/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
* Id3.java
* Copyright (C) 1999 Eibe Frank
*
*/
package weka.classifiers.trees;
import weka.classifiers.Classifier;
import weka.classifiers.DistributionClassifier;
import weka.classifiers.Evaluation;
import weka.core.*;
import java.io.*;
import java.util.*;
/**
* Class implementing an Id3 decision tree classifier. For more
* information, see<p>
*
* R. Quinlan (1986). <i>Induction of decision
* trees</i>. Machine Learning. Vol.1, No.1, pp. 81-106.<p>
*
* @author Eibe Frank (eibe@cs.waikato.ac.nz)
* @version $Revision: 1.1.1.1 $
*/
public class Id3 extends DistributionClassifier {
/** The node's successors. */
private Id3[] m_Successors;
/** Attribute used for splitting. */
private Attribute m_Attribute;
/** Class value if node is leaf. */
private double m_ClassValue;
/** Class distribution if node is leaf. */
private double[] m_Distribution;
/** Class attribute of dataset. */
private Attribute m_ClassAttribute;
/**
* Builds Id3 decision tree classifier.
*
* @param data the training data
* @exception Exception if classifier can't be built successfully
*/
public void buildClassifier(Instances data) throws Exception {
if (!data.classAttribute().isNominal()) {
throw new UnsupportedClassTypeException("Id3: nominal class, please.");
}
Enumeration enumAtt = data.enumerateAttributes();
while (enumAtt.hasMoreElements()) {
Attribute attr = (Attribute) enumAtt.nextElement();
if (!attr.isNominal()) {
throw new UnsupportedAttributeTypeException("Id3: only nominal attributes, please.");
}
Enumeration enum = data.enumerateInstances();
while (enum.hasMoreElements()) {
if (((Instance) enum.nextElement()).isMissing(attr)) {
throw new NoSupportForMissingValuesException("Id3: no missing values, please.");
}
}
}
data = new Instances(data);
data.deleteWithMissingClass();
makeTree(data);
}
/**
* Method building Id3 tree.
*
* @param data the training data
* @exception Exception if decision tree can't be built successfully
*/
private void makeTree(Instances data) throws Exception {
// Check if no instances have reached this node.
if (data.numInstances() == 0) {
m_Attribute = null;
m_ClassValue = Instance.missingValue();
m_Distribution = new double[data.numClasses()];
return;
}
// Compute attribute with maximum information gain.
double[] infoGains = new double[data.numAttributes()];
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
infoGains[att.index()] = computeInfoGain(data, att);
}
m_Attribute = data.attribute(Utils.maxIndex(infoGains));
// Make leaf if information gain is zero.
// Otherwise create successors.
if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
m_Attribute = null;
m_Distribution = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
m_Distribution[(int) inst.classValue()]++;
}
Utils.normalize(m_Distribution);
m_ClassValue = Utils.maxIndex(m_Distribution);
m_ClassAttribute = data.classAttribute();
} else {
Instances[] splitData = splitData(data, m_Attribute);
m_Successors = new Id3[m_Attribute.numValues()];
for (int j = 0; j < m_Attribute.numValues(); j++) {
m_Successors[j] = new Id3();
m_Successors[j].buildClassifier(splitData[j]);
}
}
}
/**
* Classifies a given test instance using the decision tree.
*
* @param instance the instance to be classified
* @return the classification
*/
public double classifyInstance(Instance instance) {
if (m_Attribute == null) {
return m_ClassValue;
} else {
return m_Successors[(int) instance.value(m_Attribute)].
classifyInstance(instance);
}
}
/**
* Computes class distribution for instance using decision tree.
*
* @param instance the instance for which distribution is to be computed
* @return the class distribution for the given instance
*/
public double[] distributionForInstance(Instance instance) {
if (m_Attribute == null) {
return m_Distribution;
} else {
return m_Successors[(int) instance.value(m_Attribute)].
distributionForInstance(instance);
}
}
/**
* Prints the decision tree using the private toString method from below.
*
* @return a textual description of the classifier
*/
public String toString() {
if ((m_Distribution == null) && (m_Successors == null)) {
return "Id3: No model built yet.";
}
return "Id3\n\n" + toString(0);
}
/**
* Computes information gain for an attribute.
*
* @param data the data for which info gain is to be computed
* @param att the attribute
* @return the information gain for the given attribute and data
*/
private double computeInfoGain(Instances data, Attribute att)
throws Exception {
double infoGain = computeEntropy(data);
Instances[] splitData = splitData(data, att);
for (int j = 0; j < att.numValues(); j++) {
if (splitData[j].numInstances() > 0) {
infoGain -= ((double) splitData[j].numInstances() /
(double) data.numInstances()) *
computeEntropy(splitData[j]);
}
}
return infoGain;
}
/**
* Computes the entropy of a dataset.
*
* @param data the data for which entropy is to be computed
* @return the entropy of the data's class distribution
*/
private double computeEntropy(Instances data) throws Exception {
double [] classCounts = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
classCounts[(int) inst.classValue()]++;
}
double entropy = 0;
for (int j = 0; j < data.numClasses(); j++) {
if (classCounts[j] > 0) {
entropy -= classCounts[j] * Utils.log2(classCounts[j]);
}
}
entropy /= (double) data.numInstances();
return entropy + Utils.log2(data.numInstances());
}
/**
* Splits a dataset according to the values of a nominal attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances produced by the split
*/
private Instances[] splitData(Instances data, Attribute att) {
Instances[] splitData = new Instances[att.numValues()];
for (int j = 0; j < att.numValues(); j++) {
splitData[j] = new Instances(data, data.numInstances());
}
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
splitData[(int) inst.value(att)].add(inst);
}
return splitData;
}
/**
* Outputs a tree at a certain level.
*
* @param level the level at which the tree is to be printed
*/
private String toString(int level) {
StringBuffer text = new StringBuffer();
if (m_Attribute == null) {
if (Instance.isMissingValue(m_ClassValue)) {
text.append(": null");
} else {
text.append(": "+m_ClassAttribute.value((int) m_ClassValue));
}
} else {
for (int j = 0; j < m_Attribute.numValues(); j++) {
text.append("\n");
for (int i = 0; i < level; i++) {
text.append("| ");
}
text.append(m_Attribute.name() + " = " + m_Attribute.value(j));
text.append(m_Successors[j].toString(level + 1));
}
}
return text.toString();
}
/**
* Main method.
*
* @param args the options for the classifier
*/
public static void main(String[] args) {
try {
System.out.println(Evaluation.evaluateModel(new Id3(), args));
} catch (Exception e) {
System.err.println(e.getMessage());
}
}
}