Example usage for org.apache.mahout.math VarLongWritable get

List of usage examples for org.apache.mahout.math VarLongWritable get

  1. HOME
  2. Java
  3. org.apache.mahout
  4. org.apache.mahout.math.*
  5. VarLongWritable
  6. get

Introduction

In this page you can find the example usage for org.apache.mahout.math VarLongWritable get.

Prototype

public long get()

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);
    ///*from   w w w . java2s  .  c  om*/
    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:nl.gridline.zieook.inx.movielens.hbase.UserRecommendationsStoreMap.java

License:Apache License

protected void map(VarLongWritable key, RecommendedItemsWritable value, Context context)
        throws IOException, InterruptedException {
    // <UserId, [item,value]>
    // the in the recommendations are already sorted! - this makes writing them easy

    List<RecommendedItem> recommendations = value.getRecommendedItems();
    int rank = 1;
    Put put = new Put(RowKeys.getRecommendationKey(collection, recommender, key.get()));
    for (RecommendedItem el : recommendations) {
        byte[] data = nl.gridline.zieook.model.Recommend.getRecommendation(el.getItemID(), rank, el.getValue());
        put.add(RECOMMENDATION_COLUMN, Bytes.toBytes(rank), data);
        rank++;/*from   www. j a v  a2  s .c  o m*/
    }
    context.write(new LongWritable(key.get()), put);

}

From source file:nl.gridline.zieook.inx.movielens.UserVectorSplitterMapper.java

License:Apache License

@Override
protected void map(VarLongWritable key, VectorWritable value, Context context)
        throws IOException, InterruptedException {
    long userID = key.get();
    if (usersToRecommendFor != null && !usersToRecommendFor.contains(userID)) {
        return;/*from  ww w.j ava 2 s  .c o  m*/
    }
    Vector userVector = maybePruneUserVector(value.get());
    Iterator<Vector.Element> it = userVector.iterateNonZero();
    VarIntWritable itemIndexWritable = new VarIntWritable();
    VectorOrPrefWritable vectorOrPref = new VectorOrPrefWritable();
    while (it.hasNext()) {
        Vector.Element e = it.next();
        itemIndexWritable.set(e.index());
        vectorOrPref.set(userID, (float) e.get());
        context.write(itemIndexWritable, vectorOrPref);
    }
}

From source file:org.gpfvic.mahout.cf.taste.hadoop.item.AggregateAndRecommendReducer.java

License:Apache License

/**
 * find the top entries in recommendationVector, map them to the real itemIDs and write back the result
 *//*from  w  w  w. j  a va 2  s  .c o  m*/
private void writeRecommendedItems(VarLongWritable userID, Vector recommendationVector, Context context)
        throws IOException, InterruptedException {
    TopItemsQueue topKItems = new TopItemsQueue(recommendationsPerUser);
    FastIDSet itemsForUser = null;

    if (idReader != null && idReader.isUserItemFilterSpecified()) {
        itemsForUser = idReader.getItemsToRecommendForUser(userID.get());
    }

    for (Element element : recommendationVector.nonZeroes()) {
        int index = element.index();
        long itemID;
        if (indexItemIDMap != null && !indexItemIDMap.isEmpty()) {
            itemID = indexItemIDMap.get(index);
        } else { // we don't have any mappings, so just use the original
            itemID = index;
        }

        if (shouldIncludeItemIntoRecommendations(itemID, itemsToRecommendFor, itemsForUser)) {

            float value = (float) element.get();
            if (!Float.isNaN(value)) {

                MutableRecommendedItem topItem = topKItems.top();
                if (value > topItem.getValue()) {
                    topItem.set(itemID, value);
                    topKItems.updateTop();
                }
            }
        }
    }

    List<RecommendedItem> topItems = topKItems.getTopItems();
    if (!topItems.isEmpty()) {
        recommendedItems.set(topItems);
        context.write(userID, recommendedItems);
    }
}

