Package org.apache.mahout.math

Examples of org.apache.mahout.math.NamedVector


        termInfo,weight);
   
    i = 0;
    for (Vector vector : iterable) {
      assertNotNull(vector);
      NamedVector namedVector;
      if (vector instanceof NamedVector) {
        // rename it for testing purposes
        namedVector = new NamedVector(((NamedVector) vector).getDelegate(),
            "P(" + i + ')');
       
      } else {
        namedVector = new NamedVector(vector, "P(" + i + ')');
      }
      System.out.println(AbstractCluster.formatVector(namedVector,
          termDictionary));
      sampleData.add(new VectorWritable(namedVector));
      i++;
View Full Code Here


  }
 
  @Test
  public void testDirichlet2() throws Exception {
    Path output = getTestTempDirPath("output");
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    DistributionDescription description = new DistributionDescription(
        GaussianClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(), null, prototype.getDelegate()
            .size());
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output,
        description, 15, 10, 1.0, true, true, 0, true);
    // run ClusterDumper
View Full Code Here

  }
 
  @Test
  public void testDirichlet3() throws Exception {
    Path output = getTestTempDirPath("output");
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(),
        ManhattanDistanceMeasure.class.getName(), prototype.getDelegate()
            .size());
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output,
        description, 15, 10, 1.0, true, true, 0, true);
    // run ClusterDumper
View Full Code Here

    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);
View Full Code Here

     Mapper<WritableComparable<?>, VectorWritable, Text, VectorWritable>.Context context =
            EasyMock.createMock(Mapper.Context.class);
    Vector expectVec = new DenseVector(new double[]{Math.sqrt(2.0), 1.0});
    context.write(new Text("other"), new VectorWritable(expectVec));
    EasyMock.replay(context);
    Vector vector = new NamedVector(new RandomAccessSparseVector(2), "other");
    vector.set(0, 2);
    vector.set(1, 2);

    VectorDistanceInvertedMapper mapper = new VectorDistanceInvertedMapper();
    setField(mapper, "measure", new EuclideanDistanceMeasure());
    Collection<NamedVector> seedVectors = Lists.newArrayList();
    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);
View Full Code Here

        SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
        LongWritable key = new LongWritable();
        VectorWritable value = new VectorWritable();
        while (reader.next(key, value)) {
            NamedVector namedVector = (NamedVector) value.get();
            RandomAccessSparseVector vect = (RandomAccessSparseVector) namedVector.getDelegate();

            for (Element e : vect) {
                if (e.get() > 0) {
                    //System.out.println("Token: " + e.index() + ", TF-IDF weight: " + e.get());
                    System.out.println(dict.get(e.index()) + "," + e.get());
View Full Code Here

  values[3488] = 1.30227;
  values[4417] = 2.51266;
  values[4418] = 2.60221;
  Vector delegate = new SequentialAccessSparseVector(CARDINALITY);
  delegate.assign(values);
  return new NamedVector(delegate, DOCUMENT_LABEL);
    }
View Full Code Here

  List<Pair<Text, VectorWritable>> outputs = reduceDriver.run();
  assertThat(outputs.size(), is(1));
  Pair<Text, VectorWritable> output = outputs.get(0);
  String docName = output.getFirst().toString();
  NamedVector nv = (NamedVector) output.getSecond().get();
  assertThat("data/sieve/corpus6/spam/39135.txt.gz", is(docName));
  assertThat(nv.getName(), is("1"));
    }
View Full Code Here

        values[1474] = 0.03848;
        values[570] = 0.74978;
        values[3281] = 1.11081;
        Vector delegate = new SequentialAccessSparseVector(CARDINALITY);
        delegate.assign(values);
        return new NamedVector(delegate, DOC_LABEL);
    }
View Full Code Here

        mapDriver = MapDriver.newMapDriver(mapper);
    }

    @Test
    public void testMap() {
        NamedVector expected = createExpectedNamedVector();
        when(bnsCorpusLineParser.parseFields(anyString())).thenReturn(expected);

        mapDriver.withInput(ONE, new Text(SAMPLE_LINE));
        mapDriver.withOutput(ONE, new VectorWritable(expected));
        mapDriver.runTest();
View Full Code Here

TOP

Related Classes of org.apache.mahout.math.NamedVector

Copyright © 2018 www.massapicom. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.