Lime

LIME (Local Interpretable Model-Agnostic Explanations)

Lime, Local Interpretable Model-Agnostic, is a local model interpretation technique using Local surrogate models to approximate the predictions of the underlying black-box model.

Local surrogate models are interpretable models like Linear Regression or a Decision Trees that are used to explain individual predictions of a black-box model.

Lime trains a surrogate model by generating a new data-set out of the datapoint of interest. The way it generates the data-set varies dependent on the type of data. Currently Lime supports text, image and tabular data.

Installation

Lime can be installed using PIP:

pip install lime

Or by cloning the repository and running the setup.py file:

git clone https://github.com/marcotcr/lime
cd lime/
python setup.py install

Examples

Lime can be used for many different applications. Below are some example use cases which you can use to get started.

• Use Lime for Tabular data
• Analyze NLP model
• Analyze Computer Vision model

There are also lots of other notebook available, which show you how to use LIME. You can find a bunch of them in the official repository.