部分参考
《Multi-Horizon Time Series Forecasting with Temporal Attention Learning》《A Multi-Horizon Quantile Recurrent Forecaster》这两篇文章考虑的是多步预测的情形，多步预测在有外部协变量且未来输入已知的情况下效果好一点，如果只有未知变量的历史值，还是考虑做单步预测吧！否则只能通过迭代地执行单步预测（导致误差累计）或者直接预测 h h h步之后的值（误差大），效果不好，意义不大！
单变量单步预测的分位点损失 单变量多步预测的分位点损失 多变量多步预测的分位点损失 结果可视化 模型该模型可实现多变量单步的多分位点预测
import torchimport torch.nn as nnimport torch.nn.functional as Fclass Model(nn.Module): def __init__(self, n_val, window, hidRNN, quantiles = [0.5]): super(Model, self).__init__() self.use_cuda = True self.P = window # 输入窗口大小 self.m = n_val # 列数，变量数 self.hidR = hidRNN self.quantiles = torch.tensor(quantiles) self.GRU = nn.GRU(self.m, self.hidR) self.linear = nn.Linear(self.hidR, self.m * len(quantiles)) def forward(self, x): x1 = x.permute(1, 0, 2).contiguous() # x1: [window, batch, n_val] _, h = self.GRU(x1) # h: [1, batch, hidRNN] h = torch.squeeze(h,0) # h: [batch, hidRNN] res = self.linear(h) # res: [batch, n_val * n_quantile] res = res.view(-1, len(self.quantiles), self.m) return res def MQLoss(self, pred, true): quantiles = self.quantiles.unsqueeze(1).expand(len(self.quantiles), self.m) true = true.view(-1, 1, self.m).expand(pred.shape) tau = torch.gt(pred, true).type(torch.FloatTensor) - quantiles loss = tau.mul(pred - true).sum() return loss