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

Introduction

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

Prototype

int getNumNondefaultElements();

Source Link

Document

Return the number of values in the recipient which are not the default value.

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 va  2  s .  c om
    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;
    }/* w ww . jav  a 2s  .  c o  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:ca.uwaterloo.cpami.mahout.matrix.utils.GramSchmidt.java

License:Apache License

public static void storeSparseColumns(Matrix mat) {
    int numCols = mat.numCols();
    int numRows = mat.numRows();
    for (int i = 0; i < numCols; i++) {
        Vector sparseVect = new RandomAccessSparseVector(numRows);
        Vector col = mat.viewColumn(i);
        Iterator<Vector.Element> itr = col.iterateNonZero();
        while (itr.hasNext()) {
            Element elem = itr.next();
            if (elem.get() != 0) {
                System.out.println(elem.get());
                sparseVect.set(elem.index(), elem.get());
            }//from w  w  w  .jav  a  2  s . c o m
        }
        System.out.println(sparseVect.getNumNondefaultElements());

        mat.assignColumn(i, sparseVect);
        System.out.println(mat.viewColumn(i).getNumNondefaultElements());
        System.exit(1);

    }
}

---

From source file:com.chimpler.example.eigenface.Helper.java

License:Apache License

public static double[][] readMatrixSequenceFile(String fileName) throws Exception {
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(configuration);
    Reader matrixReader = new SequenceFile.Reader(fs, new Path(fileName), configuration);

    List<double[]> rows = new ArrayList<double[]>();
    IntWritable key = new IntWritable();
    VectorWritable value = new VectorWritable();
    while (matrixReader.next(key, value)) {
        Vector vector = value.get();
        double[] row = new double[vector.size()];
        for (int i = 0; i < vector.getNumNondefaultElements(); i++) {
            Element element = vector.getElement(i);
            row[element.index()] = element.get();
        }//from  w  ww.j  a  v  a2  s  .c o  m
        rows.add(row);
    }
    return rows.toArray(new double[rows.size()][]);
}

---

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

License:Apache License

public static String vectorToSortedString(Vector vector, String[] dictionary) {
    List<Pair<String, Double>> vectorValues = new ArrayList<Pair<String, Double>>(
            vector.getNumNondefaultElements());
    Iterator<Vector.Element> it = vector.iterateNonZero();
    while (it.hasNext()) {
        Vector.Element e = it.next();
        vectorValues/*ww  w . jav  a2s .  c  om*/
                .add(Pair.of(dictionary != null ? dictionary[e.index()] : String.valueOf(e.index()), e.get()));
    }
    Collections.sort(vectorValues, new Comparator<Pair<String, Double>>() {
        @Override
        public int compare(Pair<String, Double> x, Pair<String, Double> y) {
            return y.getSecond().compareTo(x.getSecond());
        }
    });
    Iterator<Pair<String, Double>> listIt = vectorValues.iterator();
    StringBuilder bldr = new StringBuilder(2048);
    bldr.append('{');
    int i = 0;
    while (listIt.hasNext() && i < 25) {
        i++;
        Pair<String, Double> p = listIt.next();
        bldr.append(p.getFirst());
        bldr.append(':');
        bldr.append(p.getSecond());
        bldr.append(',');
    }
    if (bldr.length() > 1) {
        bldr.setCharAt(bldr.length() - 1, '}');
    }
    return bldr.toString();
}

---

From source file:com.elex.dmp.lda.InMemoryCollapsedVariationalBayes0.java

License:Apache License

private void postInitCorpus() {
    totalCorpusWeight = 0;//from  w  w  w.j  a v a 2 s. co  m
    int numNonZero = 0;
    for (int i = 0; i < numDocuments; i++) {
        Vector v = corpusWeights.viewRow(i);
        double norm;
        if (v != null && (norm = v.norm(1)) != 0) {
            numNonZero += v.getNumNondefaultElements();
            totalCorpusWeight += norm;
        }
    }
    String s = "Initializing corpus with %d docs, %d terms, %d nonzero entries, total termWeight %f";
    log.info(String.format(s, numDocuments, numTerms, numNonZero, totalCorpusWeight));
}

