Example usage for weka.core Instance setClassValue

List of usage examples for weka.core Instance setClassValue

Introduction

In this page you can find the example usage for weka.core Instance setClassValue.

Prototype

public void setClassValue(String value);

Source Link

Document

Sets the class value of an instance to the given value.

Usage

From source file:de.fub.maps.project.detector.model.inference.processhandler.InferenceDataProcessHandler.java

License:Open Source License

@Override
protected void handle() {
    clearResults();/*w  ww . j a  v a2  s . c o  m*/

    Classifier classifier = getInferenceModel().getClassifier();
    HashSet<TrackSegment> inferenceDataSet = getInferenceDataSet();
    Collection<Attribute> attributeList = getInferenceModel().getAttributes();

    if (!attributeList.isEmpty()) {
        Set<String> keySet = getInferenceModel().getInput().getTrainingsSet().keySet();
        setClassesToView(keySet);

        Instances unlabeledInstances = new Instances("Unlabeld Tracks", new ArrayList<Attribute>(attributeList),
                0); //NO18N
        unlabeledInstances.setClassIndex(0);

        ArrayList<TrackSegment> segmentList = new ArrayList<TrackSegment>();
        for (TrackSegment segment : inferenceDataSet) {
            Instance instance = getInstance(segment);
            unlabeledInstances.add(instance);
            segmentList.add(segment);
        }

        // create copy
        Instances labeledInstances = new Instances(unlabeledInstances);

        for (int index = 0; index < labeledInstances.numInstances(); index++) {
            try {
                Instance instance = labeledInstances.instance(index);

                // classify instance
                double classifyed = classifier.classifyInstance(instance);
                instance.setClassValue(classifyed);

                // get class label
                String value = unlabeledInstances.classAttribute().value((int) classifyed);

                if (index < segmentList.size()) {
                    instanceToTrackSegmentMap.put(instance, segmentList.get(index));
                }

                // put label and instance to result map
                put(value, instance);

            } catch (Exception ex) {
                Exceptions.printStackTrace(ex);
            }
        }

        // update visw
        updateVisualRepresentation();

        // update result set of the inferenceModel
        for (Entry<String, List<Instance>> entry : resultMap.entrySet()) {
            HashSet<TrackSegment> trackSegmentList = new HashSet<TrackSegment>();
            for (Instance instance : entry.getValue()) {
                TrackSegment trackSegment = instanceToTrackSegmentMap.get(instance);
                if (trackSegment != null) {
                    trackSegmentList.add(trackSegment);
                }
            }

            // only those classes are put into  the result data set, which are not empty
            if (!trackSegmentList.isEmpty()) {
                getInferenceModel().getResult().put(entry.getKey(), trackSegmentList);
            }
        }
    } else {
        throw new InferenceModelClassifyException(MessageFormat
                .format("No attributes available. Attribute list lengeth == {0}", attributeList.size()));
    }
    resultMap.clear();
    instanceToTrackSegmentMap.clear();
}

From source file:de.fub.maps.project.detector.model.inference.processhandler.SpecialInferenceDataProcessHandler.java

License:Open Source License

@Override
protected void handle() {
    clearResults();/*from  ww  w  .j a v a2s.com*/

    Classifier classifier = getInferenceModel().getClassifier();
    Collection<Attribute> attributeList = getInferenceModel().getAttributes();

    if (!attributeList.isEmpty()) {
        Set<String> keySet = getInferenceModel().getInput().getTrainingsSet().keySet();
        setClassesToView(keySet);

        Instances unlabeledInstances = new Instances("Unlabeld Tracks", new ArrayList<Attribute>(attributeList),
                0); //NO18N
        unlabeledInstances.setClassIndex(0);

        ArrayList<TrackSegment> segmentList = new ArrayList<TrackSegment>();
        for (Entry<String, HashSet<TrackSegment>> entry : getInferenceModel().getInput().getTrainingsSet()
                .entrySet()) {
            for (TrackSegment segment : entry.getValue()) {
                segment.setLabel(entry.getKey());
                Instance instance = getInstance(segment);
                unlabeledInstances.add(instance);
                segmentList.add(segment);
            }
        }

        // create copy
        Instances labeledInstances = new Instances(unlabeledInstances);

        for (int index = 0; index < labeledInstances.numInstances(); index++) {
            try {
                Instance instance = labeledInstances.instance(index);

