Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
A meta classifier for handling multi-class datasets with 2-class classifiers by building an ensemble of nested dichotomies.
For more info, check
Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies for Multi-class Problems. In: PKDD, 84-95, 2005.
Eibe Frank, Stefan Kramer: Ensembles of nested dichotomies for multi-class problems. In: Twenty-first International Conference on Machine Learning, 2004.
/*
* 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 3 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, see .
*/
/*
* END.java
* Copyright (C) 2004-2016 University of Waikato, Hamilton, New Zealand
*
*/
package weka.classifiers.meta;
import java.util.Hashtable;
import java.util.Random;
import weka.classifiers.AbstractClassifier;
import weka.classifiers.Classifier;
import weka.classifiers.RandomizableIteratedSingleClassifierEnhancer;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Randomizable;
import weka.core.RevisionUtils;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
/**
* A meta classifier for handling multi-class datasets
* with 2-class classifiers by building an ensemble of nested dichotomies.
*
* For more info, check
*
* Lin Dong, Eibe Frank, Stefan Kramer: Ensembles of Balanced Nested Dichotomies
* for Multi-class Problems. In: PKDD, 84-95, 2005.
*
* Eibe Frank, Stefan Kramer: Ensembles of nested dichotomies for multi-class
* problems. In: Twenty-first International Conference on Machine Learning,
* 2004.
*
*
*
* BibTeX:
*
* @inproceedings{Frank2004,
* author = {Eibe Frank and Stefan Kramer},
* booktitle = {Twenty-first International Conference on Machine Learning},
* publisher = {ACM},
* title = {Ensembles of nested dichotomies for multi-class problems},
* year = {2004}
* }
*
*
*
*
* Valid options are:
*
*
*
* -S <num>
* Random number seed.
* (default 1)
*
*
*
* -I <num>
* Number of iterations.
* (default 10)
*
*
*
* -D
* If set, classifier is run in debug mode and
* may output additional info to the console
*
*
*
* -W
* Full name of base classifier.
* (default: weka.classifiers.meta.nestedDichotomies.ND)
*
*
*
* Options specific to classifier weka.classifiers.meta.nestedDichotomies.ND:
*
*
*
* -S <num>
* Random number seed.
* (default 1)
*
*
*
* -D
* If set, classifier is run in debug mode and
* may output additional info to the console
*
*
*
* -W
* Full name of base classifier.
* (default: weka.classifiers.trees.J48)
*
*
*
* Options specific to classifier weka.classifiers.trees.J48:
*
*
*
* -U
* Use unpruned tree.
*
*
*
* -C <pruning confidence>
* Set confidence threshold for pruning.
* (default 0.25)
*
*
*
* -M <minimum number of instances>
* Set minimum number of instances per leaf.
* (default 2)
*
*
*
* -R
* Use reduced error pruning.
*
*
*
* -N <number of folds>
* Set number of folds for reduced error
* pruning. One fold is used as pruning set.
* (default 3)
*
*
*
* -B
* Use binary splits only.
*
*
*
* -S
* Don't perform subtree raising.
*
*
*
* -L
* Do not clean up after the tree has been built.
*
*
*
* -A
* Laplace smoothing for predicted probabilities.
*
*
*
* -Q <seed>
* Seed for random data shuffling (default 1).
*
*
*
*
* Options after -- are passed to the designated classifier.
*
*
* @author Eibe Frank
* @author Lin Dong
* @version $Revision: 13079 $
*/
public class END extends RandomizableIteratedSingleClassifierEnhancer implements
TechnicalInformationHandler {
/** for serialization */
static final long serialVersionUID = -4143242362912214956L;
/**
* The hashtable containing the classifiers for the END.
*/
protected Hashtable m_hashtable = null;
/**
* Constructor.
*/
public END() {
m_Classifier = new weka.classifiers.meta.nestedDichotomies.ND();
}
/**
* String describing default classifier.
*
* @return the default classifier classname
*/
@Override
protected String defaultClassifierString() {
return "weka.classifiers.meta.nestedDichotomies.ND";
}
/**
* Returns a string describing classifier
*
* @return a description suitable for displaying in the explorer/experimenter
* gui
*/
public String globalInfo() {
return "A meta classifier for handling multi-class datasets with 2-class "
+ "classifiers by building an ensemble of nested dichotomies.\n\n"
+ "For more info, check\n\n" + getTechnicalInformation().toString();
}
/**
* Returns an instance of a TechnicalInformation object, containing detailed
* information about the technical background of this class, e.g., paper
* reference or book this class is based on.
