我正在尝试使用pytorch对时间序列数据集进行预测。
1-首先,我将数据集分为训练和测试。
2-然后,我创建了模型。
import torch.nn as nn
import torch.nn.functional as F
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.rnn = nn.LSTM(input_size=1,hidden_size=50,num_layers=3,batch_first=True,dropout=0.2)
self.out = nn.Linear(50, 1)
def forward(self, x):
r_out, (h_n, h_c) = self.rnn(x, None)
x = r_out[:,-1,:] #last hidden output!
x = self.out(x)
return x
model = Model()
if cuda:
model.cuda()
3-训练完模型后,我进行了验证步骤。
mse = mean_squared_error(dataset['y'].iloc[60:].values,predicted)
print("RMSE:", np.sqrt(mse))
# RMSE: 0.10680269716212222
问题:我想知道,如何使用该模型来预测接下来的60天?
我读到以下内容是必要的:从我的预测中获取最后的预测值(即预测[-1]),并将其添加到total_x的最后一个数组中,但不包括第一时间步长。 >
所以,我尝试了这个:
#array --> List
today = total_x[-1].reshape(-1).tolist()
# scaling last price
last_price = scaler.transform(infered['y_pred'][-1].reshape(-1, 1))
# adding last price to list.
today.append(last_price[0])
# Exclude first(0th index) element
today = today[1:]
#reshape
today = np.array(today).reshape(-1,60,1)
today = torch.Tensor(list(today))
#predict!
tomorrow = predict_with_pytorch(model, today)
#inverse transform.
tomorrow = scaler.inverse_transform(tomorrow)[0]
这个变量tomorrow
是我明天的预测,但是,接下来60天内该如何做?