MATLAB: How to save the figure of a classification and regression tree generated with VIEW command in Statistics Toolbox 6.1 (R2007b)

Statistics and Machine Learning Toolbox

I have generated a classification and regression tree in Statistics Toolbox 6.1 (R2007b) and use the VIEW command to plot it:

load fisheriris;
t = classregtree(meas,species,'names',{'SL' 'SW' 'PL' 'PW'});
view(t)

I would like to save this picture to file.

Best Answer

It is possible to save the tree picture by using the handle of the Figure that shows the tree. First you need to ask for the handle with the VIEW method:

h = view(t);

Then you can use any of the save or print functions that work on a figure handle, for instance:

saveas(h, 'myTree.png')

Related Solutions

MATLAB: How to determine which sample was assigned to which node in CLASSREGTREE in Statistics Toolbox 7.4 (R2010b)

You can use the EVAL method of the CLASSREGTREE class to determine which sample was assigned to which final node. For example:

load fisheriris;
t = classregtree(meas,species,'names',{'SL' 'SW' 'PL' 'PW'});
[fittedval, nodes] = eval(t,meas);    % determine mapping of training samples to nodes

This code stores the nodes for each sample in "meas" in the second output argument "nodes".

MATLAB: How to retrieve the levels of a node, maximum level and maximum pruning level from a CLASSREGTREE in MATLAB 7.6 (R2008a)

There are at least two ways to obtain the level of a node in a CLASSREGTREE using MATLAB 7.6 (R2008a).

The first is to view the tree and read the number of levels from the GUI:

load fisheriris;
t = classregtree(meas,species,'names',{'SL' 'SW' 'PL' 'PW'});
view(t)

The second method allows you to programmatically obtain the number of levels. There is a file attached: 'levelOf.m' which uses recursion to obtain the level of any node in the tree, where the root node is level 1, the children of the root are level 2 and so forth. To obtain the number of levels, call LEVELOF with the following syntax:

nodeindex = t.numnodes;
nodelevel = levelOf(t,nodeindex)

To retrieve the maximum pruning level, use:

max(t.prunelist)

Best Answer

Related Solutions

MATLAB: How to determine which sample was assigned to which node in CLASSREGTREE in Statistics Toolbox 7.4 (R2010b)

MATLAB: How to retrieve the levels of a node, maximum level and maximum pruning level from a CLASSREGTREE in MATLAB 7.6 (R2008a)

Related Question