Skip to content
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.

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

Refactor Bayes Factor computation out of az.plot_bf #2402

Open
mpmbq2 opened this issue Dec 15, 2024 · 2 comments
Open

Refactor Bayes Factor computation out of az.plot_bf #2402

mpmbq2 opened this issue Dec 15, 2024 · 2 comments

Comments

@mpmbq2
Copy link

mpmbq2 commented Dec 15, 2024

The function az.plot_bf is very useful for visualizing Bayes Factors. However, some users may want to use Bayes Factors outside the context of the plot, so it would be useful to refactor the logic to compute the BF from arviz.plots to arviz.stats and make it part of the public API.

This seems like a very small change, and I'm happy to do it myself. But I am new to open source and have not communicated with you all before. So before I make the PR I wanted to make sure there's not a good reason to keep it the way it is right now.

@aloctavodia
Copy link
Contributor

Hi @mpmbq2, thanks for offering help. Your suggestion is a good one and you can send the PR if you want.

I just want to let you know that we are refactoring ArviZ. As part of the refactor, we are splitting functionality into 3 sub-packages and adding most of the new features in those packages (although there is no strict rule against adding new features to the main repo).

In the context of your proposal, the computation of the BF should live in arviz-stats and the plotting should be on arvivz-plots. Making a PR into one or both of those packages will be more work than making the changes here.

Both options will be helpful for us and the community, so please select the one that you like the most.

@mpmbq2
Copy link
Author

mpmbq2 commented Dec 24, 2024

Thanks for the heads up RE the package migration. For the sake of not over-thinking it, I decided to go ahead and make a PR to this repo. Once I get it accepted, I'll have a look at submitting PRs to the stats and plots repos.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants