mlr-org / mlr3filters

Filter-based feature selection for mlr3
https://mlr3filters.mlr-org.com
GNU Lesser General Public License v3.0
20 stars 8 forks source link

Missing filter / featsel methods #2

Open pat-s opened 5 years ago

pat-s commented 5 years ago

Filters

Pkg

No pkg

stats

FSelector

Do we want to have these filters in again? Slow and Java problems..

FSelectorRcpp

Learner integrated filters

Do we want to add the ramdomForest and randomForestSRC ones?

mRMRe

- [ ] mrmr -> slow and no support for classif tasks https://github.com/mlr-org/mlr/issues/2604

praznik

care

spFSR

Need to check.

Ensemble filters

mllg commented 5 years ago

For the filters: I'd start with stats / no pkg, then try to connect the modern filter packages (FSelectorRcpp and praznik).

We don't need 3 forest filters, we can solve this more generically by extending mlr3 learners with methods to extract feature scores.

ja-thomas commented 5 years ago

we can solve this more generically by extending mlr3 learners with methods to extract feature scores.

This is really important to be able to use all kinds of embedded feature selection directly by the learner.

ja-thomas commented 5 years ago

I don't really see a reason to use the Java FSelector package when there is FSelectoRcpp.

pat-s commented 5 years ago

I don't really see a reason to use the Java FSelector package when there is FSelectoRcpp.

The later does not have all filters of the former. See https://mlr.mlr-org.com/articles/tutorial/filter_methods.html.

ja-thomas commented 5 years ago

Well, with this argument we have to include all possible filters :smile:

I would suggest we start without it, and if people complain/open issues we can still add them later. Or are there any really important filters not yet in FSelectorRcpp?

berndbischl commented 5 years ago

there never is (should be) pressure to include everything, include what is most important

pat-s commented 5 years ago

My comment was more meant to be a comparison, not a statement that we should do it :)

mllg commented 5 years ago

NB: All learners which have some sort of "importance" are now supported via FilterVariableImportance.