interpretml/interpret-community
Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world datasets and workflows.
This tool helps data scientists understand why their machine learning models make certain predictions, especially for models trained on tabular data. It takes your trained model and data, and outputs explanations about feature importance or model behavior, even for complex deep learning or ensemble models. Data scientists can use this to debug models, ensure fairness, or build trust with stakeholders by explaining model decisions.
442 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Use this if you need to explain the predictions of your machine learning models built with Python, particularly those working with tabular data.
Not ideal if your primary need is to explain models based on image, audio, or natural language data that isn't represented in a tabular format.
Stars
442
Forks
88
Language
Python
License
MIT
Last pushed
Feb 07, 2025
Commits (30d)
0
Dependencies
9
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/interpretml/interpret-community"
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...