cassiopy.stats.SkewT.random_cluster

The random_cluster method generates multiple values from various skew-t distributions (clusters) using randomly generated parameters.

cassiopy.stats.SkewT.random_cluster(n_samples=100, n_dim=1, n_clusters=4, random_state=None, labels=None)

Generates random clusters based on the SkewT distribution.

Parameters:

n_samplesint

Number of samples to generate.

n_dimint

Number of dimensions.

n_clustersint

Number of clusters.

random_stateint

Random seed for reproducibility.

Returns:

dataarray-like

Generated data with shape (n_samples, n_dim).

y_truearray-like

Labels for the generated data with shape (n_samples,).

Notes

For more information, refer to the documentation Statistic

Examples

>>> from cassiopy.stats import SkewT
>>> sm = SkewT()
>>> data, labels = sm.random_cluster(n_samples=200, n_dim=2, n_clusters=3, random_state=123)
>>> data.shape
(200, 2)
>>> labels.shape
(200,)