这是一种快速的程序,可创建LSTN/RNN的3D数据,无需循环,并涉及此简单函数。
def create_windows(data, window_shape, step = 1, start_id = None, end_id = None):
data = np.asarray(data)
data = data.reshape(-1,1) if np.prod(data.shape) == max(data.shape) else data
start_id = 0 if start_id is None else start_id
end_id = data.shape[0] if end_id is None else end_id
data = data[int(start_id):int(end_id),:]
window_shape = (int(window_shape), data.shape[-1])
step = (int(step),) * data.ndim
slices = tuple(slice(None, None, st) for st in step)
indexing_strides = data[slices].strides
win_indices_shape = ((np.array(data.shape) - window_shape) // step) + 1
new_shape = tuple(list(win_indices_shape) + list(window_shape))
strides = tuple(list(indexing_strides) + list(data.strides))
window_data = np.lib.stride_tricks.as_strided(data, shape=new_shape, strides=strides)
return np.squeeze(window_data, 1)
从这个样本数据开始:
n_sample = 2000
n_feat_inp = 6
n_feat_out = 1
X = np.asarray([np.arange(n_sample)]*n_feat_inp).T
y = np.asarray([np.arange(n_sample)]*n_feat_out).T
如果我们想要提前一步进行预测
look_back = 5
look_ahead = 1
X_seq = create_windows(X, window_shape = look_back, end_id = -look_ahead)
y_seq = create_windows(y, window_shape = look_ahead, start_id = look_back)
生成数据的示例:
X_seq[0]: [[0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1],
[2, 2, 2, 2, 2, 2],
[3, 3, 3, 3, 3, 3],
[4, 4, 4, 4, 4, 4]]
y_seq[0]: [[5]]
如果我们想进行多步预测
look_back = 5
look_ahead = 3
X_seq = create_windows(X, window_shape = look_back, end_id = -look_ahead)
# X_seq.shape
y_seq = create_windows(y, window_shape = look_ahead, start_id = look_back)
# y_seq.shape
生成数据的例子:
X_seq[0]: [[0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1],
[2, 2, 2, 2, 2, 2],
[3, 3, 3, 3, 3, 3],
[4, 4, 4, 4, 4, 4]]
y_seq[0]: [[5],
[6],
[7]]