*
* @return the technical information about this class
*/
@Override
public TechnicalInformation getTechnicalInformation() {
TechnicalInformation result;
TechnicalInformation additional;
result = new TechnicalInformation(Type.INPROCEEDINGS);
additional = result.add(Type.INPROCEEDINGS);
additional.setValue(Field.AUTHOR, "Eibe Frank and Stefan Kramer");
additional.setValue(Field.TITLE,
"Ensembles of nested dichotomies for multi-class problems");
additional.setValue(Field.BOOKTITLE,
"Twenty-first International Conference on Machine Learning");
additional.setValue(Field.YEAR, "2004");
additional.setValue(Field.PUBLISHER, "ACM");
return result;
}
/**
* Returns default capabilities of the classifier.
*
* @return the capabilities of this classifier
*/
@Override
public Capabilities getCapabilities() {
Capabilities result = super.getCapabilities();
// instances
result.setMinimumNumberInstances(1); // at least 1 for the
// RandomNumberGenerator!
return result;
}
/**
* Builds the committee of randomizable classifiers.
*
* @param data the training data to be used for generating the bagged
* classifier.
* @throws Exception if the classifier could not be built successfully
*/
@Override
public void buildClassifier(Instances data) throws Exception {
// can classifier handle the data?
getCapabilities().testWithFail(data);
// remove instances with missing class
data = new Instances(data);
data.deleteWithMissingClass();
if (!(m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.ND)
&& !(m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.ClassBalancedND)
&& !(m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.DataNearBalancedND)
&& !(m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.RandomPairND)) {
throw new IllegalArgumentException(
"END only works with base classifiers in the nestedDichotomies package!");
}
m_hashtable = new Hashtable();
m_Classifiers = AbstractClassifier
.makeCopies(m_Classifier, m_NumIterations);
Random random = data.getRandomNumberGenerator(m_Seed);
for (Classifier m_Classifier2 : m_Classifiers) {
// Set the random number seed for the current classifier.
((Randomizable) m_Classifier2).setSeed(random.nextInt());
// Set the hashtable
if (m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.ND) {
((weka.classifiers.meta.nestedDichotomies.ND) m_Classifier2)
.setHashtable(m_hashtable);
} else if (m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.ClassBalancedND) {
((weka.classifiers.meta.nestedDichotomies.ClassBalancedND) m_Classifier2)
.setHashtable(m_hashtable);
} else if (m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.DataNearBalancedND) {
((weka.classifiers.meta.nestedDichotomies.DataNearBalancedND) m_Classifier2)
.setHashtable(m_hashtable);
} else if (m_Classifier instanceof weka.classifiers.meta.nestedDichotomies.RandomPairND) {
((weka.classifiers.meta.nestedDichotomies.RandomPairND) m_Classifier2)
.setHashtable(m_hashtable);
}
// Build the classifier.
m_Classifier2.buildClassifier(data);
}
}
/**
* Calculates the class membership probabilities for the given test instance.
*
* @param instance the instance to be classified
* @return preedicted class probability distribution
* @throws Exception if distribution can't be computed successfully
*/
@Override
public double[] distributionForInstance(Instance instance) throws Exception {
double[] sums = new double[instance.numClasses()], newProbs;
for (int i = 0; i < m_NumIterations; i++) {
if (instance.classAttribute().isNumeric() == true) {
sums[0] += m_Classifiers[i].classifyInstance(instance);
} else {
newProbs = m_Classifiers[i].distributionForInstance(instance);
for (int j = 0; j < newProbs.length; j++) {
sums[j] += newProbs[j];
}
}
}
if (instance.classAttribute().isNumeric() == true) {
sums[0] /= m_NumIterations;
return sums;
} else if (Utils.eq(Utils.sum(sums), 0)) {
return sums;
} else {
Utils.normalize(sums);
return sums;
}
}
/**
* Returns description of the committee.
*
* @return description of the committee as a string
*/
@Override
public String toString() {
if (m_Classifiers == null) {
return "END: No model built yet.";
}
StringBuffer text = new StringBuffer();
text.append("All the base classifiers: \n\n");
for (Classifier m_Classifier2 : m_Classifiers) {
text.append(m_Classifier2.toString() + "\n\n");
}
return text.toString();
}
/**
* Returns the revision string.
*
* @return the revision
*/
@Override
public String getRevision() {
return RevisionUtils.extract("$Revision: 13079 $");
}
/**
* Main method for testing this class.
*
* @param argv the options
*/
public static void main(String[] argv) {
runClassifier(new END(), argv);
}
}
