imbalanced-learn and imbalanced-ensemble
Imbalanced-learn provides foundational resampling and individual algorithm techniques (SMOTE, random undersampling, etc.), while imbalanced-ensemble builds specialized ensemble methods on top of these primitives to handle class imbalance at the ensemble level, making them complementary tools that can be used together in a machine learning pipeline.
About imbalanced-learn
scikit-learn-contrib/imbalanced-learn
A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning
Provides over-sampling, under-sampling, and hybrid re-sampling algorithms (SMOTE, ADASYN, tomek links) that integrate directly with scikit-learn's pipeline API for seamless preprocessing. Implements statistical and distance-based techniques to generate synthetic minority samples or remove noisy majority instances while maintaining data integrity. Supports TensorFlow and Keras models alongside traditional scikit-learn estimators for end-to-end imbalanced data workflows.
About imbalanced-ensemble
ZhiningLiu1998/imbalanced-ensemble
🛠️ Class-imbalanced Ensemble Learning Toolbox. | 类别不平衡/长尾机器学习库 [NeurIPS'25]
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work