                // classify instance
                double classifyed = classifier.classifyInstance(instance);
                instance.setClassValue(classifyed);

                // get class label
                String value = unlabeledInstances.classAttribute().value((int) classifyed);

                if (index < segmentList.size()) {
                    instanceToTrackSegmentMap.put(instance, segmentList.get(index));
                }

                // put label and instance to result map
                put(value, instance);

            } catch (Exception ex) {
                Exceptions.printStackTrace(ex);
            }
        }

        // update visw
        updateVisualRepresentation();

        // update result set of the inferenceModel
        for (Map.Entry<String, List<Instance>> entry : resultMap.entrySet()) {
            HashSet<TrackSegment> trackSegmentList = new HashSet<TrackSegment>();
            for (Instance instance : entry.getValue()) {
                TrackSegment trackSegment = instanceToTrackSegmentMap.get(instance);
                if (trackSegment != null) {
                    trackSegmentList.add(trackSegment);
                }
            }

            // only those classes are put into  the result data set, which are not empty
            if (!trackSegmentList.isEmpty()) {
                getInferenceModel().getResult().put(entry.getKey(), trackSegmentList);
            }
        }
    } else {
        throw new InferenceModelClassifyException(MessageFormat
                .format("No attributes available. Attribute list lengeth == {0}", attributeList.size()));
    }
    resultMap.clear();
    instanceToTrackSegmentMap.clear();
}

From source file:de.uni_koeln.phil_fak.iv.tm.p4.classification.WekaAdapter.java

License:Open Source License

private Instance instance(Document document, String label) {
    List<Float> values = document.getVector(corpus).getValues();
    /* Die Instanz enthlt alle Merkmale plus die Klasse: */
    double[] vals = new double[values.size() + 1];
    for (int i = 0; i < values.size(); i++) {
        vals[i + 1] = values.get(i);//ww  w.j  a va  2s  .  c o  m
    }
    Instance instance = new Instance(1, vals);
    /*
     * Und muss erfahren, was die Werte bedeuten, was wir fr unser
     * Trainingsset beschrieben hatten:
     */
    instance.setDataset(trainingSet);
    /*
     * Beim Training haben wir Instanzen mit vorhandenem Klassenlabel, bei
     * der Klassifikation ist die Klasse unbekannt:
     */
    if (label == null) {
        instance.setClassMissing(); // during classification
    } else
        instance.setClassValue(label); // during training
    return instance;
}

From source file:de.uni_koeln.spinfo.classification.zoneAnalysis.classifier.WekaClassifier.java

License:Open Source License

private Instance instance(ClassifyUnit cu, Instances trainingSet) {
    double[] values = cu.getFeatureVector();
    String classID = ((ZoneClassifyUnit) cu).getActualClassID() + "";
    Instance instance = new SparseInstance(1, values);
    /*/*  ww w. j a  va 2 s.co m*/
     * Weka muss 'erklrt' bekommen, was die Werte bedeuten - dies ist im Trainingsset beschrieben:
     */
    instance.setDataset(trainingSet);
    /*
     * Beim Training geben wir den Instanzen ein Klassenlabel, bei der Klassifikation ist die Klasse unbekannt:
     */
    if (classID == "0") {
        instance.setClassMissing(); // bei Klassifikation
    } else
        instance.setClassValue(classID); // beim Training
    return instance;
}

From source file:edu.brandeis.wisedb.scheduler.training.decisiontree.DTSearcher.java

License:Open Source License

@Override
public List<Action> schedule(Set<ModelQuery> toSched) {
    SingularMachineState start = new SingularMachineState(toSched, qtp, sla);
    List<Action> toR = new LinkedList<Action>();

    applyLoop: while (!start.isGoalState()) {
        log.fine("Current state: " + start);

