plot_features: Plot the features in an explanation

In lime: Local Interpretable Model-Agnostic Explanations

Plot the features in an explanation

Description

This functions creates a compact visual representation of the explanations for each case and label combination in an explanation. Each extracted feature is shown with its weight, thus giving the importance of the feature in the label prediction.

Usage

plot_features(explanation, ncol = 2, cases = NULL)

Arguments

explanation	A data.frame as returned by explain().
ncol	The number of columns in the facetted plot
cases	An optional vector with case names to plot. explanation will be filtered to only include these cases prior to plotting

Value

A ggplot object

See Also

Other explanation plots: plot_explanations(), plot_text_explanations()

Examples

# Create some explanations
library(MASS)
iris_test <- iris[1, 1:4]
iris_train <- iris[-1, 1:4]
iris_lab <- iris[[5]][-1]
model <- lda(iris_train, iris_lab)
explanation <- lime(iris_train, model)
explanations <- explain(iris_test, explanation, n_labels = 1, n_features = 2)

# Get an overview with the standard plot
plot_features(explanations)

lime documentation built on Aug. 19, 2022, 9:07 a.m.