Download
ELI5 is a Python library designed to help developers interpret, debug, and explain the predictions of machine learning models. The project focuses on improving model transparency by providing tools that visualize feature importance and prediction reasoning. It supports several popular machine learning frameworks including scikit-learn, XGBoost, LightGBM, CatBoost, and Keras. The library allows users to inspect model weights, analyze decision trees, and compute permutation feature importance for black-box models. It also provides specialized tools such as TextExplainer, which can highlight important words in text classification tasks to explain why a model produced a particular prediction. Additionally, the library integrates explanation algorithms such as LIME to interpret predictions from arbitrary machine learning models.
Features
- Tools for explaining predictions of machine learning models
- Support for frameworks such as scikit-learn, XGBoost, and LightGBM
- Visualization of feature importance and model weights
- Permutation importance for inspecting black-box models
- TextExplainer for interpreting text classification predictions
- Grad-CAM visualizations for neural network image classifiers
Project Samples