        SortedMap<String, String> features = start.getFeatures();
        Instance toClassify = new Instance(attributes.length);
        toClassify.setDataset(wekaDataSet);

        for (Attribute a : attributes) {
            if (a.name().equals("action")) {
                //toClassify.setValue(a, "N");
                continue;
            }//from w  w  w . j  a  va 2  s.  c  o  m

            try {

                if (features.get(a.name()).equals("?")) {
                    toClassify.setMissing(a);
                    continue;
                }
                try {
                    double d = Double.valueOf(features.get(a.name()));
                    toClassify.setValue(a, d);
                } catch (NumberFormatException e) {
                    toClassify.setValue(a, features.get(a.name()));
                }
            } catch (IllegalArgumentException e) {
                e.printStackTrace();
                log.warning(
                        "Encountered previously unseen attribute value! Might need better training data... making random selection.");
                log.warning("Value for attribute " + a.name() + " was " + features.get(a.name()));
                Action rand = getPUAction(start);
                log.warning("Random action selected: " + rand);
                toR.add(rand);
                start.applyAction(rand);
                continue applyLoop;
            }
        }

        toClassify.setClassMissing();
        log.finer("Going to classify: " + toClassify);

        try {
            double d = tree.classifyInstance(toClassify);
            toClassify.setClassValue(d);
            String action = toClassify.stringValue(toClassify.classIndex());
            log.finer("Got action string: " + action);

            Action selected = null;
            for (Action a : start.getPossibleActions()) {
                if (actionMatches(a, action)) {
                    selected = a;
                    break;
                }
            }

            if (selected == null) {
                //log.warning("Could not find applicable action for string: " + action + " ... picking random action");
                Action a = getPUAction(start);
                start.applyAction(a);
                toR.add(a);
                continue;
            }

            log.fine("Selected action: " + selected);

            start.applyAction(selected);

            toR.add(selected);

        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
            return null;
        }
    }

    return toR;
}

From source file:edu.oregonstate.eecs.mcplan.abstraction.EvaluateSimilarityFunction.java

License:Open Source License

/**
 * @param args//from   w  w  w .  j a v a 2 s.c o m
 * @throws IOException
 * @throws FileNotFoundException
 */
public static void main(final String[] args) throws FileNotFoundException, IOException {
    final String experiment_file = args[0];
    final File root_directory;
    if (args.length > 1) {
        root_directory = new File(args[1]);
    } else {
        root_directory = new File(".");
    }
    final CsvConfigurationParser csv_config = new CsvConfigurationParser(new FileReader(experiment_file));
    final String experiment_name = FilenameUtils.getBaseName(experiment_file);

    final File expr_directory = new File(root_directory, experiment_name);
    expr_directory.mkdirs();

    final Csv.Writer csv = new Csv.Writer(
            new PrintStream(new FileOutputStream(new File(expr_directory, "results.csv"))));
    final String[] parameter_headers = new String[] { "kpca.kernel", "kpca.rbf.sigma",
            "kpca.random_forest.Ntrees", "kpca.random_forest.max_depth", "kpca.Nbases", "multiclass.classifier",
            "multiclass.random_forest.Ntrees", "multiclass.random_forest.max_depth",
            "pairwise_classifier.max_branching", "training.label_noise" };
    csv.cell("domain").cell("abstraction");
    for (final String p : parameter_headers) {
        csv.cell(p);
    }
    csv.cell("Ntrain").cell("Ntest").cell("ami.mean").cell("ami.variance").cell("ami.confidence").newline();

    for (int expr = 0; expr < csv_config.size(); ++expr) {
        try {
            final KeyValueStore expr_config = csv_config.get(expr);
            final Configuration config = new Configuration(root_directory.getPath(), expr_directory.getName(),
                    expr_config);

            System.out.println("[Loading '" + config.training_data_single + "']");
            final Instances single = WekaUtil
                    .readLabeledDataset(new File(root_directory, config.training_data_single + ".arff"));

            final Instances train = new Instances(single, 0);
            final int[] idx = Fn.range(0, single.size());
            int instance_counter = 0;
            Fn.shuffle(config.rng, idx);
            final int Ntrain = config.getInt("Ntrain_games"); // TODO: Rename?
            final double label_noise = config.getDouble("training.label_noise");
            final int Nlabels = train.classAttribute().numValues();
            assert (Nlabels > 0);
            for (int i = 0; i < Ntrain; ++i) {
                final Instance inst = single.get(idx[instance_counter++]);
                if (label_noise > 0 && config.rng.nextDouble() < label_noise) {
                    int noisy_label = 0;
                    do {
                        noisy_label = config.rng.nextInt(Nlabels);
                    } while (noisy_label == (int) inst.classValue());
                    System.out.println("Noisy label (" + inst.classValue() + " -> " + noisy_label + ")");
                    inst.setClassValue(noisy_label);
                }
                train.add(inst);
                inst.setDataset(train);
            }

            final Fn.Function2<Boolean, Instance, Instance> plausible_p = createPlausiblePredicate(config);

