Example usage for weka.core Instances 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:gr.iti.mklab.visual.quantization.SimpleKMeansWithOutput.java

License:Open Source License

/**
 * Move the centroid to it's new coordinates. Generate the centroid coordinates based on it's members
 * (objects assigned to the cluster of the centroid) and the distance function being used.
 * //from w ww .  j a  v  a2s.  com
 * @param centroidIndex
 *            index of the centroid which the coordinates will be computed
 * @param members
 *            the objects that are assigned to the cluster of this centroid
 * @param updateClusterInfo
 *            if the method is supposed to update the m_Cluster arrays
 * @param addToCentroidInstances
 *            true if the method is to add the computed coordinates to the Instances holding the centroids
 * @return the centroid coordinates
 */
protected double[] moveCentroid(int centroidIndex, Instances members, boolean updateClusterInfo,
        boolean addToCentroidInstances) {
    double[] vals = new double[members.numAttributes()];

    // used only for Manhattan Distance
    Instances sortedMembers = null;
    int middle = 0;
    boolean dataIsEven = false;

    if (m_DistanceFunction instanceof ManhattanDistance) {
        middle = (members.numInstances() - 1) / 2;
        dataIsEven = ((members.numInstances() % 2) == 0);
        if (m_PreserveOrder) {
            sortedMembers = members;
        } else {
            sortedMembers = new Instances(members);
        }
    }

    for (int j = 0; j < members.numAttributes(); j++) {

        // in case of Euclidian distance the centroid is the mean point
        // in case of Manhattan distance the centroid is the median point
        // in both cases, if the attribute is nominal, the centroid is the mode
        if (m_DistanceFunction instanceof EuclideanDistance || members.attribute(j).isNominal()) {
            vals[j] = members.meanOrMode(j);
        } else if (m_DistanceFunction instanceof ManhattanDistance) {
            // singleton special case
            if (members.numInstances() == 1) {
                vals[j] = members.instance(0).value(j);
            } else {
                vals[j] = sortedMembers.kthSmallestValue(j, middle + 1);
                if (dataIsEven) {
                    vals[j] = (vals[j] + sortedMembers.kthSmallestValue(j, middle + 2)) / 2;
                }
            }
        }

        if (updateClusterInfo) {
            m_ClusterMissingCounts[centroidIndex][j] = members.attributeStats(j).missingCount;
            m_ClusterNominalCounts[centroidIndex][j] = members.attributeStats(j).nominalCounts;
            if (members.attribute(j).isNominal()) {
                if (m_ClusterMissingCounts[centroidIndex][j] > m_ClusterNominalCounts[centroidIndex][j][Utils
                        .maxIndex(m_ClusterNominalCounts[centroidIndex][j])]) {
                    vals[j] = Utils.missingValue(); // mark mode as missing
                }
            } else {
                if (m_ClusterMissingCounts[centroidIndex][j] == members.numInstances()) {
                    vals[j] = Utils.missingValue(); // mark mean as missing
                }
            }
        }
    }
    if (addToCentroidInstances) {
        m_ClusterCentroids.add(new DenseInstance(1.0, vals));
    }
    return vals;
}

---

From source file:Graphs.Graph.java

public Graph(Instances inst) {
    this.inst = new Instances(inst);
    dieknoten = new Knoten[inst.numAttributes()];
    for (int i = 0; i < dieknoten.length; i++) {
        dieknoten[i] = new Knoten(inst.attribute(i).name(), inst.attribute(i).name());
        dieknoten[i].setMaxKinder(inst.numAttributes() - 1);
    }//from  w  w w  .j a va 2  s . com
    adjMatrix = new int[inst.numAttributes()][inst.numAttributes()];
    matrix = new int[inst.numAttributes()][inst.numAttributes()];
    linearerepresentation = new int[inst.numAttributes() * inst.numAttributes()];
}

---

From source file:Graphs.GraphMitAngabeVernetzungsgrad.java

public GraphMitAngabeVernetzungsgrad(Instances inst, int prozent) {
    this.inst = new Instances(inst);
    dieknoten = new Knoten[inst.numAttributes()];
    for (int i = 0; i < dieknoten.length; i++) {
        dieknoten[i] = new Knoten(inst.attribute(i).name(), inst.attribute(i).name());
    }/*from  www .j a va  2 s .  co m*/
    this.prozent = prozent;
    adjMatrix = new int[inst.numAttributes()][inst.numAttributes()];
    matrix = new int[inst.numAttributes()][inst.numAttributes()];
    maxanzahkkanten = (int) Math.ceil(binomischeFormel(inst.numAttributes(), 2) * 2) / 2;
    for (int i = 0; i < adjMatrix.length; i++) {
        for (int j = 0; j < adjMatrix[i].length; j++) {
            if (i == j) {
                adjMatrix[i][j] = 0;
                adjMatrix[j][i] = 0;
            } else {
                adjMatrix[i][j] = 1;
            }
        }
    }
    linearerepresentation = new int[inst.numAttributes() * inst.numAttributes()];

