[Question/Feature Request] Any explainability output or examples available to try out

[neomatrix369]

Feature request

What is the expected behavior?
No behaviour changes. Rather add examples to the docs or the examples section of the repo.

What is motivation or use case for adding/changing the behavior?
Make it easy to allow users to adapt it into their ML workflow. As explainability is an important topic in the current atmosphere.

How should this be implemented in your opinion?
No implementation needed, just docs and examples either as a python code snippet, a Jupyter notebook or a Kaggle kernel will be sufficient.

Are you willing to work on this yourself?
yes

[eduardocarvp]

Hi @neomatrix369 ,

Our example/tutorial notebooks contain a special section for the explainability. If you have a look here https://github.com/dreamquark-ai/tabnet/blob/develop/census_example.ipynb , there is a section subtitled Local explainability and masks where we try to explain, for each input data line and for each step in the architecture, what are the mask values as well as the final explain_matrix.

Of course, if you have suggestions on how to better show these results or how to make them clearer we'd love to hear your feedback!

[neomatrix369]

Thank you for sharing the link, I will give it a whirl!