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 and is part of scikit-learn-contrib
projects.
Installation documentation, API documentation, and examples can be found on the
documentation.
imbalanced-learn is tested to work under Python 3.6+.
The dependency requirements are based on the last scikit-learn release:
- scipy(>=0.19.1)
- numpy(>=1.13.3)
- scikit-learn(>=0.23)
- joblib(>=0.11)
- keras 2 (optional)
- tensorflow (optional)
Additionally, to run the examples, you need matplotlib(>=2.0.0) and
pandas(>=0.22).
imbalanced-learn is currently available on the PyPi's repository and you can
install it via pip:
pip install -U imbalanced-learn
The package is release also in Anaconda Cloud platform:
conda install -c conda-forge imbalanced-learn
If you prefer, you can clone it and run the setup.py file. Use the following
commands to get a copy from GitHub and install all dependencies:
git clone https://github.com/scikit-learn-contrib/imbalanced-learn.git
cd imbalanced-learn
pip install .
Or install using pip and GitHub:
pip install -U git+https://github.com/scikit-learn-contrib/imbalanced-learn.git
After installation, you can use pytest to run the test suite:
make coverage
The development of this scikit-learn-contrib is in line with the one
of the scikit-learn community. Therefore, you can refer to their
Development Guide.
If you use imbalanced-learn in a scientific publication, we would appreciate
citations to the following paper:
@article{JMLR:v18:16-365,
author = {Guillaume Lema{{\^i}}tre and Fernando Nogueira and Christos K. Aridas},
title = {Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning},
journal = {Journal of Machine Learning Research},
year = {2017},
volume = {18},
number = {17},
pages = {1-5},
url = {http://jmlr.org/papers/v18/16-365}
}
Most classification algorithms will only perform optimally when the number of
samples of each class is roughly the same. Highly skewed datasets, where the
minority is heavily outnumbered by one or more classes, have proven to be a
challenge while at the same time becoming more and more common.
One way of addressing this issue is by re-sampling the dataset as to offset this
imbalance with the hope of arriving at a more robust and fair decision boundary
than you would otherwise.
- Re-sampling techniques are divided in two categories:
- Under-sampling the majority class(es).
- Over-sampling the minority class.
- Combining over- and under-sampling.
- Create ensemble balanced sets.
Below is a list of the methods currently implemented in this module.
- Under-sampling
- Random majority under-sampling with replacement
- Extraction of majority-minority Tomek links [1]
- Under-sampling with Cluster Centroids
- NearMiss-(1 & 2 & 3) [2]
- Condensed Nearest Neighbour [3]
- One-Sided Selection [4]
- Neighboorhood Cleaning Rule [5]
- Edited Nearest Neighbours [6]
- Instance Hardness Threshold [7]
- Repeated Edited Nearest Neighbours [14]
- AllKNN [14]
- Over-sampling
- Random minority over-sampling with replacement
- SMOTE - Synthetic Minority Over-sampling Technique [8]
- SMOTENC - SMOTE for Nominal Continuous [8]
- bSMOTE(1 & 2) - Borderline SMOTE of types 1 and 2 [9]
- SVM SMOTE - Support Vectors SMOTE [10]
- ADASYN - Adaptive synthetic sampling approach for imbalanced learning [15]
- KMeans-SMOTE [17]
- ROSE - Random OverSampling Examples [19]
- Over-sampling followed by under-sampling
- SMOTE + Tomek links [12]
- SMOTE + ENN [11]
- Ensemble classifier using samplers internally
- Easy Ensemble classifier [13]
- Balanced Random Forest [16]
- Balanced Bagging
- RUSBoost [18]
- Mini-batch resampling for Keras and Tensorflow
The different algorithms are presented in the sphinx-gallery.
[1] | : I. Tomek, “Two modifications of CNN,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 6, pp. 769-772, 1976. |
[2] | : I. Mani, J. Zhang. “kNN approach to unbalanced data distributions: A case study involving information extraction,” In Proceedings of the Workshop on Learning from Imbalanced Data Sets, pp. 1-7, 2003. |
[3] | : P. E. Hart, “The condensed nearest neighbor rule,” IEEE Transactions on Information Theory, vol. 14(3), pp. 515-516, 1968. |
[4] | : M. Kubat, S. Matwin, “Addressing the curse of imbalanced training sets: One-sided selection,” In Proceedings of the 14th International Conference on Machine Learning, vol. 97, pp. 179-186, 1997. |
[5] | : J. Laurikkala, “Improving identification of difficult small classes by balancing class distribution,” Proceedings of the 8th Conference on Artificial Intelligence in Medicine in Europe, pp. 63-66, 2001. |
[6] | : D. Wilson, “Asymptotic Properties of Nearest Neighbor Rules Using Edited Data,” IEEE Transactions on Systems, Man, and Cybernetrics, vol. 2(3), pp. 408-421, 1972. |
[7] | : M. R. Smith, T. Martinez, C. Giraud-Carrier, “An instance level analysis of data complexity,” Machine learning, vol. 95(2), pp. 225-256, 2014. |
[8] | (1, 2) : N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321-357, 2002. |
[9] | : H. Han, W.-Y. Wang, B.-H. Mao, “Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning,” In Proceedings of the 1st International Conference on Intelligent Computing, pp. 878-887, 2005. |
[10] | : H. M. Nguyen, E. W. Cooper, K. Kamei, “Borderline over-sampling for imbalanced data classification,” In Proceedings of the 5th International Workshop on computational Intelligence and Applications, pp. 24-29, 2009. |
[11] | : G. E. A. P. A. Batista, R. C. Prati, M. C. Monard, “A study of the behavior of several methods for balancing machine learning training data,” ACM Sigkdd Explorations Newsletter, vol. 6(1), pp. 20-29, 2004. |
[12] | : G. E. A. P. A. Batista, A. L. C. Bazzan, M. C. Monard, “Balancing training data for automated annotation of keywords: A case study,” In Proceedings of the 2nd Brazilian Workshop on Bioinformatics, pp. 10-18, 2003. |
[13] | : X.-Y. Liu, J. Wu and Z.-H. Zhou, “Exploratory undersampling for class-imbalance learning,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 39(2), pp. 539-550, 2009. |
[14] | (1, 2) : I. Tomek, “An experiment with the edited nearest-neighbor rule,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 6(6), pp. 448-452, 1976. |
[15] | : H. He, Y. Bai, E. A. Garcia, S. Li, “ADASYN: Adaptive synthetic sampling approach for imbalanced learning,” In Proceedings of the 5th IEEE International Joint Conference on Neural Networks, pp. 1322-1328, 2008. |
[16] | : C. Chao, A. Liaw, and L. Breiman. "Using random forest to learn imbalanced data." University of California, Berkeley 110 (2004): 1-12. |
[17] | : Felix Last, Georgios Douzas, Fernando Bacao, "Oversampling for Imbalanced Learning Based on K-Means and SMOTE" |
[18] | : Seiffert, C., Khoshgoftaar, T. M., Van Hulse, J., & Napolitano, A. "RUSBoost: A hybrid approach to alleviating class imbalance." IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans 40.1 (2010): 185-197. |
[19] | : Menardi, G., Torelli, N.: "Training and assessing classification rules with unbalanced data", Data Mining and Knowledge Discovery, 28, (2014): 92–122 |