LIME-Based Explanations with Interpretable Inputs Based on Ceteris Paribus Profiles

Local explanations of machine learning models describe, how features contributed to a single prediction. This package implements an explanation method based on LIME (Local Interpretable Model-agnostic Explanations, see Tulio Ribeiro, Singh, Guestrin (2016) ) in which interpretable inputs are created based on local rather than global behaviour of each original feature.

localModel: Local Explanations of Machine Learning Models for Tabular Data.

localModel is a successor to the live package. It implements a variant of LIME method for explaining single predictions of black box machine learning models for tabular data. Interpretable features are created based on Ceteris Paribus plots. Details of the methodology are described in the vignette. localModel is currently undergoing rapid changes, including bug fixes, for a stable solution please see the live package.

To get started, install the package from CRAN:

install.packages('localModel')

The development version can be installe from GitHub by using the code below. Please do not use the devtools package, since it is affected a bug which makes localModel installation impossible. This issue was solved in the Github version of remotes.

devtools::install_github("r-lib/remotes")
remotes::install_github("ModelOriented/localModel")

To get help, see examples and details of the methodology, please refer to package website and vignettes.

Acknowledgments

Work on this package is financially supported by the NCN Opus grant 2017/27/B/ST6/01307.