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

Introduction

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

Prototype

void set(int index, double value);

Source Link

Document

Set the value at the given index

Usage

From source file:com.cloudera.science.ml.parallel.fn.SvmLightFnTest.java

License:Open Source License

@Test
public void testVector() throws Exception {
    Vector v = Vectors.of(1.0, 2.0, 3.0);
    assertEquals("0:1.0 1:2.0 2:3.0", fn.map(v));

    v = Vectors.sparse(10);/*from  www . ja  va2  s  .  c om*/
    v.set(3, 7.2);
    v.set(6, 12.0);
    assertEquals("3:7.2 6:12.0", fn.map(v));
}

From source file:com.cloudera.science.ml.parallel.fn.SvmLightFnTest.java

License:Open Source License

@Test
public void testNamedVector() throws Exception {
    Vector v = Vectors.named("foo", 1.0, 2.0, 3.0);
    assertEquals("foo 0:1.0 1:2.0 2:3.0", fn.map(v));

    v = Vectors.sparse(10);// w ww  . j ava2 s  . c om
    v.set(3, 7.2);
    v.set(6, 12.0);
    v = new NamedVector(v, "bar");
    assertEquals("bar 3:7.2 6:12.0", fn.map(v));
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

private static Vector viewRowSums(Matrix m) {
    Vector v = new DenseVector(m.numRows());
    for (MatrixSlice slice : m) {
        v.set(slice.index(), slice.vector().norm(1));
    }// ww  w. j  a  v  a2s  .c o  m
    return v;
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

private static Pair<Matrix, Vector> randomMatrix(int numTopics, int numTerms, Random random) {
    Matrix topicTermCounts = new DenseMatrix(numTopics, numTerms);
    Vector topicSums = new DenseVector(numTopics);
    if (random != null) {
        for (int x = 0; x < numTopics; x++) {
            for (int term = 0; term < numTerms; term++) {
                topicTermCounts.viewRow(x).set(term, random.nextDouble());
            }//from w ww. j a v a  2s.  c om
        }
    }
    for (int x = 0; x < numTopics; x++) {
        topicSums.set(x, random == null ? 1.0 : topicTermCounts.viewRow(x).norm(1));
    }
    return Pair.of(topicTermCounts, topicSums);
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

public static Pair<Matrix, Vector> loadModel(Configuration conf, Path... modelPaths) throws IOException {
    int numTopics = -1;
    int numTerms = -1;
    List<Pair<Integer, Vector>> rows = Lists.newArrayList();
    for (Path modelPath : modelPaths) {
        for (Pair<Text, VectorWritable> row : new SequenceFileIterable<Text, VectorWritable>(modelPath, true,
                conf)) {//from w  w w. j  a v  a 2s.co  m
            rows.add(Pair.of(Integer.parseInt(row.getFirst().toString()), row.getSecond().get()));//keytext
            numTopics = Math.max(numTopics, Integer.parseInt(row.getFirst().toString()));//keytext
            if (numTerms < 0) {
                numTerms = row.getSecond().get().size();
            }
        }
    }
    if (rows.isEmpty()) {
        throw new IOException(Arrays.toString(modelPaths) + " have no vectors in it");
    }
    numTopics++;
    Matrix model = new DenseMatrix(numTopics, numTerms);
    Vector topicSums = new DenseVector(numTopics);
    for (Pair<Integer, Vector> pair : rows) {
        model.viewRow(pair.getFirst()).assign(pair.getSecond());
        topicSums.set(pair.getFirst(), pair.getSecond().norm(1));
    }
    return Pair.of(model, topicSums);
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

public void trainDocTopicModel(Vector original, Vector topics, Matrix docTopicModel) {
    // first calculate p(topic|term,document) for all terms in original, and all topics,
    // using p(term|topic) and p(topic|doc)
    pTopicGivenTerm(original, topics, docTopicModel);
    normalizeByTopic(docTopicModel);//from   w w w. j a  va2s .c  o m
    // now multiply, term-by-term, by the document, to get the weighted distribution of
    // term-topic pairs from this document.
    Iterator<Vector.Element> it = original.iterateNonZero();
    while (it.hasNext()) {
        Vector.Element e = it.next();
        for (int x = 0; x < numTopics; x++) {
            Vector docTopicModelRow = docTopicModel.viewRow(x);
            docTopicModelRow.setQuick(e.index(), docTopicModelRow.getQuick(e.index()) * e.get());
        }
    }
    // now recalculate p(topic|doc) by summing contributions from all of pTopicGivenTerm
    topics.assign(0.0);
    for (int x = 0; x < numTopics; x++) {
        topics.set(x, docTopicModel.viewRow(x).norm(1));
    }
    // now renormalize so that sum_x(p(x|doc)) = 1
    topics.assign(Functions.mult(1 / topics.norm(1)));
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

