Example usage for org.apache.mahout.common.iterator FixedSizeSamplingIterator FixedSizeSamplingIterator

Introduction

In this page you can find the example usage for org.apache.mahout.common.iterator FixedSizeSamplingIterator FixedSizeSamplingIterator.

Prototype

public FixedSizeSamplingIterator(int size, Iterator<T> source) 

Source Link

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  . j a 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:de.tuberlin.dima.recsys.ssnmm.interactioncut.InteractionCutDataModelBuilder.java

License:Apache License

@Override
public DataModel buildDataModel(FastByIDMap<PreferenceArray> trainingData) {

    FastByIDMap<PreferenceArray> sampledTrainingData = new FastByIDMap<PreferenceArray>();

    LongPrimitiveIterator userIDs = trainingData.keySetIterator();
    while (userIDs.hasNext()) {
        long userID = userIDs.nextLong();
        PreferenceArray prefs = trainingData.get(userID);
        if (prefs.length() > maxPrefsPerUser) {
            Preference[] sampledPrefs = Iterators.toArray(
                    new FixedSizeSamplingIterator<Preference>(maxPrefsPerUser, prefs.iterator()),
                    Preference.class);
            sampledTrainingData.put(userID, new GenericUserPreferenceArray(Arrays.asList(sampledPrefs)));
        } else {/*from ww w .j av a 2s .c om*/
            sampledTrainingData.put(userID, prefs);
        }
    }

    return new GenericDataModel(sampledTrainingData);
}

---

From source file:io.ssc.relationdiscovery.KMeans.java

License:Open Source License

public KMeans(Matrix A, int k, DistanceMeasure distanceMeasure) {
    this.A = A;/*from  www. jav a  2 s.  c  o  m*/
    this.k = k;
    this.distanceMeasure = distanceMeasure;

    centroids = new Centroid[k];

    log.info("Picking {} initial centroids", k);
    Iterator<MatrixSlice> samples = new FixedSizeSamplingIterator<MatrixSlice>(k, A.iterator());
    int index = 0;
    while (samples.hasNext()) {
        centroids[index] = new Centroid(index, samples.next().vector());
        index++;
    }
}

---

From source file:org.gpfvic.mahout.cf.taste.impl.recommender.SamplingCandidateItemsStrategy.java

License:Apache License

@Override
protected FastIDSet doGetCandidateItems(long[] preferredItemIDs, DataModel dataModel, boolean includeKnownItems)
        throws TasteException {
    LongPrimitiveIterator preferredItemIDsIterator = new LongPrimitiveArrayIterator(preferredItemIDs);
    if (preferredItemIDs.length > maxItems) {
        double samplingRate = (double) maxItems / preferredItemIDs.length;
        //      log.info("preferredItemIDs.length {}, samplingRate {}", preferredItemIDs.length, samplingRate);
        preferredItemIDsIterator = new SamplingLongPrimitiveIterator(preferredItemIDsIterator, samplingRate);
    }/*from www . java  2 s. c  om*/
    FastIDSet possibleItemsIDs = new FastIDSet();
    while (preferredItemIDsIterator.hasNext()) {
        long itemID = preferredItemIDsIterator.nextLong();
        PreferenceArray prefs = dataModel.getPreferencesForItem(itemID);
        int prefsLength = prefs.length();
        if (prefsLength > maxUsersPerItem) {
            Iterator<Preference> sampledPrefs = new FixedSizeSamplingIterator<>(maxUsersPerItem,
                    prefs.iterator());
            while (sampledPrefs.hasNext()) {
                addSomeOf(possibleItemsIDs, dataModel.getItemIDsFromUser(sampledPrefs.next().getUserID()));
            }
        } else {
            for (int i = 0; i < prefsLength; i++) {
                addSomeOf(possibleItemsIDs, dataModel.getItemIDsFromUser(prefs.getUserID(i)));
            }
        }
    }
    if (!includeKnownItems) {
        possibleItemsIDs.removeAll(preferredItemIDs);
    }
    return possibleItemsIDs;
}

---