Hello, I am trying to convert this notebook to PyMC v5 (from v3). I am stuck on code block 16.7. I read the updated DensityDist documentation and believe this is this should be the correct way to use that API. def logp(value, p, majority_first): phi = [None] * 5 # Probability of data …

You may need to specify ndims_params=[1, 0] to tell PyMC that the probability of a single observation is parametrized by a vector as the first parameter and a scalar for the second (if I got that correctly) There are more details about this in this guide: Distribution Dimensionality — PyMC 5.10.3 d…

Shape Issue with custom logp in DensityDist

Questions v5

yahrMason January 13, 2024, 2:37am 8

Thanks for these suggestions. Both work and there is no longer any bug messages when I call pm.sample. I appreciate your insights.

1 Like

Topic		Replies	Views
Error while using DensityDist Questions	1	881	August 5, 2018
pm.DensityDist problem under PMYC 4 v5	17	2478	June 14, 2022
DensityDist from scipy.stats distribution Questions	5	2287	May 20, 2018
Creating custom likelihoods with DensityDist - what am I doing wrong? Questions	1	865	November 5, 2017
How to do linear fitting with pymc3 by using pm.DensityDist Questions	6	1046	May 4, 2018

Shape Issue with custom logp in DensityDist

Related topics