plot.mid.importance: Plot MID Importance

In midr: Learning from Black-Box Models by Maximum Interpretation Decomposition

Plot MID Importance

Description

For "mid.importance" objects, plot() visualizes the importance of component functions of the fitted MID model.

Usage

## S3 method for class 'mid.importance'
plot(
  x,
  type = c("barplot", "dotchart", "heatmap", "boxplot"),
  theme = NULL,
  max.nterms = 30L,
  ...
)

Arguments

x	a "mid.importance" object to be visualized.
type	the plotting style. One of "barplot", "dotchart", "heatmap", or "boxplot".
theme	a character string or object defining the color theme. See color.theme for details.
max.nterms	the maximum number of terms to display in the bar, dot and box plots.
...	optional parameters passed on to the graphing functions. Possible arguments are "col", "fill", "pch", "cex", "lty", "lwd" and aliases of them.

Details

This is an S3 method for the plot() generic that produces an importance plot from a "mid.importance" object, visualizing the average contribution of component functions to the fitted MID model.

The type argument controls the visualization style. The default, type = "barplot", creates a standard bar plot where the length of each bar represents the overall importance of the term. The type = "dotchart" option creates a dot plot, offering a clean alternative to the bar plot for visualizing term importance. The type = "heatmap" option creates a matrix-shaped heat map where the color of each cell represents the importance of the interaction between a pair of variables, or the main effect on the diagonal. The type = "boxplot" option creates a box plot where each box shows the distribution of a term's contributions across all observations, providing insight into the variability of each term's effect.

Value

plot.mid.importance() produces a plot as a side effect and returns NULL invisibly.

See Also

mid.importance, ggmid.mid.importance

Examples

data(diamonds, package = "ggplot2")
set.seed(42)
idx <- sample(nrow(diamonds), 1e4)
mid <- interpret(price ~ (carat + cut + color + clarity)^2, diamonds[idx, ])
imp <- mid.importance(mid)

# Create a bar plot (default)
plot(imp)

# Create a dot chart
plot(imp, type = "dotchart", theme = "Okabe-Ito", size = 1.5)

# Create a heatmap
plot(imp, type = "heatmap")

# Create a boxplot to see the distribution of effects
plot(imp, type = "boxplot")

midr documentation built on Sept. 11, 2025, 1:07 a.m.