pyriemann.clustering.MeanShift

class pyriemann.clustering.MeanShift(kernel='uniform', bandwidth=None, metric='riemann', tol=0.001, max_iter=100, n_jobs=1)

Clustering by mean shift with SPD/HPD matrices as inputs.

The mean shift is a non-parametric clustering method used to find clusters on the manifold of SPD/HPD matrices, estimating the gradient of matrices density [1].

Parameters:

kernel{“normal”, “uniform”} | callable, default=”uniform”

Kernel used for kernel density estimation.

bandwidthNone | float, default=None

Bandwidth of the kernel.

metricstring | dict, default=”riemann”

Metric used for map estimation (for the list of supported metrics, see pyriemann.utils.tangentspace.log_map()) and for distance estimation (see pyriemann.utils.distance.distance()). The metric can be a dict with two keys, “map” and “distance” in order to pass different metrics.

tolfloat, default=1e-4

Stopping criterion to stop convergence, representing the norm of gradient.

max_iterint, default=100

Maximum number of iteration to reach convergence.

n_jobsint, default=1

Number of jobs to use for the computation. This works by computing each of the n_init runs 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.

Attributes:

modes_ndarray, shape (n_modes, n_channels, n_channels)

Modes of each cluster.

labels_ndarray, shape (n_matrices,)

Labels, ie mode indices, of each matrix of training set.

See also

Kmeans

Notes

Added in version 0.9.

References

[1]

Nonlinear Mean Shift over Riemannian Manifolds R. Subbarao & P. Meer. International Journal of Computer Vision, 84, 1-20, 2009

__init__(kernel='uniform', bandwidth=None, metric='riemann', tol=0.001, max_iter=100, n_jobs=1)

Init.

fit(X, y=None)

Fit the modes of clusters.

Parameters:

Xndarray, shape (n_matrices, n_channels, n_channels)

Set of SPD/HPD matrices.

yNone

Not used, here for compatibility with sklearn API.

Returns:

selfMeanShift instance

The MeanShift instance.

fit_predict(X, y=None)

Fit and predict in a single function.

Parameters:

Xndarray, shape (n_matrices, n_channels, n_channels)

Set of SPD matrices.

yNone

Not used, here for compatibility with sklearn API.

Returns:

predndarray of int, shape (n_matrices,)

Prediction for each matrix according to the closest cluster.

get_metadata_routing()

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routingMetadataRequest

A MetadataRequest encapsulating routing information.

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.

predict(X)

Get the predictions.

Parameters:

Xndarray, shape (n_matrices, n_channels, n_channels)

Set of SPD/HPD matrices.

Returns:

predndarray of int, shape (n_matrices,)

Prediction for each matrix according to the closest mode.

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.

Examples using pyriemann.clustering.MeanShift

Clustering algorithm comparison

Clustering algorithm comparison