Issue: Error in comparison of `mean.vect` and `censoring.thr` due to length mismatch in function of model.selector

First of all, thank you for developing and maintaining this great package! It's been really helpful for my analysis. However, I encountered the following error while running the function:

Error in mean.vect > censoring.thr: 
(converted from warning) longer object length is not a multiple of shorter object length

This occurs during the execution of the following block of code:

if (max(obj.fnc) > 0) {
    censoring.thr = support[which(obj.fnc == max(obj.fnc))]  # Set threshold
} else {
    censoring.thr = min.support - 1
}
model.selector[which(mean.vect > censoring.thr)] = 1

length(censoring.thr)

[1] 6

length(mean.vect)

[1] 2981

The error is caused by a length mismatch between mean.vect and censoring.thr. The error message indicates that the comparison between mean.vect (which is a vector with length equal to the number of features) and censoring.thr (which is a scalar) results in a length mismatch during the comparison mean.vect > censoring.thr.

Environment:

R version 4.2.1 (2022-06-23)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 18.04.5 LTS

Looking forward to any suggestions or fixes!

Start at the model.selector function and reproduce the reported comparison using the lengths shown for mean.vect and censoring.thr. Inspect how censoring.thr is produced from support and obj.fnc, then verify the intended length relationship. Done means the reported input no longer emits the length-mismatch warning and model.selector has the expected result.