Description
Makes a plot of one Logic Regression tree, fitted by logreg.
Usage
## S3 method for class 'logregtree'
plot(x, nms, full=TRUE, and.or.cx=1.0, leaf.sz=1.0,
leaf.txt.cx=1.0, coef.cx=1.0, indents=rep(0,4), coef=TRUE,
coef.rd=4, ...)
Arguments
| x | an object of class logregtree, or the trees component of such an object. Typically this object will be part of the result of an object of class logreg, generated with select = 1 (single model fit) or select = 2 (multiple model fit). |
| nms | names of variables. If nms is provided variable names will be plotted, otherwise indices will be used. |
| full | if TRUE, the tree occupies the entire window with margins specified by indents. |
| and.or.cx | character expansion (size) for the operators and/or. |
| leaf.sz | character expansion for the size of the leaves. |
| leaf.txt.cx | character expansion for the text in the leaves. |
| coef.cx | character expansion for the coefficient string. |
| indents | indents for plot - bottom, left, top, right. |
| coef | if TRUE, the coefficient of the tree is plotted. |
| coef.rd | controls how many digits of the above coefficient are displayed. |
| ... | graphical parameters can be given as arguments to plot. |
Value
This function makes a plot of one logic tree. The character expansion terms (and.or.cx, leaf.sz, leaf.txt.cx, coef.cx) defaults of 1.0 are chosen to generate a pretty plot of a single tree with up to eight leaves (4 levels deep). To plot more than one tree, or trees of different complexity, scale accordingly.
Author(s)
Ingo Ruczinski (ingo@jhu.edu) and Charles Kooperberg (clk@fredhutch.org).
References
Ruczinski I, Kooperberg C, LeBlanc ML (2003). Logic Regression, Journal of Computational and Graphical Statistics, 12, 475-511.
Ruczinski I, Kooperberg C, LeBlanc ML (2002). Logic Regression - methods and software. Proceedings of the MSRI workshop on Nonlinear Estimation and Classification (Eds: D. Denison, M. Hansen, C. Holmes, B. Mallick, B. Yu), Springer: New York, 333-344.
Selected chapters from the dissertation of Ingo Ruczinski.
See Also
logreg, frame.logreg, logreg.testdat
Examples
data(logreg.savefit2)
#
# myanneal2 <- logreg.anneal.control(start = -1, end = -4, iter = 25000, update = 0)
# logreg.savefit2 <- logreg(resp = logreg.testdat[,1], bin=logreg.testdat[, 2:21],
# type = 2, select = 2, ntrees = c(1,2), nleaves =c(1,7),
# anneal.control = myanneal2)
for(i in 1:logreg.savefit2$nmodels) for(j in 1:logreg.savefit2$alltrees[[i]]$ntrees[1]){
plot.logregtree(logreg.savefit2$alltrees[[i]]$trees[[j]])
title(main=paste("model",i,"tree",j))
}