pyriemann.utils.covariance.covariances¶

pyriemann.utils.covariance.covariances(X, estimator='cov', **kwds)¶

Estimation of covariance matrix.

Parameters

Xndarray, shape (n_matrices, n_channels, n_times)

Multi-channel time-series.

estimator{‘corr’, ‘cov’, ‘hub’, ‘lwf’, ‘mcd’, ‘oas’, ‘sch’, ‘scm’, ‘stu’, ‘tyl’}, default=’scm’

Covariance matrix estimator [est]:

‘corr’ for correlation coefficient matrix [corr] supporting complex inputs,
‘cov’ for numpy based covariance matrix [cov] supporting complex inputs,
‘hub’ for Huber’s M-estimator based covariance matrix [mest] supporting complex inputs,
‘lwf’ for Ledoit-Wolf shrunk covariance matrix [lwf],
‘mcd’ for minimum covariance determinant matrix [mcd],
‘oas’ for oracle approximating shrunk covariance matrix [oas],
‘sch’ for Schaefer-Strimmer shrunk covariance matrix [sch],
‘scm’ for sample covariance matrix [scm],
‘stu’ for Student-t’s M-estimator based covariance matrix [mest] supporting complex inputs,
‘tyl’ for Tyler’s M-estimator based covariance matrix [mest] supporting complex inputs,
or a callable function.

For regularization, consider ‘lwf’ or ‘oas’. For robustness, consider ‘hub’, ‘mcd’, ‘stu’ or ‘tyl’.

**kwdsoptional keyword parameters

Any further parameters are passed directly to the covariance estimator.

Returns

covmatsndarray, shape (n_matrices, n_channels, n_channels): Covariance matrices.

References