Philipp Adämmer

https://github.com/quanteda/quanteda/blob/06f424b7960f19068e3f6e2b33bc918d961e7499/R/convert.R#L320 https://github.com/quanteda/quanteda/blob/06f424b7960f19068e3f6e2b33bc918d961e7499/R/convert.R#L323 I assume `length(empty_docs)` has to be changed to `sum(empty_docs)`? If so the same holds for `length(empty_feats)` in line 328.

Thanks for the great package! Would it be possible to change 'CompressedPredictorMatrix' to a mutable struct? This would allow modifying the predicted values and implementing the relaxed lasso.

Yes, a sparse matrix might be better to save the parameters. Regarding the struct, I think line 90 should be changed to a mutable struct: https://github.com/JuliaStats/GLMNet.jl/blob/master/src/GLMNet.jl Or is there any...

Nice, thanks for the tip!

@azev77 Yes, I was able to implement but within a time series framework (https://github.com/AdaemmerP/DetectSparsity/blob/main/CaseStudies/Functions.jl, lines 337 - 501). I also used the Lasso.jl package for it.