@Override
protected void map(Text key, Text value, Context context)
throws IOException, InterruptedException {
StringTuple tuple = new StringTuple(key.toString());
tuple.add(value.toString());
context.write(tuple, ONE);
}
/**
* Parallel Classification
*
* @param key The label
* @param value the features (all unique) associated w/ this label
* @param output The OutputCollector to write the results to
* @param reporter Reports status back to hadoop
*/
@Override
public void map(
Text key, Text value, OutputCollector<StringTuple, DoubleWritable> output, Reporter reporter)
throws IOException {
List<String> ngrams = new NGrams(value.toString(), gramSize).generateNGramsWithoutLabel();
try {
ClassifierResult result =
classifier.classifyDocument(ngrams.toArray(new String[ngrams.size()]), defaultCategory);
String correctLabel = key.toString();
String classifiedLabel = result.getLabel();
StringTuple outputTuple = new StringTuple(BayesConstants.CLASSIFIER_TUPLE);
outputTuple.add(correctLabel);
outputTuple.add(classifiedLabel);
output.collect(outputTuple, ONE);
} catch (InvalidDatastoreException e) {
throw new IOException(e);
}
}
@Test
public void testVectorDistanceMapper() throws Exception {
Mapper<WritableComparable<?>, VectorWritable, StringTuple, DoubleWritable>.Context context =
EasyMock.createMock(Mapper.Context.class);
StringTuple tuple;
tuple = new StringTuple();
tuple.add("foo");
tuple.add("123");
context.write(tuple, new DoubleWritable(Math.sqrt(2.0)));
tuple = new StringTuple();
tuple.add("foo2");
tuple.add("123");
context.write(tuple, new DoubleWritable(1));
EasyMock.replay(context);
Vector vector = new RandomAccessSparseVector(2);
vector.set(0, 2);
vector.set(1, 2);
VectorDistanceMapper mapper = new VectorDistanceMapper();
setField(mapper, "measure", new EuclideanDistanceMeasure());
List<NamedVector> seedVectors = new ArrayList<NamedVector>();
Vector seed1 = new RandomAccessSparseVector(2);
seed1.set(0, 1);
seed1.set(1, 1);
Vector seed2 = new RandomAccessSparseVector(2);
seed2.set(0, 2);
seed2.set(1, 1);
seedVectors.add(new NamedVector(seed1, "foo"));
seedVectors.add(new NamedVector(seed2, "foo2"));
setField(mapper, "seedVectors", seedVectors);
mapper.map(new IntWritable(123), new VectorWritable(vector), context);
EasyMock.verify(context);
}
