Example usage for weka.core Instances attribute

List of usage examples for weka.core Instances attribute

  1. HOME
  2. Java
  3. weka
  4. weka.core.*
  5. Instances
  6. attribute

Introduction

In this page you can find the example usage for weka.core Instances attribute.

Prototype

publicAttribute attribute(String name)

Source Link

Document

Returns an attribute given its name.

Usage

From source file:FFNN.MultiplePerceptron.java

public static void main(String args[]) throws Exception {
    //        System.out.println("input jumlah layer 0/1 :");
    //        Scanner input = new Scanner(System.in);
    //        int layer = input.nextInt();
    //        System.out.println("input learning rate");
    //        double rate = input.nextDouble();
    //        int hidden = 0;
    //        if(layer==1){
    //            System.out.println("input jumlah neuron di hidden layer");
    //            hidden = input.nextInt();
    //        }/*from   www.j  ava  2  s  .co m*/
    //        
    //        System.out.print("Masukkan nama file : ");
    //        String filename = input.next();
    ConverterUtils.DataSource source = new ConverterUtils.DataSource(
            ("D:\\Program Files\\Weka-3-8\\data\\iris.arff"));
    Instances train = source.getDataSet();
    //        Normalize nm = new Normalize();
    //        nm.setInputFormat(train);
    //        train = Filter.useFilter(train, nm);
    for (int i = 0; i < train.numAttributes(); i++)
        System.out.println(i + ". " + train.attribute(i).name());
    System.out.print("Masukkan indeks kelas : ");
    //int classIdx = input.nextInt();
    train.setClassIndex(train.numAttributes() - 1);
    MultiplePerceptron mlp = new MultiplePerceptron(10000, 1, 13, train);
    mlp.buildClassifier(train);
    Evaluation eval = new Evaluation(train);
    eval.evaluateModel(mlp, train);
    System.out.println(eval.toSummaryString());
    //        System.out.println(eval.toMatrixString());
}

From source file:filters.MauiFilter.java

License:Open Source License

/**
 * Sets the format of the input instances.
 * /* w  w  w  .j av  a2s .com*/
 * @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
 */
public boolean setInputFormat(Instances instanceInfo) throws Exception {

    if (instanceInfo.classIndex() >= 0) {
        throw new Exception("Don't know what do to if class index set!");
    }

    if (!instanceInfo.attribute(keyphrasesAtt).isString() || !instanceInfo.attribute(documentAtt).isString()) {
        throw new Exception("Keyphrase attribute and document attribute " + "need to be string attributes.");
    }

    phraseFilter = new MauiPhraseFilter();
    int[] arr = new int[1];
    arr[0] = documentAtt;
    phraseFilter.setAttributeIndicesArray(arr);
    phraseFilter.setInputFormat(instanceInfo);

    if (vocabularyName.equals("none")) {
        numbersFilter = new NumbersFilter();
        numbersFilter.setInputFormat(phraseFilter.getOutputFormat());
        super.setInputFormat(numbersFilter.getOutputFormat());
    } else {
        super.setInputFormat(phraseFilter.getOutputFormat());
    }

    return false;

}

From source file:fr.ign.cogit.geoxygene.util.conversion.ConversionToARFF.java

License:Open Source License

/**
 * Permet de convertir des FeatureCollections en fichier ARFF
 * //from w w  w  .  j a va 2 s.c  o  m
 * @param featColl la collection en entre
 * @param outFilePath le fichier en sortie
 * @throws ParseException
 * @throws IOException
 */
public static void export(IFeatureCollection<IFeature> featColl, String outFilePath)
        throws ParseException, IOException {

    ArrayList<Attribute> atts = new ArrayList<Attribute>();
    Instances data;
    double[] vals;
    int i;

    // 1. Prparation des attributs

    IFeature feat = featColl.get(0);

    FeatureType ft = (FeatureType) feat.getFeatureType();

    List<GF_AttributeType> lAttributeTypes = ft.getFeatureAttributes();

    int nbAttributes = lAttributeTypes.size();

    for (i = 0; i < nbAttributes; i++) {

        GF_AttributeType attT = lAttributeTypes.get(i);

        if (attT.getValueType().equalsIgnoreCase("String")) {

            atts.add(new Attribute(attT.getMemberName(), (List<String>) null));

        } else {

            atts.add(new Attribute(attT.getMemberName()));
        }

    }

    // 2 on cre l'instance
    data = new Instances("MyRelation", atts, 0);

    // 3 on ajoute les donnes

    int nbElem = featColl.size();

    for (i = 0; i < nbElem; i++) {

        feat = featColl.get(i);

        vals = new double[nbAttributes];

        for (int j = 0; j < nbAttributes; j++) {

            GF_AttributeType attT = lAttributeTypes.get(j);

            if (attT.getValueType().equalsIgnoreCase("String")) {

                vals[j] = data.attribute(j).addStringValue(feat.getAttribute(attT.getMemberName()).toString());

