salimamoukou/acv00
ACV is a python library that provides explanations for any machine learning model or data. It gives local rule-based explanations for any model or data and different Shapley Values for tree-based models.
This project helps data scientists, machine learning engineers, and researchers understand why their machine learning models make certain predictions or how specific data points influence outcomes. You input your trained model and data, and it outputs clear, local, rule-based explanations for any model, or more accurate Shapley Values for tree-based models, including correct handling of encoded categorical variables. This makes complex model behavior transparent and interpretable for better decision-making.
102 stars. No commits in the last 6 months.
Use this if you need to explain individual predictions from any machine learning model or understand the critical features driving specific data outcomes, especially if you work with tree-based models and encoded categorical variables.
Not ideal if you are looking for simple, global explanations of your model's overall behavior rather than detailed, instance-level insights, or if you prefer visual explanations over rule-based outputs.
Stars
102
Forks
11
Language
Jupyter Notebook
License
MIT
Last pushed
Aug 31, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/salimamoukou/acv00"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...