bmgraph function

Bipartite multigraph

A function to create and manipulate bipartite multigraphs

bmgraph(net, layout = c("bip", "bip3", "bip3e", "bipc", "force", "rand", "circ", 
       "stress", "CA", "circ2"), scope, coord, alpha = c(1, 1, 1), showLbs, showAtts, 
       att = NULL, lbat = "1", main = NULL, cex.main, bg, mar, directed, valued, 
       collRecip, cex, pos, lwd, lty, col, ecol, vcol, vcol0, asp, seed = NULL, 
       maxiter = 100, bwd, clu, pch, rot, mirrorX, mirrorY, mirrorV, mirrorH, hds, 
       vedist, jitter, sort, add, adc, perm, ffamily, fstyle, fsize, fcol, vclu, ...)

Arguments

• net: data frame or array representing the two-mode network (see details)

• layout: the visualization layout:

  • bip (default) bipartite graph
  • bip3 bipartite graph with three columns
  • bip3e bipartite graph with three columns for events
  • bipc ``clustered'' bipartite graph
  • force force-directed algorithm
  • rand random
  • circ circular
  • stress stress-majorization algorithm
  • CA correspondence analysis
  • circ2 two semi-circles

• scope: (optional) scope of the graph (see details)

• coord: (optional) data frame with the coordinates of the vertices; if coordinates are given then the layout option is ignored

• alpha: vector (vertex, edge, bg) with the alpha color transparency

• showLbs: (optional and logical) whether or not to show the vertex labels when dimnames available

• showAtts: (optional and logical) whether or not to show the vertex attribute labels

• att: (optional) a vector or an array representing the vertex attributes

• lbat: (optional) labels for the vertex attributes

• main: (optional) title of the plot

• cex.main: (optional) size of the plot's title

• bg: (optional) background color of the plot

• mar: (optional) margins of the plot

• directed: (optional and logical) whether or not the graph is directed or undirected

• valued: (optional and logical) whether or not the graph is valued or with dichotomous data

• collRecip: (optional and logical) whether or not collapse reciprocated edges in the undirected graph

• cex: (optional) size of the vertices

• pos: (optional) position of the vertices' labels (0 means ``at the center of the vertex'')

• lwd: (optional) width of the edges; ignored if valued is set to TRUE

• lty: (optional) shape of the edges

• col: (optional) alias for vcol

• ecol: (optional) color of the edges

• vcol: (optional) color of the vertices

• vcol0: (optional) color of the vertices' contour (only works for pch 21 through 25

• asp: (optional) aspect ratio of the plot

• seed: (optional) random seed number for the vertices' initial coordinates. Ignored except for force, stress and rand

• maxiter: (optional) maximum number of iterations in layout algorithms. Ignored except for force, stress and rand

• bwd: (optional) width of the bundle edges: ranges from 0 (edges collapsed) to the default 1 (depending on the vertices' size), and for valued a value greater than one is possible

• clu: (optional) clustering of the vertices (see details)

• pch: (optional) symbol representing the vertices

• rot: (optional) clockwise rotation of the graph in degrees

• mirrorX: (optional) mirror of the $X$ axis

• mirrorY: (optional) mirror of the $Y$ axis

• mirrorV: same as mirrorX

• mirrorH: same as mirrorY

• hds: (optional and experimental) arcs' head scale

• vedist: (optional and experimental) a real number with vertex - edge distance

• jitter: (optional) jitter in stress or CA

• sort: (optional and logical) sort the vertex labels

• add: (optional) add nodes to the graph's domain

• adc: (optional) add nodes to the graph's codomain

• perm: (optional) a list of vectors for the permutation of network members in both the domain and codomain

• ffamily: (optional) font family

• fstyle: (optional) font style

• fsize: (optional) font size

• fcol: (optional) font color

• vclu: (optional) clustering information in both the domain and the codomain in a list of vectors with integers or NULL (see details)

• ...: Additional argument items (see e.g. par)

Details

Bipartite graphs serve as visual aids for two-mode networks. While these networks are typically represented as data frames, they can also be visualized using three-dimensional arrays, where each level corresponds to a specific type of connection, resulting in parallel edges within the bipartite graph. Additionally, a bipartite network can be generated using a force-directed algorithm to create a visual representation.

With bipartite graphs consisting of two sets of vertices, clustering information, such as vertex colors, can be stored in a list vclu with two vectors, one for each vertex set. It is possible to group all members of a vertex set into a single class by setting the corresponding vector to NULL.

Returns

A plot of the two-mode network as a bipartite graph or multigraph with a projection

Author(s)

Antonio Rivero Ostoic

See Also

multigraph, frcd, stsm, conc

Examples

## two binary relations among three elements
arr <- round( replace( array(runif(18), c(3,3,2)), array(runif(18),
       c(3,3,2))>.5, 3 ) )

## network as bipartite graph
bmgraph(arr)

## with a force directed algorithm
bmgraph(arr, layout = "force")

## with a Correspondence Analysis method
bmgraph(arr, layout = "CA", asp = NA)