PyTorch LSTM多变量时序负荷预测
Cyril_KI 人气:0I. 前言
在前面的一篇文章PyTorch搭建LSTM实现时间序列预测(负荷预测)中,我们利用LSTM实现了负荷预测,但我们只是简单利用负荷预测负荷,并没有利用到其他一些环境变量,比如温度、湿度等。
本篇文章主要考虑用PyTorch搭建LSTM实现多变量时间序列预测。
系列文章:
PyTorch深度学习LSTM从input输入到Linear输出
II. 数据处理
数据集为某个地区某段时间内的电力负荷数据,除了负荷以外,还包括温度、湿度等信息。
本文中,我们根据前24个时刻的负荷以及该时刻的环境变量来预测下一时刻的负荷。
def load_data(file_name): global MAX, MIN df = pd.read_csv(os.path.dirname(os.getcwd()) + '/data/new_data/' + file_name, encoding='gbk') columns = df.columns df.fillna(df.mean(), inplace=True) MAX = np.max(df[columns[1]]) MIN = np.min(df[columns[1]]) df[columns[1]] = (df[columns[1]] - MIN) / (MAX - MIN) return df class MyDataset(Dataset): def __init__(self, data): self.data = data def __getitem__(self, item): return self.data[item] def __len__(self): return len(self.data) def nn_seq(file_name, B): print('处理数据:') data = load_data(file_name) load = data[data.columns[1]] load = load.tolist() data = data.values.tolist() seq = [] for i in range(len(data) - 24): train_seq = [] train_label = [] for j in range(i, i + 24): x = [load[j]] for c in range(2, 8): x.append(data[j][c]) train_seq.append(x) train_label.append(load[i + 24]) train_seq = torch.FloatTensor(train_seq) train_label = torch.FloatTensor(train_label).view(-1) seq.append((train_seq, train_label)) # print(seq[:5]) Dtr = seq[0:int(len(seq) * 0.7)] Dte = seq[int(len(seq) * 0.7):len(seq)] train_len = int(len(Dtr) / B) * B test_len = int(len(Dte) / B) * B Dtr, Dte = Dtr[:train_len], Dte[:test_len] train = MyDataset(Dtr) test = MyDataset(Dte) Dtr = DataLoader(dataset=train, batch_size=B, shuffle=False, num_workers=0) Dte = DataLoader(dataset=test, batch_size=B, shuffle=False, num_workers=0) return Dtr, Dte
上面代码用了DataLoader来对原始数据进行处理,最终得到了batch_size=B的数据集Dtr和Dte,Dtr为训练集,Dte为测试集。
任意输出Dte中的一条数据:
[(tensor([[0.3513, 0.0000, 0.9091, 0.0000, 0.6667, 0.3023, 0.2439], [0.3333, 0.0000, 0.9091, 0.0435, 0.6667, 0.3023, 0.2439], [0.3396, 0.0000, 0.9091, 0.0870, 0.6667, 0.3023, 0.2439], [0.3427, 0.0000, 0.9091, 0.1304, 0.6667, 0.3023, 0.2439], [0.3838, 0.0000, 0.9091, 0.1739, 0.6667, 0.3023, 0.2439], [0.3700, 0.0000, 0.9091, 0.2174, 0.6667, 0.3023, 0.2439], [0.4288, 0.0000, 0.9091, 0.2609, 0.6667, 0.3023, 0.2439], [0.4474, 0.0000, 0.9091, 0.3043, 0.6667, 0.3023, 0.2439], [0.4406, 0.0000, 0.9091, 0.3478, 0.6667, 0.3023, 0.2439], [0.4657, 0.0000, 0.9091, 0.3913, 0.6667, 0.3023, 0.2439], [0.4540, 0.0000, 0.9091, 0.4348, 0.6667, 0.3023, 0.2439], [0.4939, 0.0000, 0.9091, 0.4783, 0.6667, 0.3023, 0.2439], [0.4328, 0.0000, 0.9091, 0.5217, 0.6667, 0.3023, 0.2439], [0.4238, 0.0000, 0.9091, 0.5652, 0.6667, 0.3023, 0.2439], [0.4779, 0.0000, 0.9091, 0.6087, 0.6667, 0.3023, 0.2439], [0.4591, 0.0000, 0.9091, 0.6522, 0.6667, 0.3023, 0.2439], [0.4651, 0.0000, 0.9091, 0.6957, 0.6667, 0.3023, 0.2439], [0.5102, 0.0000, 0.9091, 0.7391, 0.6667, 0.3023, 0.2439], [0.5067, 0.0000, 0.9091, 0.7826, 0.6667, 0.3023, 0.2439], [0.4635, 0.0000, 0.9091, 0.8261, 0.6667, 0.3023, 0.2439], [0.4224, 0.0000, 0.9091, 0.8696, 0.6667, 0.3023, 0.2439], [0.3796, 0.0000, 0.9091, 0.9130, 0.6667, 0.3023, 0.2439], [0.3292, 0.0000, 0.9091, 0.9565, 0.6667, 0.3023, 0.2439], [0.2940, 0.0000, 0.9091, 1.0000, 0.6667, 0.3023, 0.2439]]), tensor([0.3675]))]
每一行对应一个时刻点的负荷以及环境变量,此时input_size=7。
III. LSTM模型
这里采用了深入理解PyTorch中LSTM的输入和输出(从input输入到Linear输出)中的模型:
class LSTM(nn.Module): def __init__(self, input_size, hidden_size, num_layers, output_size, batch_size): super().__init__() self.input_size = input_size self.hidden_size = hidden_size self.num_layers = num_layers self.output_size = output_size self.num_directions = 1 self.batch_size = batch_size self.lstm = nn.LSTM(self.input_size, self.hidden_size, self.num_layers, batch_first=True) self.linear = nn.Linear(self.hidden_size, self.output_size) def forward(self, input_seq): h_0 = torch.randn(self.num_directions * self.num_layers, self.batch_size, self.hidden_size).to(device) c_0 = torch.randn(self.num_directions * self.num_layers, self.batch_size, self.hidden_size).to(device) # print(input_seq.size()) seq_len = input_seq.shape[1] # input(batch_size, seq_len, input_size) input_seq = input_seq.view(self.batch_size, seq_len, self.input_size) # output(batch_size, seq_len, num_directions * hidden_size) output, _ = self.lstm(input_seq, (h_0, c_0)) # print('output.size=', output.size()) # print(self.batch_size * seq_len, self.hidden_size) output = output.contiguous().view(self.batch_size * seq_len, self.hidden_size) # (5 * 30, 64) pred = self.linear(output) # pred() # print('pred=', pred.shape) pred = pred.view(self.batch_size, seq_len, -1) pred = pred[:, -1, :] return pred
IV. 训练
def LSTM_train(name, b): Dtr, Dte = nn_seq(file_name=name, B=b) input_size, hidden_size, num_layers, output_size = 7, 64, 1, 1 model = LSTM(input_size, hidden_size, num_layers, output_size, batch_size=b).to(device) loss_function = nn.MSELoss().to(device) optimizer = torch.optim.Adam(model.parameters(), lr=0.05) # 训练 epochs = 30 for i in range(epochs): cnt = 0 print('当前', i) for (seq, label) in Dtr: cnt += 1 seq = seq.to(device) label = label.to(device) y_pred = model(seq) loss = loss_function(y_pred, label) optimizer.zero_grad() loss.backward() optimizer.step() if cnt % 100 == 0: print('epoch', i, ':', cnt - 100, '~', cnt, loss.item()) state = {'model': model.state_dict(), 'optimizer': optimizer.state_dict()} torch.save(state, LSTM_PATH)
V. 测试
def test(name, b): global MAX, MIN Dtr, Dte = nn_seq(file_name=name, B=b) pred = [] y = [] print('loading model...') input_size, hidden_size, num_layers, output_size = 7, 64, 1, 1 model = LSTM(input_size, hidden_size, num_layers, output_size, batch_size=b).to(device) model.load_state_dict(torch.load(LSTM_PATH)['model']) model.eval() print('predicting...') for (seq, target) in Dte: target = list(chain.from_iterable(target.data.tolist())) y.extend(target) seq = seq.to(device) with torch.no_grad(): y_pred = model(seq) y_pred = list(chain.from_iterable(y_pred.data.tolist())) pred.extend(y_pred) y, pred = np.array([y]), np.array([pred]) y = (MAX - MIN) * y + MIN pred = (MAX - MIN) * pred + MIN print('accuracy:', get_mape(y, pred)) # plot x = [i for i in range(1, 151)] x_smooth = np.linspace(np.min(x), np.max(x), 900) y_smooth = make_interp_spline(x, y.T[150:300])(x_smooth) plt.plot(x_smooth, y_smooth, c='green', marker='*', ms=1, alpha=0.75, label='true') y_smooth = make_interp_spline(x, pred.T[150:300])(x_smooth) plt.plot(x_smooth, y_smooth, c='red', marker='o', ms=1, alpha=0.75, label='pred') plt.grid(axis='y') plt.legend() plt.show()
我只是训练了30轮,MAPE为7.83%:
VI. 源码及数据
源码及数据我放在了GitHub上,LSTM-Load-Forecasting
加载全部内容