visualiseGroupset: Visualise a group set

In ecpc: Flexible Co-Data Learning for High-Dimensional Prediction

Visualise a group set

Description

Visualises a group set in a graph, with directed edges indicating the hierarchy.

Usage

visualiseGroupset(Groupset, groupweights, groupset.grouplvl, nodeSize = 10, ls = 1)

Arguments

Groupset	List of G groups of covariates.
groupweights	(optional) vector with G group weights; if given, group weights are visualised too.
groupset.grouplvl	List of G_2 groups defining a hierarchy.
nodeSize	Size of the nodes in the visualisation; scalar.
ls	Line size; scalar.

Value

A ggplot object.

See Also

visualiseGroupsetweights to plot estimated group set weights. and visualiseGroupweights to plot estimated group weights.

Examples

#groups without hierarchical constraints
groupset <- list("Group1"=c(1:20),"Group2"=c(15,30))
visualiseGroupset(groupset,c(0.5,2))

#hierarchical groups
cont.codata <- seq(0,1,length.out=20) #continuous co-data
#only split at lower continous co-data group
hierarchicalgroupset <- splitMedian(values=cont.codata,split="lower",minGroupSize=5)
#obtain groups on group level defining the hierarchy
groupset.grouplvl <- obtainHierarchy(hierarchicalgroupset)
visualiseGroupset(hierarchicalgroupset, groupset.grouplvl=groupset.grouplvl)

ecpc documentation built on March 7, 2023, 6:46 p.m.