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

List of usage examples for org.apache.mahout.math Vector get

  1. HOME
  2. Java
  3. org.apache.mahout
  4. org.apache.mahout.math.*
  5. Vector
  6. get

Introduction

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

Prototype

double get(int index);

Source Link

Document

Return the value at the given index

Usage

From source file:edu.indiana.d2i.htrc.io.SparseVectorUtil.java

License:Apache License

public static Vector transform2Vector(String text, String field, Analyzer analyzer, HTRCFilter filter,
        Dictionary dictionary) throws IOException {
    Vector result = new RandomAccessSparseVector(dictionary.size());

    TokenStream stream = analyzer.reusableTokenStream(field, new StringReader(text.toString()));
    CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
    stream.reset();/*w  w  w  .j av a  2  s  .  c om*/
    while (stream.incrementToken()) {
        // String term = new String(termAtt.buffer(), 0,
        // termAtt.length());
        String term = new String(termAtt.buffer(), 0, termAtt.length()).toLowerCase();
        if (filter.accept(term, 0)) {
            int index = dictionary.get(term);
            result.setQuick(index, result.get(index) + 1);
        }
    }

    return result;
}

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 w w w  .  ja v  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.
 *//*  ww  w  .  j av  a2  s.  co m*/
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.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.
     *///from   www. j  ava2s  .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.VectorSumTest.java

License:Apache License

/**
 * Add two random VectorSums with VectorSum.add(),
 * and then check if the result really is the addition of the two VectorSums.
 *///from   w w  w  .  ja  v a  2  s.  co m
@Test
public final void testAddSum() {
    final int vectorSize = (int) (Math.random() * 1000);
    final Vector vectorA = new DenseVector(vectorSize);
    for (int i = 0; i < vectorSize; i++) {
        vectorA.set(i, Math.random());
    }
    final VectorSum vectorSumA = new VectorSum(vectorA, (int) (Math.random() * 1000));

    final Vector vectorB = new DenseVector(vectorSize);
    for (int i = 0; i < vectorSize; i++) {
        vectorB.set(i, Math.random());
    }
    final VectorSum vectorSumB = new VectorSum(vectorB, (int) (Math.random() * 1000));

    final Vector expectedVector = new DenseVector(vectorSize);
    for (int i = 0; i < vectorSize; i++) {
        expectedVector.set(i, vectorA.get(i) + vectorB.get(i));
    }
    final VectorSum expectedSum = new VectorSum(expectedVector, vectorSumA.count + vectorSumB.count);

    vectorSumA.add(vectorSumB);

    assertEquals(expectedSum.sum.size(), vectorSumA.sum.size());
    for (int i = 0; i < vectorSize; i++) {
        assertEquals(expectedSum.sum.get(i), vectorSumA.sum.get(i), 0.001);
    }
    assertEquals(expectedSum.count, vectorSumA.count);
}

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

License:Apache License

/**
 * Add a random VectorSum and random Vector with VectorSum.add(),
 * and then check if the result really is the addition of the VectorSum and Vector.
 *//* w  w  w  .j a  va  2  s .com*/
@Test
public final void testAddVector() {
    final int vectorSize = (int) (Math.random() * 1000);
    final Vector vectorA = new DenseVector(vectorSize);
    for (int i = 0; i < vectorSize; i++) {
        vectorA.set(i, Math.random());
    }
    final VectorSum vectorSumA = new VectorSum(vectorA, (int) (Math.random() * 1000));

    final Vector vectorB = new DenseVector(vectorSize);
    for (int i = 0; i < vectorSize; i++) {
        vectorB.set(i, Math.random());
    }

    final Vector expectedVector = new DenseVector(vectorSize);
    for (int i = 0; i < vectorSize; i++) {
        expectedVector.set(i, vectorA.get(i) + vectorB.get(i));
    }
    final VectorSum expectedSum = new VectorSum(expectedVector, vectorSumA.count + 1);

    vectorSumA.add(vectorB);

    assertEquals(expectedSum.sum.size(), vectorSumA.sum.size());
    for (int i = 0; i < vectorSize; i++) {
        assertEquals(expectedSum.sum.get(i), vectorSumA.sum.get(i), 0.001);
    }
    assertEquals(expectedSum.count, vectorSumA.count);
}

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  w w. j a  v a  2s  .co 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.data.ClusterStats.java

License:Apache License

/**
 * Compute the covariance matrix from the statistics.
 * @return// w w  w. j a v a  2 s  . c o m
 */
public Matrix computeCovariance() {
    final Vector mean = computeMean();
    final Matrix covariance = outProdSum.clone();

    final Iterator<MatrixSlice> sliceIterator = outProdSum.iterator();
    while (sliceIterator.hasNext()) {
        final MatrixSlice slice = sliceIterator.next();
        final int row = slice.index();
        for (final Vector.Element e : slice.nonZeroes()) {
            final int col = e.index();
            final double squaredSum = e.get();
            covariance.set(row, col, squaredSum / probSum - mean.get(row) * mean.get(col));
        }
    }
    return covariance;
}

From source file:edu.snu.dolphin.bsp.examples.ml.data.EuclideanDistance.java

License:Apache License

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

    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.dolphin.bsp.examples.ml.sub.CentroidListCodec.java

License:Apache License

@Override
public 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.
     *//*from  ww w .  java2 s  . c o  m*/
    final int numClusters = list.size();
    int dimension = 0;
    if (numClusters > 0) {
        dimension = list.get(0).size();
    }

    final ByteArrayOutputStream baos = new ByteArrayOutputStream(Integer.SIZE * 2 // for dimension and the number of clusters
            + Double.SIZE * dimension * numClusters);
    try (final DataOutputStream daos = new DataOutputStream(baos)) {
        daos.writeInt(numClusters);
        daos.writeInt(dimension);
        for (final Vector centroid : list) {
            for (int i = 0; i < dimension; i++) {
                daos.writeDouble(centroid.get(i));
            }
        }
    } catch (final IOException e) {
        throw new RuntimeException(e.getCause());
    }

    return baos.toByteArray();
}