pyriemann.channelselection.ElectrodeSelection

class pyriemann.channelselection.ElectrodeSelection(nelec=16, metric='riemann', n_jobs=1)

Channel selection based on a Riemannian geometry criterion.

For each class, a centroid is estimated, and the channel selection is based on the maximization of the distance between centroids. This is done by a backward elimination where the electrode that carries the less distance is removed from the subset at each iteration. This algorithm is described in [1].

Parameters

nelecint, default=16

The number of electrode to keep in the final subset.

metricstring | dict, default=’riemann’

The type of metric used for centroid and distance estimation. see mean_covariance for the list of supported metric. the metric could be a dict with two keys, mean and distance in order to pass different metric for the centroid estimation and the distance estimation. Typical usecase is to pass ‘logeuclid’ metric for the mean in order to boost the computional speed and ‘riemann’ for the distance in order to keep the good sensitivity for the selection.

n_jobsint, default=1

The number of jobs to use for the computation. This works by computing each of the class centroid in parallel. If -1 all CPUs are used. If 1 is given, no parallel computing code is used at all, which is useful for debugging. For n_jobs below -1, (n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one are used.

See also

Kmeans

FgMDM

References

1

Channel selection procedure using riemannian distance for BCI applications A. Barachant and S. Bonnet. The 5th International IEEE EMBS Conference on Neural Engineering, Apr 2011, Cancun, Mexico.

Attributes

covmeans_list

The class centroids.

dist_list

List of distance at each interation.

__init__(nelec=16, metric='riemann', n_jobs=1)

Init.

fit(X, y=None, sample_weight=None)

Find the optimal subset of electrodes.

Parameters

Xndarray, shape (n_matrices, n_channels, n_channels)

Set of SPD matrices.

yNone | ndarray, shape (n_matrices,), default=None

Labels for each matrix.

sample_weightNone | ndarray, shape (n_matrices,), default=None

Weights for each matrix. If None, it uses equal weights.

Returns

selfElectrodeSelection instance

The ElectrodeSelection instance.

fit_transform(X, y=None, **fit_params)

Fit to data, then transform it.

Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.

Parameters

Xarray-like of shape (n_samples, n_features)

Input samples.

yarray-like of shape (n_samples,) or (n_samples, n_outputs), default=None

Target values (None for unsupervised transformations).

**fit_paramsdict

Additional fit parameters.

Returns

X_newndarray array of shape (n_samples, n_features_new)

Transformed array.

get_params(deep=True)

Get parameters for this estimator.

Parameters

deepbool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns

paramsdict

Parameter names mapped to their values.

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters

**paramsdict

Estimator parameters.

Returns

selfestimator instance

Estimator instance.

transform(X)

Return reduced matrices.

Parameters

Xndarray, shape (n_matrices, n_channels, n_channels)

Set of SPD matrices.

Returns

covsndarray, shape (n_matrices, n_elec, n_elec)

Set of SPD matrices after reduction of the number of channels.