ModelOriented/DALEX
moDel Agnostic Language for Exploration and eXplanation
This tool helps data scientists and analysts understand how complex machine learning models make predictions. It takes an existing "black box" model and associated data, then produces explanations about how different input features influence the model's decisions, both generally and for specific cases. This is for anyone who needs to trust, validate, or communicate the reasoning behind their predictive models.
1,458 stars. Used by 1 other package. Available on PyPI.
Use this if you need to explain, debug, or ensure fairness in predictions made by complex machine learning models like neural networks or boosted trees.
Not ideal if your models are already simple and inherently interpretable, or if you don't need to justify or understand their internal workings.
Stars
1,458
Forks
171
Language
Python
License
GPL-3.0
Last pushed
Jan 20, 2026
Commits (30d)
0
Dependencies
7
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ModelOriented/DALEX"
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...