List of usage examples for org.apache.mahout.math Vector getNumNondefaultElements
int getNumNondefaultElements();
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;// ww w . jav a 2s . 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
private Vector maybePruneUserVector(Vector userVector) { if (userVector.getNumNondefaultElements() <= maxPrefsPerUserConsidered) { return userVector; }/*from w w w. j a va2s.c o m*/ float smallestLargeValue = findSmallestLargeValue(userVector); // "Blank out" small-sized prefs to reduce the amount of partial products // generated later. They're not zeroed, but NaN-ed, so they come through // and can be used to exclude these items from prefs. for (Element e : userVector.nonZeroes()) { float absValue = Math.abs((float) e.get()); if (absValue < smallestLargeValue) { e.set(Float.NaN); } } return userVector; }
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 ww .ja 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); }