RaPlot: Visualize the feature ranking results of a fitted RaSE...

In RaSEn: Random Subspace Ensemble Classification and Variable Screening

Description

This function plots the feature ranking results from a fitted 'RaSE' object via ggplot2. In the figure, x-axis represents the feature number and y-axis represents the selected percentage of each feature in B1 subspaces.

Usage

RaPlot(
  object,
  main = NULL,
  xlab = "feature",
  ylab = "selected percentage",
  ...
)

Arguments

object	fitted 'RaSE' model object.
main	title of the plot. Default = NULL, which makes the title following the orm 'RaSE-base' with subscript i (rounds of iterations), where base represents the type of base classifier. i is omitted when it is zero.
xlab	the label of x-axis. Default = 'feature'.
ylab	the label of y-axis. Default = 'selected percentage'.
...	additional arguments.

Value

a 'ggplot' object.

References

Tian, Y. and Feng, Y., 2021. RaSE: Random subspace ensemble classification. Journal of Machine Learning Research, 22(45), pp.1-93.

See Also

Rase.

Examples

set.seed(0, kind = "L'Ecuyer-CMRG")
train.data <- RaModel("classification", 1, n = 100, p = 50)
xtrain <- train.data$x
ytrain <- train.data$y

# fit RaSE classifier with QDA base classifier
fit <- Rase(xtrain, ytrain, B1 = 50, B2 = 50, iteration = 1, base = 'qda',
cores = 2, criterion = 'ric')

# plot the selected percentage of each feature appearing in B1 subspaces
RaPlot(fit)

RaSEn documentation built on Oct. 16, 2021, 9:06 a.m.