Cluster Analysis - Revision history

Raj at 05:23, 28 October 2016

2016-10-28T05:23:39Z

← Older revision		Revision as of 05:23, 28 October 2016
Line 1:		Line 1:
	[[:Category:R]]		[[Category:R]]

	= Cluster Analysis =		= Cluster Analysis =

Raj at 15:18, 12 March 2013

2013-03-12T15:18:15Z

← Older revision		Revision as of 15:18, 12 March 2013
Line 1:		Line 1:
	[[Category:R]]		[[:Category:R]]

	= Cluster Analysis =		= Cluster Analysis =

Raj: /* Hierarcheal Clustering */

2012-02-15T04:10:36Z

Hierarcheal Clustering

@@ Line 44: / Line 44: @@
 # draw dendogram with red borders around the 5 clusters
 > rect.hclust(fit, k=5, border="red")
 </pre>

Raj: /* Formatting the Data */

2012-02-15T04:04:47Z

Formatting the Data

← Older revision		Revision as of 04:04, 15 February 2012
Line 6:		Line 6:
	<pre>		<pre>


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

Raj: /* Formatting the Data */

2012-02-15T04:00:19Z

Formatting the Data

← Older revision		Revision as of 04:00, 15 February 2012
Line 9:		Line 9:
	> mydata <- scale(mydata) # standardize variables		> mydata <- scale(mydata) # standardize variables

	# (~~Opyional~~) Determine number of clusters		# (Optional) Determine number of clusters
	> wss <- (nrow(mydata)-1)*sum(apply(mydata,2,var)) for (i in 2:15)		> wss <- (nrow(mydata)-1)*sum(apply(mydata,2,var)) for (i in 2:15)
	> wss[i] <- sum(kmeans(mydata, centers=i)$withinss)		> wss[i] <- sum(kmeans(mydata, centers=i)$withinss)

Raj: /* Kmeans Clustering */

2012-02-15T04:00:07Z

Kmeans Clustering

← Older revision		Revision as of 04:00, 15 February 2012
Line 19:		Line 19:
	== Kmeans Clustering ==		== Kmeans Clustering ==
	<pre>		<pre>

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

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

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

	</pre>		</pre>

Raj: /* Hierarcheal Clustering */

2012-02-15T03:59:44Z

Hierarcheal Clustering

← Older revision		Revision as of 03:59, 15 February 2012
Line 27:		Line 27:

	== Hierarcheal Clustering ==		== Hierarcheal Clustering ==

			<pre>

			# 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")

			</pre>

Raj: /* Kmeans Clustering */

2012-02-15T03:58:14Z

Kmeans Clustering

← Older revision		Revision as of 03:58, 15 February 2012
Line 18:		Line 18:

	== Kmeans Clustering ==		== Kmeans Clustering ==
			<pre>
			> 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)
			</pre>

	== Hierarcheal Clustering ==		== Hierarcheal Clustering ==

Raj: Created page with "Category:R = Cluster Analysis = == Formatting the Data ==

  > mydata <- na.omit(mydata) # listwise deletion of missing > mydata <- scale(mydata) # standardize variable..."

2012-02-15T03:00:25Z

Created page with "Category:R = Cluster Analysis = == Formatting the Data == <pre> > mydata <- na.omit(mydata) # listwise deletion of missing > mydata <- scale(mydata) # standardize variable..."

New page

[[Category:R]]

= Cluster Analysis =

== Formatting the Data ==
<pre>

> mydata <- na.omit(mydata) # listwise deletion of missing
> mydata <- scale(mydata) # standardize variables

# (Opyional) 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")

</pre>

== Kmeans Clustering ==

== Hierarcheal Clustering ==