Hierarchical clustering using R

Hierarchical clustering, also known as hierarchical cluster analysis, is an algorithm that clusters similar data points into groups called clusters. The endpoint is a hierarchy of clusters and the objects within each cluster are similar to each other.

Agglomerative: This is a “bottom-up” approach: each observation starts in its own cluster, and pairs of clusters are merged as one moves up the hierarchy.

-Advertisement-

Divisive: This is a “top-down” approach: all observations start in one cluster, and splits are performed recursively as one moves down the hierarchy.

Hierarchical clustering dendrogram of the Iris dataset (https://en.wikipedia.org/wiki/Hierarchical_clustering)

We can perform hierarchical clustering on a data matrix in R using function “hclust”.

Usage

hclust(d, method = “complete”, members = NULL)

Data set from clustering

#We can genrate randome data:
x <- rbind(matrix(rnorm(100, sd = 0.3), ncol = 2),
           matrix(rnorm(100, mean = 1, sd = 0.3), ncol = 2))
colnames(x) <- c("x", "y")
summary(x)

##        x                  y           
##  Min.   :-0.62946   Min.   :-0.82754  
##  1st Qu.: 0.04838   1st Qu.:-0.01679  
##  Median : 0.57912   Median : 0.43242  
##  Mean   : 0.53057   Mean   : 0.47489  
##  3rd Qu.: 0.98021   3rd Qu.: 1.01691  
##  Max.   : 1.73683   Max.   : 1.93000

#We also can use famous <i>Iris</i> flower data set.
summary(iris)

##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 

Now use hclust function on the dataset, all four columns (Sepal length, Petal length, Sepal width, and Petal width.

data <- dist(iris[, 1:4])
hcluster <- hclust(data)
hcluster

## 
## Call:
## hclust(d = data)
## 
## Cluster method   : complete 
## Distance         : euclidean 
## Number of objects: 150

Let’s plot our cluster dendrogram data

# Convert hclust into a dendrogram and plot
hcd <- as.dendrogram(hcluster)
# Define nodePar
nodePar <- list(lab.cex = 0.6, pch = c(20, 19),
                cex = 0.7, col = c("green","yellow"))
plot(hcd,  xlab = "Height", nodePar = nodePar, main = "Cluster dendrogram",
     edgePar = list(col = c("red","blue"), lwd = 2:1), horiz = TRUE)

nodePar:
It is a list of plotting parameters to use for the nodes.