plotvolu: Makes a volume plot of a level set tree, a shape plot of a...
In denpro: Visualization of Multivariate Functions, Sets, and Data

Description Usage Arguments Value Author(s) See Also Examples

View source: R/denpro.R View source: R/plotvolu.R

Plots a volume plot of a level set tree to the graphics window, or a shape plot of a shape tree, or a tail frequency plot of a tail tree.

plotvolu(lst, length=NULL,
toplot=TRUE, data=FALSE, crit=NULL, orderrule="distcenter",
modelabel=FALSE, ptext=0, leimat=NULL, symbo=NULL, 
info=NULL, infolift=0, infopos=0,
xmarginleft=0, xmarginright=0, ymargin=0, 
xlim=NULL, ylim=NULL, 
col="black", col.axis="black", 
cutlev=NULL, xaxt="s", yaxt="s",
exmavisu=NULL, bg="transparent", tyyppi="n", lty="solid",colo=FALSE, 
lowest="dens", proba=FALSE,
paletti=NULL, cex=NULL, modecolo = NULL, modepointer = NULL, upper = TRUE,
cex.axis = 1, xlab="", ylab="", cex.lab=1, colothre=NULL, nodes=NULL)

`lst`	level set tree or shape tree; list of vectors. The list contain at least vectors "level", "volume", and "parent". For example, the output of "leafsfirst", "profkern" or "profhist".
`length`	vector of positive real numbers; the length of "length" is equal to the number of nodes of the level set tree "lst"; the nodes will be drawn as lines whose length is proportional to the corresponding value in vector "length". If length=NULL, then the length of the lines will be proportional to the values given in vector "volume" in the list "lst"; these are the volumes of the sets associated with nodes of the level set tree. We may for example apply function "excmas" which calculates the excess masses of the nodes and give this vector of excess masses as an argument: length=excmas(lst).
`toplot`	T or F; TRUE if we make a plot, otherwise FALSE.
`data`	T or F; TRUE if we want the output to contain some information, for example an ordering for siblings. This option is needed only by other plotting functions of the package, it is not needed by the end user.
`crit`	d-vector of real numbers; gives a way to control the ordering of siblings. The leftmost sibling is the one whose barycenter is furthest away from vector "crit".
`orderrule`	lowel level parameter
`modelabel`	T or F; TRUE if the modes will be labelled. The default is to use labels M1, M2,...
`ptext`	non-negative real number; the amount by which the mode labels will be lifted.
`leimat`	vector of characters; the length of the vector should be equal to the number of modes of the estimate. This option is for the case we do not want the ordering of the labels to be done automatically.
`symbo`	character; for example "L". The default value for the automatic labelling of the modes is to use M1, M2,... With "symbo" we may switch to L1, L2,..., for example.
`info`	vector of numbers or characters; the length of the vector is equal to the number of nodes of the level set tree. The elements of "info" will be placed on the right side of the nodes. For example, "info" may be generated by "excmas", or we may define "info" to be frequencies of the nodes. (Frequencies may be obtained directly from the function "profhist".)
`infolift`	real number; controls the vertical positioning of the elements of "info".
`infopos`	real number; controls the horizontal positioning of the elements of "info". Negative "infopos" will move elements of "info" to the right hand side.
`xmarginleft`	nonnegative real number; adds more margin on the left hand side. The box around the plot will be moved to the left with the amount "xmarginleft".
`xmarginright`	nonnegative real number; adds more margin on the right hand side. The box around the plot will be moved to the right with the amount "xmarginright".
`ymargin`	nonnegative real number; adds more margin on the top of the plot. The box around the plot will be moved up with the amount "ymargin".
`xlim`	vector of 2 real numbers; gives the limits for the scale of x-axis.
`ylim`	vector of 2 real numbers; gives the limits for the scale of y-axis.
`col`	colour for the nodes; for example "black" or "blue".
`col.axis`	color for the x and y-axis; for example "black" or "blue".
`cutlev`	positive real number; we may cut the volume plot at "cutlev" and thus zoom to the upper levels.
`xaxt`	a character which specifies the x axis type; either "s" or "n"; see "par"
`yaxt`	a character which specifies the y axis type; either "s" or "n"; see "par"
`exmavisu`	lower level parameter
`bg`	lower level parameter
`tyyppi`	lower level parameter
`lty`	lower level paremeter
`colo`	F or T; if T, then the regions under the curve of the volume transform/radius transform will be colored with the same color as the corresponding node in the barycenter plot/location plot
`lowest`	if lowest="dens" then the lowest value of y-axis is equal to 0, else the lowest value of y-axis is equal to the minimum of the function; this option allows to plot functions with negative values
`proba`	TRUE, if one wants to plot a tail probability plot of a shape tree
`paletti`	the colors for the segments of the graph; the colors are used to indicate the correspondence with the barycenter plot and thus the paletti should be the same
`cex`	the magnification factor for the symbols; see "par"
`modecolo`	internal; used by "scaletable" to set the colors of the leaf nodes
`modepointer`	internal; used by "scaletable" to find the modes
`upper`	TRUE or FALSE; if upper=TRUE, then a volume plot of an upper level set tree is drawn, otherwise a volume plot of a lower level set tree is drawn
`cex.axis`	magnification factor for the axis annotation; see "par"
`xlab`	character string; label of the x-axis
`ylab`	character string; label of the y-axis
`cex.lab`	positive real number; indicates the largeness of the labels of the plot
`colothre`	NULL or a postitive real number; used to color the volume plot when it is used to visualize a clustering
`nodes`	a vector of positive integers; used to color the volume plot when it is used to visualize a clustering with locally changing levels

A plot is made on the graphics window.

Jussi Klemela

leafsfirst, treedisc, prunemodes, plotbary plottree,

# level set tree

dendat<-sim.data(n=100,type="mulmod")
pcf<-pcf.kern(dendat,h=1,N=c(32,32))
lst<-leafsfirst(pcf)             
td<-treedisc(lst,pcf,ngrid=30)

plotvolu(td)

plotvolu(td,ptext=0.002,modelabel=TRUE,symbo="L",colo=TRUE)

# shape tree

dendat<-sim.data(n=100,type="cross")
pcf<-pcf.kern(dendat,h=1,N=c(32,32))
st<-leafsfirst(pcf,propor=0.01)   
td<-treedisc(st,pcf,ngrid=60)

plotvolu(td)

plotvolu(td,proba=TRUE)

# tail tree

tt<-leafsfirst(dendat=dendat,rho=0.65)  
plotvolu(tt)