interaction_statistic: Plot feature interaction

In mirka-henninger/InterpretationMethods: Facilitates the implementation of interpretation techniques for social science research

Description

This function allows to plot the Hamilton feature interaction statistic

Usage

interaction_statistic(
  pred,
  type = "overall",
  feature = NA,
  limits = c(0, 1),
  title = "",
  xlabel = "",
  ylabel = "Interaction Statistic"
)

Arguments

pred	A prediction object from package iml
type	A character string indicating the type of the interaction statistic. Either "overall" (Default) or "2way"
feature	A character string indicating the name of the feature that is the basis for 2-way interactions
limits	An optional two-entry vector indicating the y-axis limits. Default is c(0,1)
title	An optional character string indicating the title of the plot
xlabel	An optional character string indicating x-axis label
ylabel	An optional character string indicating y-axis label

Value

a plot of type ggplot

Examples

## Not run: 
N <- 1000
x1 <- runif(N, -1, 1)
x2 <- runif(N, -1, 1)
x3 <- runif(N, -1, 1)
y <- 5 + 5 * x1 * x2 + x3 + rnorm(N,1)
dat <- data.frame(x1,x2,x3,y)
rfmod <- randomForest::randomForest(y~., dat)
pred <- iml::Predictor$new(rfmod)
interaction_statistic(pred)
interaction_statistic(pred, type = "2way", feature = "x1")

## End(Not run)

mirka-henninger/InterpretationMethods documentation built on Jan. 12, 2022, 4:10 p.m.