tld.java

代码是一个分类器的实现,其中使用了部分weka的源代码。可以将项目导入eclipse运行

/*
 *    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.
 */

/*
 * TLD.java
 * Copyright (C) 2005 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.classifiers.mi;

import weka.classifiers.RandomizableClassifier;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.MultiInstanceCapabilitiesHandler;
import weka.core.Optimization;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.Capabilities.Capability;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;

import java.util.Enumeration;
import java.util.Random;
import java.util.Vector;

/** 
 <!-- globalinfo-start -->
 * Two-Level Distribution approach, changes the starting value of the searching algorithm, supplement the cut-off modification and check missing values.<br/>
 * <br/>
 * For more information see:<br/>
 * <br/>
 * Xin Xu (2003). Statistical learning in multiple instance problem. Hamilton, NZ.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;mastersthesis{Xu2003,
 *    address = {Hamilton, NZ},
 *    author = {Xin Xu},
 *    note = {0657.594},
 *    school = {University of Waikato},
 *    title = {Statistical learning in multiple instance problem},
 *    year = {2003}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -C
 *  Set whether or not use empirical
 *  log-odds cut-off instead of 0</pre>
 * 
 * <pre> -R &lt;numOfRuns&gt;
 *  Set the number of multiple runs 
 *  needed for searching the MLE.</pre>
 * 
 * <pre> -S &lt;num&gt;
 *  Random number seed.
 *  (default 1)</pre>
 * 
 * <pre> -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console</pre>
 * 
 <!-- options-end -->
 *
 * @author Eibe Frank ([e-mail])
 * @author Xin Xu ([e-mail])
 * @version $Revision: 1.5 $ 
 */
public class TLD 
  extends RandomizableClassifier 
  implements OptionHandler, MultiInstanceCapabilitiesHandler,
             TechnicalInformationHandler {

  /** for serialization */
  static final long serialVersionUID = 6657315525171152210L;
  
  /** The mean for each attribute of each positive exemplar */
  protected double[][] m_MeanP = null;

  /** The variance for each attribute of each positive exemplar */
  protected double[][] m_VarianceP = null;

  /** The mean for each attribute of each negative exemplar */
  protected double[][] m_MeanN = null;

  /** The variance for each attribute of each negative exemplar */
  protected double[][] m_VarianceN = null;

  /** The effective sum of weights of each positive exemplar in each dimension*/
  protected double[][] m_SumP = null;

  /** The effective sum of weights of each negative exemplar in each dimension*/
  protected double[][] m_SumN = null;

  /** The parameters to be estimated for each positive exemplar*/
  protected double[] m_ParamsP = null;

  /** The parameters to be estimated for each negative exemplar*/
  protected double[] m_ParamsN = null;

  /** The dimension of each exemplar, i.e. (numAttributes-2) */
  protected int m_Dimension = 0;

  /** The class label of each exemplar */
  protected double[] m_Class = null;

  /** The number of class labels in the data */
  protected int m_NumClasses = 2;

  /** The very small number representing zero */
  static public double ZERO = 1.0e-6;   

  /** The number of runs to perform */
  protected int m_Run = 1;

  protected double m_Cutoff;

  protected boolean m_UseEmpiricalCutOff = false;   

  /**
   * Returns a string describing this filter
   *
   * @return a description of the filter suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return 
        "Two-Level Distribution approach, changes the starting value of "
      + "the searching algorithm, supplement the cut-off modification and "
      + "check missing values.\n\n"
      + "For more information see:\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
   */
  public TechnicalInformation getTechnicalInformation() {
    TechnicalInformation 	result;
    
    result = new TechnicalInformation(Type.MASTERSTHESIS);
    result.setValue(Field.AUTHOR, "Xin Xu");
    result.setValue(Field.YEAR, "2003");
    result.setValue(Field.TITLE, "Statistical learning in multiple instance problem");
    result.setValue(Field.SCHOOL, "University of Waikato");
    result.setValue(Field.ADDRESS, "Hamilton, NZ");
    result.setValue(Field.NOTE, "0657.594");
    
    return result;
  }

  /**
   * Returns default capabilities of the classifier.
   *
   * @return      the capabilities of this classifier
   */
  public Capabilities getCapabilities() {
    Capabilities result = super.getCapabilities();

