GPAV.parallel: GPAV Over Examples - Parallel Implementation

In gecko515/HEMDAG: Hierarchical Ensemble Methods for Directed Acyclic Graphs

Description

Function to compute GPAV across all the examples (parallel implementation).

Usage

GPAV.parallel(S, g, W = NULL, ncores = 8)

Arguments

S	a named flat scores matrix with examples on rows and classes on columns (root node included).
g	a graph of class graphNEL. It represents the hierarchy of the classes.
W	vector of weight relative to a single example. If the vector W is not specified (def. W=NULL), it is assumed that W is is a unitary vector of the same length of the columns' number of the matrix S (root node included).
ncores	number of cores to use for parallel execution (def. 8).

Value

a named matrix with the scores of the classes corrected according to the GPAV algorithm.

Examples

data(graph);
data(scores);
if (Sys.info()['sysname']!="Windows"){
   S.GPAV <- GPAV.parallel(S,W=NULL,g,ncores=2);
}

gecko515/HEMDAG documentation built on Oct. 18, 2019, 6:34 a.m.