Skip to content

sample_posterior_predictive does not handle InferenceData well #4025

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
twiecki opened this issue Jul 21, 2020 · 4 comments
Closed

sample_posterior_predictive does not handle InferenceData well #4025

twiecki opened this issue Jul 21, 2020 · 4 comments

Comments

@twiecki
Copy link
Member

twiecki commented Jul 21, 2020 •
edited
Loading

sample_posterior_predictive seems to require an old-school trace, but does not directly accept an InferenceData object. There is an easy workaround to just call sample_posterior_predictive(inference_object.trace) but I think it would be nice if it would detect that.
@rpgoldman
Copy link
Contributor

@michaelosthege has fixed this to the best of my knowledge, and there are even tests. If you can't use an inference data in place of a trace, it's a bug: please give details.

@rpgoldman
Copy link
Contributor

Plus, in general fast_sample_posterior_predictive is probably preferable...

@twiecki
Copy link
Member Author

twiecki commented Jul 23, 2020

I see, this is only fixed on master by #4006. Should probably do a new bugfix release.

@twiecki twiecki closed this as completed Jul 23, 2020
@AlexAndorra
Copy link
Contributor

Yeah probably. Could be a good time to update the docs too 😉

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@rpgoldman @twiecki @AlexAndorra