    // attributes
    result.enable(Capability.NOMINAL_ATTRIBUTES);
    result.enable(Capability.RELATIONAL_ATTRIBUTES);
    result.enable(Capability.MISSING_VALUES);

    // class
    result.enable(Capability.BINARY_CLASS);
    result.enable(Capability.MISSING_CLASS_VALUES);
    
    // other
    result.enable(Capability.ONLY_MULTIINSTANCE);
    
    return result;
  }

  /**
   * Returns the capabilities of this multi-instance classifier for the
   * relational data.
   *
   * @return            the capabilities of this object
   * @see               Capabilities
   */
  public Capabilities getMultiInstanceCapabilities() {
    Capabilities result = super.getCapabilities();
    
    // attributes
    result.enable(Capability.NUMERIC_ATTRIBUTES);
    result.enable(Capability.MISSING_VALUES);

    // class
    result.disableAllClasses();
    result.enable(Capability.NO_CLASS);
    
    return result;
  }

  /**
   *
   * @param exs the training exemplars
   * @throws Exception if the model cannot be built properly
   */    
  public void buildClassifier(Instances exs)throws Exception{
    // can classifier handle the data?
    getCapabilities().testWithFail(exs);

    // remove instances with missing class
    exs = new Instances(exs);
    exs.deleteWithMissingClass();
    
    int numegs = exs.numInstances();
    m_Dimension = exs.attribute(1).relation(). numAttributes();
    Instances pos = new Instances(exs, 0), neg = new Instances(exs, 0);

    for(int u=0; u<numegs; u++){
      Instance example = exs.instance(u);
      if(example.classValue() == 1)
        pos.add(example);
      else
        neg.add(example);
    }

    int pnum = pos.numInstances(), nnum = neg.numInstances();	

    m_MeanP = new double[pnum][m_Dimension];
    m_VarianceP = new double[pnum][m_Dimension];
    m_SumP = new double[pnum][m_Dimension];
    m_MeanN = new double[nnum][m_Dimension];
    m_VarianceN = new double[nnum][m_Dimension];
    m_SumN = new double[nnum][m_Dimension];
    m_ParamsP = new double[4*m_Dimension];
    m_ParamsN = new double[4*m_Dimension];

    // Estimation of the parameters: as the start value for search
    double[] pSumVal=new double[m_Dimension], // for m 
      nSumVal=new double[m_Dimension]; 
    double[] maxVarsP=new double[m_Dimension], // for a
      maxVarsN=new double[m_Dimension]; 
    // Mean of sample variances: for b, b=a/E(\sigma^2)+2
    double[] varMeanP = new double[m_Dimension],
      varMeanN = new double[m_Dimension]; 
    // Variances of sample means: for w, w=E[var(\mu)]/E[\sigma^2]
    double[] meanVarP = new double[m_Dimension],
      meanVarN = new double[m_Dimension];
    // number of exemplars without all values missing
    double[] numExsP = new double[m_Dimension],
      numExsN = new double[m_Dimension];

    // Extract metadata fro both positive and negative bags
    for(int v=0; v < pnum; v++){
      /*Exemplar px = pos.exemplar(v);
        m_MeanP[v] = px.meanOrMode();
        m_VarianceP[v] = px.variance();
        Instances pxi =  px.getInstances();
        */

