K-means represents one of the most popular clustering algorithm. However, it has some limitations: it requires the user to specify the number of clusters in advance and selects initial centroids randomly. The final k-means clustering solution is very sensitive to this initial random selection of cluster centers. The result might be (slightly) different each time you compute k-means.
In this chapter, we described an hybrid method, named hierarchical k-means clustering (hkmeans), for improving k-means results.
The algorithm is summarized as follow:
- Compute hierarchical clustering and cut the tree into k-clusters
- Compute the center (i.e the mean) of each cluster
- Compute k-means by using the set of cluster centers (defined in step 2) as the initial cluster centers
Note that, k-means algorithm will improve the initial partitioning generated at the step 2 of the algorithm. Hence, the initial partitioning can be slightly different from the final partitioning obtained in the step 4.
The R function hkmeans() [in factoextra], provides an easy solution to compute the hierarchical k-means clustering. The format of the result is similar to the one provided by the standard kmeans() function (see Chapter @ref(kmeans-clustering)).
To install factoextra, type this: install.packages(“factoextra”).
We’ll use the USArrest data set and we start by standardizing the data:
df <- scale(USArrests)
# Compute hierarchical k-means clustering library(factoextra) res.hk <-hkmeans(df, 4) # Elements returned by hkmeans() names(res.hk)
##  "cluster" "centers" "totss" "withinss" ##  "tot.withinss" "betweenss" "size" "iter" ##  "ifault" "data" "hclust"
To print all the results, type this:
# Print the results res.hk
# Visualize the tree fviz_dend(res.hk, cex = 0.6, palette = "jco", rect = TRUE, rect_border = "jco", rect_fill = TRUE)
# Visualize the hkmeans final clusters fviz_cluster(res.hk, palette = "jco", repel = TRUE, ggtheme = theme_classic())
We described hybrid hierarchical k-means clustering for improving k-means results.