himalaya.kernel_ridge.generate_dirichlet_samples

himalaya.kernel_ridge.generate_dirichlet_samples(n_samples, n_kernels, concentration=[0.1, 1.0], random_state=None)[source]

Generate samples from a Dirichlet distribution.

Parameters
n_samplesint

Number of samples to generate.

n_kernelsint

Number of dimension of the distribution.

concentrationfloat, or list of float

Concentration parameters of the Dirichlet distribution. A value of 1 corresponds to uniform sampling over the simplex. A value of infinity corresponds to equal weights. If a list, samples cycle through the list.

random_stateint, or None

Random generator seed. Use an int for deterministic samples.

Returns
gammasarray of shape (n_samples, n_kernels)

Dirichlet samples.