feat: check_enough_train_data #283
Conversation
| #' when [prep()] is run, some operations may not be able to be | ||
| #' conducted on new data (e.g. processing the outcome variable(s)). | ||
| #' Care should be taken when using `skip = TRUE` as it may affect | ||
| #' the computations for subsequent operations. |
There was a problem hiding this comment.
I'm wondering if looks like you have a test demonstrating it does do that! So we definitely have a functional check for training data, if not test data.skip=TRUE by default would solve the issue about running during fit vs predict?
There was a problem hiding this comment.
yup! I'd like to handle test data checking next, unclear if that will be possible.
There was a problem hiding this comment.
This is failing checks because purrr isn't in the namespace (though map() is available internally).
Also a few comments below. The simplification for counting is perhaps important (at least easier).
I'm requesting changes only because of the possible bug and the missing NAMESPACE.
|
@dshemetov One more thing before merging: can you add the check to the |
|
Sure, let me take a look at how much work that will be. |
Attempt at fixing #106.
It seems to work well (see the tests) for both geo pooled and non geo pooled (more generally key col pooled) cases, but I still don't know how to keep this from running at test time, where the number of data points available will be way different and may cause problems.
@dajmcdon any suggestions?