sna (version 2.8)

gvectorize: Vectorization of Adjacency Matrices

Description

gvectorize takes an input graph set and converts it into a corresponding number of vectors by row concatenation.

Usage

gvectorize(mats, mode="digraph", diag=FALSE, censor.as.na=TRUE)

Value

An nxk matrix, where n is the number of arcs and k is the number of graphs; if censor.as.na==FALSE, n will be reflect the relevant number of uncensored arcs.

Arguments

mats

one or more input graphs.

mode

``digraph'' if data is taken to be directed, else ``graph''.

diag

boolean indicating whether diagonal entries (loops) are taken to contain meaningful data.

censor.as.na

if TRUE, code unused parts of the adjacency matrix as NAs prior to vectorizing; otherwise, unused parts are simply removed.

Author

Carter T. Butts

Details

The output of gvectorize is a matrix in which each column corresponds to an input graph, and each row corresponds to an edge. The columns of the output matrix are formed by simple row-concatenation of the original adjacency matrices, possibly after removing cells which are not meaningful (if censor.as.na==FALSE). This is useful when preprocessing edge sets for use with glm or the like.

Examples

#Draw two random graphs
g<-rgraph(10,2)

#Examine the vectorized form of the adjacency structure
gvectorize(g)