Function for importance variables of tidy models variables, workflow

Question

I need a function to use in a Workflow of the importance of variables that returns something similar to %IncMSE, I used a function from the VIP package but it only returns the plot, I want the column name format and its importance on the side. Below is the format I need for the output: https://i.stack.imgur.com/62dau.png

Answer 1

You could use the function vi form vip:

Compute variable importance scores for the predictors in a model.

Here a reproducible example:

library(tidymodels)
library(mlbench)
library(vip)
library(rpart)
set.seed(101)  
trn <- as.data.frame(mlbench::mlbench.friedman1(500))
tree <- rpart(y ~ ., data = trn)
vi(tree)
#> # A tibble: 10 × 2
#>    Variable Importance
#>    <chr>         <dbl>
#>  1 x.4           4234.
#>  2 x.2           2513.
#>  3 x.1           2461.
#>  4 x.5           1230.
#>  5 x.3            688.
#>  6 x.6            533.
#>  7 x.7            357.
#>  8 x.9            331.
#>  9 x.8            276.
#> 10 x.10           275.

^{Created on 2022-07-17 by the reprex package (v2.0.1)}