RidgeFusion (version 1.0-3)

SSRidgeFused: Semis Supervised Ridge Fusion Model Based Clustering

Description

Calculates parameters for model based clustering using ridge fusion estimation of precision matrix

Usage

SSRidgeFused(Z, Xu, lambda1, lambda2, Scale=FALSE, warm=NULL,tol=.001)

Arguments

Z

A list of length J that contains the labeled data for each class

Xu

The unlabeled data

lambda1

A vector with all possible Ridge tuning parameters

lambda2

A vector with all possible Ridge Fusion tuning parameters

Scale

If TRUE scale invariant method is used

warm

Default is NULL, if initialized with mixing distributions for each of the unlabeled data, will use in initialization of parameters

tol

tolerence for convergence criterion of the alphas

Value

An object of class SSRidgeFusion, basically a list including elements

Omega

a list where each element is the precision matrix estimate for the corresponding element of S

Ridge

lambda1

FusedRidge

lambda2

iter

The number of iterations until the EM algorithm converged

Alpha

Mixing coefficients for each of the unlabeled data points

Means

Class/Cluster Means

Pi

Probability Mass Function for the classes

Examples

## Creating a toy example with 5 variables
library(mvtnorm)
set.seed(526)
p=5
    Sig1=matrix(0,p,p)
	for(j in 1:p){
		for(i in j:p){          
            Sig1[j,i]=.7^abs(i-j)
            Sig1[i,j]=Sig1[j,i]
            
		}
	}
    Sig2=diag(c(rep(2,p-5),rep(1,5)),p,p)
X1=rmvnorm(100,rep(2*log(p)/p,p),Sig1)
Y=rmvnorm(100,,Sig2)

## Creating a list of the data for each class
Z=list(X1,Y)

##Creating Unlabeled data set
Z1=rmvnorm(250,rep(2*log(p)/p,p),Sig1)
Z2=rmvnorm(250,,Sig2)
ZU=rbind(Z1,Z2)
## Running Semi-Supervised Ridge Fused Model based clustering 
Hi=SSRidgeFused(Z,ZU,1,1,Scale=TRUE,warm=NULL)
## Showing example of a warm.start
Hi2=SSRidgeFused(Z,ZU,1,1,Scale=TRUE,warm=Hi$Alphas)