Tidymodels: ...columns were requested but there were x predictors

[user_login_forked_up]

What does this message mean?:

! Fold1: preprocessor 1/1, model 8/12: 99 columns were requested but there were 97 predictors in the data. 97 wil...

Thx.

[Max]

Can you please provide a minimal reprex (reproducible example)? The goal of a reprex is to make it as easy as possible for me to recreate your problem so that I can fix it: please help me help you!

If you've never heard of a reprex before, start by reading "What is a reprex", and follow the advice further down that page.

[user_login_forked_up]

reprex()
#> Error in reprex(): could not find function "reprex"
Created on 2021-08-03 by the reprex package (v2.0.0)

reprex::reprex()
#> i Non-interactive session, setting html_preview = FALSE.
#> CLIPR_ALLOW has not been set, so clipr will not run interactively
#> Error in switch(where, expr = stringify_expression(x_expr), clipboard = ingest_clipboard(), : EXPR must be a length 1 vector

[user_login_forked_up]

Is the initial message probably coused by a divergence between vfold_cv() and recipe(), in their results, in regard to count of features/columns?

[Max]

There's really no way to know without code and a small, reproducible example that we can execute.

[user_login_forked_up]

Did someone else got this message- and in which context?

[user_login_forked_up]

@user_login_forked_up

vfold_cv

I think the answer is, that vfold_cv() indeed needs proceeded recipe data, when used in trainings e.g. tune_grid().

[Max]

That is not the case. You should never need to resample the preprocessed data.