From source file:org.gpfvic.mahout.cf.taste.hadoop.item.ItemFilterAsVectorAndPrefsReducer.java

License:Apache License

@Override
protected void reduce(VarLongWritable itemID, Iterable<VarLongWritable> values, Context ctx)
        throws IOException, InterruptedException {

    int itemIDIndex = TasteHadoopUtils.idToIndex(itemID.get());
    Vector vector = new RandomAccessSparseVector(Integer.MAX_VALUE, 1);
    /* artificial NaN summand to exclude this item from the recommendations for all users specified in userIDs */
    vector.set(itemIDIndex, Double.NaN);

    List<Long> userIDs = new ArrayList<>();
    List<Float> prefValues = new ArrayList<>();
    for (VarLongWritable userID : values) {
        userIDs.add(userID.get());//  ww  w . java2s . c o  m
        prefValues.add(1.0f);
    }

    itemIDIndexWritable.set(itemIDIndex);
    vectorAndPrefs.set(vector, userIDs, prefValues);
    ctx.write(itemIDIndexWritable, vectorAndPrefs);
}

From source file:org.gpfvic.mahout.cf.taste.hadoop.item.ItemIDIndexReducer.java

License:Apache License

@Override
protected void reduce(VarIntWritable index, Iterable<VarLongWritable> possibleItemIDs, Context context)
        throws IOException, InterruptedException {
    long minimumItemID = Long.MAX_VALUE;
    for (VarLongWritable varLongWritable : possibleItemIDs) {
        long itemID = varLongWritable.get();
        if (itemID < minimumItemID) {
            minimumItemID = itemID;//from  w w w .j  a  va  2s . c o m
        }
    }
    if (minimumItemID != Long.MAX_VALUE) {
        minimumItemIDWritable.set(minimumItemID);
        context.write(index, minimumItemIDWritable);
    }
}

From source file:org.gpfvic.mahout.cf.taste.hadoop.item.ToUserVectorsReducer.java

License:Apache License

@Override
protected void reduce(VarLongWritable userID, Iterable<VarLongWritable> itemPrefs, Context context)
        throws IOException, InterruptedException {
    Vector userVector = new RandomAccessSparseVector(Integer.MAX_VALUE, 100);
    for (VarLongWritable itemPref : itemPrefs) {
        int index = TasteHadoopUtils.idToIndex(itemPref.get());
        float value = itemPref instanceof EntityPrefWritable ? ((EntityPrefWritable) itemPref).getPrefValue()
                : 1.0f;/*w  w w  .  j  a  v a  2  s  .c  o m*/
        userVector.set(index, value);
    }

    if (userVector.getNumNondefaultElements() >= minPreferences) {
        userVectorWritable.set(userVector);
        userVectorWritable.setWritesLaxPrecision(true);
        context.getCounter(Counters.USERS).increment(1);
        context.write(userID, userVectorWritable);
    }
}

From source file:org.gpfvic.mahout.cf.taste.hadoop.item.UserVectorSplitterMapper.java

License:Apache License

@Override
protected void map(VarLongWritable key, VectorWritable value, Context context)
        throws IOException, InterruptedException {
    long userID = key.get();

    log.info("UserID = {}", userID);

    if (usersToRecommendFor != null && !usersToRecommendFor.contains(userID)) {
        return;/*from   w  ww .  j a va 2s  .c  o m*/
    }
    Vector userVector = maybePruneUserVector(value.get());

    for (Element e : userVector.nonZeroes()) {
        itemIndexWritable.set(e.index());
        vectorOrPref.set(userID, (float) e.get());
        context.write(itemIndexWritable, vectorOrPref);
    }
}

From source file:org.gpfvic.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 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());//w  ww .  j  ava  2  s  .co m
        itemVector.setQuick(column, elem.get());
        itemVectorWritable.set(itemVector);
        ctx.write(itemID, itemVectorWritable);
        // reset vector for reuse
        itemVector.setQuick(elem.index(), 0.0);
    }
}

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());//w w w  .ja v  a 2  s .com
        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);
}