Main Page | Class Hierarchy | Class List | Class Members

kddml.Core.DataMining.ClassificationTrees.TreeModel Class Reference

Inheritance diagram for kddml.Core.DataMining.ClassificationTrees.TreeModel:

kddml.Core.DataMining.MiningModel kddml.Core.DataMining.ClassificationTrees.TreeModelManager kddml.Core.KDDMLObject kddml.Core.DataMining.MiningModelManager kddml.Core.DataMining.MiningModelManager kddml.Core.HTMLTranslator List of all members.

Public Member Functions

KDDMLObjectType getType ()
boolean isEmpty ()
void saveToRepository () throws kddml.Core.KDDMLCoreException
String toString ()
void saveHTML () throws KDDMLCoreException
boolean isDecisionTree () throws KDDMLCoreException
NodeManager getRoot ()
ConfusionMatrixManager getTrainingConfusionMatrix ()
ConfusionMatrixManager getTestConfusionMatrix ()
void setTrainingConfusionMatrix (ConfusionMatrixManager cm)
void setTestConfusionMatrix (ConfusionMatrixManager cm)
boolean isBinarySplitting ()
String getTargetAttributeName () throws KDDMLCoreException
String[] getTargetAttributeValues () throws KDDMLCoreException
String classify (Object instance) throws KDDMLCoreException

Protected Member Functions

String classify (NodeManager node, Instance instance) throws KDDMLCoreException
ScoreDistribution getDistribution (SimpleNode node, Instance instance) throws KDDMLCoreException

Detailed Description

A tree model in data mining is used to predict the class of a case with unknown categorical label. A classification tree is a flow-chart-like structure, where each internal node denotes a test on an attribute, each branch represents an outcome of the test, and the leaf nodes represent classes or class distributions. The top-most node in a tree is the root node.
In order to classify an unknown sample, the attribute values of the sample are tested against the decision tree. A path is traced from the root to a leaf node that holds the class prediction for that sample.
Given a pre-determined set of classes in the target attribute, classification analyzes the build data to determine to which class a given case belongs.
A decision tree is a classification tree in witch the target attribute is binary. A tree model consists of a reference to the Node root. Each Node holds a logical predicate expression that defines the rule for choosing the Node or any of the branching Nodes.
Optionally, a classification model can have two confusion matrixes related to the training and test instances resplectively. It depends to the algorithm used to build the model. A confusion matrix is a two-dimensional table that indicates the number of correct and incorrect predictions a tree model made on specific data. It provides a measure of accuracy of the model.

Title: KDDML

Description: Knowledge Discovery in Database Environment

Copyright: Copyright (c) 2003-2005

Company: Universita' di Pisa - Dipartimento di Informatica

Author:
Andrea Romei (romei@di.unipi.it)
Version:
2.0.16


Member Function Documentation

KDDMLObjectType kddml.Core.DataMining.ClassificationTrees.TreeModel.getType  )  [virtual]
 

It returns the type of this object.

Returns:
KDDMLObjectType the type of this object

Implements kddml.Core.KDDMLObject.

boolean kddml.Core.DataMining.ClassificationTrees.TreeModel.isEmpty  )  [virtual]
 

Tests if the object is empty. This depends on the type of the object. For example, the method can return true if a table do not contain instances or if an association model do not contain association rules.

Returns:
boolean false

Implements kddml.Core.KDDMLObject.

void kddml.Core.DataMining.ClassificationTrees.TreeModel.saveToRepository  )  throws kddml.Core.KDDMLCoreException [virtual]
 

Saves the object into the system repository. The destination path is provided by the object_path variable. Throws an exception if a I/O error occurs.

Exceptions:
KDDMLCoreException 

Implements kddml.Core.KDDMLObject.

String kddml.Core.DataMining.ClassificationTrees.TreeModel.toString  ) 
 

Returns a representation of this object as string.

Returns:
String

Reimplemented from kddml.Core.DataMining.MiningModel.

void kddml.Core.DataMining.ClassificationTrees.TreeModel.saveHTML  )  throws KDDMLCoreException [virtual]
 

Saves the object in the system repository as HTML document.

