K-Means Clustering Visualization in R: Step By Step Guide

library(ggpubr)
library(factoextra)
data("iris")
df <- iris
head(df, 3)
# Compute k-means with k = 3
set.seed(123)
res.km <- kmeans(scale(df[, -5]), 3, nstart = 25)
# K-means clusters showing the group of each individuals
res.km$cluster
fviz_cluster(res.km, data = df[, -5],
             palette = c("#2E9FDF", "#00AFBB", "#E7B800"), 
             geom = "point",
             ellipse.type = "convex", 
             ggtheme = theme_bw()
)

library(ggpubr)
library(factoextra)
data("iris")
df <- iris
head(df, 3)
# Compute k-means with k = 3
set.seed(123)
# Dimension reduction using PCA
res.pca <- prcomp(df[, -5],  scale = TRUE)
# Coordinates of individuals
ind.coord <- as.data.frame(get_pca_ind(res.pca)$coord)
# Add clusters obtained using the K-means algorithm
ind.coord$cluster <- factor(res.km$cluster)
# Add Species groups from the original data sett
ind.coord$Species <- df$Species
# Data inspection
head(ind.coord)
# Percentage of variance explained by dimensions
eigenvalue <- round(get_eigenvalue(res.pca), 1)
variance.percent <- eigenvalue$variance.percent
head(eigenvalue)
ggscatter(
  ind.coord, x = "Dim.1", y = "Dim.2", 
  color = "cluster", palette = "npg", ellipse = TRUE, ellipse.type = "convex",
  shape = "Species", size = 1.5,  legend = "right", ggtheme = theme_bw(),
  xlab = paste0("Dim 1 (", variance.percent[1], "% )" ),
  ylab = paste0("Dim 2 (", variance.percent[2], "% )" )
) +
  stat_mean(aes(color = cluster), size = 4)

原文链接