K-Means Analysis in R
Javier Aguilar
2025-10-4
Data Preparation
df <- USArrestsdf <- na.omit(df)df <- scale(df)
head(df)## Murder Assault UrbanPop Rape
## Alabama 1.24256408 0.7828393 -0.5209066 -0.003416473
## Alaska 0.50786248 1.1068225 -1.2117642 2.484202941
## Arizona 0.07163341 1.4788032 0.9989801 1.042878388
## Arkansas 0.23234938 0.2308680 -1.0735927 -0.184916602
## California 0.27826823 1.2628144 1.7589234 2.067820292
## Colorado 0.02571456 0.3988593 0.8608085 1.864967207Clustering Distance Measures
distance <- get_dist(df)
fviz_dist(distance, gradient = list(low = "#00AFBB", mid = "white", high = "#FC4E07"))## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <https://github.com/kassambara/factoextra/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
Computing k-means clustering in R
k2 <- kmeans(df, centers = 2, nstart = 25)
str(k2)## List of 9
## $ cluster : Named int [1:50] 1 1 1 2 1 1 2 2 1 1 ...
## ..- attr(*, "names")= chr [1:50] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ centers : num [1:2, 1:4] 1.005 -0.67 1.014 -0.676 0.198 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:2] "1" "2"
## .. ..$ : chr [1:4] "Murder" "Assault" "UrbanPop" "Rape"
## $ totss : num 196
## $ withinss : num [1:2] 46.7 56.1
## $ tot.withinss: num 103
## $ betweenss : num 93.1
## $ size : int [1:2] 20 30
## $ iter : int 1
## $ ifault : int 0
## - attr(*, "class")= chr "kmeans"k2## K-means clustering with 2 clusters of sizes 20, 30
##
## Cluster means:
## Murder Assault UrbanPop Rape
## 1 1.004934 1.0138274 0.1975853 0.8469650
## 2 -0.669956 -0.6758849 -0.1317235 -0.5646433
##
## Clustering vector:
## Alabama Alaska Arizona Arkansas California
## 1 1 1 2 1
## Colorado Connecticut Delaware Florida Georgia
## 1 2 2 1 1
## Hawaii Idaho Illinois Indiana Iowa
## 2 2 1 2 2
## Kansas Kentucky Louisiana Maine Maryland
## 2 2 1 2 1
## Massachusetts Michigan Minnesota Mississippi Missouri
## 2 1 2 1 1
## Montana Nebraska Nevada New Hampshire New Jersey
## 2 2 1 2 2
## New Mexico New York North Carolina North Dakota Ohio
## 1 1 1 2 2
## Oklahoma Oregon Pennsylvania Rhode Island South Carolina
## 2 2 2 2 1
## South Dakota Tennessee Texas Utah Vermont
## 2 1 1 2 2
## Virginia Washington West Virginia Wisconsin Wyoming
## 2 2 2 2 2
##
## Within cluster sum of squares by cluster:
## [1] 46.74796 56.11445
## (between_SS / total_SS = 47.5 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"fviz_cluster(k2, data = df)
df %>%
as_tibble() %>%
mutate(cluster = k2$cluster,
state = row.names(USArrests)) %>%
ggplot(aes(UrbanPop, Murder, color = factor(cluster), label = state)) +
geom_text()
k3 <- kmeans(df, centers = 3, nstart = 25)
k4 <- kmeans(df, centers = 4, nstart = 25)
k5 <- kmeans(df, centers = 5, nstart = 25)
p1 <- fviz_cluster(k2, geom = "point", data = df) + ggtitle("k = 2")
p2 <- fviz_cluster(k3, geom = "point", data = df) + ggtitle("k = 3")
p3 <- fviz_cluster(k4, geom = "point", data = df) + ggtitle("k = 4")
p4 <- fviz_cluster(k5, geom = "point", data = df) + ggtitle("k = 5")
grid.arrange(p1, p2, p3, p4, nrow = 2)
Determining Optimal Clusters
Elbow Method
set.seed(123)
wss <- function(k) {
