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:br.com.edu.arff.ConstructArff.java

public static void main(String[] args) throws Exception {
    FastVector atts;//from w w  w.  j a  v a  2 s  .  c o m
    FastVector attsRel;
    FastVector attVals;
    FastVector attValsRel;
    Instances data;
    Instances dataRel;
    double[] vals;
    double[] valsRel;
    int i, j, cont;

    ConnectionLAK conexao = new ConnectionLAK();
    ArrayList<String> uris;
    ArrayList<String> todos_topicos;
    ArrayList<Topicos> valores;

    uris = conexao.buscaURIS();
    todos_topicos = conexao.BuscarTodosTopicos();

    atts = new FastVector();
    for (String topicos : todos_topicos) {
        atts.addElement(new Attribute(topicos));
    }

    data = new Instances("Relacao", atts, 0);

    for (String uri : uris) {
        i = 0;
        vals = new double[data.numAttributes()];
        valores = conexao.BuscarTopicos(uri);
        for (int t = 0; t < data.numAttributes(); t++) {
            for (Topicos topic : valores) {
                String comparacao = topic.getTopico();
                String atributo = data.attribute(t).name();
                if (comparacao.equals(atributo)) {
                    vals[t] = topic.getValor();
                    break;
                }
            }
        }

        data.add(new Instance(1.0, vals));
    }

    System.out.println(data);
}

---

From source file:br.com.edu.arff.LoadArff.java

public ArrayList<Cluster> carregarArff(String caminho) throws FileNotFoundException, IOException {
    BufferedReader reader = new BufferedReader(new FileReader(caminho));
    ArffReader arff = new ArffReader(reader);
    Instances data = arff.getData();
    data.setClassIndex(data.numAttributes() - 1);
    Instance inst = null;//  w  ww. jav a2  s .  co  m
    Attribute att = data.attribute("Cluster");

    ArrayList<String> uris;
    ArrayList<Cluster> lista = new ArrayList<Cluster>();

    Fuseki fuseki = new Fuseki();

    uris = fuseki.buscaURIS();

    for (int i = 0; i <= data.numInstances() - 1; i++) {
        Cluster cluster = new Cluster();
        String clusters = String.valueOf(data.get(i).stringValue(att));
        cluster.setUri(uris.get(i));
        cluster.setGrupo(clusters);
        lista.add(cluster);
    }

    //        for (Cluster c : lista) {
    //              System.out.println(c.getUri());
    //              System.out.println(c.getGrupo());
    //        } 
    return lista;
}

---

From source file:br.ufrn.ia.core.clustering.EMIaProject.java

License:Open Source License

private void EM_Init(Instances inst) throws Exception {
    int i, j, k;/*from www. ja  va 2 s  .  co m*/

    // run k means 10 times and choose best solution
    SimpleKMeans bestK = null;
    double bestSqE = Double.MAX_VALUE;
    for (i = 0; i < 10; i++) {
        SimpleKMeans sk = new SimpleKMeans();
        sk.setSeed(m_rr.nextInt());
        sk.setNumClusters(m_num_clusters);
        sk.setDisplayStdDevs(true);
        sk.buildClusterer(inst);
        if (sk.getSquaredError() < bestSqE) {
            bestSqE = sk.getSquaredError();
            bestK = sk;
        }
    }

    // initialize with best k-means solution
    m_num_clusters = bestK.numberOfClusters();
    m_weights = new double[inst.numInstances()][m_num_clusters];
    m_model = new DiscreteEstimator[m_num_clusters][m_num_attribs];
    m_modelNormal = new double[m_num_clusters][m_num_attribs][3];
    m_priors = new double[m_num_clusters];
    Instances centers = bestK.getClusterCentroids();
    Instances stdD = bestK.getClusterStandardDevs();
    double[][][] nominalCounts = bestK.getClusterNominalCounts();
    double[] clusterSizes = bestK.getClusterSizes();

    for (i = 0; i < m_num_clusters; i++) {
        Instance center = centers.instance(i);
        for (j = 0; j < m_num_attribs; j++) {
            if (inst.attribute(j).isNominal()) {
                m_model[i][j] = new DiscreteEstimator(m_theInstances.attribute(j).numValues(), true);
                for (k = 0; k < inst.attribute(j).numValues(); k++) {
                    m_model[i][j].addValue(k, nominalCounts[i][j][k]);
                }
            } else {
                double minStdD = (m_minStdDevPerAtt != null) ? m_minStdDevPerAtt[j] : m_minStdDev;
                double mean = (center.isMissing(j)) ? inst.meanOrMode(j) : center.value(j);
                m_modelNormal[i][j][0] = mean;
                double stdv = (stdD.instance(i).isMissing(j))
                        ? ((m_maxValues[j] - m_minValues[j]) / (2 * m_num_clusters))
                        : stdD.instance(i).value(j);
                if (stdv < minStdD) {
                    stdv = inst.attributeStats(j).numericStats.stdDev;
                    if (Double.isInfinite(stdv)) {
                        stdv = minStdD;
                    }
                    if (stdv < minStdD) {
                        stdv = minStdD;
                    }
                }
                if (stdv <= 0) {
                    stdv = m_minStdDev;
                }

