gru预测模型python
时间: 2023-12-02 13:43:26 浏览: 287
以下是一个使用GRU模型进行时间序列预测的Python代码示例:
```python
import torch
import torch.nn as nn
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# 加载数据
data = pd.read_csv('data.csv', header=None)
data = data.values.astype('float32')
# 划分训练集和测试集
train_size = int(len(data) * 0.7)
train_data = data[:train_size]
test_data = data[train_size:]
# 定义超参数
input_size = 1
hidden_size = 32
num_layers = 1
output_size = 1
seq_length = 5
learning_rate = 0.01
num_epochs = 1000
# 定义GRU模型
class GRU(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, output_size):
super(GRU, self).__init__()
self.hidden_size = hidden_size
self.num_layers = num_layers
self.gru = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, x, h):
out, h = self.gru(x, h)
out = self.fc(out[:, -1, :])
return out, h
# 实例化模型
model = GRU(input_size, hidden_size, num_layers, output_size)
# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
train_loss = []
for epoch in range(num_epochs):
inputs = train_data[:-1].reshape(-1, seq_length, input_size)
targets = train_data[1:].reshape(-1, seq_length, output_size)
h = torch.zeros(num_layers, inputs.size(0), hidden_size)
outputs, h = model(inputs, h)
loss = criterion(outputs, targets)
train_loss.append(loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (epoch+1) % 100 == 0:
print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))
# 测试模型
model.eval()
with torch.no_grad():
inputs = test_data[:-1].reshape(-1, seq_length, input_size)
targets = test_data[1:].reshape(-1, seq_length, output_size)
h = torch.zeros(num_layers, inputs.size(0), hidden_size)
outputs, h = model(inputs, h)
test_loss = criterion(outputs, targets)
print('Test Loss: {:.4f}'.format(test_loss.item()))
# 可视化结果
plt.plot(targets[:, -1, 0], label='true')
plt.plot(outputs[:, -1, 0], label='predicted')
plt.legend()
plt.show()
```