---

GenericML.java

gehe zur Dokumentation dieser Datei

/*
 * $Source: /shared/cvsroot/diplom/app/src/java/de/picana/clusterer/GenericML.java,v $
 * $Author: mstolpe $
 * $Date: 2003/04/21 18:15:55 $
 * $Revision: 1.3 $
 * $Release$ 
 *
 * Created on 3. M?rz 2003, 23:52
 *
 * Copyright 2002 by Marco Stolpe
 */

package de.picana.clusterer;

import de.picana.control.*;
import de.picana.logging.*;
import de.picana.math.*;

import java.io.*;
import java.util.*;

import weka.core.*;


public abstract class GenericML extends Clusterer {
    
    protected List freq_table;
    protected List centroids;
    protected Map freq_htable;
    
    protected int dim;
   
    protected long time_freq;
    protected long time_step1;
    protected long time_step2;
    protected long time_total;
    
    
    public GenericML() {
    }

    
    public void buildClusterer(Instances set) throws TaskException {
        
        statwriter.println("algo_clusterer_model:" + modelfile);
        statwriter.println("algo_clusterer_training_set:" + infile);
        
        int i, j;
        MLVector vec;
        
        centroids = new ArrayList();
        
        Integer freq;
        Instance inst;
        
        time_total = System.currentTimeMillis();
        
        time_freq = System.currentTimeMillis();
        
        freq_htable = new HashMap();
        
        // build frequency hash table
        
        logger.info(LOGSRC, "Build frequency table from " + set.numInstances() + " instances ...");
        for (i=0; i < set.numInstances(); i++) {
            vec = new MLVector(set.instance(i));
            dim = vec.dim;
            freq = (Integer)freq_htable.get(vec);
            
            freq_htable.put(vec, (freq==null) ? ONE :
                 new Integer(freq.intValue() + 1));
        }
        logger.info(LOGSRC, "frequency table containing " + freq_htable.size() + " instances built.");
        
        // build frequency table (list) for access by index
        
        freq_table = new ArrayList();
        Iterator entries = freq_htable.entrySet().iterator();
        Map.Entry entry;
        while (entries.hasNext()) {
            entry = (Map.Entry)entries.next();
            vec = (MLVector)entry.getKey();
            freq = (Integer)entry.getValue();
            vec.freq = freq.intValue();
            freq_table.add(vec);
        }
        freq_htable = null;
        
        time_freq = System.currentTimeMillis() - time_freq;
        
        logger.info(LOGSRC, "Frequency table built took " + getTimeString(time_freq));
   
        statwriter.println("stat_Instances:" + set.numInstances());
        statwriter.println("stat_UniqueInst:" + freq_table.size());
        
        logger.info(LOGSRC, "Find farthest pair (= first two centroids) ...");
        time_step1 = System.currentTimeMillis();
        buildFirst();
        time_step1 = System.currentTimeMillis() - time_step1;
        logger.info(LOGSRC, "found farthest pair.");
        
        logger.info(LOGSRC, "Step 1 took " + getTimeString(time_step1));
        
        logger.info(LOGSRC, "Find the last " + (num_clusters-2) + " centroids ...");
        time_step2 = System.currentTimeMillis();
        buildRest();
        time_step2 = System.currentTimeMillis() - time_step2;
        logger.info(LOGSRC, "found the last " + (num_clusters-2) + " centroids.");
        
        logger.info(LOGSRC, "Step 2 took " + getTimeString(time_step2));
        
        time_total = System.currentTimeMillis() - time_total;

        logger.info(LOGSRC, "Algorithm took " + getTimeString(time_total));
        
        statwriter.println("time_clusterer_freq:" + time_freq);
        statwriter.println("time_clusterer_step1:" + time_step1);
        statwriter.println("time_clusterer_step2:" + time_step2);
        statwriter.println("time_clusterer_total:" + time_total);
    }
        
    
    protected abstract void buildFirst();   
    
    protected abstract void buildRest();
   
    
    protected Object getRandomElement(Collection c) {
        int index = rand.nextInt(c.size());
        int i=0;
        Object obj = null;
        Iterator elems = c.iterator();
        while (elems.hasNext()) {
            if (i==index)
                obj = elems.next();
            else
                elems.next();
            i++;
        }
        return obj;
    }
    
    
    public void saveModel(String filename) throws TaskException {
        
        try {
            File outfile = new File(filename);
            FileOutputStream out = new FileOutputStream(outfile);
            PrintWriter pw = new PrintWriter(out);
        
            for (int att=0; att < training_set.numAttributes(); att++) {
                pw.print(training_set.attribute(att).name());
                if (att != training_set.numAttributes()-1)
                    pw.print(",");
            }
            pw.println();
            
            for (int i=0; i < centroids.size(); i++) {
                MLVector vec = (MLVector)centroids.get(i);    
            
                for (int j=0; j < vec.value.length; j++) {
             
                    pw.print(vec.value[j]);
                    if (j != vec.value.length-1) {
                        pw.print(",");    
                    }
                }
                pw.println();
            }
            
            pw.close();
            
        } catch (Exception e) {
            throw new TaskException(e.toString());
        }
    }
}

---