---

FreqConverter.java

gehe zur Dokumentation dieser Datei

/*
 * $Source: /shared/cvsroot/diplom/app/src/java/de/picana/converter/FreqConverter.java,v $
 * $Author: mstolpe $
 * $Date: 2003/04/07 12:50:02 $
 * $Revision: 1.3 $
 * $Release$ 
 *
 * Created on 9. M?rz 2003, 15:06
 *
 * Copyright 2002 by Marco Stolpe
 */

package de.picana.converter;

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

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

import weka.core.*;


public class FreqConverter extends Task {
    
    protected String srcfile;
    protected String destfile;
    protected String transformation;
    
    protected Instances training_set;
    
    protected List freq_table;
    protected Map freq_htable;
    
    
    public FreqConverter() {
    }
    
    
    public void init(ParameterSet params, Logger logger) {
        
        super.init(params, logger);
        
        srcfile = (String)params.getParameter("src");
        destfile = (String)params.getParameter("dest");
        transformation = (String)params.getParameter("transformation");
        
    }
    
    
    public void start() throws TaskException {
        
        try {
            File infile = new File(srcfile);
            File outfile = new File(destfile);
            
            if (!outfile.exists()
                || (outfile.exists() && (outfile.lastModified() <= infile.lastModified()))) {
            
                logger.info(LOGSRC, "Started.");
            
                //statwriter = new PrintWriter(new FileOutputStream(new File(statfile), true));
            
                logger.info(LOGSRC, "Read srcfile '" + srcfile + "' ...");
                FileInputStream fis = new FileInputStream(infile);
                InputStreamReader reader = new InputStreamReader(fis);
                training_set = new Instances(reader);
                logger.info(LOGSRC, "reading '" + srcfile + "' done.");
         
                freq_htable = new HashMap();
        
                MLVector vec;
                Instance inst;
                Integer freq;
            
                // build frequency hash table
        
                logger.info(LOGSRC, "Build frequency table from " + training_set.numInstances() + " instances ...");
                for (int i=0; i < training_set.numInstances(); i++) {
                    vec = new MLVector(training_set.instance(i));
                    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.");
            
            
                // ver?ndere die H?ufigkeiten und schreibe modifizierte
                // Instanzen in neue Liste
            
                freq_table = new ArrayList();
            
                Iterator iter = freq_htable.entrySet().iterator();
                while (iter.hasNext()) {
                    Map.Entry entry = (Map.Entry)iter.next();
                    vec = (MLVector)entry.getKey();
                    freq = (Integer)entry.getValue();
            
                    // Passe die H?ufigkeit an
                
                    if (transformation.equals("picana")) {
                        vec.freq = (int)Math.ceil(freq.intValue() *
                            ((arccot((1.0/40.0)*((double)freq.intValue()-80.0)) / 12.5663706) + 0.75));
                    }
                    if (transformation.equals("unique")) {
                        vec.freq = 1;
                    }
                    freq_table.add(vec);
                }                
            
            
                // gebe die modifizierte Liste in zuf?lliger Reihenfolge
                // in ARFF-Datei aus
            
                FileOutputStream output = new FileOutputStream(outfile);
                PrintWriter pw = new PrintWriter(output);
            
                pw.println("% ARFF file for picture data from PNG files");
                pw.println("%");
                pw.println("@relation colour");
                pw.println();
                pw.println("@attribute red numeric");
                pw.println("@attribute green numeric");
                pw.println("@attribute blue numeric");
                pw.println();
                pw.println("@data");
                pw.println("%");
                pw.println("% x instances");
                pw.println("%");
            
                int rand_index;
            
                while(freq_table.size() > 0) {
            
                    rand_index = rand.nextInt(freq_table.size());
                    vec = (MLVector)freq_table.get(rand_index);
                    vec.freq--;
                
                    if (vec.freq == 0)
                        freq_table.remove(rand_index);
                
                    for (int i=0; i < vec.dim; i++) {
                        pw.print(vec.value[i]);
                        if (i != (vec.dim-1))
                            pw.print(", ");
                    }
                    pw.println();
                }
            
                pw.close();
            
                logger.info(LOGSRC, "Stopped.");
            }
            
        } catch (Exception e) {
            throw new TaskException(e.toString());   
        }
        
    }
    
    public void stop() {
        
    }
    
    public void pause() {
        
    }
    
    public void resume() {
        
    }
    
    protected double arccot(double x) {
        if (x >= 0.0)
            return Math.acos (1.0/Math.sqrt(1.0+x*x)) + 1.570796327;
        return -Math.acos (1.0/Math.sqrt(1.0+x*x)) + 1.570796327;
    }
}

---