}

---

From source file:guineu.modules.dataanalysis.clustering.ClusteringTask.java

License:Open Source License

/**
 * Creates the weka data set for clustering of samples
 * @param rawData Data extracted from selected Raw data files and rows.
 * @return Weka library data set/*from  w  w  w. j  a  v a2  s.  c om*/
 */
private Instances createSampleWekaDataset(double[][] rawData) {
    FastVector attributes = new FastVector();

    for (int i = 0; i < rawData[0].length; i++) {
        String varName = "Var" + i;
        Attribute var = new Attribute(varName);
        attributes.addElement(var);
    }

    if (clusteringAlgorithm.toString().equals("Hierarchical Clusterer")) {
        Attribute name = new Attribute("name", (FastVector) null);
        attributes.addElement(name);
    }
    Instances data = new Instances("Dataset", attributes, 0);

    for (int i = 0; i < rawData.length; i++) {
        double[] values = new double[data.numAttributes()];
        System.arraycopy(rawData[i], 0, values, 0, rawData[0].length);
        if (clusteringAlgorithm.toString().equals("Hierarchical Clusterer")) {
            values[data.numAttributes() - 1] = data.attribute("name")
                    .addStringValue("\"" + this.selectedRawDataFiles[i] + "\"");
        }
        Instance inst = new SparseInstance(1.0, values);
        data.add(inst);
    }
    return data;
}

---

From source file:guineu.modules.dataanalysis.clustering.ClusteringTask.java

License:Open Source License

/**
 * Creates the weka data set for clustering of variables (metabolites)
 * @param rawData Data extracted from selected Raw data files and rows.
 * @return Weka library data set//from   w w  w  .  ja va  2s. c o  m
 */
private Instances createVariableWekaDataset(double[][] rawData) {
    FastVector attributes = new FastVector();

    for (int i = 0; i < this.selectedRawDataFiles.length; i++) {
        String varName = "Var" + i;
        Attribute var = new Attribute(varName);
        attributes.addElement(var);
    }

    if (clusteringAlgorithm.toString().equals("Hierarchical Clusterer")) {
        Attribute name = new Attribute("name", (FastVector) null);
        attributes.addElement(name);
    }
    Instances data = new Instances("Dataset", attributes, 0);

    for (int i = 0; i < selectedRows.length; i++) {
        double[] values = new double[data.numAttributes()];
        System.arraycopy(rawData[i], 0, values, 0, rawData[0].length);

        if (clusteringAlgorithm.toString().equals("Hierarchical Clusterer")) {
            String rowName = selectedRows[i].getName();
            values[data.numAttributes() - 1] = data.attribute("name").addStringValue(rowName);
        }
        Instance inst = new SparseInstance(1.0, values);
        data.add(inst);
    }
    return data;
}

---

From source file:gyc.OverBoostM1.java

License:Open Source License

/**
 * //from   ww w.  ja va 2  s  .  com
 * nMajnMin
 * @param data
 * @param i
 * @return
 */
protected Instances randomSampling(Instances copia, int majC, int minC, int nMaj, int nMin,
        Random simplingRandom) {
    int[] majExamples = new int[copia.numInstances()];
    int[] minExamples = new int[copia.numInstances()];
    int majCount = 0, minCount = 0;
    // First, we copy the examples from the minority class and save the indexes of the majority
    // the new data-set contains samples_min + samples_min * N / 100
    int size = nMaj + nMin;
    //selected = new int[size]; // we store the selected examples indexes

    String majClassName = copia.attribute(copia.classIndex()).value(majC);

    Instances myDataset = new Instances(copia, 0);
    int nData = 0;
    for (int i = 0; i < copia.numInstances(); i++) {
        if (copia.instance(i).stringValue(copia.classIndex()).equalsIgnoreCase(majClassName)) {
            // save index
            majExamples[majCount] = i;
            majCount++;
        } else {
            minExamples[minCount] = i;
            minCount++;
        }
    }
    if (minCount <= 0)
        return copia;
    /* random undersampling of the majority */
    //boolean[] taken = new boolean[copia.numInstances()];
    int r;
    if (nMaj == majCount) {
        //System.out.println("#equal");
        for (int i = 0; i < nMaj; i++) {
            myDataset.add(copia.instance(majExamples[i]));
        }
    } else {
        for (int i = 0; i < nMaj; i++) {
            r = simplingRandom.nextInt(majCount);
            //selected[nData] = majExamples[r];
            myDataset.add(copia.instance(majExamples[r]));
            //taken[majExamples[r]] = true;
        }
    }
    for (int i = 0; i < nMin; i++) {
        r = simplingRandom.nextInt(minCount);
        //System.out.print("_"+r);

        //selected[nData] = minExamples[r];
        myDataset.add(copia.instance(minExamples[r]));
        //taken[minExamples[r]] = true;
    }

