Cluster Analysis

Cluster Analysis

Formatting the Data

> mydata <- read.table ("/home/raj/R/data/data_rudresh.csv", header=T, sep="\t")
> mydata <- na.omit(mydata) # listwise deletion of missing
> mydata <- scale(mydata) # standardize variables

#  (Optional) Determine number of clusters
> wss <- (nrow(mydata)-1)*sum(apply(mydata,2,var)) for (i in 2:15)
> wss[i] <- sum(kmeans(mydata, centers=i)$withinss)
> plot(1:15, wss, type="b", xlab="Number of Clusters", ylab="Within groups sum of squares")

Kmeans Clustering

> fit <- kmeans(mydata, 5) # 5 cluster solution

# get cluster means 
> aggregate(mydata,by=list(fit$cluster),FUN=mean)

# append cluster assignment
> mydata <- data.frame(mydata, fit$cluster)

Hierarcheal Clustering

# Ward Hierarchical Clustering
> d <- dist(mydata, method = "euclidean") # distance matrix
> fit <- hclust(d, method="ward") 
> plot(fit) # display dendogram
> groups <- cutree(fit, k=5) # cut tree into 5 clusters

# draw dendogram with red borders around the 5 clusters 
> rect.hclust(fit, k=5, border="red")

Ward Hierarchical Clustering with Bootstrapped p values

> library(pvclust)
> fit <- pvclust(mydata, method.hclust="ward", method.dist="euclidean")
> plot(fit) # dendogram with p values

# add rectangles around groups highly supported by the data
> pvrect(fit, alpha=.95)