scikit-learn-contrib/imbalanced-learn

This tool helps data scientists and machine learning engineers build more accurate predictive models when their datasets have unequal numbers of examples across different categories. It takes a raw, imbalanced dataset and processes it using various re-sampling techniques to create a more balanced dataset, which then leads to improved model performance, especially for the under-represented categories. This is particularly useful for tasks where correctly identifying rare events is critical.

7,090 stars. Used by 23 other packages. Actively maintained with 1 commit in the last 30 days. Available on PyPI.