Package org.apache.mahout.math

Examples of org.apache.mahout.math.VectorWritable

61
62
63
64
65
66
67
68
69
70
71
  }

  @Override
  public double classifyScalar(Vector instance) {
    if (models.size() == 2) {
      double pdf0 = models.get(0).pdf(new VectorWritable(instance));
      double pdf1 = models.get(1).pdf(new VectorWritable(instance));
      return pdf0 / (pdf0 + pdf1);
    }
    throw new IllegalStateException();
  }
View Full Code Here
102
103
104
105
106
107
108
109
110
   *          double standard deviation of the samples
   */
  private void generateSamples(int num, double mx, double my, double sd) {
    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
124
125
126
127
128
129
130
131
132
133
134
135
136
      for (FileStatus file : fs.listStatus(out)) {
        if (!file.getPath().getName().startsWith(".")) {
          SequenceFile.Reader reader = new SequenceFile.Reader(fs, file.getPath(), conf);
          try {
            Writable clusterId = new IntWritable(0);
            VectorWritable point = new VectorWritable();
            while (reader.next(clusterId, point)) {
              System.out.println("\tC-" + clusterId + ": " + AbstractCluster.formatVector(point.get(), null));
            }
          } finally {
            reader.close();
          }
        }
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
163
    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
235
236
237
238
239
240
241
242
243
244
245
    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);
    ClusterEvaluator evaluator = new ClusterEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.33333333333333315, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
266
267
    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);
    ClusterEvaluator evaluator = new ClusterEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.33333333333333315, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
338
339
340
341
342
343
344
345
346
347
348
  }

  @Test
  public void testDirichlet() throws Exception {
    ClusteringTestUtils.writePointsToFile(sampleData, new Path(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;
    Configuration conf = new Configuration();
    Path clustersIn = new Path(output, "clusters-5");
    RepresentativePointsDriver.run(conf,
View Full Code Here
313
314
315
316
317
318
319
320
321
322
323
    Path input = getTestTempDirPath("testdata");
    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(input.toUri(), conf);
    Collection<VectorWritable> points = new ArrayList<VectorWritable>();
    for (Vector v : raw) {
      points.add(new VectorWritable(v));
    }
    ClusteringTestUtils.writePointsToFile(points, getTestTempFilePath("testdata/file1"), fs, conf);
    ClusteringTestUtils.writePointsToFile(points, getTestTempFilePath("testdata/file2"), fs, conf);
    // now run the Job using the run() command. Other tests can continue to use runJob().
    Path output = getTestTempDirPath("output");
View Full Code Here
350
351
352
353
354
355
356
357
358
359
360
    Path input = getTestTempDirPath("testdata");
    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(input.toUri(), conf);
    Collection<VectorWritable> points = new ArrayList<VectorWritable>();
    for (Vector v : raw) {
      points.add(new VectorWritable(v));
    }
    ClusteringTestUtils.writePointsToFile(points, getTestTempFilePath("testdata/file1"), fs, conf);
    ClusteringTestUtils.writePointsToFile(points, getTestTempFilePath("testdata/file2"), fs, conf);
    // now run the Job using the run() command. Other tests can continue to use runJob().
    Path output = getTestTempDirPath("output");
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
      for (FileStatus file : fs.listStatus(out)) {
        if (!file.getPath().getName().startsWith(".")) {
          SequenceFile.Reader reader = new SequenceFile.Reader(fs, file.getPath(), conf);
          try {
            Writable clusterId = new IntWritable(0);
            VectorWritable point = new VectorWritable();
            while (reader.next(clusterId, point)) {
              System.out.println("\tC-" + clusterId + ": " + AbstractCluster.formatVector(point.get(), null));
            }
          } finally {
            reader.close();
          }
        }
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.