TreePartition: Convert the recursively defined partitions of a tree into a...

In TreeHotspots: Hotspot Detection using Classification Trees

Description

We extract the leaf rectangles of a tree.

Usage

TreePartition(TreeFit, label = "yval", add = FALSE, ordvars, 


    ndigits = 3, ScaleAREA = 1, verbose = 0, ...)

Arguments

TreeFit	An object of class "tree".
label	A character string giving the column of the frame component of tree to be used to label the regions.
add	If true, add to existing plot, otherwise start a new plot.
ordvars	The ordering of the variables to be used in a 2D plot. Specify the names in a character string of length 2; the first will be used on the x axis.
ndigits	number of digits to display/keep
ScaleAREA	multiplier applied to simple area computations
verbose	level of verbosity
...	Graphical parameters passed to line

Value

data.frame where each row describes a leaf rectangle of the tree.

The first row pertains to the global bounding box, .i.e. the rectangle containing all data

The columns in detail are:

columns 1-4 (xleft,ybottom,xright,ytop) are the bounding box for the respective rectangle

columns 5-6 (yy1,yy2) contain the (x,y) coords of the center of the rectangle

area gives the rectangular area computed by $ScaleAREA * delta X * delta Y$

yval for factors: maximum class probability, for regression: conditional average of response inside rectangle

lab label used by PlotPartition

maxClass for factors only: majority class label inside rectangle

Author(s)

Markus Loecher

Examples

#examples to come


 print(1)

TreeHotspots documentation built on May 2, 2019, 5:17 p.m.