Example usage for org.apache.mahout.math Vector size

Introduction

In this page you can find the example usage for org.apache.mahout.math Vector size.

Prototype

int size();

Source Link

Document

Return the cardinality of the recipient (the maximum number of values)

Usage

From source file:edu.snu.cms.reef.ml.kmeans.CentroidListCodecTest.java

License:Apache License

@Before
public final void setUp() {
    for (int j = 0; j < (int) (Math.random() * 1000); j++) {
        final Vector vector = new DenseVector((int) (Math.random() * 1000));
        for (int i = 0; i < vector.size(); i++) {
            vector.set(i, Math.random());
        }//from  w ww  .ja  va2 s .com
        final Centroid centroid = new Centroid((int) (Math.random() * 1000000), vector);
        list.add(centroid);
    }
}

From source file:edu.snu.cms.reef.ml.kmeans.data.Centroid.java

License:Apache License

/**
 * A copy constructor that creates a deep copy of a centroid.
 *
 * The newly created KMeansCentroid does not reference
 * anything from the original KMeansCentroid.
 *///from w w  w  .  j  a  v  a2 s  . com
public Centroid(final Centroid centroid) {
    this.clusterId = centroid.clusterId;
    final Vector vector = new DenseVector(centroid.vector.size());
    for (int i = 0; i < vector.size(); i++) {
        vector.set(i, centroid.vector.get(i));
    }
    this.vector = vector;
}

From source file:edu.snu.cms.reef.ml.kmeans.data.EuclideanDistance.java

License:Apache License

@Override
public final double distance(Vector v1, Vector v2) {
    if (v1.size() != v2.size()) {
        throw new IllegalArgumentException("Vector dimensions are not consistent");
    }/*from   ww w .j av  a 2s  . co  m*/

    double distance = 0;
    for (int i = 0; i < v1.size(); i++) {
        distance += (v1.get(i) - v2.get(i)) * (v1.get(i) - v2.get(i));
    }
    return Math.sqrt(distance);
}

From source file:edu.snu.cms.reef.ml.kmeans.data.VectorSum.java

License:Apache License

/**
 * We may select whether to create a deep copy of @member sum, or just a reference.
 *///from  w ww  .  j  a  v a 2s .  c  om
public VectorSum(final Vector sum, final int count, final boolean isDeepCopy) {
    this.count = count;
    if (isDeepCopy) {
        final Vector newSum = new DenseVector(sum.size());
        for (int i = 0; i < newSum.size(); i++) {
            newSum.set(i, sum.get(i));
        }
        this.sum = newSum;
    } else {
        this.sum = sum;
    }
}

From source file:edu.snu.cms.reef.ml.kmeans.data.VectorSum.java

License:Apache License

public final Vector computeVectorMean() {
    final Vector mean = new DenseVector(sum.size());
    for (int i = 0; i < mean.size(); i++) {
        mean.set(i, sum.get(i) / count);
    }/*w ww .  j  a  va 2s .  com*/
    return mean;
}

From source file:edu.snu.cms.reef.ml.kmeans.groupcomm.subs.VectorListCodec.java

License:Apache License

@Override
public final byte[] encode(final List<Vector> list) {

    /* This codec does not assume consistent centroid vector sizes(dimensions).
     * Therefore to specify the initial data size,
     * a quick iteration over the input list to compute
     * the sums of vector sizes is required.
     */// www . j  av  a 2s . c om
    int vectorSizeSum = 0;
    for (final Vector vector : list) {
        vectorSizeSum += vector.size();
    }

    final ByteArrayOutputStream baos = new ByteArrayOutputStream(
            Integer.SIZE + Integer.SIZE * list.size() + Double.SIZE * vectorSizeSum);
    try (final DataOutputStream daos = new DataOutputStream(baos)) {
        daos.writeInt(list.size());

        for (final Vector vector : list) {
            daos.writeInt(vector.size());

            for (int i = 0; i < vector.size(); i++) {
                daos.writeDouble(vector.get(i));
            }
        }
    } catch (final IOException e) {
        throw new RuntimeException(e.getCause());
    }

