HyperGeometric distribution causes AttributeError when calling model_to_graphviz()

Hello :slight_smile:

it seems that when a model contains a HyperGeometric distribution, model_to_graphiz() fails due to AttributeError.

Could it be that some of the parameters are stored as Numpy NdArray instead of Theano Tensor (i.e. missing eval() method) ?

I am a bit clueless here, any insight?

Code:

with pm.Model() as model:
    
    x =  pm.HyperGeometric('test', 5, 10, 100)

pm.model_to_graphviz(model)

TraceBack

This was solved updating to the last available version of PyMC3 (3.11.4) on conda.

1 Like