Tommy Lees

How do we do this in a principled and defensible way. - From their contribution to predictive accuracy? - by their SHAP values? - by our understanding of drought processes...

Current working assumptions: - Doesn’t matter for predictive accuracy - But does matter for interpretability (SHAP Values) - Yes is important because we’re diagnosing the important features as well as...

Some testing ideas / principles

1

Ref: [PR 53: Pytest to environment.yml](https://github.com/spaceml-org/ml4floods/pull/53) First thing to say is that you probably don't need to write much more code. The notebooks contain the test principles, it's just an...

select individual levels from the Dimensions to plot pystan

3

## Short Description I want to select individual levels from the Dimensions to plot because plotting all of the levels of a variable is slow and the plot uninterpretable. ##...

when running `invoke ssl` i get the following error: `command not found: invoke` Any thoughts?

TODO: figure out how to run posterior predictive simulations in Bambi

1

I don't know if this is helpful but I noticed in a few of the notebooks you have notes to yourself about using Bambi to get a posterior predictive check....