Better explain the groups param & batch effects in the intro vignette #234
Labels
documentation
Improvements or additions to documentation
good first issue
Good issue for first-time contributors
Note from lab meeting code club on the documentation:
There was confusion about how the
groups
parameter works and why one would want to use it. Need to explicitly state that observations (rows) from the same group are kept together in the train/test split. Overfitting was brought up as a concern -- thinking that usinggroups
might cause models to be overfit. But really it would reveal whether overfitting has occurred.The text was updated successfully, but these errors were encountered: