Comparing numbers from papers directly is not very informative because different cross-validation sets are used. A better way would be to wrap MLJ.jl around the original sirus implementation in R. This PR is an attempt to do that. If it doesn't work, I'll probably have to fallback to taking numbers from the paper.
Comparing numbers from papers directly is not very informative because different cross-validation sets are used. A better way would be to wrap MLJ.jl around the original sirus implementation in R. This PR is an attempt to do that. If it doesn't work, I'll probably have to fallback to taking numbers from the paper.
Fixes #51.