            final int Ntest = config.Ntest_games;
            int Ntest_added = 0;
            final ArrayList<Instances> tests = new ArrayList<Instances>();
            while (instance_counter < single.size() && Ntest_added < Ntest) {
                final Instance inst = single.get(idx[instance_counter++]);
                boolean found = false;
                for (final Instances test : tests) {
                    // Note that 'plausible_p' should be transitive
                    if (plausible_p.apply(inst, test.get(0))) {
                        WekaUtil.addInstance(test, inst);
                        if (test.size() == 30) {
                            Ntest_added += test.size();
                        } else if (test.size() > 30) {
                            Ntest_added += 1;
                        }
                        found = true;
                        break;
                    }
                }

                if (!found) {
                    final Instances test = new Instances(single, 0);
                    WekaUtil.addInstance(test, inst);
                    tests.add(test);
                }
            }
            final Iterator<Instances> test_itr = tests.iterator();
            while (test_itr.hasNext()) {
                if (test_itr.next().size() < 30) {
                    test_itr.remove();
                }
            }
            System.out.println("=== tests.size() = " + tests.size());
            System.out.println("=== Ntest_added = " + Ntest_added);

            System.out.println("[Training]");
            final Evaluator evaluator = createEvaluator(config, train);
            //            final Instances transformed_test = evaluator.prepareInstances( test );

            System.out.println("[Evaluating]");

            final int Nxval = evaluator.isSensitiveToOrdering() ? 10 : 1;
            final MeanVarianceAccumulator ami = new MeanVarianceAccumulator();

            final MeanVarianceAccumulator errors = new MeanVarianceAccumulator();
            final MeanVarianceAccumulator relative_error = new MeanVarianceAccumulator();

            int c = 0;
            for (int xval = 0; xval < Nxval; ++xval) {
                for (final Instances test : tests) {
                    // TODO: Debugging
                    WekaUtil.writeDataset(new File(config.root_directory), "test_" + (c++), test);

                    //               transformed_test.randomize( new RandomAdaptor( config.rng ) );
                    //               final ClusterContingencyTable ct = evaluator.evaluate( transformed_test );
                    test.randomize(new RandomAdaptor(config.rng));
                    final ClusterContingencyTable ct = evaluator.evaluate(test);
                    System.out.println(ct);

                    int Nerrors = 0;
                    final MeanVarianceAccumulator mv = new MeanVarianceAccumulator();
                    for (int i = 0; i < ct.R; ++i) {
                        final int max = Fn.max(ct.n[i]);
                        Nerrors += (ct.a[i] - max);
                        mv.add(((double) ct.a[i]) / ct.N * Nerrors / ct.a[i]);
                    }
                    errors.add(Nerrors);
                    relative_error.add(mv.mean());

                    System.out.println("exemplar: " + test.get(0));
                    System.out.println("Nerrors = " + Nerrors);
                    final PrintStream ct_out = new PrintStream(
                            new FileOutputStream(new File(expr_directory, "ct_" + expr + "_" + xval + ".csv")));
                    ct.writeCsv(ct_out);
                    ct_out.close();
                    final double ct_ami = ct.adjustedMutualInformation_max();
                    if (Double.isNaN(ct_ami)) {
                        System.out.println("! ct_ami = NaN");
                    } else {
                        ami.add(ct_ami);
                    }
                    System.out.println();
                }
            }
            System.out.println("errors = " + errors.mean() + " (" + errors.confidence() + ")");
            System.out.println(
                    "relative_error = " + relative_error.mean() + " (" + relative_error.confidence() + ")");
            System.out.println("AMI_max = " + ami.mean() + " (" + ami.confidence() + ")");

            csv.cell(config.domain).cell(config.get("abstraction.discovery"));
            for (final String p : parameter_headers) {
                csv.cell(config.get(p));
            }
            csv.cell(Ntrain).cell(Ntest).cell(ami.mean()).cell(ami.variance()).cell(ami.confidence()).newline();
        } catch (final Exception ex) {
            ex.printStackTrace();
        }
    }
}

