moving_avg

selfeeg.augmentation.functional.moving_avg(x: ArrayLike, order: int = 5) → ArrayLike

applies a moving average filter to the input ArrayLike object.

Filter is applied along its last dimension. The filter order can be given as function argument.

Parameters:

• x (ArrayLike) – The input Tensor or Array. The last two dimensions must refer to the EEG recording (Channels x Samples).

• order (int, optional) –

  The order of the filter.

  Default = 5

Returns:

x (ArrayLike) – The augmented version of the input Tensor or Array.

Example

>>> import torch
>>> import selfeeg.augmentation as aug
>>> x = torch.randn(16,32,1024)
>>> xaug = aug.moving_avg(x, 5)
>>> print(
...     math.isclose( x[0,0,5:5+5].sum()/5, xaug[0,0,7],
...     rel_tol=1e-8)) #Should output True