lstm时间序列预测pytorch代码

下面是一个基于PyTorch的LSTM时间序列预测代码示例：

import torch
import torch.nn as nn
import numpy as np

# 数据准备
data = np.sin(np.arange(0, 1000, 0.1))
train_data = data[:800]
test_data = data[800:]

# 定义LSTM模型
class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(LSTM, self).__init__()
        self.hidden_size = hidden_size
        self.lstm = nn.LSTM(input_size, hidden_size)
        self.fc = nn.Linear(hidden_size, output_size)
        
    def forward(self, input):
        lstm_out, _ = self.lstm(input.view(len(input), 1, -1))
        out = self.fc(lstm_out.view(len(input), -1))
        return out[-1]

# 模型训练
input_size = 1
hidden_size = 10
output_size = 1
lr = 0.01
epochs = 100

model = LSTM(input_size, hidden_size, output_size)
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=lr)

for epoch in range(epochs):
    inputs = torch.from_numpy(train_data[:-1]).float()
    labels = torch.from_numpy(train_data[1:]).float()

    optimizer.zero_grad()

    outputs = model(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()

    if epoch % 10 == 0:
        print(f'Epoch: {epoch}, Loss: {loss.item()}')

# 模型测试
model.eval()
test_inputs = torch.from_numpy(test_data[:-1]).float()
test_labels = torch.from_numpy(test_data[1:]).float()
test_outputs = model(test_inputs)

# 可视化结果
import matplotlib.pyplot as plt
plt.plot(test_data[1:])
plt.plot(test_outputs.detach().numpy())
plt.legend(['True', 'Predicted'])
plt.show()

在这个示例中，我们首先准备了一组正弦波数据，然后定义了一个LSTM模型，并使用均方误差作为损失函数和Adam优化器进行训练。最后，我们使用模型对测试数据进行预测，并使用matplotlib进行可视化。