pyeeg.mcca.mCCA.denoise

mCCA.denoise(X, num_comps, idx)

Denoise a dataset by projecting onto its low-rank canonical space.

The dataset is projected onto the first num_comps canonical components of its own transform, then back into the original channel space, retaining the shared (signal) part while discarding the components that are not shared across datasets.

Parameters:

• X (array-like (Time x channels)) – The dataset to denoise.

• num_comps (int) – Number of canonical components kept for reconstruction.

• idx (int) – Index of the dataset in the fitted list, used to select the matching per-dataset transform.

Returns:

• X_denoised (ndarray) – The denoised dataset, same shape as X.

• no-index: