Examples of weka.filters.Filter

weka.filters.Filter
An abstract class for instance filters: objects that take instances as input, carry out some transformation on the instance and then output the instance. The method implementations in this class assume that most of the work will be done in the methods overridden by subclasses.
A simple example of filter use. This example doesn't remove instances from the output queue until all instances have been input, so has higher memory consumption than an approach that uses output instances as they are made available:
```
 Filter filter = ..some type of filter.. Instances instances = ..some instances.. for (int i = 0; i < data.numInstances(); i++) { filter.input(data.instance(i)); } filter.batchFinished(); Instances newData = filter.outputFormat(); Instance processed; while ((processed = filter.output()) != null) { newData.add(processed); } ..do something with newData.. 
```
@author Len Trigg (trigg@cs.waikato.ac.nz) @version $Revision: 6833 $

    else 
      m_Filter = null;




    Instances transformedInsts;
    Filter convertToProp = new MultiInstanceToPropositional();
    Filter convertToMI = new PropositionalToMultiInstance();


    //transform the data into single-instance format
    if (m_minimax){ 
      /* using SimpleMI class minimax transform method. 
         this method transforms the multi-instance dataset into minmax feature space (single-instance) */
      SimpleMI transMinimax = new SimpleMI();
      transMinimax.setTransformMethod(
          new SelectedTag(
            SimpleMI.TRANSFORMMETHOD_MINIMAX, SimpleMI.TAGS_TRANSFORMMETHOD));
      transformedInsts = transMinimax.transform(insts);
    }
    else { 
      convertToProp.setInputFormat(insts);
      transformedInsts=Filter.useFilter(insts, convertToProp);
    }


    if (m_Missing != null) {
      m_Missing.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_Missing); 
    }


    if (m_NominalToBinary != null) { 
      m_NominalToBinary.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_NominalToBinary); 
    }


    if (m_Filter != null) {
      m_Filter.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_Filter); 
    }


    // convert the single-instance format to multi-instance format
    convertToMI.setInputFormat(transformedInsts);
    insts = Filter.useFilter( transformedInsts, convertToMI);


    m_classIndex = insts.classIndex();
    m_classAttribute = insts.classAttribute();

View Full Code Here

    //convert instance into instances
    Instances insts = new Instances(inst.dataset(), 0);
    insts.add(inst);


    //transform the data into single-instance format
    Filter convertToProp = new MultiInstanceToPropositional();
    Filter convertToMI = new PropositionalToMultiInstance();


    if (m_minimax){ // using minimax feature space
      SimpleMI transMinimax = new SimpleMI();
      transMinimax.setTransformMethod(
          new SelectedTag(
            SimpleMI.TRANSFORMMETHOD_MINIMAX, SimpleMI.TAGS_TRANSFORMMETHOD));
      insts = transMinimax.transform (insts);
    }
    else{
      convertToProp.setInputFormat(insts);
      insts=Filter.useFilter( insts, convertToProp);
    }


    // Filter instances 
    if (m_Missing!=null) 
      insts = Filter.useFilter(insts, m_Missing); 


    if (m_Filter!=null)
      insts = Filter.useFilter(insts, m_Filter);     


    // convert the single-instance format to multi-instance format
    convertToMI.setInputFormat(insts);
    insts=Filter.useFilter( insts, convertToMI);


    inst = insts.instance(0);  


    if (!m_fitLogisticModels) {

View Full Code Here

   * @throws Exception  if the option setting fails
   */
  public void setOptions(String[] options) throws Exception {
    String  tmpStr;
    String[]  tmpOptions;
    Filter  filter;


    super.setOptions(options);


    tmpStr = Utils.getOption("A", options);
    if (tmpStr.length() != 0)

View Full Code Here

     */
    protected AbstractClusterer createClusterer(MarkovAttributeSet aset, Instances trainingData) throws Exception {
        if (trace.val) LOG.trace(String.format("Clustering %d %s instances with %d attributes", trainingData.numInstances(), CatalogUtil.getDisplayName(catalog_proc), aset.size()));
        
        // Create the filter we need so that we only include the attributes in the given MarkovAttributeSet
        Filter filter = aset.createFilter(trainingData);
        
        // Using our training set to build the clusterer
        int seed = this.rand.nextInt(); 
//        SimpleKMeans inner_clusterer = new SimpleKMeans();
        EM inner_clusterer = new EM();

View Full Code Here

    public void testCreateMarkovAttributeSetFilter() throws Exception {
        // Test that we can create a filter from an MarkovAttributeSet
        MarkovAttributeSet aset = new MarkovAttributeSet(data, FeatureUtil.getFeatureKeyPrefix(ParamArrayLengthFeature.class));
        assertEquals(CatalogUtil.getArrayProcParameters(catalog_proc).size(), aset.size());
        
        Filter filter = aset.createFilter(data);
        Instances newData = Filter.useFilter(data, filter);
        for (int i = 0, cnt = newData.numInstances(); i < cnt; i++) {
            Instance processed = newData.instance(i);
//            System.err.println(processed);
            assertEquals(aset.size(), processed.numAttributes());

View Full Code Here

        {
          Instances train = data.trainCV(folds, n, random);
            Instances test = data.testCV(folds, n);
            
            // Apply log filter
          Filter logFilter = new LogFilter();
            logFilter.setInputFormat(train);
            train = Filter.useFilter(train, logFilter);        
            logFilter.setInputFormat(test);
            test = Filter.useFilter(test, logFilter);
            
            // Copy the classifier
            Classifier classifier = AbstractClassifier.makeCopy(baseClassifier);

View Full Code Here

        {
          Instances train = data.trainCV(folds, n, random);
            Instances test = data.testCV(folds, n);
            
            // Apply log filter
          Filter logFilter = new LogFilter();
            logFilter.setInputFormat(train);
            train = Filter.useFilter(train, logFilter);        
            logFilter.setInputFormat(test);
            test = Filter.useFilter(test, logFilter);
            
            // Copy the classifier
            Classifier classifier = AbstractClassifier.makeCopy(baseClassifier);

View Full Code Here

   * Get the filter + options as a string
   *
   * @return a String containing the name of the filter + any options
   */
  protected String getFilterSpec() {
    Filter c = getFilter();
    if (c instanceof OptionHandler) {
      return c.getClass().getName() + " "
  + Utils.joinOptions(((OptionHandler)c).getOptions());
    }
    return c.getClass().getName();
  }

View Full Code Here

    PointDouble      values;
    Instances      data;
    Evaluation      eval;
    PointDouble      result;
    Classifier      classifier;
    Filter      filter;
    int        size;
    boolean      cached;
    boolean      allCached;
    Performance      p1;
    Performance      p2;
    double      x;
    double      y;
    
    performances = new Vector();
    
    log("Determining best pair with " + cv + "-fold CV in Grid:\n" + grid + "\n");
    
    if (m_Traversal == TRAVERSAL_BY_COLUMN)
      size = grid.width();
    else
      size = grid.height();
    
    allCached = true;


    for (i = 0; i < size; i++) {
      if (m_Traversal == TRAVERSAL_BY_COLUMN)
  enm = grid.column(i);
      else
  enm = grid.row(i);
      
      filter = null;
      data   = null;
      
      while (enm.hasMoreElements()) {
  values = enm.nextElement();
  
  // already calculated?
  cached = m_Cache.isCached(cv, values);
  if (cached) {
    performances.add(m_Cache.get(cv, values));
  }
  else {
    allCached = false;
    
    x = evaluate(values.getX(), true);
    y = evaluate(values.getY(), false);
    
    // data pass through filter
    if (filter == null) {
      filter = (Filter) setup(getFilter(), x, y);
      filter.setInputFormat(inst);
      data = Filter.useFilter(inst, filter);
      // make sure that the numbers don't get too small - otherwise NaNs!
      Filter cleaner = new NumericCleaner();
      cleaner.setInputFormat(data);
      data = Filter.useFilter(data, cleaner);
    }


    // setup classifier
    classifier = (Classifier) setup(getClassifier(), x, y);

View Full Code Here

   *
   * @return the filter string.
   */
  protected String getFilterSpec() {
    
    Filter c = getFilter();
    if (c instanceof OptionHandler) {
      return c.getClass().getName() + " "
  + Utils.joinOptions(((OptionHandler)c).getOptions());
    }
    return c.getClass().getName();
  }

View Full Code Here

0 1 2 3

TOP

Related Classes of weka.filters.Filter

bnGUI.gui_WekaExperiment

bnGUI.Thread_weka_run

edu.brown.markov.FeatureClusterer

edu.brown.markov.TestFeatureClusterer

weka.associations.FilteredAssociator

weka.attributeSelection.FilteredAttributeEval

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.