Exceptions:
KDDMLCoreException 

Implements kddml.Core.HTMLTranslator.

boolean kddml.Core.DataMining.ClassificationTrees.TreeModel.isDecisionTree  )  throws KDDMLCoreException
 

Returns true if the target attribute is binary (i.e. with exactly two category values). Throws an exception if the target attribute connot be found in the mining schema and data dictionary of the model.

Exceptions:
KDDMLCoreException 
Returns:
boolean

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

NodeManager kddml.Core.DataMining.ClassificationTrees.TreeModel.getRoot  ) 
 

Returns the root node for this classification tree.

Returns:
NodeManager

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

ConfusionMatrixManager kddml.Core.DataMining.ClassificationTrees.TreeModel.getTrainingConfusionMatrix  ) 
 

Returns the training confusion matrix related to the model. Returns null if the model do not have a confusion matrix associated.

Returns:
ConfusionMatrixManager the training confusion matrix or null.

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

ConfusionMatrixManager kddml.Core.DataMining.ClassificationTrees.TreeModel.getTestConfusionMatrix  ) 
 

Returns the test confusion matrix related to the model. Returns null if the model do not have a confusion matrix associated.

Returns:
ConfusionMatrixManager the test confusion matrix or null.

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

void kddml.Core.DataMining.ClassificationTrees.TreeModel.setTrainingConfusionMatrix ConfusionMatrixManager  cm  ) 
 

Sets the training confusion matrix to the model.

Parameters:
cm ConfusionMatrixManager

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

void kddml.Core.DataMining.ClassificationTrees.TreeModel.setTestConfusionMatrix ConfusionMatrixManager  cm  ) 
 

Sets the test confusion matrix to the model.

Parameters:
cm ConfusionMatrixManager

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

boolean kddml.Core.DataMining.ClassificationTrees.TreeModel.isBinarySplitting  ) 
 

Indicates whether the tree model has exactly two children per node, or multiple childrens per node. In the case of binary_split = false, it means that each node may have 2 or more child nodes.

Returns:
boolean true if the model has exactly two clindren per node. False otherwise.

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

String kddml.Core.DataMining.ClassificationTrees.TreeModel.getTargetAttributeName  )  throws KDDMLCoreException
 

Returns the name of the target attribute. Throws an exception if the target attribute connot be found in the mining schema.

Exceptions:
KDDMLCoreException 
Returns:
String

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

String [] kddml.Core.DataMining.ClassificationTrees.TreeModel.getTargetAttributeValues  )  throws KDDMLCoreException
 

Returns the categories associated to the target attributes. Throws an exception if the target attribute connot be found in the mining schema.

Exceptions:
KDDMLCoreException 
Returns:
String[]

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

String kddml.Core.DataMining.ClassificationTrees.TreeModel.classify Object  instance  )  throws KDDMLCoreException
 

Method used to classify an input instance. Returns the classification value. Cannot be null. Throws an exception is an error occurs.

Parameters:
instance Object the instance as in weka.Core.Instance.
Exceptions:
KDDMLCoreException 
Returns:
String the classification balue. Cannot be null.

Implements kddml.Core.DataMining.ClassificationTrees.TreeModelManager.

String kddml.Core.DataMining.ClassificationTrees.TreeModel.classify NodeManager  node,
Instance  instance
throws KDDMLCoreException [protected]
 

Returns the prediction target value as string for the input node.

Parameters:
node NodeManager
instance Instance
Exceptions:
KDDMLCoreException 
Returns:
String

ScoreDistribution kddml.Core.DataMining.ClassificationTrees.TreeModel.getDistribution SimpleNode  node,
Instance  instance
throws KDDMLCoreException [protected]
 

Returns the distribution related to a node for a given input instance.

Parameters:
node SimpleNode
instance Instance
Exceptions:
KDDMLCoreException 
Returns:
ScoreDistribution


Generated on Thu Feb 23 13:04:40 2006 for kddml by  doxygen 1.4.3