Parameters for class-imbalance samplingSource:
For up- and down-sampling methods, these parameters control how much data are added or removed from the training set.
A two-element vector holding the defaults for the smallest and largest possible values, respectively. If a transformation is specified, these values should be in the transformed units.
transobject from the
scalespackage, such as
scales::reciprocal_trans(). If not provided, the default is used which matches the units used in
range. If no transformation,
recipes::step_downsample() for the
interpretation of these parameters.