pymc.dims.Categorical

class pymc.dims.Categorical(name, *dist_params, dims=None, initval=None, observed=None, total_size=None, transform=UNSET, default_transform=UNSET, model=None, **kwargs)

Categorical distribution.

Parameters:

pxtensor_like, optional

Probabilities of each category. Must sum to 1 along the core dimension. Must be provided if logit_p is not specified.

logit_pxtensor_like, optional

Alternative parametrization using logits. Must be provided if p is not specified.

core_dimsstr

The core dimension of the distribution, which represents the categories. The dimension must be present in p or logit_p.

**kwargs

Other keyword arguments used to define the distribution.

Returns:

XTensorVariable

An xtensor variable representing the categorical distribution. The output does not contain the core dimension, as it is absorbed into the distribution.

Methods

Categorical.dist([p, logit_p, core_dims])