EthicalML/xai
XAI - An eXplainability toolbox for machine learning
This tool helps data scientists and machine learning engineers analyze and evaluate their machine learning models to ensure fairness and transparency. It takes in your dataset and trained model, then outputs visualizations and metrics that highlight data imbalances, feature importance, and model performance across different groups. This is for anyone building or deploying machine learning models who needs to understand why their model makes certain decisions and identify potential biases.
1,229 stars. Available on PyPI.
Use this if you need to understand the underlying reasons for your machine learning model's predictions and ensure it performs fairly across different user groups.
Not ideal if you are looking for a simple plug-and-play solution without any technical understanding of data science or machine learning workflows.
Stars
1,229
Forks
186
Language
Python
License
MIT
Last pushed
Nov 29, 2025
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EthicalML/xai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...