Emil Hvitfeldt

this is correct! nice find!

Thanks for the heads up and keen eye for detail

protection against deletion would be a great example of an alternative role. https://github.com/tidymodels/recipes/issues/252

Hello @yonisidi 👋 Sure would! I'll take a look next time to do a yardstick issue push

Hello @aminadibi 👋 Thanks for reporting this bug! This bug happens in `predict_class.model_fit()` where https://github.com/tidymodels/parsnip/blob/145bac2d319db9debdd4c3be062c8b20f1f9c780/R/predict_class.R#L31 returns a `1 x n` logical matrix. This object doens't have an `$values` field so...

I don't know if I would but it under clustering. It feels much close in something like applicable. Like it is a type of anomaly detection, like https://github.com/tidymodels/applicable/issues/19 right?

I have pull some of the features of this package into `step_textfeatures()` https://textrecipes.tidymodels.org/reference/step_textfeature.html. Is there other parts of this package that you need that you don't find there?

Quick note: if you install the latest dev version of {sparsevctrs} and run `withr::local_options("sparsevctrs.verbose_materialize" = 3)` you now get an error if a sparse vector is forced materialized by something...

# `mold()` issues Reprex: ```{r} mat

we will not be doing `mold()` and `forge()` this time around