Example usage for org.apache.mahout.math.hadoop.similarity.cooccurrence Vectors maybeSample

Introduction

In this page you can find the example usage for org.apache.mahout.math.hadoop.similarity.cooccurrence Vectors maybeSample.

Prototype

public static Vector maybeSample(Vector original, int sampleSize) 

Source Link

Usage

From source file:com.pocketx.gravity.recommender.cf.similarity.mapreduce.ToItemVectorsMapper.java

License:Apache License

@Override
protected void map(VarLongWritable rowIndex, VectorWritable vectorWritable, Context ctx)
        throws IOException, InterruptedException {
    Vector userRatings = vectorWritable.get();

    int numElementsBeforeSampling = userRatings.getNumNondefaultElements();
    userRatings = Vectors.maybeSample(userRatings, sampleSize);
    int numElementsAfterSampling = userRatings.getNumNondefaultElements();

    int column = TasteHadoopUtils.idToIndex(rowIndex.get());
    VectorWritable itemVector = new VectorWritable(new RandomAccessSparseVector(Integer.MAX_VALUE, 1));
    itemVector.setWritesLaxPrecision(true);
    ////ww w . j  a v  a  2 s .c o  m
    Iterator<Vector.Element> iterator = userRatings.nonZeroes().iterator();
    //
    while (iterator.hasNext()) {
        Vector.Element elem = iterator.next();
        itemVector.get().setQuick(column, elem.get());
        ctx.write(new IntWritable(elem.index()), itemVector);
    }

    ctx.getCounter(Elements.USER_RATINGS_USED).increment(numElementsAfterSampling);
    ctx.getCounter(Elements.USER_RATINGS_NEGLECTED)
            .increment(numElementsBeforeSampling - numElementsAfterSampling);
}

---

From source file:org.hf.mls.mahout.cf.taste.hadoop.preparation.ToItemVectorsMapper.java

License:Apache License

@Override
protected void map(VarLongWritable rowIndex, VectorWritable vectorWritable, Context ctx)
        throws IOException, InterruptedException {
    Vector userRatings = vectorWritable.get();

    int numElementsBeforeSampling = userRatings.getNumNondefaultElements();
    userRatings = Vectors.maybeSample(userRatings, sampleSize);
    int numElementsAfterSampling = userRatings.getNumNondefaultElements();

    int column = TasteHadoopUtils.idToIndex(rowIndex.get());

    itemVectorWritable.setWritesLaxPrecision(true);

    Vector itemVector = new RandomAccessSparseVector(Integer.MAX_VALUE, 1);
    for (Vector.Element elem : userRatings.nonZeroes()) {
        itemID.set(elem.index());//from   www.j  a v a2  s.  c  o  m
        itemVector.setQuick(column, elem.get());
        itemVectorWritable.set(itemVector);
        ctx.write(itemID, itemVectorWritable);
        // reset vector for reuse
        itemVector.setQuick(elem.index(), 0.0);
    }

    ctx.getCounter(Elements.USER_RATINGS_USED).increment(numElementsAfterSampling);
    ctx.getCounter(Elements.USER_RATINGS_NEGLECTED)
            .increment(numElementsBeforeSampling - numElementsAfterSampling);
}

---