mne_denoise.qa.variance_removed#

mne_denoise.qa.variance_removed(data_before: ndarray, data_after: ndarray) → float[source]#

Percentage of total variance removed after denoising.

Parameters:

  • data_before (ndarray) – Data before denoising.

  • data_after (ndarray) – Data after denoising.

Returns:

pct_removed – Percentage of variance removed: 100 * (1 - var(data_after) / var(data_before)).

Return type:

float

Notes

Returns 0.0 when data_before has zero variance.

Examples

>>> import numpy as np
>>> from mne_denoise.qa import variance_removed
>>> x = np.array([1.0, -1.0, 1.0, -1.0])
>>> variance_removed(x, 0.5 * x)
75.0