Variation on “How to plot decision boundary of a k-nearest neighbor classifier from Elements of Statistical Learning?”

Question

This is a question related to https://stats.stackexchange.com/questions/21572/how-to-plot-decision-boundary-of-a-k-nearest-neighbor-classifier-from-elements-o

For co

Answer 1

Separating the main parts in the code will help outlining how to achieve this:

Test data with 3 classes

 train <- rbind(iris3[1:25,1:2,1],
                iris3[1:25,1:2,2],
                iris3[1:25,1:2,3])
 cl <- factor(c(rep("s",25), rep("c",25), rep("v",25)))

Test data covering a grid

 require(MASS)

 test <- expand.grid(x=seq(min(train[,1]-1), max(train[,1]+1),
                           by=0.1),
                     y=seq(min(train[,2]-1), max(train[,2]+1), 
                           by=0.1))

Classification for that grid

3 classes obviously

 require(class)
 classif <- knn(train, test, cl, k = 3, prob=TRUE)
 prob <- attr(classif, "prob")

Data structure for plotting

 require(dplyr)

 dataf <- bind_rows(mutate(test,
                           prob=prob,
                           cls="c",
                           prob_cls=ifelse(classif==cls,
                                           1, 0)),
                    mutate(test,
                           prob=prob,
                           cls="v",
                           prob_cls=ifelse(classif==cls,
                                           1, 0)),
                    mutate(test,
                           prob=prob,
                           cls="s",
                           prob_cls=ifelse(classif==cls,
                                           1, 0)))

Plot

 require(ggplot2)
 ggplot(dataf) +
    geom_point(aes(x=x, y=y, col=cls),
               data = mutate(test, cls=classif),
               size=1.2) + 
    geom_contour(aes(x=x, y=y, z=prob_cls, group=cls, color=cls),
                 bins=2,
                 data=dataf) +
    geom_point(aes(x=x, y=y, col=cls),
               size=3,
               data=data.frame(x=train[,1], y=train[,2], cls=cl))

We can also be a little fancier and plot the probability of class membership as a indication of the "confidence".

 ggplot(dataf) +
    geom_point(aes(x=x, y=y, col=cls, size=prob),
               data = mutate(test, cls=classif)) + 
    scale_size(range=c(0.8, 2)) +
    geom_contour(aes(x=x, y=y, z=prob_cls, group=cls, color=cls),
                 bins=2,
                 data=dataf) +
    geom_point(aes(x=x, y=y, col=cls),
               size=3,
               data=data.frame(x=train[,1], y=train[,2], cls=cl)) +
    geom_point(aes(x=x, y=y),
               size=3, shape=1,
               data=data.frame(x=train[,1], y=train[,2], cls=cl))