MOA 12.03
Real Time Analytics for Data Streams
|
00001 /* 00002 * MajorityClass.java 00003 * Copyright (C) 2007 University of Waikato, Hamilton, New Zealand 00004 * @author Richard Kirkby ([email protected]) 00005 * 00006 * This program is free software; you can redistribute it and/or modify 00007 * it under the terms of the GNU General Public License as published by 00008 * the Free Software Foundation; either version 3 of the License, or 00009 * (at your option) any later version. 00010 * 00011 * This program is distributed in the hope that it will be useful, 00012 * but WITHOUT ANY WARRANTY; without even the implied warranty of 00013 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 00014 * GNU General Public License for more details. 00015 * 00016 * You should have received a copy of the GNU General Public License 00017 * along with this program. If not, see <http://www.gnu.org/licenses/>. 00018 * 00019 */ 00020 package moa.classifiers.functions; 00021 00022 import moa.classifiers.AbstractClassifier; 00023 import moa.core.DoubleVector; 00024 import moa.core.Measurement; 00025 import moa.core.StringUtils; 00026 import weka.core.Instance; 00027 00034 public class MajorityClass extends AbstractClassifier { 00035 00036 private static final long serialVersionUID = 1L; 00037 00038 @Override 00039 public String getPurposeString() { 00040 return "Majority class classifier: always predicts the class that has been observed most frequently the in the training data."; 00041 } 00042 00043 protected DoubleVector observedClassDistribution; 00044 00045 @Override 00046 public void resetLearningImpl() { 00047 this.observedClassDistribution = new DoubleVector(); 00048 } 00049 00050 @Override 00051 public void trainOnInstanceImpl(Instance inst) { 00052 this.observedClassDistribution.addToValue((int) inst.classValue(), inst.weight()); 00053 } 00054 00055 public double[] getVotesForInstance(Instance i) { 00056 return this.observedClassDistribution.getArrayCopy(); 00057 } 00058 00059 @Override 00060 protected Measurement[] getModelMeasurementsImpl() { 00061 return null; 00062 } 00063 00064 @Override 00065 public void getModelDescription(StringBuilder out, int indent) { 00066 StringUtils.appendIndented(out, indent, "Predicted majority "); 00067 out.append(getClassNameString()); 00068 out.append(" = "); 00069 out.append(getClassLabelString(this.observedClassDistribution.maxIndex())); 00070 StringUtils.appendNewline(out); 00071 for (int i = 0; i < this.observedClassDistribution.numValues(); i++) { 00072 StringUtils.appendIndented(out, indent, "Observed weight of "); 00073 out.append(getClassLabelString(i)); 00074 out.append(": "); 00075 out.append(this.observedClassDistribution.getValue(i)); 00076 StringUtils.appendNewline(out); 00077 } 00078 } 00079 00080 public boolean isRandomizable() { 00081 return false; 00082 } 00083 }