ggplot

Heirarchical Clustering

Illustrating clusters

set.seed(96)
x = rnorm(12, mean = rep(1:3, each = 4), sd = 0.2)
y = rnorm(12, mean = rep(c(1,2,1),each = 4), sd = 0.2)
plot(x, y, col = "orange", pch = 19,cex = 1.5)
text(x+0.05, y+0.05, labels = as.character(1:12))

Step 1

Find the pairwise distance between each points using the dist() function

data = data.frame(x,y)
distxy = dist(data)
distxy

##            1         2         3         4         5         6         7
## 2  0.5437960                                                            
## 3  0.3815662 0.6174629                                                  
## 4  0.2857667 0.3503437 0.2787112                                        
## 5  1.1921330 1.3695806 0.8303631 1.0878976                              
## 6  1.1534655 1.4528453 0.8496384 1.1278820 0.3223282                    
## 7  1.8555210 2.0439466 1.5051844 1.7663981 0.6787189 0.7483020          
## 8  1.5071417 1.7439180 1.1729397 1.4437660 0.3890738 0.3789129 0.3697452
## 9  2.0378454 1.7847065 1.7046487 1.7725298 1.3968812 1.7191597 1.5712478
## 10 2.0038226 1.7280288 1.6807817 1.7335403 1.4239434 1.7452463 1.6367795
## 11 1.4154969 1.1841454 1.0906637 1.1498184 0.9715091 1.2733600 1.3950015
## 12 1.9010201 1.5963685 1.5939898 1.6249871 1.4194203 1.7363256 1.6983574
##            8         9        10        11
## 2                                         
## 3                                         
## 4                                         
## 5                                         
## 6                                         
## 7                                         
## 8                                         
## 9  1.6141887                              
## 10 1.6607389 0.1007910                    
## 11 1.2942430 0.6229117 0.5906916          
## 12 1.6874935 0.2595640 0.1635275 0.5106738

Step 2

Heirarchical Clustering using hclust()

hClustering = hclust(distxy)
plot(hClustering)

myplclust <- function( hclust, lab=hclust$labels, lab.col=rep(1,length(hclust$labels)), hang=0.1,...){
  ## modifiction of plclust for plotting hclust objects *in colour*!
  ## Copyright Eva KF Chan 2009
  ## Arguments:
  ##    hclust:    hclust object
  ##    lab:        a character vector of labels of the leaves of the tree
  ##    lab.col:    colour for the labels; NA=default device foreground colour
  ##    hang:     as in hclust & plclust
  ## Side effect:
  ##    A display of hierarchical cluster with coloured leaf labels.
  y <- rep(hclust$height,2); x <- as.numeric(hclust$merge)
  y <- y[which(x<0)]; x <- x[which(x<0)]; x <- abs(x)
  y <- y[order(x)]; x <- x[order(x)]
  plot( hclust, labels=FALSE, hang=hang, ... )
  text( x=x, y=y[hclust$order]-(max(hclust$height)*hang),
        labels=lab[hclust$order], col=lab.col[hclust$order], 
        srt=90, adj=c(1,0.5), xpd=NA, ... )
}

Using a custom function to plot the clusters

myplclust(hClustering, lab = rep(1:3, each = 4), lab.col = rep(2:4, each = 4))

Using the heatmap function to derive correlation between points in data

Inorder to be able to organise the data with some logical way

dataAsMatrix = as.matrix(data)[sample(1:12),]
heatmap(dataAsMatrix)