public Vector infer(Vector original, Vector docTopics) {
    Vector pTerm = original.like();
    Iterator<Vector.Element> it = original.iterateNonZero();
    while (it.hasNext()) {
        Vector.Element e = it.next();
        int term = e.index();
        // p(a) = sum_x (p(a|x) * p(x|i))
        double pA = 0;
        for (int x = 0; x < numTopics; x++) {
            pA += (topicTermCounts.viewRow(x).get(term) / topicSums.get(x)) * docTopics.get(x);
        }/*w  w  w  .j av  a 2  s.c  om*/
        pTerm.set(term, pA);
    }
    return pTerm;
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

public void update(int termId, Vector topicCounts) {
    for (int x = 0; x < numTopics; x++) {
        Vector v = topicTermCounts.viewRow(x);
        v.set(termId, v.get(termId) + topicCounts.get(x));
    }//  ww w.j  av a  2s.com
    topicSums.assign(topicCounts, Functions.PLUS);
}

From source file:com.elex.dmp.core.TopicModel.java

License:Apache License

/**
 * Computes {@code p(topic x|term a, document i)} distributions given input document {@code i}.
 * {@code pTGT[x][a]} is the (un-normalized) {@code p(x|a,i)}, or if docTopics is {@code null},
 * {@code p(a|x)} (also un-normalized)./*from  www .jav a2  s.c  om*/
 *
 * @param document doc-term vector encoding {@code w(term a|document i)}.
 * @param docTopics {@code docTopics[x]} is the overall weight of topic {@code x} in given
 *          document. If {@code null}, a topic weight of {@code 1.0} is used for all topics.
 * @param termTopicDist storage for output {@code p(x|a,i)} distributions.
 */
private void pTopicGivenTerm(Vector document, Vector docTopics, Matrix termTopicDist) {
    // for each topic x
    for (int x = 0; x < numTopics; x++) {
        // get p(topic x | document i), or 1.0 if docTopics is null
        double topicWeight = docTopics == null ? 1.0 : docTopics.get(x);
        // get w(term a | topic x)
        Vector topicTermRow = topicTermCounts.viewRow(x);
        // get \sum_a w(term a | topic x)
        double topicSum = topicSums.get(x);
        // get p(topic x | term a) distribution to update
        Vector termTopicRow = termTopicDist.viewRow(x);

        // for each term a in document i with non-zero weight
        Iterator<Vector.Element> it = document.iterateNonZero();
        while (it.hasNext()) {
            Vector.Element e = it.next();
            int termIndex = e.index();

            // calc un-normalized p(topic x | term a, document i)
            double termTopicLikelihood = (topicTermRow.get(termIndex) + eta) * (topicWeight + alpha)
                    / (topicSum + eta * numTerms);
            termTopicRow.set(termIndex, termTopicLikelihood);
        }
    }
}

From source file:com.elex.dmp.lda.TopicModel.java

License:Apache License

public static Pair<Matrix, Vector> loadModel(Configuration conf, Path... modelPaths) throws IOException {
    int numTopics = -1;
    int numTerms = -1;
    List<Pair<Integer, Vector>> rows = Lists.newArrayList();
    for (Path modelPath : modelPaths) {
        for (Pair<Text, VectorWritable> row : new SequenceFileIterable<Text, VectorWritable>(modelPath, true,
                conf)) {//from w w  w. j  a  va 2  s .  co m
            rows.add(Pair.of(Integer.parseInt(row.getFirst().toString()), row.getSecond().get()));//keytext
            numTopics = Math.max(numTopics, Integer.parseInt(row.getFirst().toString()));//keytext
            if (numTerms < 0) {
                numTerms = row.getSecond().get().size();
            }
        }
    }
    if (rows.isEmpty()) {
        throw new IOException(Arrays.toString(modelPaths) + " have no vectors in it");
    }
    numTopics++;
    Matrix model = new DenseMatrix(numTopics, numTerms);
    Vector topicSums = new DenseVector(numTopics);
    for (Pair<Integer, Vector> pair : rows) {
        model.viewRow(pair.getFirst()).assign(pair.getSecond());
        topicSums.set(pair.getFirst(), pair.getSecond().norm(1));
    }
    return Pair.of(model, topicSums);
}