poloclub/webshap
JavaScript library to explain any machine learning models anywhere!
This is a JavaScript library that helps you understand why a machine learning model made a particular decision, right in your web browser. It takes your model's prediction for a specific data point and tells you how much each input factor contributed to that outcome. Data scientists, machine learning engineers, and product managers can use this to make ML models more transparent.
No commits in the last 6 months.
Use this if you need to provide clear, interactive explanations for your machine learning model's predictions directly within a web application, without sending data to a server.
Not ideal if your primary need is for server-side or batch explanations, or if you require extremely high performance for very large models or data points where real-time browser computation would be too slow.
Stars
68
Forks
20
Language
TypeScript
License
MIT
Last pushed
Mar 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/poloclub/webshap"
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...