GithubHelp home page GithubHelp logo

GLM model selection about pymc-examples HOT 9 OPEN

OriolAbril avatar OriolAbril commented on May 20, 2024
GLM model selection

from pymc-examples.

Comments (9)

chiral-carbon avatar chiral-carbon commented on May 20, 2024 1

@OriolAbril can I work on this?

from pymc-examples.

OriolAbril avatar OriolAbril commented on May 20, 2024 1

Great!

from pymc-examples.

OriolAbril avatar OriolAbril commented on May 20, 2024

I tried moving from nbsphinx to myst-nb and was unable to do so because the widgets in this notebook are not saved correctly, see https://github.com/jupyter/jupyter-sphinx/blob/master/jupyter_sphinx/ast.py#L607. After manually editing the metadata to remove the widgets completely I was able to build the documentation.

Side note: the DE-MCMC notebooks also have widgets but they are correctly saved are are not a problem.

from pymc-examples.

drbenvincent avatar drbenvincent commented on May 20, 2024

This could do with some simplification to focus on the core aspects of model comparison. Specific proposals:

  • remove interactive aspects of this notebook. They only work when running locally, not when viewing on the website. And in fact it is pretty clunky when I run the ipywidgets locally. Seems like a distraction.
    • remove interactive the dataset viewing
    • remove the interactive posterior plot viewing and just show static posterior predictions
  • remove plot_annotated_trace and just use az.plot_trace
  • why are we sometimes using raw data, sometimes the standardised data?

from pymc-examples.

OriolAbril avatar OriolAbril commented on May 20, 2024

Always in favour of simplifying notebooks to have a clearer and more to the point scope. My main concern (not remembering the content of either notebook right now so tread lightly) is that it might end up being too similar to https://www.pymc.io/projects/docs/en/stable/learn/core_notebooks/model_comparison.html

from pymc-examples.

drbenvincent avatar drbenvincent commented on May 20, 2024

Good point. Could potentially be expanded to include model comparison by Savage Dickey method perhaps

from pymc-examples.

drbenvincent avatar drbenvincent commented on May 20, 2024

I didn't actually realise there were these separate core notebooks.

I think it's very cool to have these core notebooks under "Learn". But I think these notebooks should additionally be visible along with the regular pymc example notebooks. Some people might go straight to the Examples and not know about the extra ones under Learn.

Can I propose that these core notebooks stay where they are, but are additionally available with the rest of the Example notebooks?

from pymc-examples.

OriolAbril avatar OriolAbril commented on May 20, 2024

But I think these notebooks should additionally be visible along with the regular pymc example notebooks

Yes, they should be listed at the top of the gallery page. We can use cards manually with sphinx-design

from pymc-examples.

drbenvincent avatar drbenvincent commented on May 20, 2024

I'll submit an issue and PR for this. Hopefully in the next few days.

from pymc-examples.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.