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

Introduction

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

Prototype

double norm(double power);

Source Link

Document

Return the k-norm of the vector.

Usage

From source file:org.trustedanalytics.atk.giraph.algorithms.lda.CVB0LDAComputation.java

License:Apache License

/**
 * Initialize vertex/edges, collect graph statistics and send out messages
 *
 * @param vertex of the graph/*from   w w w .ja  va2  s  .  c  o  m*/
 */
private void initialize(Vertex<LdaVertexId, LdaVertexData, LdaEdgeData> vertex) {

    // initialize vertex vector, i.e., the theta for doc and phi for word in LDA
    double[] vertexValues = new double[config.numTopics()];
    vertex.getValue().setLdaResult(new DenseVector(vertexValues));

    // initialize edge vector, i.e., the gamma in LDA
    Random rand1 = new Random(vertex.getId().seed());
    long seed1 = rand1.nextInt();
    double maxDelta = 0d;
    double sumWeights = 0d;
    for (Edge<LdaVertexId, LdaEdgeData> edge : vertex.getMutableEdges()) {
        double weight = edge.getValue().getWordCount();

        // generate the random seed for this edge
        Random rand2 = new Random(edge.getTargetVertexId().seed());
        long seed2 = rand2.nextInt();
        long seed = seed1 + seed2;
        Random rand = new Random(seed);
        double[] edgeValues = new double[config.numTopics()];
        for (int i = 0; i < config.numTopics(); i++) {
            edgeValues[i] = rand.nextDouble();
        }
        Vector vector = new DenseVector(edgeValues);
        vector = vector.normalize(1d);
        edge.getValue().setVector(vector);
        // find the max delta among all edges
        double delta = vector.norm(1d) / config.numTopics();
        if (delta > maxDelta) {
            maxDelta = delta;
        }
        // the sum of weights from all edges
        sumWeights += weight;
    }
    // update vertex value
    updateVertex(vertex);
    // aggregate max delta value
    aggregate(MAX_DELTA, new DoubleWritable(maxDelta));

    // collect graph statistics
    if (vertex.getId().isDocument()) {
        aggregate(SUM_DOC_VERTEX_COUNT, new LongWritable(1));
    } else {
        aggregate(SUM_OCCURRENCE_COUNT, new DoubleWritable(sumWeights));
        aggregate(SUM_WORD_VERTEX_COUNT, new LongWritable(1));
    }

    // send out messages
    LdaMessage newMessage = new LdaMessage(vertex.getId().copy(), vertex.getValue().getLdaResult());
    sendMessageToAllEdges(vertex, newMessage);
}

---

From source file:org.trustedanalytics.atk.giraph.algorithms.lda.GiraphLdaComputation.java

License:Apache License

/**
 * Initialize vertex/edges, collect graph statistics and send out messages
 *
 * @param vertex of the graph//from  www .  ja v  a 2s  .c  o m
 */
private void initialize(Vertex<LdaVertexId, LdaVertexData, LdaEdgeData> vertex) {

    // initialize vertex vector, i.e., the theta for doc and phi for word in LDA
    double[] vertexValues = new double[config.numTopics()];
    vertex.getValue().setLdaResult(new DenseVector(vertexValues));
    Vector updatedVector = vertex.getValue().getLdaResult().clone().assign(0d);
    // initialize edge vector, i.e., the gamma in LDA
    Random rand1 = new Random(vertex.getId().seed());
    long seed1 = rand1.nextInt();
    double maxDelta = 0d;
    double sumWeights = 0d;
    for (Edge<LdaVertexId, LdaEdgeData> edge : vertex.getMutableEdges()) {
        double weight = edge.getValue().getWordCount();

        // generate the random seed for this edge
        Random rand2 = new Random(edge.getTargetVertexId().seed());
        long seed2 = rand2.nextInt();
        long seed = seed1 + seed2;
        Random rand = new Random(seed);
        double[] edgeValues = new double[config.numTopics()];
        for (int i = 0; i < config.numTopics(); i++) {
            edgeValues[i] = rand.nextDouble();
        }
        Vector vector = new DenseVector(edgeValues);
        vector = vector.normalize(1d);
        edge.getValue().setVector(vector);
        // find the max delta among all edges
        double delta = vector.norm(1d) / config.numTopics();
        if (delta > maxDelta) {
            maxDelta = delta;
        }
        // the sum of weights from all edges
        sumWeights += weight;
        updatedVector = updateVector(updatedVector, edge);
    }
    // update vertex value
    vertex.getValue().setLdaResult(updatedVector);
    ;
    // aggregate max delta value
    aggregateWord(vertex);
    aggregate(MAX_DELTA, new DoubleWritable(maxDelta));

    // collect graph statistics
    if (vertex.getId().isDocument()) {
        aggregate(SUM_DOC_VERTEX_COUNT, new LongWritable(1));
    } else {
        aggregate(SUM_OCCURRENCE_COUNT, new DoubleWritable(sumWeights));
        aggregate(SUM_WORD_VERTEX_COUNT, new LongWritable(1));
    }

    // send out messages
    LdaMessage newMessage = new LdaMessage(vertex.getId().copy(), vertex.getValue().getLdaResult());
    sendMessageToAllEdges(vertex, newMessage);
}

---

From source file:zx.soft.mahout.knn.search.AbstractSearchTest.java

License:Apache License

@Test
public void testNearMatch() {
    List<MatrixSlice> queries = Lists.newArrayList(Iterables.limit(testData(), 100));
    Searcher s = getSearch(20);/* w w  w.  j av  a2  s . c  om*/
    s.addAllMatrixSlicesAsWeightedVectors(testData());

    MultiNormal noise = new MultiNormal(0.01, new DenseVector(20));
    for (MatrixSlice slice : queries) {
        Vector query = slice.vector();
        final Vector epsilon = noise.sample();
        //         List<WeightedThing<Vector>> r0 = s.search(query, 2);
        query = query.plus(epsilon);
        List<WeightedThing<Vector>> r = s.search(query, 2);
        r = s.search(query, 2);
        assertEquals("Distance has to be small", epsilon.norm(2), r.get(0).getWeight(), 1e-5);
        assertEquals("Answer must be substantially the same as query", epsilon.norm(2),
                r.get(0).getValue().minus(query).norm(2), 1e-5);
        assertTrue("Wrong answer must be further away", r.get(1).getWeight() > r.get(0).getWeight());
    }
}

---

• «
• 1
• 2
• »