kmeans(df, k, nstart = 10 )$tot.withinss
}
k.values <- 1:15
wss_values <- map_dbl(k.values, wss)
plot(k.values, wss_values,
type="b", pch = 19, frame = FALSE,
xlab="Number of clusters K",
ylab="Total within-clusters sum of squares")
set.seed(123)
fviz_nbclust(df, kmeans, method = "wss")
Average Silhouette Method
avg_sil <- function(k) {
km.res <- kmeans(df, centers = k, nstart = 25)
ss <- silhouette(km.res$cluster, dist(df))
mean(ss[, 3])
}
k.values <- 2:15
avg_sil_values <- map_dbl(k.values, avg_sil)
plot(k.values, avg_sil_values,
type = "b", pch = 19, frame = FALSE,
xlab = "Number of clusters K",
ylab = "Average Silhouettes")
fviz_nbclust(df, kmeans, method = "silhouette")
Gap Statistic Method
set.seed(123)
gap_stat <- clusGap(df, FUN = kmeans, nstart = 25,
K.max = 10, B = 50)
print(gap_stat, method = "firstmax")## Clustering Gap statistic ["clusGap"] from call:
## clusGap(x = df, FUNcluster = kmeans, K.max = 10, B = 50, nstart = 25)
## B=50 simulated reference sets, k = 1..10; spaceH0="scaledPCA"
## --> Number of clusters (method 'firstmax'): 4
## logW E.logW gap SE.sim
## [1,] 3.458369 3.640154 0.1817845 0.04422857
## [2,] 3.135112 3.372283 0.2371717 0.03559601
## [3,] 2.977727 3.233771 0.2560446 0.03749193
## [4,] 2.826221 3.119172 0.2929511 0.04067348
## [5,] 2.738868 3.019965 0.2810969 0.04185469
## [6,] 2.666967 2.930002 0.2630347 0.04105040
## [7,] 2.609895 2.852152 0.2422572 0.04184725
## [8,] 2.539156 2.778562 0.2394054 0.04292750
## [9,] 2.468162 2.711752 0.2435901 0.04344197
## [10,] 2.407265 2.647595 0.2403307 0.04548446fviz_gap_stat(gap_stat)
Extracting Results
set.seed(123)
final <- kmeans(df, 4, nstart = 25)
print(final)## K-means clustering with 4 clusters of sizes 16, 13, 8, 13
##
## Cluster means:
## Murder Assault UrbanPop Rape
## 1 -0.4894375 -0.3826001 0.5758298 -0.26165379
## 2 0.6950701 1.0394414 0.7226370 1.27693964
## 3 1.4118898 0.8743346 -0.8145211 0.01927104
## 4 -0.9615407 -1.1066010 -0.9301069 -0.96676331
##
## Clustering vector:
## Alabama Alaska Arizona Arkansas California
## 3 2 2 3 2
## Colorado Connecticut Delaware Florida Georgia
## 2 1 1 2 3
## Hawaii Idaho Illinois Indiana Iowa
## 1 4 2 1 4
## Kansas Kentucky Louisiana Maine Maryland
## 1 4 3 4 2
## Massachusetts Michigan Minnesota Mississippi Missouri
## 1 2 4 3 2
## Montana Nebraska Nevada New Hampshire New Jersey
## 4 4 2 4 1
## New Mexico New York North Carolina North Dakota Ohio
## 2 2 3 4 1
## Oklahoma Oregon Pennsylvania Rhode Island South Carolina
## 1 1 1 1 3
## South Dakota Tennessee Texas Utah Vermont
## 4 3 2 1 4
## Virginia Washington West Virginia Wisconsin Wyoming
## 1 1 4 4 1
##
## Within cluster sum of squares by cluster:
## [1] 16.212213 19.922437 8.316061 11.952463
## (between_SS / total_SS = 71.2 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"fviz_cluster(final, data = df)
USArrests %>%
mutate(Cluster = final$cluster) %>%
group_by(Cluster) %>%
summarise_all("mean")## # A tibble: 4 × 5
## Cluster Murder Assault UrbanPop Rape
## <int> <dbl> <dbl> <dbl> <dbl>
## 1 1 5.66 139. 73.9 18.8
## 2 2 10.8 257. 76 33.2
## 3 3 13.9 244. 53.8 21.4
## 4 4 3.6 78.5 52.1 12.2Code taken from: K-means Clustering.