#7979th of 105 in ML frameworks and libraries
interpret
Python library for training interpretable models and explaining blackbox ML models
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Mar 2026
- Language
- C++
Missed the latest GitHub check; these facts may be older.
Overview
InterpretML is a Python package that trains glassbox models, mainly the Explainable Boosting Machine (a boosted GA2M-style additive model), and wraps blackbox explainers such as SHAP, LIME, Morris sensitivity and partial dependence. It produces global and local explanations and a comparison dashboard via show(), and includes differentially private EBMs. The core is C++ with a Python API for tabular data.
Who it is for: Data scientists who need explainable tabular models
Strengths
- EBM AUROC is on par with XGBoost on the README's five benchmark datasets, with exact explanations
- One API covers glassbox models plus SHAP, LIME, Morris and partial dependence explainers
- Includes differentially private EBMs with epsilon and delta parameters
- README reports EBMs fitting 100 million samples in several hours; distributed option on Azure SynapseML
Weaknesses
- Aimed at tabular classification and regression; no LLM or deep network interpretability in the README
- EBMs use pairwise interactions by default; 3-way and higher need a custom notebook
- Distributed training for larger workloads relies on Azure SynapseML
- Blackbox explainers are wrappers around existing packages such as shap and lime
What it needs
- no GPU
- Needs Python 3.10+, scikit-learn, plotly, dash
- Models: Explainable Boosting Machine, APLR, Decision Tree, Decision Rule List, Linear/Logistic Regression
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |