The mlr3 ecosystem has a new package mlr3inferr that allows to construct confidence intervals for the generalization error.
Tasks
The mlr3 packages also ship with some data sets, readily usable as Task objects. The goal of these tasks is to quickly demonstrate the capabilities of the packages.
Example Usage
Create a classification task from the data set in the palmerpenguins package.
library("mlr3verse")# create a tasktask =tsk("breast_cancer")task
<TaskClassif:breast_cancer> (683 x 10): Wisconsin Breast Cancer
* Target: class
* Properties: twoclass
* Features (9):
- ord (9): bare_nuclei, bl_cromatin, cell_shape, cell_size,
cl_thickness, epith_c_size, marg_adhesion, mitoses, normal_nucleoli