Cluster Analysis in R Simplified and Enhanced

install.packages("factoextra")
library(factoextra)
# Load and scale the dataset
data("USArrests")
df <- scale(USArrests)
head(df)
library(factoextra)
# Correlation-based distance method
res.dist <- get_dist(df, method = "pearson")
head(round(as.matrix(res.dist), 2))[, 1:6]
# Visualize the dissimilarity matrix
fviz_dist(res.dist, lab_size = 8)

# Load and scale the dataset
data("USArrests")
df <- scale(USArrests)

# Compute dissimilarity matrix
res.dist <- dist(df, method = "euclidean")

# Compute hierarchical clustering
res.hc <- hclust(res.dist, method = "ward.D2")

# Visualize
plot(res.hc, cex = 0.5)
eclust(x, FUNcluster = "kmeans", hc_metric = "euclidean", ...)

library("factoextra")

# Enhanced k-means clustering
res.km <- eclust(df, "kmeans", nstart = 25)

library("factoextra")

# Gap statistic plot
fviz_gap_stat(res.km$gap_stat)

library("factoextra")

# Silhouette plot
fviz_silhouette(res.km)

library("factoextra")
res.hc <- eclust(df, "hclust") # compute hclust
fviz_dend(res.hc, rect = TRUE) # dendrogam

library("factoextra")
fviz_silhouette(res.hc) # silhouette plot

library("factoextra")
fviz_cluster(res.hc) # scatter plot

原文链接