Emil Hvitfeldt

You are getting these errors because the package recipeselectors is changing its name to 'colino'. Continued package development and eventual release top CRAN will occur from the 'https://github.com/stevenpawley/colino' repository.

With the help of @lbui30, we were able to locate the problem which happened with a modification of an example we had on tidymodels.org. Thus purrr wasn't at fault.

I used `NextMethod()` to make it so `print.model_fit()` is in charge of the actually printing, and `print._coxnet()` only adds extra.

looking good!

This is a good idea! Once I around to doing some {discrim} work I'll make sure to take a look at this

Hello @StevenWallaert Do you mind clarifying a bit? Below I was able to apply `group_bootstraps()` on a data.frame with 10000 rows and 500 groups. Does this mirror your setup? ```...

Brain dump: The main thought I have about this, is that to be tidymodels compliant we need to stay within tibbles, and rectangular data.

Hello @LordRudolf, this feels like is more of a {caret} issue than a {recipes} issue.

We should also think about how we handle wrongly specified tuning parameters. The following is obviously nonsense, ```r boost_tree("regression", min_n = threshold(range = c(0, 0.5))) ``` But we can't match...

thanks for reporting! that does appear to be a bug, or at least the wrong way to handle this situation. We will look into it