nyuvis/explanation_explorer
A user interface to interpret machine learning models.
This tool helps data scientists and machine learning engineers understand why a machine learning model makes certain predictions. You provide a trained model and its predictions for a dataset, and it outputs an interactive visual interface. This interface groups similar explanations together, allowing you to explore the most significant features influencing predictions and their prevalence across your data.
No commits in the last 6 months.
Use this if you need to interpret the behavior of your binary classification models, such as understanding why a model predicts a loan as high-risk or a product review as positive.
Not ideal if you're looking for a tool to train models or if your models are not binary classifiers.
Stars
71
Forks
4
Language
JavaScript
License
BSD-3-Clause
Last pushed
Jan 14, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nyuvis/explanation_explorer"
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...