    //System.out.println();
    //System.out.println("minC="+minCount+"; majC="+majCount);

    myDataset.randomize(simplingRandom);
    return myDataset;
}

---

From source file:gyc.SMOTEBagging.java

License:Open Source License

/**
 * /*from w w w .  j  av  a2 s . c o  m*/
 * 100%majminSMOTE (k, a).
 * @param data
 * @param i
 * @return
 */
protected Instances randomSampling(Instances copia, int majC, int minC, int a, Random simplingRandom) {
    int[] majExamples = new int[copia.numInstances()];
    int[] minExamples = new int[copia.numInstances()];
    int majCount = 0, minCount = 0;
    // First, we copy the examples from the minority class and save the indexes of the majority
    // resample min at rate (Nmaj/Nmin)*a%
    int size = copia.attributeStats(copia.classIndex()).nominalCounts[majC] * a / 100;
    // class name
    String majClassName = copia.attribute(copia.classIndex()).value(majC);

    for (int i = 0; i < copia.numInstances(); i++) {
        if (copia.instance(i).stringValue(copia.classIndex()).equalsIgnoreCase(majClassName)) {
            // save index
            majExamples[majCount] = i;
            majCount++;
        } else {
            minExamples[minCount] = i;
            minCount++;
        }
    }

    /* random undersampling of the majority */
    Instances myDataset = new Instances(copia, 0);
    int r;
    //100%majC
    for (int i = 0; i < majCount; i++) {
        myDataset.add(copia.instance(majExamples[i]));
    }
    if (minCount == 0)
        return myDataset;
    //(Nmaj/Nmin)*a% minC
    for (int i = 0; i < size; i++) {
        r = simplingRandom.nextInt(minCount);
        myDataset.add(copia.instance(minExamples[r]));
    }
    myDataset.randomize(simplingRandom);

    if (size == 1) {
        try {
            //neighbor
            Resample filter = new Resample();
            filter.setInputFormat(myDataset);
            filter.setBiasToUniformClass(1.0);
            filter.setRandomSeed(simplingRandom.nextInt());
            myDataset = Filter.useFilter(myDataset, filter);
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    if (size > 1) {
        try {
            SMOTE filter = new SMOTE();
            filter.setInputFormat(myDataset); // filter capabilities are checked here
            //data.
            double value = 100.0 * majCount / size - 100;
            //Percentage
            filter.setPercentage(value);
            //if (nMin<5) filter.setNearestNeighbors(nMin);
            filter.setRandomSeed(simplingRandom.nextInt());
            //filterSMOTESMOTE
            myDataset = Filter.useFilter(myDataset, filter);
            //t.stop();
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    return myDataset;
}

---

From source file:gyc.UnderOverBoostM1.java

License:Open Source License

/**
 * /*  w ww .j  av  a  2  s . c  o m*/
 * nMajnMin
 * @param data
 * @param i
 * @return
 */
protected Instances randomSampling(Instances copia, int majC, int minC, int a, Random simplingRandom) {
    int[] majExamples = new int[copia.numInstances()];
    int[] minExamples = new int[copia.numInstances()];
    int majCount = 0, minCount = 0;
    // First, we copy the examples from the minority class and save the indexes of the majority
    // the new data-set contains samples_min + samples_min * N / 100
    int size = copia.attributeStats(copia.classIndex()).nominalCounts[majC] * a / 100 * 2;
    // class name
    String majClassName = copia.attribute(copia.classIndex()).value(majC);

    for (int i = 0; i < copia.numInstances(); i++) {
        if (copia.instance(i).stringValue(copia.classIndex()).equalsIgnoreCase(majClassName)) {
            // save index
            majExamples[majCount] = i;
            majCount++;
        } else {
            minExamples[minCount] = i;
            minCount++;
        }
    }

    /* random undersampling of the majority */
    Instances myDataset = new Instances(copia, 0);
    int r;
    for (int i = 0; i < size / 2; i++) {
        r = simplingRandom.nextInt(majCount);
        myDataset.add(copia.instance(majExamples[r]));

        if (minCount > 0) {
            r = simplingRandom.nextInt(minCount);
            myDataset.add(copia.instance(minExamples[r]));
        }
    }

    myDataset.randomize(simplingRandom);
    return myDataset;
}

---

From source file:Helper.CustomFilter.java

public Instances convertNumericRange(Instances structure) throws Exception {
    for (int i = 0; i < structure.numAttributes() - 1; i++) {
        if (structure.attribute(i).typeToString(structure.attribute(i)).equals("numeric")) {
            structure.sort(i);//from ww  w  .j a  v  a2  s .  c o m
            structure = toRange(structure, i);
        }
    }
    return structure;
}

---

From source file:Helper.CustomFilter.java

private Instances toRange(Instances structure, int index) throws Exception {
    Attribute attr = structure.attribute(index);
    Attribute classlabel = structure.attribute(structure.numAttributes() - 1);
    String label = structure.instance(0).stringValue(classlabel);
    double threshold = structure.instance(0).value(index);
    for (int i = 0; i < structure.numInstances(); i++) {
        if (!structure.instance(i).stringValue(classlabel).equals(label)) {
            label = structure.instance(i).stringValue(classlabel);
            threshold = structure.instance(i).value(index);
        }/* w  w  w. ja v a  2s .c om*/
        structure.instance(i).setValue(attr, threshold);
    }
    return structure;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »