Skip to content

gaussian mixture model #102

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

Closed
OriolAbril opened this issue Apr 5, 2021 · 6 comments
Closed

gaussian mixture model #102

OriolAbril opened this issue Apr 5, 2021 · 6 comments
Assignees
Labels
tracker id Issues used as trackers in the notebook update project, do not close!

Comments

@OriolAbril
Copy link
Member

File: https://github.com/pymc-devs/pymc-examples/blob/main/examples/mixture_models/gaussian_mixture_model.ipynb
Reviewers:

The sections below may still be pending. If so, the issue is still available, it simply doesn't
have specific guidance yet. Please refer to this overview of updates

Known changes needed

Changes listed in this section should all be done at some point in order to get this
notebook to a "Best Practices" state. However, these are probably not enough!
Make sure to thoroughly review the notebook and search for other updates.

General updates

ArviZ related

Changes for discussion

Changes listed in this section are up for discussion, these are ideas on how to improve
the notebook but may not have a clear implementation, or fix some know issue only partially.

General updates

ArviZ related

Notes

Exotic dependencies

Computing requirements

@OriolAbril OriolAbril added the tracker id Issues used as trackers in the notebook update project, do not close! label Apr 5, 2021
@chiral-carbon chiral-carbon self-assigned this Aug 14, 2021
@drbenvincent
Copy link
Contributor

This could be updated to use new pm.Mixture

@drbenvincent
Copy link
Contributor

Any reason why the cluster means can't use pymc.distributions.transforms.Ordered?

@drbenvincent
Copy link
Contributor

Actually, anyone mind if I update this with pm.NormalMixture? We can get some significant simplification of this notebook.

@OriolAbril
Copy link
Member Author

That sounds amazing and things like that are the reason there is a v4 (auto) and a Done category in the tracker project that are clearly separated. It wasn't the case, but this notebook might have run when changing import pymc3 to import pymc and theano to aesara, but that a notebook runs on v4 doesn't mean it is updated to be documentation for v4.

I am not sure how much of that was already available in latest v3 releases, but the issue is the same. A notebook is added to cover and explain a specific use case, a while later we see (or have time to implement) a way to make that case better and easier, but when the feature is added to pymc, the notebook is not updated. When that happens many users won't be aware the new feature exists, and others might now but be unable to use it without an example notebook so the new feature ends up being underused and the old but well documented way of doing things prevails.

@drbenvincent
Copy link
Contributor

Great. Will put in a PR soon.

@drbenvincent
Copy link
Contributor

Moving this in the notebook state tracker from 'todo' to 'done'. And closing issue

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
tracker id Issues used as trackers in the notebook update project, do not close!
Projects
Development

No branches or pull requests

3 participants