catnet (version 1.00.0)

cnSearchHistCluster: Parent Histogram Matrix - Parallel Version

Description

Estimation of the parent matrix of nodes from data by parallel processing.

Usage

cnSearchHistCluster(data, perturbations, 
	maxParentSet, maxComplexity, 
	parentsPool=NULL, fixedParentsPool=NULL, niter=32, 
	clusterNodes=2, clusterHost="localhost", echo=FALSE)

Arguments

data

a matrix in row-nodes format or a data.frame in column-nodes format

perturbations

a binary matrix with the dimensions of data. A value 1 designates the corresponding node in the sample as perturbed

maxParentSet

an integer, the maximal number of parents per node

maxComplexity

an integer, the maximal network complexity for the search

parentsPool

a list of parent sets to choose from

fixedParentsPool

a list of parent sets to choose from

niter

an integer, the number of single order searches to be performed

clusterNodes

number of processing units to be used

clusterHost

IP address of the cluster host; 'localhost' as default

echo

a boolean that sets on/off some functional progress and debug information

Value

• A matrix

Details

After performing niter calls of cnSearchOrder for randomly generated node orders (uniformly over the space of all possible node orders), the function returns the histogram matrix of the parent-child relations, as given by cnMatParents function, for the resulting optimal networks. This is essentially the parallel version of cnSearchHist.

See Also

cnMatParents, cnSearchOrder, cnSearchHist

Examples

library(snow)
  cnet <- cnRandomCatnet(numnodes=8, maxParents=3, numCategories=2)
  psamples  <- cnSamples(object=cnet, numsamples=100)
  mhisto <- cnSearchHistCluster(data=psamples, perturbations=NULL, 
		maxParentSet=2, maxComplexity=20)
  mhisto