--- a +++ b/man/getClustNum.Rd @@ -0,0 +1,49 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/getClustNum.R +\name{getClustNum} +\alias{getClustNum} +\title{Get estimation of optimal clustering number} +\usage{ +getClustNum( + data = NULL, + is.binary = rep(FALSE, length(data)), + try.N.clust = 2:8, + center = TRUE, + scale = TRUE, + fig.path = getwd(), + fig.name = "optimal_number_cluster" +) +} +\arguments{ +\item{data}{List of matrices.} + +\item{is.binary}{A logicial vector to indicate if the subdata is binary matrix of 0 and 1 such as mutation.} + +\item{try.N.clust}{A integer vector to indicate possible choices of number of clusters.} + +\item{center}{A logical value to indicate if the variables should be centered. TRUE by default.} + +\item{scale}{A logical value to indicate if the variables should be scaled. FALSE by default.} + +\item{fig.path}{A string value to indicate the output figure path.} + +\item{fig.name}{A string value to indicate the name of the figure.} +} +\value{ +A figure that helps to choose the optimal clustering number (argument of `N.clust`) for `get%algorithm_name%()` or `getMOIC()`, and a list contains the following components: + + \code{CPI} possible cluster number identified by clustering prediction index + + \code{Gapk} possible cluster number identified by Gap-statistics +} +\description{ +This function provides two measurements (i.e., clustering prediction index [CPI] and Gap-statistics) and aims to search the optimal number for multi-omics integrative clustering. In short, the peaks reach by the red (CPI) and blue (Gap-statistics) lines should be referred to determine `N.clust`. +} +\examples{ +# There is no example and please refer to vignette. +} +\references{ +Chalise P, Fridley BL (2017). Integrative clustering of multi-level omic data based on non-negative matrix factorization algorithm. PLoS One, 12(5):e0176278. + +Tibshirani, R., Walther, G., Hastie, T. (2001). Estimating the number of data clusters via the Gap statistic. J R Stat Soc Series B Stat Methodol, 63(2):411-423. +}