Package org.apache.mahout.math

Examples of org.apache.mahout.math.VectorWritable

130
131
132
133
134
135
136
137
138
139
140
141
    clusters.add(new Canopy(new DenseVector(new double[] { dC, -dC }), 7, measure));
    representativePoints = new HashMap<Integer, List<VectorWritable>>();
    for (Cluster cluster : clusters) {
      List<VectorWritable> points = new ArrayList<VectorWritable>();
      representativePoints.put(cluster.getId(), points);
      points.add(new VectorWritable(cluster.getCenter().clone()));
      points.add(new VectorWritable(cluster.getCenter().plus(new DenseVector(new double[] { dP, dP }))));
      points.add(new VectorWritable(cluster.getCenter().plus(new DenseVector(new double[] { dP, -dP }))));
      points.add(new VectorWritable(cluster.getCenter().plus(new DenseVector(new double[] { -dP, -dP }))));
      points.add(new VectorWritable(cluster.getCenter().plus(new DenseVector(new double[] { -dP, dP }))));
    }
  }
View Full Code Here
154
155
156
157
158
159
160
161
162
   * @throws Exception
   */
  private void generateSamples(int num, double mx, double my, double sd) throws Exception {
    log.info("Generating {} samples m=[{}, {}] sd={}", new Object[] { num, mx, my, sd });
    for (int i = 0; i < num; i++) {
      sampleData.add(new VectorWritable(new DenseVector(new double[] { UncommonDistributions.rNorm(mx, sd),
          UncommonDistributions.rNorm(my, sd) })));
    }
  }
View Full Code Here
225
226
227
228
229
230
231
232
233
234
235
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.25, measure);
    Canopy cluster = new Canopy(new DenseVector(new double[] { 0, 0 }), 19, measure);
    clusters.add(cluster);
    List<VectorWritable> points = new ArrayList<VectorWritable>();
    points.add(new VectorWritable(cluster.getCenter().plus(new DenseVector(new double[] { 1, 1 }))));
    representativePoints.put(cluster.getId(), points);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 20.485281374238568, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.8, evaluator.intraClusterDensity(), EPSILON);
View Full Code Here
247
248
249
250
251
252
253
254
255
256
257
258
259
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.25, measure);
    Canopy cluster = new Canopy(new DenseVector(new double[] { 0, 0 }), 19, measure);
    clusters.add(cluster);
    List<VectorWritable> points = new ArrayList<VectorWritable>();
    points.add(new VectorWritable(cluster.getCenter()));
    points.add(new VectorWritable(cluster.getCenter()));
    points.add(new VectorWritable(cluster.getCenter()));
    representativePoints.put(cluster.getId(), points);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 20.485281374238568, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.8, evaluator.intraClusterDensity(), EPSILON);
View Full Code Here
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
    initData(1, 0.25, measure);
    Canopy cluster = new Canopy(new DenseVector(new double[] { 0, 0 }), 19, measure);
    clusters.add(cluster);
    List<VectorWritable> points = new ArrayList<VectorWritable>();
    Vector delta = new DenseVector(new double[] { 0, Double.MIN_NORMAL });
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    representativePoints.put(cluster.getId(), points);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 28.970562748477143, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 1.8, evaluator.intraClusterDensity(), EPSILON);
View Full Code Here
362
363
364
365
366
367
368
369
370
371
372
  }

  @Test
  public void testDirichlet() throws Exception {
    ClusteringTestUtils.writePointsToFile(sampleData, getTestTempFilePath("testdata/file1"), fs, conf);
    ModelDistribution<VectorWritable> modelDistribution = new GaussianClusterDistribution(new VectorWritable(new DenseVector(2)));
    DirichletDriver.run(testdata, output, modelDistribution, 15, 5, 1.0, true, true, 0, true);
    int numIterations = 10;
    Path clustersIn = new Path(output, "clusters-0");
    RepresentativePointsDriver.run(conf,
                                   clustersIn,
View Full Code Here
122
123
124
125
126
127
128
129
    int i = 0;
    for (Vector vector : iterable) {
      assertNotNull(vector);
      System.out.println("Vector[" + i++ + "]=" + formatVector(vector));
      sampleData.add(new VectorWritable(vector));
    }
  }
View Full Code Here
185
186
187
188
189
190
191
192
193
194
195
      System.out.println("Model[" + m + "] had " + count + " hits (!) and " + (samples.size() - count)
          + " misses (? in pdf order) during the last iteration:");
      MapElement[] map = new MapElement[samples.size()];
      // sort the samples by pdf
      for (int i = 0; i < samples.size(); i++) {
        VectorWritable sample = samples.get(i);
        map[i] = new MapElement(model.pdf(sample), docs[i]);
      }
      Arrays.sort(map);
      // now find the n=model.count() most likely docs and output them
      for (int i = 0; i < map.length; i++) {
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
      context = DummyRecordWriter.build(mapper, conf, writer);
    mapper.setup(2.0, 0.25, new DenseVector(eigenvalues), new DenseVector(diagonal));
   
    // perform the mapping
    for (int i = 0; i < eigenvectors.length; i++) {
      VectorWritable row = new VectorWritable(new DenseVector(eigenvectors[i]));
      mapper.map(new IntWritable(i), row, context);
    }
   
    // the results line up
    for (IntWritable key : writer.getKeys()) {
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
    // write the vector out
    VectorCache.save(key, value, path, conf, true, true);
   
    // can we read it from here?
    SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
    VectorWritable old = new VectorWritable();
    reader.next(key, old);
    reader.close();
   
    // test if the values are identical
    assertTrue("Saved vector is identical to original", old.get().equals(value));
  }
View Full Code Here
TOP

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

  • com.mozilla.grouperfish.mahout.clustering.display.lda.DisplayLDABase
  • com.mozilla.grouperfish.mahout.clustering.display.lda.OriginalText
  • com.mozilla.grouperfish.transforms.coclustering.pig.storage.MahoutVectorStorage
  • com.twitter.elephantbird.pig.mahout.VectorWritableConverter
  • mia.recommender.ch02.CSVToMahout
  • org.apache.mahout.benchmark.VectorBenchmarks
  • org.apache.mahout.cf.taste.hadoop.als.ALS
  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJob
  • org.apache.mahout.cf.taste.hadoop.als.VectorWithIndexWritable
  • org.apache.mahout.cf.taste.hadoop.item.PrefAndSimilarityColumnWritable
    • 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.