In the cancer dataset, there are miRNA and mRNA variables that are categorical appear to not have any values. What is the most efficient way to drop these variables?
I'm also stuck on this!! I was going through the dataset and changing each one to to numeric but I figured that this is not a very efficient way considering I would probably eliminate these points later.
edit: so I used Preprocess and dragged Remove Sparse Features to remove any features with too many zeros. I wasn't sure what a good threshold (i tried 20%) was but this seemed to do the trick!
I tried using the Purge Domain widget which seemed to remove all of them but i'm not sure if that is the correct way to go about this.
Awesome! I used the same but i set the threshold to 99% since there are some values that have zero which I want to keep for now. The ones I want to remove exclusively have zeros.