unitvector.java

wekaUT是 university texas austin 开发的基于weka的半指导学习(semi supervised learning)的分类器

/*
 *    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.
 */

/*
 *    UnitVector.java
 *    Copyright (C) 2003 Misha Bilenko
 *
 */

package weka.filters.unsupervised.attribute;

import weka.filters.*;
import java.io.*;
import java.util.*;
import weka.core.*;

/** 
 * Re-normalize the attributes for every instance so that
 * it lies on a hypersphere of radius 1.  
 *
 * @author Mikhail Bilenko ([e-mail]) 
 * @version $Revision: 1.1 $
 */
public class UnitVector extends Filter implements UnsupervisedFilter {

  /**
   * Sets the format of the input instances.
   *
   * @param instanceInfo an Instances object containing the input 
   * instance structure (any instances contained in the object are 
   * ignored - only the structure is required).
   * @return true if the outputFormat may be collected immediately
   * @exception Exception if the input format can't be set 
   * successfully
   */
  public boolean setInputFormat(Instances instanceInfo) 
       throws Exception {

    super.setInputFormat(instanceInfo);
    setOutputFormat(instanceInfo);
    return true;
  }

  /**
   * Input an instance for filtering. Filter requires all
   * training instances be read before producing output.
   *
   * @param instance the input instance
   * @return true if the filtered instance may now be
   * collected with output().
   * @exception IllegalStateException if no input format has been set.
   */
  public boolean input(Instance instance) {

    if (getInputFormat() == null) {
      throw new IllegalStateException("No input instance format defined");
    }
    if (m_NewBatch) {
      resetQueue();
      m_NewBatch = false;
    }
    convertInstance(instance);
    return true;
  }

  /**
   * Signify that this batch of input to the filter is finished. 
   * If the filter requires all instances prior to filtering,
   * output() may now be called to retrieve the filtered instances.
   *
   * @return true if there are instances pending output
   * @exception IllegalStateException if no input structure has been defined
   */
  public boolean batchFinished() {

    if (getInputFormat() == null) {
      throw new IllegalStateException("No input instance format defined");
    }

    Instances input = getInputFormat();
    // Convert pending input instances
    for(int i = 0; i < input.numInstances(); i++) {
      convertInstance(input.instance(i));
    }
    // Free memory
    flushInput();

    m_NewBatch = true;
    return (numPendingOutput() != 0);
  }

  /**
   * Convert a single instance over. The converted instance is 
   * added to the end of the output queue.
   *
   * @param instance the instance to convert
   */
  private void convertInstance(Instance instance) {
  
    Instance inst = null;
    if (instance instanceof SparseInstance) {
      double[] newVals = new double[instance.numAttributes()];
      int[] newIndices = new int[instance.numAttributes()];
      double[] vals = instance.toDoubleArray();
      int ind = 0;
      double length = 0;

      // calculate length
      for (int i = 0; i < vals.length; i++) {
	if (instance.attribute(i).isNumeric() &&
	    (!Instance.isMissingValue(vals[i]))) {
	  length += vals[i] * vals[i];
	}
      }
      length = Math.sqrt(length);
      
      // scale all values
      for (int j = 0; j < instance.numAttributes(); j++) {
	double value; 
	if (instance.attribute(j).isNumeric() && (!Instance.isMissingValue(vals[j])) && length != 0) {
	  value = vals[j]/length;
	  if (value != 0.0) {
	    newVals[ind] = value;
	    newIndices[ind] = j;
	    ind++;
	  }
	} else { // missing and non-numeric values
	  value = vals[j];
	  if (value != 0.0) {
	    newVals[ind] = value;
	    newIndices[ind] = j;
	    ind++;
	  }
	}
      }	
      double[] tempVals = new double[ind];
      int[] tempInd = new int[ind];
      System.arraycopy(newVals, 0, tempVals, 0, ind);
      System.arraycopy(newIndices, 0, tempInd, 0, ind);
      inst = new SparseInstance(instance.weight(), tempVals, tempInd,
                                instance.numAttributes());
    } else {
      double[] vals = instance.toDoubleArray();
      // calculate length
      double length = 0; 
      for (int j = 0; j < getInputFormat().numAttributes(); j++) {
	if (instance.attribute(j).isNumeric() &&
	    (!Instance.isMissingValue(vals[j]))) {
	  length += vals[j] * vals[j];
	}
      }
      length = Math.sqrt(length);
      
      for (int j = 0; j < getInputFormat().numAttributes(); j++) {
	if (instance.attribute(j).isNumeric() && (!Instance.isMissingValue(vals[j])) && length != 0) {
	  vals[j] = vals[j] / length;
	}
      }	
      inst = new Instance(instance.weight(), vals);
    }
    inst.setDataset(instance.dataset());
    push(inst);
  }

  /**
   * Main method for testing this class.
   *
   * @param argv should contain arguments to the filter: 
   * use -h for help
   */
  public static void main(String [] argv) {

    try {
      if (Utils.getFlag('b', argv)) {
 	Filter.batchFilterFile(new UnitVector(), argv);
      } else {
	Filter.filterFile(new UnitVector(), argv);
      }
    } catch (Exception ex) {
      System.out.println(ex.getMessage());
    }
  }
}