From source file:elh.eus.absa.CLI.java

License:Open Source License

/**
 * Main access to the train-atc functionalities. Train ATC using a double one vs. all classifier
 * (E and A) for E#A aspect categories/*from   w  ww .j  a  va 2 s.  c o m*/
 * @throws Exception 
 */
public final void trainATC2(final InputStream inputStream) throws IOException {
    // load training parameters file
    String paramFile = parsedArguments.getString("params");
    String testFile = parsedArguments.getString("testset");
    String paramFile2 = parsedArguments.getString("params2");
    String corpusFormat = parsedArguments.getString("corpusFormat");
    //String validation = parsedArguments.getString("validation");
    String lang = parsedArguments.getString("language");
    //int foldNum = Integer.parseInt(parsedArguments.getString("foldNum"));
    //boolean printPreds = parsedArguments.getBoolean("printPreds");
    boolean nullSentenceOpinions = parsedArguments.getBoolean("nullSentences");
    boolean onlyTest = parsedArguments.getBoolean("testOnly");
    double threshold = 0.5;
    double threshold2 = 0.5;
    String modelsPath = "/home/inaki/elixa-atp/ovsaModels";

    CorpusReader reader = new CorpusReader(inputStream, corpusFormat, nullSentenceOpinions, lang);
    Features atcTrain = new Features(reader, paramFile, "3");
    Instances traindata = atcTrain.loadInstances(true, "atc");

    if (onlyTest) {
        if (FileUtilsElh.checkFile(testFile)) {
            System.err.println("read from test file");
            reader = new CorpusReader(new FileInputStream(new File(testFile)), corpusFormat,
                    nullSentenceOpinions, lang);
            atcTrain.setCorpus(reader);
            traindata = atcTrain.loadInstances(true, "atc");
        }
    }

    //setting class attribute (entCat|attCat|entAttCat|polarityCat)

    //HashMap<String, Integer> opInst = atcTrain.getOpinInst();      
    //WekaWrapper classifyAtts;
    WekaWrapper onevsall;
    try {

        //classify.printMultilabelPredictions(classify.multiLabelPrediction());      */   

        //onevsall
        Instances entdata = new Instances(traindata);
        entdata.deleteAttributeAt(entdata.attribute("attCat").index());
        entdata.deleteAttributeAt(entdata.attribute("entAttCat").index());
        entdata.setClassIndex(entdata.attribute("entCat").index());
        onevsall = new WekaWrapper(entdata, true);

        if (!onlyTest) {
            onevsall.trainOneVsAll(modelsPath, paramFile + "entCat");
            System.out.println("trainATC: one vs all models ready");
        }
        onevsall.setTestdata(entdata);
        HashMap<Integer, HashMap<String, Double>> ovsaRes = onevsall.predictOneVsAll(modelsPath,
                paramFile + "entCat");
        System.out.println("trainATC: one vs all predictions ready");
        HashMap<Integer, String> instOps = new HashMap<Integer, String>();
        for (String oId : atcTrain.getOpinInst().keySet()) {
            instOps.put(atcTrain.getOpinInst().get(oId), oId);
        }

        atcTrain = new Features(reader, paramFile2, "3");
        entdata = atcTrain.loadInstances(true, "attTrain2_data");
        entdata.deleteAttributeAt(entdata.attribute("entAttCat").index());
        //entdata.setClassIndex(entdata.attribute("entCat").index());

        Attribute insAtt = entdata.attribute("instanceId");
        double maxInstId = entdata.kthSmallestValue(insAtt, entdata.numDistinctValues(insAtt) - 1);
        System.err.println("last instance has index: " + maxInstId);
        for (int ins = 0; ins < entdata.numInstances(); ins++) {
            System.err.println("ins" + ins);
            int i = (int) entdata.instance(ins).value(insAtt);
            Instance currentInst = entdata.instance(ins);
            //System.err.println("instance "+i+" oid "+kk.get(i+1)+"kk contains key i?"+kk.containsKey(i));
            String sId = reader.getOpinion(instOps.get(i)).getsId();
            String oId = instOps.get(i);
            reader.removeSentenceOpinions(sId);
            int oSubId = 0;
            for (String cl : ovsaRes.get(i).keySet()) {
                //System.err.println("instance: "+i+" class "+cl+" value: "+ovsaRes.get(i).get(cl));
                if (ovsaRes.get(i).get(cl) > threshold) {
                    //System.err.println("one got through ! instance "+i+" class "+cl+" value: "+ovsaRes.get(i).get(cl));                  
                    // for the first one update the instances
                    if (oSubId >= 1) {
                        Instance newIns = new SparseInstance(currentInst);
                        newIns.setDataset(entdata);
                        entdata.add(newIns);
                        newIns.setValue(insAtt, maxInstId + oSubId);
                        newIns.setClassValue(cl);
                        instOps.put((int) maxInstId + oSubId, oId);