            } else {
                vals[j] = Double.parseDouble(feat.getAttribute(attT.getMemberName()).toString());
            }

        }

        DenseInstance densInstance = new DenseInstance(1.0, vals);

        data.add(densInstance);
    }

    ArffSaver arffSaver = new ArffSaver();
    arffSaver.setInstances(data);
    arffSaver.setFile(new File(outFilePath));
    arffSaver.writeBatch();

}

From source file:fr.loria.synalp.jtrans.phonetiseur.Classifieurs.java

License:Open Source License

private String resultatClassifieur(Instance instance, Classifier classifieur, Instances instances)
        throws Exception {
    double r = classifieur.classifyInstance(instance);
    return instances.attribute(instances.numAttributes() - 1).value((int) r);
}

From source file:gnusmail.learning.ClassifierManager.java

License:Open Source License

public void setDataSet(Instances dataSet) {
    this.dataSet = dataSet;
    this.dataSet.setClass(dataSet.attribute("Label"));
}

From source file:gov.va.chir.tagline.dao.DatasetUtil.java

License:Open Source License

@SuppressWarnings("unchecked")
public static Instances createDataset(final Instances header, final Collection<Document> documents)
        throws Exception {

    // Update header to include all docIDs from the passed in documents
    // (Weka requires all values for nominal features)
    final Set<String> docIds = new TreeSet<String>();

    for (Document document : documents) {
        docIds.add(document.getName());//w w  w  . j a v  a 2s.c  o  m
    }

    final AddValues avf = new AddValues();
    avf.setLabels(StringUtils.join(docIds, ","));

    // Have to add 1 because SingleIndex.setValue() has a bug, expecting
    // the passed in index to be 1-based rather than 0-based. Why? I have 
    // no idea.
    // Calling path: AddValues.setInputFormat() -->
    //               SingleIndex.setUpper() -->
    //               SingleIndex.setValue()
    avf.setAttributeIndex(String.valueOf(header.attribute(DOC_ID).index() + 1));

    avf.setInputFormat(header);
    final Instances newHeader = Filter.useFilter(header, avf);

    final Instances instances = new Instances(newHeader, documents.size());

    // Map attributes
    final Map<String, Attribute> attrMap = new HashMap<String, Attribute>();

    final Enumeration<Attribute> en = newHeader.enumerateAttributes();

    while (en.hasMoreElements()) {
        final Attribute attr = en.nextElement();

        attrMap.put(attr.name(), attr);
    }

    attrMap.put(newHeader.classAttribute().name(), newHeader.classAttribute());

    final Attribute docId = attrMap.get(DOC_ID);
    final Attribute lineId = attrMap.get(LINE_ID);
    final Attribute classAttr = attrMap.get(LABEL);

    // Add data
    for (Document document : documents) {
        final Map<String, Object> docFeatures = document.getFeatures();

        for (Line line : document.getLines()) {
            final Instance instance = new DenseInstance(attrMap.size());

            final Map<String, Object> lineFeatures = line.getFeatures();
            lineFeatures.putAll(docFeatures);

            instance.setValue(docId, document.getName());
            instance.setValue(lineId, line.getLineId());

            if (line.getLabel() == null) {
                instance.setMissing(classAttr);
            } else {
                instance.setValue(classAttr, line.getLabel());
            }

            for (Attribute attribute : attrMap.values()) {
                if (!attribute.equals(docId) && !attribute.equals(lineId) && !attribute.equals(classAttr)) {
                    final String name = attribute.name();
                    final Object obj = lineFeatures.get(name);

                    if (obj instanceof Double) {
                        instance.setValue(attribute, ((Double) obj).doubleValue());
                    } else if (obj instanceof Integer) {
                        instance.setValue(attribute, ((Integer) obj).doubleValue());
                    } else {
                        instance.setValue(attribute, obj.toString());
                    }
                }
            }

            instances.add(instance);
        }
    }

    // Set last attribute as class
    instances.setClassIndex(attrMap.size() - 1);

    return instances;
}

From source file:gr.auth.ee.lcs.data.representations.complex.ComplexRepresentation.java

License:Open Source License

/**
 * Build the representation for some instances.
 * //from   www. ja va 2s  . c  o m
 * @param instances
 *            the instances
 */

protected void buildRepresentationFromInstance(final Instances instances) {

    for (int i = 0; i < (instances.numAttributes() - numberOfLabels); i++) {

        final String attributeName = instances.attribute(i).name();

        if (instances.attribute(i).isNominal()) {

            String[] attributeNames = new String[instances.attribute(i).numValues()];

            final Enumeration<?> values = instances.attribute(i).enumerateValues();

            for (int j = 0; j < attributeNames.length; j++) {
                attributeNames[j] = (String) values.nextElement();
            }

