Over-sampling methods#

The imblearn.over_sampling provides a set of method to perform over-sampling.

Basic over-sampling#

RandomOverSampler(*[, sampling_strategy, ...])

Class to perform random over-sampling.

SMOTE algorithms#

SMOTE(*[, sampling_strategy, random_state, ...])

Class to perform over-sampling using SMOTE.

SMOTENC(categorical_features, *[, ...])

Synthetic Minority Over-sampling Technique for Nominal and Continuous.

SMOTEN([categorical_encoder, ...])

Synthetic Minority Over-sampling Technique for Nominal.

ADASYN(*[, sampling_strategy, random_state, ...])

Oversample using Adaptive Synthetic (ADASYN) algorithm.

BorderlineSMOTE(*[, sampling_strategy, ...])

Over-sampling using Borderline SMOTE.

KMeansSMOTE(*[, sampling_strategy, ...])

Apply a KMeans clustering before to over-sample using SMOTE.

SVMSMOTE(*[, sampling_strategy, ...])

Over-sampling using SVM-SMOTE.