dialnd / imbalanced-algorithms

Python-based implementations of algorithms for learning on imbalanced data.

ND DIAL: Imbalanced Algorithms

Minimalist Python-based implementations of algorithms for imbalanced learning. Includes deep and representational learning algorithms (implemented via TensorFlow). Below is a list of the methods currently implemented.

• Undersampling

  1. Random Majority Undersampling with/without Replacement

• Oversampling

  1. SMOTE - Synthetic Minority Over-sampling Technique [1]
  2. DAE - Denoising Autoencoder [2] (TensorFlow)
  3. GAN - Generative Adversarial Network [3] (TensorFlow)
  4. VAE - Variational Autoencoder [4] (TensorFlow)

• Ensemble Sampling

  1. RAMOBoost [5]
  2. RUSBoost [6]
  3. SMOTEBoost [7]

References:

[1]	: N. V. Chawla, K. W. Bowyer, L. O. Hall, and P. Kegelmeyer. "SMOTE: Synthetic Minority Over-Sampling Technique." Journal of Artificial Intelligence Research (JAIR), 2002.

[2]	: P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol. "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion". Journal of Machine Learning Research (JMLR), 2010.

[3]	: I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. "Generative Adversarial Nets". Advances in Neural Information Processing Systems 27 (NIPS), 2014.

[4]	: D. P. Kingma and M. Welling. "Auto-Encoding Variational Bayes". arXiv preprint arXiv:1312.6114, 2013.

[5]	: S. Chen, H. He, and E. A. Garcia. "RAMOBoost: Ranked Minority Oversampling in Boosting". IEEE Transactions on Neural Networks, 2010.

[6]	: C. Seiffert, T. M. Khoshgoftaar, J. V. Hulse, and A. Napolitano. "RUSBoost: Improving Classification Performance when Training Data is Skewed". International Conference on Pattern Recognition (ICPR), 2008.

[7]	: N. V. Chawla, A. Lazarevic, L. O. Hall, and K. W. Bowyer. "SMOTEBoost: Improving Prediction of the Minority Class in Boosting." European Conference on Principles of Data Mining and Knowledge Discovery (PKDD), 2003.

imbalanced-algorithms's Issues

Toy example

Thank you for sharing the code. Could you also share a toy example which make use of these algorithms?

In gan.py pre-train = True leads to error on Python 2.7 and 3.6

The error message is:
AttributeError: 'mtrand.RandomState' object has no attribute 'random'

The fix is:
Change mtrand to np.random.rand.

is:issue is:open Multi-class SMOTEBoost

Just curious to ask, does this package supports a multi-class problem with a multi-minority scenario? Not sure if I read this correctly, but it seems to me the support is only for the binary class problem:

if minority_target is None:
    # Determine the minority class label.
    stats_c_ = Counter(y)
    maj_c_ = max(stats_c_, key=stats_c_.get)
    min_c_ = min(stats_c_, key=stats_c_.get)
    self.minority_target = min_c_
else:
    self.minority_target = minority_target

In my current task, I have a multi-majority multi-minority scenario:

Class = 0,	Count = 18749,	Percentage = 22.01
Class = 1,	Count = 3482,	Percentage = 4.09
Class = 2,	Count = 9566,	Percentage = 11.23
Class = 3,	Count = 49741,	Percentage = 58.4
Class = 4,	Count = 3634,	Percentage = 4.27