            // Create boolean or generic nominal
            if (attributeNames.length > 2)
                attributeList[i] = new ComplexRepresentation.NominalAttribute(this.chromosomeSize,
                        attributeName, attributeNames, attributeGeneralizationRate);
            else
                attributeList[i] = new ComplexRepresentation.BooleanAttribute(chromosomeSize, attributeName,
                        attributeGeneralizationRate);

        } else if (instances.attribute(i).isNumeric()) {
            float minValue, maxValue;
            minValue = (float) instances.instance(0).toDoubleArray()[i];
            maxValue = minValue;
            for (int sample = 0; sample < instances.numInstances(); sample++) {
                final float currentVal = (float) instances.instance(sample).toDoubleArray()[i];
                if (currentVal > maxValue)
                    maxValue = currentVal;
                if (currentVal < minValue)
                    minValue = currentVal;
            }
            attributeList[i] = new ComplexRepresentation.IntervalAttribute(this.chromosomeSize, attributeName,
                    minValue, maxValue, precision, attributeGeneralizationRate);
        }
    }

    createClassRepresentation(instances);
}

From source file:gr.auth.ee.lcs.data.representations.complex.GenericMultiLabelRepresentation.java

License:Open Source License

@Override
protected void createClassRepresentation(final Instances instances) {

    for (int i = 0; i < numberOfLabels; i++) {

        final int labelIndex = (attributeList.length - numberOfLabels) + i;

        final String attributeName = instances.attribute(labelIndex).name();

        attributeList[labelIndex] = new GenericLabel(chromosomeSize, attributeName, labelGeneralizationRate);
    }//from  w w w  .ja  v a  2 s .  c o m
}

From source file:gr.auth.ee.lcs.data.representations.complex.StrictMultiLabelRepresentation.java

License:Open Source License

@Override
protected void createClassRepresentation(final Instances instances) {
    for (int i = 0; i < numberOfLabels; i++) {

        final int labelIndex = (attributeList.length - numberOfLabels) + i;

        final String attributeName = instances.attribute(labelIndex).name();

        attributeList[labelIndex] = new Label(chromosomeSize, attributeName);
    }/* ww w . j  a v a2s.c  o  m*/

}

From source file:gr.iti.mklab.visual.quantization.SimpleKMeansWithOutput.java

License:Open Source License

/**
 * Generates a clusterer. Has to initialize all fields of the clusterer that are not being set via
 * options./*from w ww  . jav a  2 s  . com*/
 * 
 * @param data
 *            set of instances serving as training data
 * @throws Exception
 *             if the clusterer has not been generated successfully
 */
@Override
public void buildClusterer(Instances data) throws Exception {

    // can clusterer handle the data?
    getCapabilities().testWithFail(data);

    m_Iterations = 0;

    m_ReplaceMissingFilter = new ReplaceMissingValues();
    Instances instances = new Instances(data);

    instances.setClassIndex(-1);
    if (!m_dontReplaceMissing) {
        m_ReplaceMissingFilter.setInputFormat(instances);
        instances = Filter.useFilter(instances, m_ReplaceMissingFilter);
    }

    m_FullMissingCounts = new int[instances.numAttributes()];
    if (m_displayStdDevs) {
        m_FullStdDevs = new double[instances.numAttributes()];
    }
    m_FullNominalCounts = new int[instances.numAttributes()][0];

    m_FullMeansOrMediansOrModes = moveCentroid(0, instances, false, false);
    for (int i = 0; i < instances.numAttributes(); i++) {
        m_FullMissingCounts[i] = instances.attributeStats(i).missingCount;
        if (instances.attribute(i).isNumeric()) {
            if (m_displayStdDevs) {
                m_FullStdDevs[i] = Math.sqrt(instances.variance(i));
            }
            if (m_FullMissingCounts[i] == instances.numInstances()) {
                m_FullMeansOrMediansOrModes[i] = Double.NaN; // mark missing as mean
            }
        } else {
            m_FullNominalCounts[i] = instances.attributeStats(i).nominalCounts;
            if (m_FullMissingCounts[i] > m_FullNominalCounts[i][Utils.maxIndex(m_FullNominalCounts[i])]) {
                m_FullMeansOrMediansOrModes[i] = -1; // mark missing as most common
                // value
            }
        }
    }

    m_ClusterCentroids = new Instances(instances, m_NumClusters);
    int[] clusterAssignments = new int[instances.numInstances()];

    if (m_PreserveOrder)
        m_Assignments = clusterAssignments;

    m_DistanceFunction.setInstances(instances);

    Random RandomO = new Random(getSeed());
    int instIndex;
    HashMap initC = new HashMap();
    DecisionTableHashKey hk = null;

    Instances initInstances = null;
    if (m_PreserveOrder)
        initInstances = new Instances(instances);
    else
        initInstances = instances;

    if (m_initializeWithKMeansPlusPlus) {
        kMeansPlusPlusInit(initInstances);
    } else {
        for (int j = initInstances.numInstances() - 1; j >= 0; j--) {
            instIndex = RandomO.nextInt(j + 1);
            hk = new DecisionTableHashKey(initInstances.instance(instIndex), initInstances.numAttributes(),
                    true);
            if (!initC.containsKey(hk)) {
                m_ClusterCentroids.add(initInstances.instance(instIndex));
                initC.put(hk, null);
            }
            initInstances.swap(j, instIndex);

            if (m_ClusterCentroids.numInstances() == m_NumClusters) {
                break;
            }
        }
    }

    m_NumClusters = m_ClusterCentroids.numInstances();

    // removing reference
    initInstances = null;

    int i;
    boolean converged = false;
    int emptyClusterCount;
    Instances[] tempI = new Instances[m_NumClusters];
    m_squaredErrors = new double[m_NumClusters];
    m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0];
    m_ClusterMissingCounts = new int[m_NumClusters][instances.numAttributes()];
    startExecutorPool();

    long start = System.currentTimeMillis();
    while (!converged) {
        emptyClusterCount = 0;
        m_Iterations++;
        converged = true;
        System.out.print(new Date() + ": " + "Iter " + m_Iterations + " ");
        if (m_executionSlots <= 1 || instances.numInstances() < 2 * m_executionSlots) {
            for (i = 0; i < instances.numInstances(); i++) {
                Instance toCluster = instances.instance(i);
                int newC = clusterProcessedInstance(toCluster, true, true);
                if (newC != clusterAssignments[i]) {
                    converged = false;
                }
                clusterAssignments[i] = newC;
            }
        } else {
            converged = launchAssignToClusters(instances, clusterAssignments);
        }

        // update centroids
        m_ClusterCentroids = new Instances(instances, m_NumClusters);
        for (i = 0; i < m_NumClusters; i++) {
            tempI[i] = new Instances(instances, 0);
        }
        for (i = 0; i < instances.numInstances(); i++) {
            tempI[clusterAssignments[i]].add(instances.instance(i));
        }
        if (m_executionSlots <= 1 || instances.numInstances() < 2 * m_executionSlots) {
            for (i = 0; i < m_NumClusters; i++) {
                if (tempI[i].numInstances() == 0) {
                    // empty cluster
                    emptyClusterCount++;
                } else {
                    moveCentroid(i, tempI[i], true, true);
                }
            }
        } else {
            emptyClusterCount = launchMoveCentroids(tempI);
        }

        if (m_Iterations == m_MaxIterations)
            converged = true;

        if (emptyClusterCount > 0) {
            m_NumClusters -= emptyClusterCount;
            if (converged) {
                Instances[] t = new Instances[m_NumClusters];
                int index = 0;
                for (int k = 0; k < tempI.length; k++) {
                    if (tempI[k].numInstances() > 0) {
                        t[index++] = tempI[k];
                    }
                }
                tempI = t;
            } else {
                tempI = new Instances[m_NumClusters];
            }
        }

        if (!converged) {
            m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0];
        }
        System.out.println("Sum of within cluster distances: " + Utils.sum(m_squaredErrors));
        // reset erros to zero
        m_squaredErrors = new double[m_NumClusters];
    }
    long end = System.currentTimeMillis();
    System.out.println("\nClustering completed in " + (end - start) + " ms and converged in " + m_Iterations
            + " iterations");

    // calculate errors
    if (!m_FastDistanceCalc) {
        for (i = 0; i < instances.numInstances(); i++) {
            clusterProcessedInstance(instances.instance(i), true, false);
        }
    }

    if (m_displayStdDevs) {
        m_ClusterStdDevs = new Instances(instances, m_NumClusters);
    }
    m_ClusterSizes = new int[m_NumClusters];
    for (i = 0; i < m_NumClusters; i++) {
        if (m_displayStdDevs) {
            double[] vals2 = new double[instances.numAttributes()];
            for (int j = 0; j < instances.numAttributes(); j++) {
                if (instances.attribute(j).isNumeric()) {
                    vals2[j] = Math.sqrt(tempI[i].variance(j));
                } else {
                    vals2[j] = Utils.missingValue();
                }
            }
            m_ClusterStdDevs.add(new DenseInstance(1.0, vals2));
        }
        m_ClusterSizes[i] = tempI[i].numInstances();
    }

    m_executorPool.shutdown();
}