plotAll,ClusterizLongData {kml}R Documentation

~ Function: plotAll for ClusterizLongData ~

Description

plot the trajectories, the Calinski's criterions and the subgroups of an object ClusterizLongData on a single graph.

Usage

plotAll(x, y, ...)

Arguments

x [ClusterizLongData] Object containing the trajectories to plot.
y [numeric] or [vector(numeric)] Give the Clusterization to represent. If y is missing, the Clusterization with the highest Calinski creterion is selected. If y is a number, the first Clusterization of the sublist c y is selected. If y is a couple of numeric, the y[2]th Clusterization of the sublist c y[1] is selected.
... Graphical parameters to be passed to methods (see plot). For ClusterizLongData object specificly :
printCall
[logical]: if TRUE, the Calinski criterion will be printed.
printTraj
[logical]: if TRUE, a "main" graph, showing all the trajectories at once, will be printed.
printSub
[logical]: if TRUE, several sub-graphs, each containing a specific cluster of trajetories, will be printed.
colorTraj
[character]: Precise the color of the trajectories on the main graph. 'black' draw all the trajectories in black. 'color' draw each subgroups with a specific color. 'no' does not plot the trajectories.
colorTrajSub
[character] Precise the color of the trajectories on the sub-graphs. Same option that colorTraj.
colorMean
[character]: Precise the color of the mean trajectories of each subgroups on the main graph. 'black' draw all the mean trajectories in black. 'color' draw each mean trajectories with a specific color. 'both' draw each mean trajectories with a specific color and add a small border in black. 'no' does not plot the mean trajectories.
colorMeanSub
[character]: Precise the color of the mean trajectories of each subgroups on the sub-graphs. Same option that colorMean.
main
[charater]: give the title on the main graph.
mainSub
[charater] give the title of the sub-graphs.
point
[character]: Precise the kind of the point to plot on the mean trajectories on the main graph. 'point' adds a black dot ; 'symbols' adds a symbol ; 'letters' adds letters ; 'no' does not add points.
pointSub
[character]: Precise the kind of the point to plot on the mean trajectories on the sub-graphs. Same option that point.
size
[numeric]: If some point are added on the mean trajectories, size fixe the size of the point (on the main graph).
sizeSub
[numeric]: If some point are added on the mean trajectories, size fixe the size of the point on the sub-graphs.
ylimSub
[numeric]: give the y limit of the sub-graphs

Details

For every clusterizLongData object, there is three possible graphical representation: calinski criterion, all the trajectories at once and trajectories clusters by clusters. This function combine these three graphical output (or only two, or one, accorind to the three arguments printCal, printTraj and printSub). Thus every option (like colorMean,...) are duplicate : one is for the main graph (colorMean), the second is for the sub-graphs (colorMeanSub).

Author(s)

Christophe Genolini
PSIGIAM: Paris Sud Innovation Group in Adolescent Mental Health
INSERM U669 / Maison de Solenn / Paris

Contact author : <genolini@u-paris10.fr>

English translation

Raphaël Ricaud
Laboratoire "Sport & Culture" / "Sports & Culture" Laboratory
University of Paris 10 / Nanterre

References

Article submited
Web site: http://christophe.genolini.free.fr/kml

See Also

Overview: kml-package
Classes : ClusterizLongData, ArtificialLongData
Plot : plot: overview, plot(ClusterizLongData), plot(Calinski), plotSubGroups(ClusterizLongData)

Examples

ld <- gald()
kml(ld,2:5,5)
kml(ld,16,5)
par(ask=TRUE)

### Default ploting
plotAll(ld)

### Only the calinski criterion (same effect than plotCalinski(ld))
plotAll(ld,printCal=TRUE,printTraj=FALSE,printSub=FALSE)

### Groups and sub-groups
plotAll(ld,printCal=FALSE,printTraj=TRUE,printSub=TRUE)
plotAll(ld,printCal=FALSE,printTraj=TRUE,printSub=TRUE,colorTraj="black",colorMean="no",colorMeanSub="black")

### All at once
plotAll(ld,printCal=TRUE,printTraj=TRUE,printSub=TRUE)

### To see the clusterization with only 2 clusters
plotAll(ld,2,printCal=FALSE,printTraj=TRUE,printSub=TRUE)

### To see the third clusterization with 16 clusters
plotAll(ld,c(16,3),printCal=FALSE,printTraj=TRUE,printSub=TRUE)

par(ask=FALSE)

[Package kml version 0.9.2 Index]