weka.classifiers.trees
Class UserClassifier

java.lang.Object
  weka.classifiers.Classifier
      weka.classifiers.trees.UserClassifier

All Implemented Interfaces:

java.lang.Cloneable, Drawable, OptionHandler, java.io.Serializable, TreeDisplayListener, VisualizePanelListener

public class UserClassifier

extends Classifier

implements Drawable, TreeDisplayListener, VisualizePanelListener

Class for generating an user defined decision tree. For more info see

Ware M., Frank E., Holmes G., Hall M. and Witten I.H. (2000). interactive machine learning - letting users build classifiers, Working Paper 00/4, Department of Computer Science, University of Waikato; March. Also available online at http://www.cs.waikato.ac.nz/~ml/publications/2000/ 00MW-etal-Interactive-ML.ps.

Version:

$Revision: 1.15 $

Author:

Malcolm Ware (mfw4@cs.waikato.ac.nz)

See Also:

Serialized Form

Nested Class Summary

private class

UserClassifier.TreeClass Inner class used to represent the actual decision tree structure and data.

Field Summary

private static int	HLINE
private static int	LEAF I am not sure if these are strictly adhered to in visualizepanel so I am making them private to avoid confusion, (note that they will be correct in this class, VLINE and HLINE aren't used).
private boolean	m_built The status of whether there is a decision tree ready or not.
private GenericObjectEditor	m_classifiers A list of other m_classifiers.
private UserClassifier.TreeClass	m_focus Two references to the structure of the decision tree.
private VisualizePanel	m_iView The instances display.
private javax.swing.JFrame	m_mainWin The window.
private int	m_nextId The next number that can be used as a unique id for a node.
private PropertyDialog	m_propertyDialog A window for selecting other classifiers.
private javax.swing.JTabbedPane	m_reps The tabbed window for the tree and instances view.
private UserClassifier.TreeClass	m_top Two references to the structure of the decision tree.
private javax.swing.JFrame	m_treeFrame These two frames aren't used anymore.
private TreeVisualizer	m_tView The tree display panel.
private javax.swing.JFrame	m_visFrame
private static int	POLYGON
private static int	POLYLINE
private static int	RECTANGLE
private static int	VLINE

Fields inherited from class weka.classifiers.Classifier

m_Debug

Fields inherited from interface weka.core.Drawable

BayesNet, NOT_DRAWABLE, TREE

Constructor Summary

UserClassifier()
Constructor

Method Summary

private void	blocker(boolean tf) A function used to stop the code that called buildclassifier from continuing on before the user has finished the decision tree.
void	buildClassifier(Instances i) Call this function to build a decision tree for the training data provided.
double[]	distributionForInstance(Instance i) Call this function to get a double array filled with the probability of how likely each class type is the class of the instance.
java.lang.String	globalInfo() This will return a string describing the classifier.
java.lang.String	graph() Returns a string that describes a graph representing the object.
int	graphType() Returns the type of graph this classifier represents.
static void	main(java.lang.String[] argv) Main method for testing this class.
java.lang.String	toString()
void	userCommand(TreeDisplayEvent e) Receives user choices from the tree view, and then deals with these choices.
void	userDataEvent(VisualizePanelEvent e) This receives shapes from the data view.

Methods inherited from class weka.classifiers.Classifier

classifyInstance, debugTipText, forName, getDebug, getOptions, listOptions, makeCopies, setDebug, setOptions

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

LEAF

private static final int LEAF

I am not sure if these are strictly adhered to in visualizepanel so I am making them private to avoid confusion, (note that they will be correct in this class, VLINE and HLINE aren't used).

See Also:

Constant Field Values

RECTANGLE

private static final int RECTANGLE

See Also:

Constant Field Values

POLYGON

private static final int POLYGON

See Also:

Constant Field Values

POLYLINE

private static final int POLYLINE

See Also:

Constant Field Values

VLINE

private static final int VLINE

See Also:

Constant Field Values

HLINE

private static final int HLINE

See Also:

Constant Field Values

m_tView

private TreeVisualizer m_tView

The tree display panel.

m_iView

private VisualizePanel m_iView

The instances display.

m_top

private UserClassifier.TreeClass m_top

Two references to the structure of the decision tree.

m_focus

private UserClassifier.TreeClass m_focus

Two references to the structure of the decision tree.

m_nextId

private int m_nextId

The next number that can be used as a unique id for a node.

m_treeFrame

private javax.swing.JFrame m_treeFrame

These two frames aren't used anymore.

m_visFrame

private javax.swing.JFrame m_visFrame

m_reps

private javax.swing.JTabbedPane m_reps

The tabbed window for the tree and instances view.

m_mainWin

private javax.swing.JFrame m_mainWin

The window.

m_built

private boolean m_built

The status of whether there is a decision tree ready or not.

m_classifiers

private GenericObjectEditor m_classifiers

A list of other m_classifiers.

m_propertyDialog

private PropertyDialog m_propertyDialog

A window for selecting other classifiers.

Constructor Detail

UserClassifier

public UserClassifier()

Constructor

Method Detail

main

public static void main(java.lang.String[] argv)

Main method for testing this class.

Parameters:

argv - should contain command line options (see setOptions)

toString

public java.lang.String toString()

Returns:

a string that represents this objects tree.

userCommand

public void userCommand(TreeDisplayEvent e)

Receives user choices from the tree view, and then deals with these choices.

Specified by:

userCommand in interface TreeDisplayListener

Parameters:

e - The choice.

userDataEvent

public void userDataEvent(VisualizePanelEvent e)

This receives shapes from the data view. It then enters these shapes into the decision tree structure.

Specified by:

userDataEvent in interface VisualizePanelListener

Parameters:

e - Contains the shapes, and other info.

graphType

public int graphType()

Returns the type of graph this classifier represents.

Specified by:

graphType in interface Drawable

Returns:

Drawable.TREE

graph

public java.lang.String graph()
                       throws java.lang.Exception

Description copied from interface: Drawable

Returns a string that describes a graph representing the object. The string should be in XMLBIF ver. 0.3 format if the graph is a BayesNet, otherwise it should be in dotty format.

Specified by:

graph in interface Drawable

Returns:

A string formatted with a dotty representation of the decision tree.

Throws:

java.lang.Exception - if String can't be built properly.

blocker

private void blocker(boolean tf)

A function used to stop the code that called buildclassifier from continuing on before the user has finished the decision tree.

Parameters:

tf - True to stop the thread, False to release the thread that is waiting there (if one).

globalInfo

public java.lang.String globalInfo()

This will return a string describing the classifier.

Returns:

The string.

buildClassifier

public void buildClassifier(Instances i)
                     throws java.lang.Exception

Call this function to build a decision tree for the training data provided.

Specified by:

buildClassifier in class Classifier

Parameters:

i - The training data.

Throws:

java.lang.Exception - if can't build classification properly.

distributionForInstance

public double[] distributionForInstance(Instance i)
                                 throws java.lang.Exception

Call this function to get a double array filled with the probability of how likely each class type is the class of the instance.

Overrides:

distributionForInstance in class Classifier

Parameters:

i - The instance to classify.

Returns:

A double array filled with the probalities of each class type.

Throws:

java.lang.Exception - if can't classify instance.