用pytorch写一个天气预测的代码，用LSTM或CNN，读取天气中的csv文件，由时间和气温两列数据，区分训练集和测试集，用gpu训练，输入为60天的天气，输出为某一天的天气,并画出60天的实际曲线和预测曲线图，注意维度要一致

好的，以下是天气预测的PyTorch代码，使用了LSTM模型：

import torch
import torch.nn as nn
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# 读取天气数据
data = pd.read_csv('weather.csv')

# 选取需要的时间和气温数据
data = data[['Time', 'Temperature']]

# 归一化数据
max_temp = data['Temperature'].max()
min_temp = data['Temperature'].min()
data['Temperature'] = (data['Temperature'] - min_temp) / (max_temp - min_temp)

# 划分训练集和测试集
train_data = data.iloc[:-30, :]
test_data = data.iloc[-30:, :]

# 定义函数，将数据集转换为LSTM模型的输入格式
def create_dataset(data, seq_len):
    X = []
    y = []
    for i in range(len(data)-seq_len-1):
        X.append(data[i:i+seq_len])
        y.append(data[i+seq_len])
    return np.array(X), np.array(y)

# 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))
        output = self.fc(lstm_out.view(len(input), -1))
        return output[-1]

# 定义超参数
seq_len = 60
input_size = 1
hidden_size = 64
output_size = 1
lr = 0.001
epochs = 200

# 转换数据集为LSTM模型的输入格式
train_X, train_y = create_dataset(train_data['Temperature'].values, seq_len)
test_X, test_y = create_dataset(test_data['Temperature'].values, seq_len)

# 将数据集转换为PyTorch张量
train_X = torch.from_numpy(train_X).float()
train_y = torch.from_numpy(train_y).float()
test_X = torch.from_numpy(test_X).float()
test_y = torch.from_numpy(test_y).float()

# 定义模型和优化器
model = LSTM(input_size, hidden_size, output_size)
optimizer = torch.optim.Adam(model.parameters(), lr=lr)

# 将模型和数据移动到GPU上
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
train_X = train_X.to(device)
train_y = train_y.to(device)
test_X = test_X.to(device)
test_y = test_y.to(device)

# 训练模型
for epoch in range(epochs):
    loss = 0
    for i in range(len(train_X)):
        optimizer.zero_grad()
        output = model(train_X[i])
        loss = loss + nn.MSELoss()(output, train_y[i])
        loss.backward()
        optimizer.step()
    if epoch % 10 == 0:
        print('Epoch {}/{} Loss {:.6f}'.format(epoch+1, epochs, loss))

# 测试模型
model.eval()
test_predict = []
with torch.no_grad():
    for i in range(len(test_X)):
        output = model(test_X[i])
        test_predict.append(output.item())

# 将预测结果还原为原始数据范围
test_predict = np.array(test_predict) * (max_temp - min_temp) + min_temp
test_y = np.array(test_y) * (max_temp - min_temp) + min_temp

# 绘制实际曲线和预测曲线图
plt.plot(range(len(test_y)), test_y, color='blue', label='Actual')
plt.plot(range(len(test_predict)), test_predict, color='red', label='Predict')
plt.legend()
plt.show()

这段代码读取名为`weather.csv`的天气数据文件，选取其中的时间和气温数据，并进行归一化处理。然后将数据集划分为训练集和测试集，使用`create_dataset`函数将数据集转换为LSTM模型的输入格式。接着定义LSTM模型和优化器，将模型和数据移动到GPU上，训练模型并测试模型。最后将预测结果还原为原始数据范围，并绘制实际曲线和预测曲线图。