LIME

What it does

LIME (Local Interpretable Model-agnostic Explanations) is an open-source Python library (BSD-2-Clause) that explains individual predictions of any classifier. It perturbs an input, watches how the model's output changes and fits a simple linear model around that one example, showing which words, features or image regions drove the prediction. It works with text, tabular and image classifiers.

Compare with

• LvsCaptum
• LvsSHAP
• LvsInterpretML

People who use it also use

Not enough marks yet to tell. When people who use LIME mark the rest of their stack, it shows up here.