Function reference • themis

Over-sampling

Over-sampling is the act of synthetically generating observations for the minority classes. This is done either by random sampling or using more advanced methods.

step_upsample(): Up-Sample a Data Set Based on a Factor Variable

step_smote(): Apply SMOTE Algorithm

step_smotenc(): Apply SMOTENC algorithm

step_bsmote(): Apply borderline-SMOTE Algorithm

step_adasyn(): Apply Adaptive Synthetic Algorithm

step_rose(): Apply ROSE Algorithm

Under-sampling

Under-sampling is the act of removing observations from the majority classes.

step_downsample(): Down-Sample a Data Set Based on a Factor Variable

step_nearmiss(): Remove Points Near Other Classes

step_tomek(): Remove Tomek’s Links

Methods

Some of the methods implemented in this package as steps are also available as their own functions.

smote(): SMOTE Algorithm

smotenc(): SMOTENC Algorithm

bsmote(): borderline-SMOTE Algorithm

adasyn(): Adaptive Synthetic Algorithm

nearmiss(): Remove Points Near Other Classes

tomek(): Remove Tomek's links

Datasets

circle_example: Synthetic Dataset With a Circle

Tidy Methods

tidy(<step_adasyn>) tidy(<step_bsmote>) tidy(<step_downsample>) tidy(<step_nearmiss>) tidy(<step_rose>) tidy(<step_smote>) tidy(<step_smotenc>) tidy(<step_tomek>) tidy(<step_upsample>): Tidy the Result of a Recipe