature_size)
|
|
|
|
dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)
|
|
|
|
# dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)
|
|
|
|
|
|
|
|
#
|
|
|
|
pred_test = model(dataset_x)
|
|
|
|
# pred_test = model(dataset_x)
|
|
|
|
# 模型输出 (seq_size, batch_size, output_size)
|
|
|
|
# # 模型输出 (seq_size, batch_size, output_size)
|
|
|
|
pred_test = pred_test.view(-1)
|
|
|
|
# pred_test = pred_test.view(-1)
|
|
|
|
pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
|
|
|
|
# pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
|
|
|
|
|
|
|
|
#
|
|
|
|
plt.plot(pred_test.reshape(-1), 'r', label='prediction')
|
|
|
|
# plt.plot(pred_test.reshape(-1), 'r', label='prediction')
|
|
|
|
plt.plot(dataset_y.reshape(-1), 'b', label='real')
|
|
|
|
# plt.plot(dataset_y.reshape(-1), 'b', label='real')
|
|
|
|
plt.plot((train_size*3, train_size*3), (0, 1), 'g--') # 分割线 左边是训练数据 右边是测试数据的输出
|
|
|
|
# plt.plot((train_size*3, train_size*3), (0, 1), 'g--') # 分割线 左边是训练数据 右边是测试数据的输出
|
|
|
|
plt.legend(loc='best')
|
|
|
|
# plt.legend(loc='best')
|
|
|
|
plt.show()
|
|
|
|
# plt.show()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 创建测试集
|
|
|
|
# 创建测试集
|
|
|
|