localModel

localModel-package

This package implements LIME-like explanation method
(see Tulio Ribeiro, Singh, Guestrin (2016) &lt;doi:10.1145/2939672.2939778&gt;) in which interpretable
inputs are created based on local rather than global behaviour of each original feature.#'

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) <doi:10.1145/2939672.2939778>) in which interpretable
inputs are created based on local rather than global behaviour of each original feature.

Mateusz Staniak

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

localModel function

<code><a rd-options="" href="/link/individual_surrogate_model?package=localModel&version=0.3.11" data-mini-rdoc="localModel::individual_surrogate_model">individual_surrogate_model</a></code> generates an explanation for a single prediction with
interpretable features based on Ceteris Paribus profiles.
<code><a rd-options="" href="/link/plot.local_surrogate_explainer?package=localModel&version=0.3.11" data-mini-rdoc="localModel::plot.local_surrogate_explainer">plot.local_surrogate_explainer</a></code> plots the explanation.

Important functions

localModel: LIME-like explanations with interpretable features based on Ceteris Paribus profiles — localModel

<code><a rd-options='' href='individual_surrogate_model'>individual_surrogate_model</a></code> generates an explanation for a single prediction with
interpretable features based on Ceteris Paribus profiles.
<code><a rd-options='' href='plot.local_surrogate_explainer'>plot.local_surrogate_explainer</a></code> plots the explanation.

localModel: localModel: LIME-like explanations with interpretable features based on Ceteris Paribus profiles

Description

Arguments

Important functions