    return baos.toByteArray();
}

From source file:edu.snu.cms.reef.ml.kmeans.groupcomm.subs.VectorListCodec.java

License:Apache License

public final List<Vector> decode(final byte[] data) {
    final ByteArrayInputStream bais = new ByteArrayInputStream(data);
    final List<Vector> resultList = new ArrayList<>();

    try (final DataInputStream dais = new DataInputStream(bais)) {
        final int listSize = dais.readInt();

        for (int i = 0; i < listSize; i++) {
            final Vector vector = new DenseVector(dais.readInt());

            for (int j = 0; j < vector.size(); j++) {
                vector.set(j, dais.readDouble());
            }/* ww  w  .  ja  v  a2 s  .  c o  m*/
            resultList.add(vector);
        }

    } catch (final IOException e) {
        throw new RuntimeException(e.getCause());
    }

    return resultList;
}

From source file:edu.snu.cms.reef.ml.kmeans.MapOfIntVSumCodecTest.java

License:Apache License

@Before
public final void setUp() throws Exception {
    for (int i = 0; i < 1000; i++) {
        final Vector vector = new DenseVector((int) (Math.random() * 1000));
        for (int j = 0; j < vector.size(); j++) {
            vector.set(j, Math.random());
        }/*  w  ww  . ja va 2s .  c  o  m*/

        map.put(i, new VectorSum(vector, (int) (Math.random() * 1000)));
    }
}

From source file:edu.snu.dolphin.bsp.examples.ml.algorithms.clustering.em.EMMainCmpTask.java

License:Apache License

@Override
public void run(final int iteration) {
    clusterToStats = new HashMap<>();
    final int numClusters = clusterSummaries.size();

    // Compute the partial statistics of each cluster
    for (final Vector vector : points) {
        final int dimension = vector.size();
        Matrix outProd = null;/*from   w ww  . jav a2s  .c o  m*/

        if (isCovarianceDiagonal) {
            outProd = new SparseMatrix(dimension, dimension);
            for (int j = 0; j < dimension; j++) {
                outProd.set(j, j, vector.get(j) * vector.get(j));
            }
        } else {
            outProd = vector.cross(vector);
        }

        double denominator = 0;
        final double[] numerators = new double[numClusters];
        for (int i = 0; i < numClusters; i++) {
            final ClusterSummary clusterSummary = clusterSummaries.get(i);
            final Vector centroid = clusterSummary.getCentroid();
            final Matrix covariance = clusterSummary.getCovariance();
            final Double prior = clusterSummary.getPrior();

            final Vector differ = vector.minus(centroid);
            numerators[i] = prior / Math.sqrt(covariance.determinant())
                    * Math.exp(differ.dot(inverse(covariance).times(differ)) / (-2));
            denominator += numerators[i];
        }

        for (int i = 0; i < numClusters; i++) {
            final double posterior = denominator == 0 ? 1.0 / numerators.length : numerators[i] / denominator;
            if (!clusterToStats.containsKey(i)) {
                clusterToStats.put(i,
                        new ClusterStats(times(outProd, posterior), vector.times(posterior), posterior, false));
            } else {
                clusterToStats.get(i).add(
                        new ClusterStats(times(outProd, posterior), vector.times(posterior), posterior, false));
            }
        }
    }
}

From source file:edu.snu.dolphin.bsp.examples.ml.algorithms.clustering.em.EMMainCtrlTask.java

License:Apache License

/**
 * Receive initial centroids from the preprocess task.
 *///  ww w.  j  av  a2  s.  com
@Override
public void initialize() {

    // Load the initial centroids from the previous stage
    centroids = keyValueStore.get(Centroids.class);

    // Initialize cluster summaries
    final int numClusters = centroids.size();
    for (int clusterID = 0; clusterID < numClusters; clusterID++) {
        final Vector vector = centroids.get(clusterID);
        final int dimension = vector.size();
        clusterSummaries.add(new ClusterSummary(1.0, vector, DiagonalMatrix.identity(dimension)));
    }
}