kmeansNormalize {CSSQ}R Documentation

Perform k-means clustering, normalize anscombe data and calculate cluster variances for a sample.

Description

This function performs normalization on the anscombe transformed data by clustering them using k-means algorithmn and utilizing the information from clusters. It returns an DataFrame object normalized counts, cluster information and the variance of that cluster for that sample.

Usage

kmeansNormalize(ansDataVec, numClusters = 4)

Arguments

ansDataVec

Anscombe transformed count data for a sample.

numClusters

A number indicating the number of clusters to use for k-means clustering. (default: 4)

Value

DataFrame containing the normalized counts, cluster information and the variance of the cluster in the sample.

See Also

normalizeData which iterates over this function.

Examples

exCount <- c(1,2,3,4,5,6,7,8,9,10)
kmeansEx <- kmeansNormalize(exCount,numClusters=2)
kmeansEx

[Package CSSQ version 1.6.0 Index]