explainX/explainx
Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms8909@nyu.edu
This tool helps data scientists and business users understand, explain, and debug their machine learning models. It takes your trained black-box model and datasets as input, providing insights into why a model made a specific prediction, identifying biases, and helping build trust with stakeholders through interactive dashboards. It's designed for anyone working with AI solutions who needs to articulate model behavior clearly.
445 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to explain your machine learning model's predictions, debug its behavior, or demonstrate its fairness and trustworthiness to non-technical business users and compliance officers.
Not ideal if you primarily work with TensorFlow or PyTorch models, as direct support for these is still under development.
Stars
445
Forks
57
Language
Jupyter Notebook
License
MIT
Last pushed
Aug 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/explainX/explainx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
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...