如何建立 LSTM 网络？

Question

我正在学习如何设置 RNN-LSTM 网络进行预测。我已经用一个变量创建了数据集。

x  y
1  2.5
2  6
3  8.6
4  11.2
5  13.8
6  16.4
...

和y(t) = 2.5x(t) + x(t-1) -0.9*x(t-2)的关系。我正在尝试设置 RNN-LSTM 来学习该模式，但它发生了我的程序错误。我的程序如下：

df= pd.read_excel('dataset.xlsx')

def split_dataset(data):
    # split into standard weeks
    train, test = data[:-328], data[-328:-6]
    # restructure into windows of weekly data
    train = np.array(np.split(train, len(train)/1))
    test = np.array(np.split(test, len(test)/1))
    return train, test

verbose, epochs, batch_size = 0, 20, 16
train, test = split_dataset(df.values)
train_x, train_y = train[:,:,0], train[:,:,1]


model = Sequential()
model.add(LSTM(200, return_sequences=True, input_shape = train_x.shape))
model.compile(loss='mse', optimizer='adam')

发生ValueError:

ValueError: Error when checking input: expected lstm_35_input to have 3 dimensions, but got array with shape (8766, 1)

有经验的DS或者pythoner可以教教我怎么设置网络吗？

谢谢

Answer 1

对于基于 LSTM 的 RNN，输入应该是 3 维（批次、时间、数据点）。我假设您的 x 变量的索引是它的时间。在这种情况下，你必须将你的输入转换成一些窗口的批次，比如一个 3 的窗口，那么你的输入是：

批次#       输入      目标

0        x[0:3]       y[3]

1        x[1:4]        y[4]

2        x[2:5]        y[5]

注意：您的 y 从 t=3 开始，因为您使用最后 3 个时间步来预测下一个第 4 个值。如果您的 y 已经按照您所说的从最后三个时间步计算，那么 y 应该从 0 索引开始，即在第 0 批您有 y[0] 作为目标

UPDATE 根据以下评论 如果你想有多个序列，那么你可以将它建模为一个序列到序列的问题，并且将是一个N to M 映射，你需要五个 x 值来预测三个 y：

批次#       输入      目标

0        x[0:5]       y[3:6]

1        x[1:6]        y[4:7]

2        x[2:7]        y[5:8]

Answer 2

目前，我已经创建了数据窗口，它看起来适合我提到的案例。

下面是我的代码：

df= pd.read_excel('dataset.xlsx')

# split a univariate dataset into train/test sets
def split_dataset(data):
    train, test = data[:-328], data[-328:-6]
    return train, test

train, test  = split_dataset(df.values)

# scale train and test data to [-1, 1]
def scale(train, test):
    # fit scaler
    scaler = MinMaxScaler(feature_range=(0,1))
    scaler = scaler.fit(train)
    # transform train
    #train = train.reshape(train.shape[0], train.shape[1])
    train_scaled = scaler.transform(train)
    # transform test
    #test = test.reshape(test.shape[0], test.shape[1])
    test_scaled = scaler.transform(test)
    return scaler, train_scaled, test_scaled

scaler, train_scaled, test_scaled = scale(train, test)

def to_supervised(train, n_input, n_out=7):
    # flatten data
    data = train
    X, y = list(), list()
    in_start = 0
    # step over the entire history one time step at a time
    for _ in range(len(data)):
        # define the end of the input sequence
        in_end = in_start + n_input
        out_end = in_end + n_out
        # ensure we have enough data for this instance
        if out_end <= len(data):
            x_input = data[in_start:in_end, 0]
            x_input = x_input.reshape((len(x_input), 1))
            X.append(x_input)
            y.append(data[in_end:out_end, 0])
        # move along one time step
        in_start += 1
    return np.array(X), np.array(y)
train_x, train_y = to_supervised(train_scaled, n_input = 3, n_out = 1)
test_x, test_y =  to_supervised(test_scaled, n_input = 3, n_out = 1)

verbose, epochs, batch_size = 0, 20, 16
n_timesteps, n_features, n_outputs = train_x.shape[1], train_x.shape[2], train_y.shape[1]


model = Sequential()
model.add(LSTM(200, return_sequences= False, input_shape = (train_x.shape[1],train_x.shape[2])))
model.add(Dense(1))
model.compile(loss = 'mse', optimizer = 'adam')
history = model.fit(train_x, train_y, epochs=epochs, verbose=verbose, validation_data = (test_x, test_y))

不过，我对此还有其他疑问：

Q1：LSTM中的units是什么意思？ [model.add(LSTM(units, ...))]

（我已经为模型尝试了不同的单位，随着单位的增加会更准确。）

Q2：我应该设置多少层？

Q3：如何预测多步？例如基于 (x(t),x(t-1)) 预测 y(t), y(t+1) 我曾尝试在to_supervised函数中设置n_out = 2，但是当我应用相同的方法时，它返回了错误

train_x, train_y = to_supervised(train_scaled, n_input = 3, n_out = 2)
test_x, test_y =  to_supervised(test_scaled, n_input = 3, n_out = 2)

verbose, epochs, batch_size = 0, 20, 16
n_timesteps, n_features, n_outputs = train_x.shape[1], train_x.shape[2], train_y.shape[1]

model = Sequential()
model.add(LSTM(200, return_sequences= False, input_shape = (train_x.shape[1],train_x.shape[2])))
model.add(Dense(1))
model.compile(loss = 'mse', optimizer = 'adam')
history = model.fit(train_x, train_y, epochs=epochs, verbose=verbose, validation_data = (test_x, test_y))

ValueError: Error when checking target: expected dense_27 to have shape (1,) but got array with shape (2,)

Q3（续）：我应该在模型设置中添加或更改什么？

Q3（续）：return_sequences 是什么？我应该什么时候设置True？