List of usage examples for org.apache.mahout.common StringTuple length
public int length()
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 w w . j a va 2 s . co m*/ } 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:edu.rosehulman.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 w w.jav a 2 s .c o m } 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); sf.reset(); 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.close(sf, true); } } 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("TFPartialVectorReducer", "emptyVectorCount").increment(1); } }