Create a use case for the gallery

[mllg]

[sebffischer]

I suggest using this dataset (5000 obs, 1k features)

[mllg]

Are you suggesting it because of its dimension or because filtering works pretty well on it?

What about spam in mlr3?

[pat-s]

spam would also work I'd say. In the end the question is what the use case should show:

• compare filters against wrappers?
• compare single filters against ensemble filters?
• showcase the caching attribute of filters?

None of the above do really depend on the dataset unless you want to find a use case where features outperform wrappers.

[sebffischer]

Yes, my idea was because there are so many features. I would prefer a regression task (because then I can use it for MaRDI), that would make spam less attractive for me.

Are there already benchmark studies on those questions @pat-s ? In this case we could make a gallery-posts that gives some recommendations on what to do with filters? I.e. giving the reader the answer to those questions :)