\name{cluster.sizestat}
\alias{cluster.sizestat}
\title{generate statistics on sizes of clusters}
\description{
	'cluster.sizestat' is used to do simple statistics on sizes of clusters
	generated by 'cmp.cluster'. It will return a dataframe which maps a cluster
	size to  the number of clusters with that size. It is often used along
	with 'cluster.visualize'.
}
\usage{
cluster.sizestat(cls, cluster.result=1)
}
\arguments{
  \item{cls}{The clustering result returned by 'cmp.cluster'}
  \item{cluster.result}{If multiple cutoff values are used in clustering process, this argument tells which cutoff value is to be considered here.}
}
\details{
    'cluster.sizestat' depends on the format that is returned by 'cmp.cluster' - it
    will treat the first column as the indecies, and the second column as the
    cluster sizes of effective clustering. Because of this, when multiple
    cutoffs are used when 'cmp.cluster' is called, 'cluster.sizestat' will only
    consider the clustering result of the first cutoff. If you want to work on
    an alternative cutoff, you have to manually reorder/remove columns.
}
\value{
    Returns a data frame of two columns.
    \item{cluster size}{This column lists cluster sizes}
    \item{count}{This column lists number of clusters of a cluster size}
}
\author{Y. Eddie Cao}
\seealso{\code{\link{cmp.cluster}}, \code{\link{cluster.visualize}}}
\examples{
## Load sample SD file
# data(sdfsample); sdfset <- sdfsample

## Generate atom pair descriptor database for searching
# apset <- sdf2ap(sdfset) 

## Loads same atom pair sample data set provided by library
data(apset) 

## Binning clustering using variable similarity cutoffs.
cluster <- cmp.cluster(db=apset, cutoff = c(0.65, 0.5))

## Statistics on sizes of clusters
cluster.sizestat(cluster[,c(1,2,3)])
cluster.sizestat(cluster[,c(1,4,5)])
}
\keyword{utilities}