LIME (Local Interpretable Model-agnostic Explanations)
VerifiedOpen-source Python library for explaining predictions of any machine learning classifier in an interpretable and faithful manner. 12,000+ GitHub stars.
Frameworks Covered
NIST-AI-RMF
Services
model-explainabilityinterpretabilitylocal-explanations
About LIME
LIME (Local Interpretable Model-agnostic Explanations) is a technique that explains the prediction of any classifier in an interpretable and faithful way, by learning an interpretable model locally around the prediction.
Features
- Model-agnostic explanations
- Local fidelity around individual predictions
- Supports tabular, text, and image data
- Feature importance for individual predictions
- Sparse linear explanations
- Works with any black-box classifier
Installation
pip install lime
Loading reviews...