imbalanced-learn
scikit-learn-contribResampling library for classification on imbalanced data, built on the scikit-learn estimator interface. It provides over-sampling (SMOTE and its variants, ADASYN), under-sampling (NearMiss, Tomek links, edited nearest neighbours), combined methods and imbalance-aware ensembles such as balanced random forests and RUSBoost. It is a scikit-learn-contrib project run by volunteer maintainers.
Openness
5 high confidence- license
- MIT(OSI)
- source
- public(github.com/scikit-learn-contrib/imbalanced-learn)
- core features withheld
- no — community project in scikit-learn-contrib
MIT-licensed and built from the public repository. It is a volunteer-maintained scikit-learn-contrib project with no company behind it and nothing for sale.
- https://raw.githubusercontent.com/scikit-learn-contrib/imbalanced-learn/master/LICENSE recorded 2026-09-27
LICENSE is "The MIT License (MIT)", "Copyright (c) 2014-2020 The imbalanced-learn developers."
- https://raw.githubusercontent.com/scikit-learn-contrib/scikit-learn-contrib/master/README.md recorded 2026-09-27
scikit-learn-contrib README: "a github organization for gathering high-quality scikit-learn compatible projects"; imbalanced-learn "Maintained by Guillaume Lemaitre, Fernando Nogueira, Dayvid Oliveira and Christos Aridas."
- https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scikit-learn-contrib/imbalanced-learn recorded 2026-09-27
Repository record for scikit-learn-contrib/imbalanced-learn, not archived and not a fork, license mit, last pushed 2026-06-29.
- https://ungh.cc/repos/scikit-learn-contrib/imbalanced-learn/files/master recorded 2026-09-27
Repository tree of 251 paths with no ee, enterprise, commercial or pro directory.
Adoption
4 high confidenceMeasured on monthly PyPI downloads of the imbalanced-learn package.
- https://pypistats.org/api/packages/imbalanced-learn/recent recorded 2026-09-27
last_month 5,748,456 downloads of imbalanced-learn
Capability
2 medium confidenceimbalanced-learn fixes the class balance of the training data and adds a handful of ensembles built for skewed classes. It is a specialist add-on to scikit-learn, whose other learners it relies on, rather than a toolkit for choosing among many kinds of model.
- https://imbalanced-learn.org/stable/references/index.html recorded 2026-09-27
API reference sections: Under-sampling methods, Over-sampling methods, Combination of over- and under-sampling methods (SMOTEENN, SMOTETomek), Ensemble methods (EasyEnsembleClassifier, RUSBoostClassifier, BalancedBaggingClassifier, BalancedRandomForestClassifier), Miscellaneous, Pipeline, Metrics.
- https://raw.githubusercontent.com/scikit-learn-contrib/imbalanced-learn/master/README.rst recorded 2026-09-27
README: "imbalanced-learn is a python package offering a number of re-sampling techniques commonly used in datasets showing strong between-class imbalance. It is compatible with scikit-learn".
Verified 2026-09-27