A Python package to assess and improve fairness of machine learning models.
Open source
24 alternativesELI5
Python package which helps to debug machine learning classifiers and explain their predictions.
About ELI5
ELI5 is an open-source Python package for debugging and inspecting machine learning classifiers and explaining their predictions. It supports scikit-learn, Keras, xgboost, LightGBM, CatBoost, lightning, sklearn-crfsuite, and the OpenAI Python client. Its scikit-learn support includes linear classifiers and regressors, decision trees, tree ensembles, text processing utilities, Pipeline and FeatureUnion, and debugging pipelines containing HashingVectorizer by undoing hashing. Other capabilities include Grad-CAM visualizations for Keras image classifiers, feature importances for several libraries, and LLM prediction explanations with token probabilities.
For black-box models, ELI5 provides TextExplainer using the LIME algorithm for any text classifier, plus permutation importance for feature importances. LIME utilities for non-text data and arbitrary black-box classifiers are described as experimental. Explanation and formatting are separated, so results can be returned as text for console display, HTML for notebooks or web dashboards, a pandas.DataFrame, or JSON. The project is MIT-licensed.
Key features
- Explains scikit-learn linear classifiers and regressors, decision trees, and tree ensembles
- Prints decision trees as text or SVG and shows feature importances
- Supports Keras image classifier explanations via Grad-CAM visualizations
- Explains xgboost, LightGBM, CatBoost, lightning, and sklearn-crfsuite models
- TextExplainer uses LIME to explain predictions of any text classifier
- Outputs explanations as text, HTML, pandas.DataFrame, or JSON
Best for: Data scientists and machine learning practitioners who need to debug classifiers and inspect or explain their predictions in Python.
Good for
- Supports multiple machine learning frameworks and packages, including scikit-learn, Keras, xgboost, LightGBM, CatBoost, lightning, and sklearn-crfsuite.
- Separates explanation from formatting with text, HTML, pandas.DataFrame, and JSON options.
- Includes black-box inspection methods such as TextExplainer with LIME and permutation importance.
Watch out for
- LIME utilities for non-text data and arbitrary black-box classifiers are experimental.
ELI5 at a glance
- Website
- github.com/eli5-org/eli5
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
ELI5 alternatives
Tools and sites you could use instead, ranked by how closely they match.
nilearn provides Python tools for machine learning and neuroimaging analysis.
Open source
24 alternatives
An open source Python library for drift detection in machine learning systems.
Open source
24 alternatives
Feature Engine provides Python tools for feature engineering and selection that are compatible with scikit-learn.
Open source
24 alternatives
modAL provides a modular active learning framework for Python built on top of scikit-learn.
Open source
24 alternatives
The lightly Python library supports self supervised learning on images.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
ELI5 FAQ
What is ELI5?
ELI5 is a Python package that helps debug machine learning classifiers and explain their predictions.
Which frameworks and packages does ELI5 support?
It supports scikit-learn, Keras, xgboost, LightGBM, CatBoost, lightning, sklearn-crfsuite, and the OpenAI Python client, with black-box inspection methods such as TextExplainer and permutation importance.
What output formats can ELI5 explanations use?
Explanations can be produced as text for console display, HTML for notebooks or web dashboards, a pandas.DataFrame, or JSON.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.