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

Introduction

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

Prototype

Vector like();

Source Link

Document

Return an empty vector of the same underlying class as the receiver

Usage

From source file:Vectors.java

License:Apache License

public static Vector maybeSample(Vector original, int sampleSize) {
    if (original.getNumNondefaultElements() <= sampleSize) {
        return original;
    }//from  w w w.ja v  a 2 s.  c  o m
    Vector sample = original.like();
    Iterator<Vector.Element> sampledElements = new FixedSizeSamplingIterator<Vector.Element>(sampleSize,
            original.iterateNonZero());
    while (sampledElements.hasNext()) {
        Vector.Element elem = sampledElements.next();
        sample.setQuick(elem.index(), elem.get());
    }
    return sample;
}

---

From source file:Vectors.java

License:Apache License

public static Vector topKElements(int k, Vector original) {
    if (original.getNumNondefaultElements() <= k) {
        return original;
    }//from   w w w .  j  ava  2s  . co m
    TopK<Vector.Element> topKQueue = new TopK<Vector.Element>(k, BY_VALUE);
    Iterator<Vector.Element> nonZeroElements = original.iterateNonZero();
    while (nonZeroElements.hasNext()) {
        Vector.Element nonZeroElement = nonZeroElements.next();
        topKQueue.offer(new Vectors.TemporaryElement(nonZeroElement));
    }
    Vector topKSimilarities = original.like();
    for (Vector.Element topKSimilarity : topKQueue.retrieve()) {
        topKSimilarities.setQuick(topKSimilarity.index(), topKSimilarity.get());
    }
    return topKSimilarities;
}

---

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);
        }/*from  w w  w .  j  av a  2  s . c o m*/
        pTerm.set(term, pA);
    }
    return pTerm;
}

---

From source file:com.netease.news.classifier.naivebayes.AbstractThetaTrainer.java

License:Apache License

protected AbstractThetaTrainer(Vector weightsPerFeature, Vector weightsPerLabel, double alphaI) {
    Preconditions.checkNotNull(weightsPerFeature);
    Preconditions.checkNotNull(weightsPerLabel);
    this.weightsPerFeature = weightsPerFeature;
    this.weightsPerLabel = weightsPerLabel;
    this.alphaI = alphaI;
    perLabelThetaNormalizer = weightsPerLabel.like();
    totalWeightSum = weightsPerLabel.zSum();
    numFeatures = weightsPerFeature.getNumNondefaultElements();
}

---

From source file:mlbench.bayes.BayesUtils.java

License:Apache License

public static NaiveBayesModel readModelFromDir(Path base, Configuration conf) {

    float alphaI = conf.getFloat(ThetaMapper.ALPHA_I, 1.0f);

    // read feature sums and label sums
    Vector scoresPerLabel = null;
    Vector scoresPerFeature = null;
    for (Pair<Text, VectorWritable> record : new SequenceFileDirIterable<Text, VectorWritable>(
            new Path(base, TrainNaiveBayesJob.WEIGHTS), PathType.LIST, PathFilters.partFilter(), conf)) {
        String key = record.getFirst().toString();
        VectorWritable value = record.getSecond();
        if (key.equals(TrainNaiveBayesJob.WEIGHTS_PER_FEATURE)) {
            scoresPerFeature = value.get();
        } else if (key.equals(TrainNaiveBayesJob.WEIGHTS_PER_LABEL)) {
            scoresPerLabel = value.get();
        }/*from   w w w.  j  ava2 s  .  c o m*/
    }

    // Preconditions.checkNotNull(scoresPerFeature);
    // Preconditions.checkNotNull(scoresPerLabel);

    Matrix scoresPerLabelAndFeature = new SparseMatrix(scoresPerLabel.size(), scoresPerFeature.size());
    for (Pair<IntWritable, VectorWritable> entry : new SequenceFileDirIterable<IntWritable, VectorWritable>(
            new Path(base, TrainNaiveBayesJob.SUMMED_OBSERVATIONS), PathType.LIST, PathFilters.partFilter(),
            conf)) {
        scoresPerLabelAndFeature.assignRow(entry.getFirst().get(), entry.getSecond().get());
    }

    Vector perlabelThetaNormalizer = scoresPerLabel.like();
    /*
     * for (Pair<Text,VectorWritable> entry : new
     * SequenceFileDirIterable<Text,VectorWritable>( new Path(base,
     * TrainNaiveBayesJob.THETAS), PathType.LIST, PathFilters.partFilter(),
     * conf)) { if (entry.getFirst().toString().equals(TrainNaiveBayesJob.
     * LABEL_THETA_NORMALIZER)) { perlabelThetaNormalizer =
     * entry.getSecond().get(); } }
     * 
     * Preconditions.checkNotNull(perlabelThetaNormalizer);
     */
    return new NaiveBayesModel(scoresPerLabelAndFeature, scoresPerFeature, scoresPerLabel,
            perlabelThetaNormalizer, alphaI, false);
}

---