---

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

License:Apache License

public void train(VectorIterable matrix, VectorIterable docTopicCounts, int numDocTopicIters) {
    start();//from w w w .  j  av  a 2 s .c o m
    Iterator<MatrixSlice> docIterator = matrix.iterator();
    Iterator<MatrixSlice> docTopicIterator = docTopicCounts.iterator();
    long startTime = System.nanoTime();
    int i = 0;
    double[] times = new double[100];
    Map<Vector, Vector> batch = Maps.newHashMap();
    int numTokensInBatch = 0;
    long batchStart = System.nanoTime();
    while (docIterator.hasNext() && docTopicIterator.hasNext()) {
        i++;
        Vector document = docIterator.next().vector();
        Vector topicDist = docTopicIterator.next().vector();
        if (isReadWrite) {
            if (batch.size() < numTrainThreads) {
                batch.put(document, topicDist);
                if (log.isDebugEnabled()) {
                    numTokensInBatch += document.getNumNondefaultElements();
                }
            } else {
                batchTrain(batch, true, numDocTopicIters);
                long time = System.nanoTime();
                log.debug("trained {} docs with {} tokens, start time {}, end time {}",
                        new Object[] { numTrainThreads, numTokensInBatch, batchStart, time });
                batchStart = time;
                numTokensInBatch = 0;
            }
        } else {
            long start = System.nanoTime();
            train(document, topicDist, true, numDocTopicIters);
            if (log.isDebugEnabled()) {
                times[i % times.length] = (System.nanoTime() - start)
                        / (1.0e6 * document.getNumNondefaultElements());
                if (i % 100 == 0) {
                    long time = System.nanoTime() - startTime;
                    log.debug("trained " + i + " documents in " + (time / 1.0e6) + "ms");
                    if (i % 500 == 0) {
                        Arrays.sort(times);
                        log.debug("training took median " + times[times.length / 2] + "ms per token-instance");
                    }
                }
            }
        }
    }
    stop();
}

---

From source file:com.elex.dmp.vectorizer.TFPartialVectorReducer.java

License:Apache License

@Override
protected void reduce(Text key, Iterable<StringTuple> values, Context context)
        throws IOException, InterruptedException {
    Iterator<StringTuple> it = values.iterator();
    if (!it.hasNext()) {
        return;/*from w ww .j av  a2  s. com*/
    }
    StringTuple value = it.next();

    Vector vector = new RandomAccessSparseVector(dimension, value.length()); // guess at initial size

    if (maxNGramSize >= 2) {
        ShingleFilter sf = new ShingleFilter(new IteratorTokenStream(value.getEntries().iterator()),
                maxNGramSize);
        try {
            do {
                String term = sf.getAttribute(CharTermAttribute.class).toString();
                if (!term.isEmpty() && dictionary.containsKey(term)) { // ngram
                    int termId = dictionary.get(term);
                    vector.setQuick(termId, vector.getQuick(termId) + 1);
                }
            } while (sf.incrementToken());

            sf.end();
        } finally {
            Closeables.closeQuietly(sf);
        }
    } else {
        for (String term : value.getEntries()) {
            if (!term.isEmpty() && dictionary.containsKey(term)) { // unigram
                int termId = dictionary.get(term);
                vector.setQuick(termId, vector.getQuick(termId) + 1);
            }
        }
    }
    if (sequentialAccess) {
        vector = new SequentialAccessSparseVector(vector);
    }

    if (namedVector) {
        vector = new NamedVector(vector, key.toString());
    }

    // if the vector has no nonZero entries (nothing in the dictionary), let's not waste space sending it to disk.
    if (vector.getNumNondefaultElements() > 0) {
        VectorWritable vectorWritable = new VectorWritable(vector);
        context.write(key, vectorWritable);
    } else {
        context.getCounter("TFParticalVectorReducer", "emptyVectorCount").increment(1);
    }
}

---

From source file:com.innometrics.integration.app.recommender.ml.als.AlternatingLeastSquaresSolver.java

License:Apache License

public static Vector solve(Iterable<Vector> featureVectors, Vector ratingVector, double lambda,
        int numFeatures) {

    Preconditions.checkNotNull(featureVectors, "Feature Vectors cannot be null");
    Preconditions.checkArgument(!Iterables.isEmpty(featureVectors));
    Preconditions.checkNotNull(ratingVector, "Rating Vector cannot be null");
    Preconditions.checkArgument(ratingVector.getNumNondefaultElements() > 0, "Rating Vector cannot be empty");
    Preconditions.checkArgument(Iterables.size(featureVectors) == ratingVector.getNumNondefaultElements());

    int nui = ratingVector.getNumNondefaultElements();

    Matrix MiIi = createMiIi(featureVectors, numFeatures);
    Matrix RiIiMaybeTransposed = createRiIiMaybeTransposed(ratingVector);

    /* compute Ai = MiIi * t(MiIi) + lambda * nui * E */
    Matrix Ai = miTimesMiTransposePlusLambdaTimesNuiTimesE(MiIi, lambda, nui);
    /* compute Vi = MiIi * t(R(i,Ii)) */
    Matrix Vi = MiIi.times(RiIiMaybeTransposed);
    /* compute Ai * ui = Vi */
    return solve(Ai, Vi);
}

---

From source file:com.innometrics.integration.app.recommender.ml.als.AlternatingLeastSquaresSolver.java

License:Apache License

static Matrix createRiIiMaybeTransposed(Vector ratingVector) {
    Preconditions.checkArgument(ratingVector.isSequentialAccess(),
            "Ratings should be iterable in Index or Sequential Order");

    double[][] RiIiMaybeTransposed = new double[ratingVector.getNumNondefaultElements()][1];
    int index = 0;
    for (Vector.Element elem : ratingVector.nonZeroes()) {
        RiIiMaybeTransposed[index++][0] = elem.get();
    }//  ww  w. j  a  v a 2  s  . co m
    return new DenseMatrix(RiIiMaybeTransposed, true);
}

---

• «
• 1
• 2
• 3
• 4
• »