                    }
                    // if the are more create new instances
                    else {
                        currentInst.setClassValue(cl);
                        //create and add opinion to the structure
                        //   trgt, offsetFrom, offsetTo, polarity, cat, sId);
                        //Opinion op = new Opinion(instOps.get(i)+"_"+oSubId, "", 0, 0, "", cl, sId);
                        //reader.addOpinion(op);
                    }
                    oSubId++;
                }
            } //finished updating instances data                                    
        }

        entdata.setClass(entdata.attribute("attCat"));
        onevsall = new WekaWrapper(entdata, true);

        /**
         *  Bigarren sailkatzailea
         * 
         * */
        if (!onlyTest) {
            onevsall.trainOneVsAll(modelsPath, paramFile + "attCat");
            System.out.println("trainATC: one vs all attcat models ready");
        }

        ovsaRes = onevsall.predictOneVsAll(modelsPath, paramFile + "entAttCat");

        insAtt = entdata.attribute("instanceId");
        maxInstId = entdata.kthSmallestValue(insAtt, insAtt.numValues());
        System.err.println("last instance has index: " + maxInstId);
        for (int ins = 0; ins < entdata.numInstances(); ins++) {
            System.err.println("ins: " + ins);
            int i = (int) entdata.instance(ins).value(insAtt);
            Instance currentInst = entdata.instance(ins);
            //System.err.println("instance "+i+" oid "+kk.get(i+1)+"kk contains key i?"+kk.containsKey(i));
            String sId = reader.getOpinion(instOps.get(i)).getsId();
            String oId = instOps.get(i);
            reader.removeSentenceOpinions(sId);
            int oSubId = 0;
            for (String cl : ovsaRes.get(i).keySet()) {
                //System.err.println("instance: "+i+" class "+cl+" value: "+ovsaRes.get(i).get(cl));
                if (ovsaRes.get(i).get(cl) > threshold2) {
                    ///System.err.println("instance: "+i+" class "+cl+" value: "+ovsaRes.get(i).get(cl));
                    if (ovsaRes.get(i).get(cl) > threshold) {
                        //System.err.println("one got through ! instance "+i+" class "+cl+" value: "+ovsaRes.get(i).get(cl));                  
                        // for the first one update the instances
                        if (oSubId >= 1) {
                            String label = currentInst.stringValue(entdata.attribute("entAtt")) + "#" + cl;
                            //create and add opinion to the structure
                            //   trgt, offsetFrom, offsetTo, polarity, cat, sId);                     
                            Opinion op = new Opinion(oId + "_" + oSubId, "", 0, 0, "", label, sId);
                            reader.addOpinion(op);
                        }
                        // if the are more create new instances
                        else {
                            String label = currentInst.stringValue(entdata.attribute("entAtt")) + "#" + cl;
                            //create and add opinion to the structure
                            //   trgt, offsetFrom, offsetTo, polarity, cat, sId);
                            reader.removeOpinion(oId);
                            Opinion op = new Opinion(oId + "_" + oSubId, "", 0, 0, "", label, sId);
                            reader.addOpinion(op);
                        }
                        oSubId++;
                    }
                } //finished updating instances data                                    
            }
        }
        reader.print2Semeval2015format(paramFile + "entAttCat.xml");
    } catch (Exception e) {
        e.printStackTrace();
    }

    //traindata.setClass(traindata.attribute("entAttCat"));
    System.err.println("DONE CLI train-atc2 (oneVsAll)");
}

From source file:fantail.algorithms.RankingByPairwiseComparison.java

License:Open Source License

@Override
public void buildRanker(Instances data) throws Exception {
    m_Classifiers = new ArrayList<weka.classifiers.AbstractClassifier>();
    m_AlgoPairs = new ArrayList<String>();
    m_NumLabels = Tools.getNumberTargets(data);

    // build pb datasets
    for (int a = 0; a < m_NumLabels; a++) {
        for (int b = 0; b < m_NumLabels; b++) {

            String pairStr = a + "|" + b;
            if (!hasPair(m_AlgoPairs, pairStr) && a != b) {
                m_AlgoPairs.add(pairStr);

