stat_classifier: Plot RSSL classifier boundaries

In RSSL: Implementations of Semi-Supervised Learning Approaches for Classification

Plot RSSL classifier boundaries

Description

Plot RSSL classifier boundaries

Usage

stat_classifier(mapping = NULL, data = NULL, show.legend = NA,
  inherit.aes = TRUE, breaks = 0, precision = 50, brute_force = FALSE,
  classifiers = classifiers, ...)

Arguments

mapping	aes; aesthetic mapping
data	data.frame; data to be displayed
show.legend	logical; Whether this layer should be included in the legend
inherit.aes	logical; If FALSE, overrides the default aesthetics
breaks	double; decision value for which to plot the boundary
precision	integer; grid size to sketch classification boundary
brute_force	logical; If TRUE, uses numerical estimation even for linear classifiers
classifiers	List of Classifier objects to plot
...	Additional parameters passed to geom

Examples

library(RSSL)
library(ggplot2)
library(dplyr)

df <- generateCrescentMoon(200)

# This takes a couple of seconds to run
## Not run: 
g_svm <- SVM(Class~.,df,kernel = kernlab::rbfdot(sigma = 1))
g_ls <- LeastSquaresClassifier(Class~.,df)
g_nm <- NearestMeanClassifier(Class~.,df)


df %>% 
  ggplot(aes(x=X1,y=X2,color=Class,shape=Class)) +
  geom_point(size=3) +
  coord_equal() +
  scale_x_continuous(limits=c(-20,20), expand=c(0,0)) +
  scale_y_continuous(limits=c(-20,20), expand=c(0,0)) +
  stat_classifier(aes(linetype=..classifier..),
                  color="black", precision=50,
                  classifiers=list("SVM"=g_svm,"NM"=g_nm,"LS"=g_ls)
  )

## End(Not run)   

RSSL documentation built on March 31, 2023, 7:27 p.m.