      Instances pxi =  pos.instance(v).relationalValue(1);
      for (int k=0; k<pxi.numAttributes(); k++) { 
        m_MeanP[v][k] = pxi.meanOrMode(k);
        m_VarianceP[v][k] = pxi.variance(k);
      }

      for (int w=0,t=0; w < m_Dimension; w++,t++){		
        //if((t==m_ClassIndex) || (t==m_IdIndex))
        //  t++;		

        if(!Double.isNaN(m_MeanP[v][w])){
          for(int u=0;u<pxi.numInstances();u++){
            Instance ins = pxi.instance(u);			
            if(!ins.isMissing(t))
              m_SumP[v][w] += ins.weight();			   
          }   
          numExsP[w]++;  
          pSumVal[w] += m_MeanP[v][w];
          meanVarP[w] += m_MeanP[v][w]*m_MeanP[v][w];    
          if(maxVarsP[w] < m_VarianceP[v][w])
            maxVarsP[w] = m_VarianceP[v][w];
          varMeanP[w] += m_VarianceP[v][w];
          m_VarianceP[v][w] *= (m_SumP[v][w]-1.0);
          if(m_VarianceP[v][w] < 0.0)
            m_VarianceP[v][w] = 0.0;
        }
      }
    }

    for(int v=0; v < nnum; v++){
      /*Exemplar nx = neg.exemplar(v);
        m_MeanN[v] = nx.meanOrMode();
        m_VarianceN[v] = nx.variance();
        Instances nxi =  nx.getInstances();
        */
      Instances nxi =  neg.instance(v).relationalValue(1);
      for (int k=0; k<nxi.numAttributes(); k++) {
        m_MeanN[v][k] = nxi.meanOrMode(k);
        m_VarianceN[v][k] = nxi.variance(k);
      }

      for (int w=0,t=0; w < m_Dimension; w++,t++){		
        //if((t==m_ClassIndex) || (t==m_IdIndex))
        //  t++;		

        if(!Double.isNaN(m_MeanN[v][w])){
          for(int u=0;u<nxi.numInstances();u++)
            if(!nxi.instance(u).isMissing(t))
              m_SumN[v][w] += nxi.instance(u).weight();
          numExsN[w]++; 	
          nSumVal[w] += m_MeanN[v][w];
          meanVarN[w] += m_MeanN[v][w]*m_MeanN[v][w]; 
          if(maxVarsN[w] < m_VarianceN[v][w])
            maxVarsN[w] = m_VarianceN[v][w];
          varMeanN[w] += m_VarianceN[v][w];
          m_VarianceN[v][w] *= (m_SumN[v][w]-1.0);
          if(m_VarianceN[v][w] < 0.0)
            m_VarianceN[v][w] = 0.0;
        }
      }
    }

    for(int w=0; w<m_Dimension; w++){
      pSumVal[w] /= numExsP[w];
      nSumVal[w] /= numExsN[w];
      if(numExsP[w]>1)
        meanVarP[w] = meanVarP[w]/(numExsP[w]-1.0) 
          - pSumVal[w]*numExsP[w]/(numExsP[w]-1.0);
      if(numExsN[w]>1)
        meanVarN[w] = meanVarN[w]/(numExsN[w]-1.0) 
          - nSumVal[w]*numExsN[w]/(numExsN[w]-1.0);
      varMeanP[w] /= numExsP[w];
      varMeanN[w] /= numExsN[w];
    }

    //Bounds and parameter values for each run
    double[][] bounds = new double[2][4];
    double[] pThisParam = new double[4], 
      nThisParam = new double[4];

    // Initial values for parameters
    double a, b, w, m;

    // Optimize for one dimension
    for (int x=0; x < m_Dimension; x++){
      if (getDebug())
	System.err.println("\n\n!!!!!!!!!!!!!!!!!!!!!!???Dimension #"+x);

      // Positive examplars: first run
      a = (maxVarsP[x]>ZERO) ? maxVarsP[x]:1.0; 
      if (varMeanP[x]<=ZERO)   varMeanP[x] = ZERO;  // modified by LinDong (09/2005)
      b = a/varMeanP[x]+2.0; // a/(b-2) = E(\sigma^2)
      w = meanVarP[x]/varMeanP[x]; // E[var(\mu)] = w*E[\sigma^2]	    
      if(w<=ZERO)  w=1.0;

      m = pSumVal[x]; 	  
      pThisParam[0] = a;    // a