                m_modelNormal[i][j][1] = stdv;
                m_modelNormal[i][j][2] = 1.0;
            }
        }
    }

    for (j = 0; j < m_num_clusters; j++) {
        // m_priors[j] += 1.0;
        m_priors[j] = clusterSizes[j];
    }
    Utils.normalize(m_priors);
}

---

From source file:br.ufrn.ia.core.clustering.EMIaProject.java

License:Open Source License

private void M(Instances inst) throws Exception {

    int i, j, l;//w  w  w  .ja v  a  2  s . co m

    new_estimators();

    for (i = 0; i < m_num_clusters; i++) {
        for (j = 0; j < m_num_attribs; j++) {
            for (l = 0; l < inst.numInstances(); l++) {
                Instance in = inst.instance(l);
                if (!in.isMissing(j)) {
                    if (inst.attribute(j).isNominal()) {
                        m_model[i][j].addValue(in.value(j), in.weight() * m_weights[l][i]);
                    } else {
                        m_modelNormal[i][j][0] += (in.value(j) * in.weight() * m_weights[l][i]);
                        m_modelNormal[i][j][2] += in.weight() * m_weights[l][i];
                        m_modelNormal[i][j][1] += (in.value(j) * in.value(j) * in.weight() * m_weights[l][i]);
                    }
                }
            }
        }
    }

    // calcualte mean and std deviation for numeric attributes
    for (j = 0; j < m_num_attribs; j++) {
        if (!inst.attribute(j).isNominal()) {
            for (i = 0; i < m_num_clusters; i++) {
                if (m_modelNormal[i][j][2] <= 0) {
                    m_modelNormal[i][j][1] = Double.MAX_VALUE;
                    // m_modelNormal[i][j][0] = 0;
                    m_modelNormal[i][j][0] = m_minStdDev;
                } else {

                    // variance
                    m_modelNormal[i][j][1] = (m_modelNormal[i][j][1]
                            - (m_modelNormal[i][j][0] * m_modelNormal[i][j][0] / m_modelNormal[i][j][2]))
                            / (m_modelNormal[i][j][2]);

                    if (m_modelNormal[i][j][1] < 0) {
                        m_modelNormal[i][j][1] = 0;
                    }

                    // std dev
                    double minStdD = (m_minStdDevPerAtt != null) ? m_minStdDevPerAtt[j] : m_minStdDev;

                    m_modelNormal[i][j][1] = Math.sqrt(m_modelNormal[i][j][1]);

                    if ((m_modelNormal[i][j][1] <= minStdD)) {
                        m_modelNormal[i][j][1] = inst.attributeStats(j).numericStats.stdDev;
                        if ((m_modelNormal[i][j][1] <= minStdD)) {
                            m_modelNormal[i][j][1] = minStdD;
                        }
                    }
                    if ((m_modelNormal[i][j][1] <= 0)) {
                        m_modelNormal[i][j][1] = m_minStdDev;
                    }
                    if (Double.isInfinite(m_modelNormal[i][j][1])) {
                        m_modelNormal[i][j][1] = m_minStdDev;
                    }

                    // mean
                    m_modelNormal[i][j][0] /= m_modelNormal[i][j][2];
                }
            }
        }
    }
}

---

From source file:br.ufrn.ia.core.clustering.SimpleKMeansIaProject.java

License:Open Source License

public void buildClusterer(Instances data) throws Exception {

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

    m_Iterations = 0;//www .j  a v  a 2  s . com

    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);
    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;

    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()];
    while (!converged) {
        emptyClusterCount = 0;
        m_Iterations++;
        converged = true;
        for (i = 0; i < instances.numInstances(); i++) {
            Instance toCluster = instances.instance(i);
            int newC = clusterProcessedInstance(toCluster, true);
            if (newC != clusterAssignments[i]) {
                converged = false;
            }
            clusterAssignments[i] = newC;
        }

        // 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));
        }
        for (i = 0; i < m_NumClusters; i++) {
            if (tempI[i].numInstances() == 0) {
                // empty cluster
                emptyClusterCount++;
            } else {
                moveCentroid(i, tempI[i], 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 (m_Iterations == m_MaxIterations)
            converged = true;

        if (!converged) {
            m_squaredErrors = new double[m_NumClusters];
            m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0];
        }
    }