                Instances d = new Instances(data);
                d.setClassIndex(-1);//from w  w  w . ja v  a 2  s .co  m
                d.deleteAttributeAt(d.numAttributes() - 1);

                weka.filters.unsupervised.attribute.Add add = new weka.filters.unsupervised.attribute.Add();
                add.setInputFormat(d);
                add.setOptions(weka.core.Utils
                        .splitOptions("-T NOM -N class -L " + ((int) a) + "," + ((int) b) + " -C last"));

                d = Filter.useFilter(d, add);
                d.setClassIndex(d.numAttributes() - 1);

                for (int i = 0; i < d.numInstances(); i++) {

                    Instance metaInst = (Instance) data.instance(i);
                    Instance inst = d.instance(i);

                    double[] rankVector = Tools.getTargetVector(metaInst);

                    double rank_a = rankVector[a];
                    double rank_b = rankVector[b];

                    if (rank_a < rank_b) {
                        inst.setClassValue(0.0);
                    } else {
                        inst.setClassValue(1.0);
                    }
                }

                //weka.classifiers.functions.SMO cls = new weka.classifiers.functions.SMO();
                //String ops = "weka.classifiers.functions.SMO -C 1.0 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K \"weka.classifiers.functions.supportVector.RBFKernel -C 250007 -G 0.01\"";
                //cls.setOptions(weka.core.Utils.splitOptions(ops));                   
                //cls.buildClassifier(d);
                //weka.classifiers.functions.Logistic cls = new weka.classifiers.functions.Logistic();
                //weka.classifiers.trees.J48 cls = new weka.classifiers.trees.J48();
                //weka.classifiers.rules.ZeroR cls = new weka.classifiers.rules.ZeroR();
                weka.classifiers.trees.DecisionStump cls = new weka.classifiers.trees.DecisionStump();
                cls.buildClassifier(d);
                m_Classifiers.add(cls);
                m_BaseClassifierName = cls.getClass().getSimpleName();
                m_Add = add;
            }
        }
    }
}

From source file:fcul.viegas.ml.learners.NetworkStreamLearningClassifierMapFunction.java

public InstanceStreamDTO map(InstanceStreamDTO instance) throws Exception {

    weka.core.Instance inst = instance.getInstance();
    inst.setDataset(this.coreInstances);
    inst.setClassValue(inst.classValue());
    inst = classifier.constructMappedInstance(inst);

    HoeffdingTree tree = (HoeffdingTree) classifier.getClassifier();
    double[] classe = tree.distributionForInstance(inst);
    instance.setInstance(null);/* www  . j av a 2s.c o m*/
    //System.out.println("\t classe[0]: " + classe[0] + " classe[1]: " + classe[1]);
    if (classe[0] > classe[1]) {
        instance.setAssignedClassValueFromLearner(0.0d);
    } else {
        instance.setAssignedClassValueFromLearner(1.0d);
    }
    return instance;
}

From source file:GroupProject.DMChartUI.java

/**
* Action for the generate button/*from   w  ww . j  a  va2  s. c om*/
* It reads the user input from the table and the selected options and performs
* a classifiecation of the user input
* the user can choose linear regression, naive bayes classifier, or j48 trees to classify 
*
*/
private void generateButtonActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_generateButtonActionPerformed
    // TODO add your handling code here:                                              
    // TODO add your handling code here:
    //File file = new File("studentTemp.csv");
    CSVtoArff converter = new CSVtoArff();
    Instances students = null;
    Instances students2 = null;
    try {
        converter.convert("studentTemp.csv", "studentTemp.arff");
    } catch (IOException ex) {
        Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
    }

    try {
        students = new Instances(new BufferedReader(new FileReader("studentTemp.arff")));
        students2 = new Instances(new BufferedReader(new FileReader("studentTemp.arff")));
    } catch (IOException ex) {
        Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
    }

    //get column to predict values for 
    //int target=students.numAttributes()-1; 
    int target = dataSelector.getSelectedIndex() + 1;
    System.out.printf("this is the target: %d\n", target);
    //set target 
    students.setClassIndex(target);
    students2.setClassIndex(target);

    //case on which radio button is selected 
    //Linear Regressions
    if (LRB.isSelected()) {

        LinearRegression model = null;
        if (Lmodel != null) {
            model = Lmodel;
        } else {
            buildLinearModel();
            model = Lmodel;
        }

        System.out.println("im doing linear regression");

        equationDisplayArea.setText(model.toString());

        System.out.println("im going to get the instance");

        Instance prediction2 = getInstance(true);

        Remove remove = new Remove();
        int[] toremove = { 0, 2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17 };
        remove.setAttributeIndicesArray(toremove);

        try {
            remove.setInputFormat(students);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        Instances instNew = null;
        try {
            instNew = Filter.useFilter(students, remove);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        prediction2.setDataset(instNew);
        System.err.print("i got the instance");
        double result = 0;
        try {
            result = model.classifyInstance(prediction2);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        System.out.printf("the result : %f \n ", result);
        predictValue.setText(Double.toString(result));
        System.out.println("I'm done with Linear Regression");
    }

    //Naive Bayes
    else if (NBB.isSelected()) {
        Classifier cModel = null;

        if (NBmodel != null) {
            cModel = NBmodel;
        } else {
            buildNBClassifier();
            cModel = NBmodel;
        }

        System.out.println("im doing NB");

        //build test 
        Evaluation eTest = null;
        try {
            eTest = new Evaluation(students);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }
        System.out.println("Using NB");

        try {
            eTest.evaluateModel(cModel, students);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        //display the test results to console 
        String strSummary = eTest.toSummaryString();
        System.out.println(strSummary);

        //build instance to predict 
        System.out.println("im going to get the instance");

        Instance prediction2 = getInstance(false);

        prediction2.setDataset(students);
        System.err.print("i got the instance");

        //replace with loop stating the class names 
        //fit text based on name of categories 
        double pred = 0;
        try {
            pred = cModel.classifyInstance(prediction2);
            prediction2.setClassValue(pred);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }
        //get the predicted value and set predictValue to it 
        predictValue.setText(prediction2.classAttribute().value((int) pred));

        System.out.println("I'm done with Naive Bayes");

        double[] fDistribution2 = null;
        try {
            fDistribution2 = cModel.distributionForInstance(prediction2);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        double max = 0;
        int maxindex = 0;
        max = fDistribution2[0];
        for (int i = 0; i < fDistribution2.length; i++) {
            if (fDistribution2[i] > max) {
                maxindex = i;
                max = fDistribution2[i];
            }
            System.out.println("the value at " + i + " : " + fDistribution2[i]);
            System.out.println("the label at " + i + prediction2.classAttribute().value(i));
        }
        prediction2.setClassValue(maxindex);
        predictValue.setText(prediction2.classAttribute().value(maxindex));

    }
    //J48 Tree
    else if (JB.isSelected()) {

        System.out.println("im doing j48 ");

        Classifier jModel = null;
        if (Jmodel != null) {
            jModel = Jmodel;
        } else {
            buildJClassifier();
            jModel = Jmodel;
        }
        //test model 
        Evaluation eTest2 = null;
        try {
            eTest2 = new Evaluation(students);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }
        System.out.println("Using J48 test");
        try {
            eTest2.evaluateModel(jModel, students);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }
        String strSummary2 = eTest2.toSummaryString();
        System.out.println(strSummary2);

        System.out.println("im going to get the instance");

        Instance prediction2 = getInstance(false);

        prediction2.setDataset(students);
        System.err.print("i got the instance\n");

        double pred = 0;
        try {
            pred = jModel.classifyInstance(prediction2);
            prediction2.setClassValue(pred);
            System.out.println("i did a prediction");
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        //get the predicted value and set predictValue to it 
        System.out.println("this was pred:" + pred);
        predictValue.setText(prediction2.classAttribute().value((int) pred));

        System.out.println("I'm done with J48");
        //replace with loop stating the class names 
        //fit text based on name of categories 

        double[] fDistribution2 = null;
        try {
            fDistribution2 = jModel.distributionForInstance(prediction2);
        } catch (Exception ex) {
            Logger.getLogger(DMChartUI.class.getName()).log(Level.SEVERE, null, ex);
        }

        double max = 0;
        int maxindex = 0;
        max = fDistribution2[0];
        for (int i = 0; i < fDistribution2.length; i++) {
            if (fDistribution2[i] > max) {
                maxindex = i;
                max = fDistribution2[i];
            }
            System.out.println("the value at " + i + " : " + fDistribution2[i]);
            System.out.println("the label at " + i + " " + prediction2.classAttribute().value(i));
        }
        prediction2.setClassValue(maxindex);
        predictValue.setText(prediction2.classAttribute().value(maxindex));

    }

}