    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();
    }
}

---

From source file:br.ufrn.ia.core.clustering.SimpleKMeansIaProject.java

License:Open Source License

protected double[] moveCentroid(int centroidIndex, Instances members, boolean updateClusterInfo) {
    double[] vals = new double[members.numAttributes()];

    // used only for Manhattan Distance
    Instances sortedMembers = null;/*ww  w . j  a va 2 s . com*/
    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 {
                sortedMembers.kthSmallestValue(j, middle + 1);
                vals[j] = sortedMembers.instance(middle).value(j);
                if (dataIsEven) {
                    sortedMembers.kthSmallestValue(j, middle + 2);
                    vals[j] = (vals[j] + sortedMembers.instance(middle + 1).value(j)) / 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 (updateClusterInfo)
        m_ClusterCentroids.add(new DenseInstance(1.0, vals));
    return vals;
}

---

From source file:c4.pkg5crossv.Preview.java

/**
 * method to write arff data into s.o.p.
 * @throws IOException /*from  w w w . j a  v  a2 s .c  o m*/
 */

public static void showData() throws IOException {

    String source = MainWindow.browsedFileLabel.getText();
    Instances data = DataLoad.loadData(source.replace("\\", "/"));
    data.setClassIndex(data.numAttributes() - 1);
    String field = "";
    for (int i = 0; i < data.numAttributes(); i++) {
        // Print the current attribute.
        System.out.print(data.attribute(i).name() + ": ");
        previewTextArea.append("\n" + data.attribute(i).name() + ": ");
        // Print the values associated with the current attribute.
        double[] values = data.attributeToDoubleArray(i);

        System.out.println(Arrays.toString(values));
        previewTextArea.append(Arrays.toString(values));
    }

}

---

From source file:cba.AprioriItemSet.java

License:Open Source License

/**
 * Converts the header info of the given set of instances into a set 
 * of item sets (singletons). The ordering of values in the header file 
 * determines the lexicographic order.//w ww .j av a  2 s.c  om
 *
 * @param instances the set of instances whose header info is to be used
 * @return a set of item sets, each containing a single item
 * @exception Exception if singletons can't be generated successfully
 */
public static FastVector singletons(Instances instances, boolean treatZeroAsMissing) throws Exception {

    FastVector setOfItemSets = new FastVector();
    ItemSet current;

    for (int i = 0; i < instances.numAttributes(); i++) {
        if (instances.attribute(i).isNumeric())
            throw new Exception("Can't handle numeric attributes!");
        int j = (treatZeroAsMissing) ? 1 : 0;
        for (; j < instances.attribute(i).numValues(); j++) {
            current = new AprioriItemSet(instances.numInstances());
            current.setTreatZeroAsMissing(treatZeroAsMissing);
            current.m_items = new int[instances.numAttributes()];
            for (int k = 0; k < instances.numAttributes(); k++)
                current.m_items[k] = -1;
            current.m_items[i] = j;
            setOfItemSets.addElement(current);
        }
    }
    return setOfItemSets;
}

---

From source file:cba.ItemSet.java

License:Open Source License

/**
 * Converts the header info of the given set of instances into a set 
 * of item sets (singletons). The ordering of values in the header file 
 * determines the lexicographic order./* ww w  .ja v a  2 s .  co  m*/
 *
 * @param instances the set of instances whose header info is to be used
 * @return a set of item sets, each containing a single item
 * @exception Exception if singletons can't be generated successfully
 */
public static FastVector singletons(Instances instances) throws Exception {

    FastVector setOfItemSets = new FastVector();
    ItemSet current;

    for (int i = 0; i < instances.numAttributes(); i++) {
        if (instances.attribute(i).isNumeric())
            throw new Exception("Can't handle numeric attributes!");
        for (int j = 0; j < instances.attribute(i).numValues(); j++) {
            current = new ItemSet(instances.numInstances());
            current.m_items = new int[instances.numAttributes()];
            for (int k = 0; k < instances.numAttributes(); k++)
                current.m_items[k] = -1;
            current.m_items[i] = j;

            setOfItemSets.addElement(current);
        }
    }
    return setOfItemSets;
}

---

From source file:cba.ItemSet.java

License:Open Source License

/**
 * Returns the contents of an item set as a string.
 *
 * @param instances contains the relevant header information
 * @return string describing the item set
 *///from w  w w  .  j a va 2s .  c om
public String toString(Instances instances) {

    StringBuffer text = new StringBuffer();

    for (int i = 0; i < instances.numAttributes(); i++)
        if (m_items[i] != -1) {
            text.append(instances.attribute(i).name() + '=');
            text.append(instances.attribute(i).value(m_items[i]) + ' ');
        }
    text.append(m_counter);
    return text.toString();
}

---

• «
• 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
• »