Package org.apache.mahout.clustering.dirichlet.models

Examples of org.apache.mahout.clustering.dirichlet.models.DistributionDescription

102
103
104
105
106
107
108
109
110
111
112
    boolean runClustering = hasOption(DefaultOptionCreator.CLUSTERING_OPTION);
    boolean runSequential = getOption(DefaultOptionCreator.METHOD_OPTION).equalsIgnoreCase(
        DefaultOptionCreator.SEQUENTIAL_METHOD);
    int prototypeSize = readPrototypeSize(input);
   
    DistributionDescription description = new DistributionDescription(modelFactory, modelPrototype, distanceMeasure,
        prototypeSize);
   
    run(getConf(), input, output, description, numModels, maxIterations, alpha0, runClustering, emitMostLikely,
        threshold, runSequential);
    return 0;
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
    ClusteringTestUtils.writePointsToFile(sampleData,
            getTestTempFilePath("testdata/file1"), fs, conf);

    DenseVector prototype = (DenseVector) sampleData.get(0).get();
   
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(),
        ManhattanDistanceMeasure.class.getName(), prototype.size());
   
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output,
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
    ClusteringTestUtils.writePointsToFile(sampleData, true,
            getTestTempFilePath("testdata/file1"), fs, conf);

    DenseVector prototype = (DenseVector) sampleData.get(0).get();
   
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(),
        ManhattanDistanceMeasure.class.getName(), prototype.size());
   
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output,
View Full Code Here
51
52
53
54
55
56
57
58
59
60
      ToolRunner.run(new Configuration(), new Job(), args);
    } else {
      log.info("Running with default arguments");
      Path output = new Path("output");
      HadoopUtil.delete(new Configuration(), output);
      DistributionDescription description = new DistributionDescription(GaussianClusterDistribution.class.getName(),
          RandomAccessSparseVector.class.getName(), null, 60);
      run(new Path("testdata"), output, description, 10, 5, 1.0, true, 0);
    }
  }
View Full Code Here
111
112
113
114
115
116
117
118
119
120
    int numModels = Integer.parseInt(getOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION));
    int maxIterations = Integer.parseInt(getOption(DefaultOptionCreator.MAX_ITERATIONS_OPTION));
    boolean emitMostLikely = Boolean.parseBoolean(getOption(DefaultOptionCreator.EMIT_MOST_LIKELY_OPTION));
    double threshold = Double.parseDouble(getOption(DefaultOptionCreator.THRESHOLD_OPTION));
    double alpha0 = Double.parseDouble(getOption(DirichletDriver.ALPHA_OPTION));
    DistributionDescription description = new DistributionDescription(modelFactory, modelPrototype, distanceMeasure, 60);
   
    run(input, output, description, numModels, maxIterations, alpha0, emitMostLikely, threshold);
    return 0;
  }
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
  }
 
  private static void runSequentialDirichletClusterer(Path input, Path output,
      ModelDistribution<VectorWritable> modelDist, int numClusters, int numIterations, double alpha0)
      throws IOException, ClassNotFoundException, InterruptedException {
    DistributionDescription description = new DistributionDescription(modelDist.getClass().getName(),
        RandomAccessSparseVector.class.getName(), ManhattanDistanceMeasure.class.getName(), 2);
   
    DirichletDriver.run(new Configuration(), input, output, description, numClusters, numIterations, alpha0, true,
        true, 0, true);
  }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
    generateSamples(100, 2, 2, 1);
    ClusteringTestUtils.writePointsToFile(sampleData, getTestTempFilePath("input/data.txt"), fs, conf);
    // Now run the driver using the run() method. Others can use runJob() as
    // before
    Integer maxIterations = 5;
    DistributionDescription description = new DistributionDescription(GaussianClusterDistribution.class.getName(),
        DenseVector.class.getName(), null, 2);
    Path outputPath = getTestTempDirPath("output");
    String[] args = {optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("input").toString(),
        optKey(DefaultOptionCreator.OUTPUT_OPTION), outputPath.toString(),
        optKey(DirichletDriver.MODEL_DISTRIBUTION_CLASS_OPTION), description.getModelFactory(),
        optKey(DirichletDriver.MODEL_PROTOTYPE_CLASS_OPTION), description.getModelPrototype(),
        optKey(DefaultOptionCreator.NUM_CLUSTERS_OPTION), "20", optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION),
        maxIterations.toString(), optKey(DirichletDriver.ALPHA_OPTION), "1.0",
        optKey(DefaultOptionCreator.OVERWRITE_OPTION), optKey(DefaultOptionCreator.CLUSTERING_OPTION),
        optKey(DefaultOptionCreator.METHOD_OPTION), DefaultOptionCreator.SEQUENTIAL_METHOD};
    ToolRunner.run(conf, new DirichletDriver(), args);
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
    generateSamples(100, 2, 2, 1);
    ClusteringTestUtils.writePointsToFile(sampleData, true, getTestTempFilePath("input/data.txt"), fs, conf);
    // Now run the driver using the run() method. Others can use runJob() as
    // before
    Integer maxIterations = 5;
    DistributionDescription description = new DistributionDescription(GaussianClusterDistribution.class.getName(),
        DenseVector.class.getName(), null, 2);
    Path outputPath = getTestTempDirPath("output");
    String[] args = {optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("input").toString(),
        optKey(DefaultOptionCreator.OUTPUT_OPTION), outputPath.toString(),
        optKey(DirichletDriver.MODEL_DISTRIBUTION_CLASS_OPTION), description.getModelFactory(),
        optKey(DirichletDriver.MODEL_PROTOTYPE_CLASS_OPTION), description.getModelPrototype(),
        optKey(DefaultOptionCreator.NUM_CLUSTERS_OPTION), "20", optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION),
        maxIterations.toString(), optKey(DirichletDriver.ALPHA_OPTION), "1.0",
        optKey(DefaultOptionCreator.OVERWRITE_OPTION), optKey(DefaultOptionCreator.CLUSTERING_OPTION)};
    ToolRunner.run(conf, new DirichletDriver(), args);
    // and inspect results
View Full Code Here
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
    generateAsymmetricSamples(100, 0, 3, 0.3, 4.0);
    ClusteringTestUtils.writePointsToFile(sampleData, getTestTempFilePath("input/data.txt"), fs, conf);
    // Now run the driver using the run() method. Others can use runJob() as
    // before
    MahalanobisDistanceMeasure measure = new MahalanobisDistanceMeasure();
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(), DenseVector.class.getName(),
        MahalanobisDistanceMeasure.class.getName(), 2);
   
    Vector meanVector = new DenseVector(new double[] {0.0, 0.0});
    measure.setMeanVector(meanVector);
    Matrix m = new DenseMatrix(new double[][] { {0.5, 0.0}, {0.0, 4.0}});
    measure.setCovarianceMatrix(m);
   
    Path inverseCovarianceFile = new Path(getTestTempDirPath("mahalanobis"),
        "MahalanobisDistanceMeasureInverseCovarianceFile");
    conf.set("MahalanobisDistanceMeasure.inverseCovarianceFile", inverseCovarianceFile.toString());
    FileSystem fs = FileSystem.get(inverseCovarianceFile.toUri(), conf);
    MatrixWritable inverseCovarianceMatrix = new MatrixWritable(measure.getInverseCovarianceMatrix());
    DataOutputStream out = fs.create(inverseCovarianceFile);
    try {
      inverseCovarianceMatrix.write(out);
    } finally {
      Closeables.closeQuietly(out);
    }
   
    Path meanVectorFile = new Path(getTestTempDirPath("mahalanobis"), "MahalanobisDistanceMeasureMeanVectorFile");
    conf.set("MahalanobisDistanceMeasure.meanVectorFile", meanVectorFile.toString());
    fs = FileSystem.get(meanVectorFile.toUri(), conf);
    VectorWritable meanVectorWritable = new VectorWritable(meanVector);
    out = fs.create(meanVectorFile);
    try {
      meanVectorWritable.write(out);
    } finally {
      Closeables.closeQuietly(out);
    }
   
    conf.set("MahalanobisDistanceMeasure.maxtrixClass", MatrixWritable.class.getName());
    conf.set("MahalanobisDistanceMeasure.vectorClass", VectorWritable.class.getName());
   
    Integer maxIterations = 5;
    Path outputPath = getTestTempDirPath("output");
    String[] args = {optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("input").toString(),
        optKey(DefaultOptionCreator.OUTPUT_OPTION), outputPath.toString(),
        optKey(DirichletDriver.MODEL_DISTRIBUTION_CLASS_OPTION), description.getModelFactory(),
        optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION), description.getDistanceMeasure(),
        optKey(DirichletDriver.MODEL_PROTOTYPE_CLASS_OPTION), description.getModelPrototype(),
        optKey(DefaultOptionCreator.NUM_CLUSTERS_OPTION), "20", optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION),
        maxIterations.toString(), optKey(DirichletDriver.ALPHA_OPTION), "1.0",
        optKey(DefaultOptionCreator.OVERWRITE_OPTION), optKey(DefaultOptionCreator.CLUSTERING_OPTION),
        optKey(DefaultOptionCreator.METHOD_OPTION), DefaultOptionCreator.SEQUENTIAL_METHOD};
    DirichletDriver dirichletDriver = new DirichletDriver();
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
    ClusteringTestUtils.writePointsToFile(sampleData, true, getTestTempFilePath("input/data.txt"), fs, conf);
    // Now run the driver using the run() method. Others can use runJob() as
    // before
   
    MahalanobisDistanceMeasure measure = new MahalanobisDistanceMeasure();
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(), DenseVector.class.getName(),
        MahalanobisDistanceMeasure.class.getName(), 2);
   
    Vector meanVector = new DenseVector(new double[] {0.0, 0.0});
    measure.setMeanVector(meanVector);
    Matrix m = new DenseMatrix(new double[][] { {0.5, 0.0}, {0.0, 4.0}});
    measure.setCovarianceMatrix(m);
   
    Path inverseCovarianceFile = new Path(getTestTempDirPath("mahalanobis"),
        "MahalanobisDistanceMeasureInverseCovarianceFile");
    conf.set("MahalanobisDistanceMeasure.inverseCovarianceFile", inverseCovarianceFile.toString());
    FileSystem fs = FileSystem.get(inverseCovarianceFile.toUri(), conf);
    MatrixWritable inverseCovarianceMatrix = new MatrixWritable(measure.getInverseCovarianceMatrix());
    DataOutputStream out = fs.create(inverseCovarianceFile);
    try {
      inverseCovarianceMatrix.write(out);
    } finally {
      Closeables.closeQuietly(out);
    }
   
    Path meanVectorFile = new Path(getTestTempDirPath("mahalanobis"), "MahalanobisDistanceMeasureMeanVectorFile");
    conf.set("MahalanobisDistanceMeasure.meanVectorFile", meanVectorFile.toString());
    fs = FileSystem.get(meanVectorFile.toUri(), conf);
    VectorWritable meanVectorWritable = new VectorWritable(meanVector);
    out = fs.create(meanVectorFile);
    try {
      meanVectorWritable.write(out);
    } finally {
      Closeables.closeQuietly(out);
    }
   
    conf.set("MahalanobisDistanceMeasure.maxtrixClass", MatrixWritable.class.getName());
    conf.set("MahalanobisDistanceMeasure.vectorClass", VectorWritable.class.getName());
   
    Integer maxIterations = 5;
    Path outputPath = getTestTempDirPath("output");
    String[] args = {optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("input").toString(),
        optKey(DefaultOptionCreator.OUTPUT_OPTION), outputPath.toString(),
        optKey(DirichletDriver.MODEL_DISTRIBUTION_CLASS_OPTION), description.getModelFactory(),
        optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION), description.getDistanceMeasure(),
        optKey(DirichletDriver.MODEL_PROTOTYPE_CLASS_OPTION), description.getModelPrototype(),
        optKey(DefaultOptionCreator.NUM_CLUSTERS_OPTION), "20", optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION),
        maxIterations.toString(), optKey(DirichletDriver.ALPHA_OPTION), "1.0",
        optKey(DefaultOptionCreator.OVERWRITE_OPTION), optKey(DefaultOptionCreator.CLUSTERING_OPTION)};
    Tool dirichletDriver = new DirichletDriver();
    dirichletDriver.setConf(conf);
View Full Code Here
TOP

Related Classes of org.apache.mahout.clustering.dirichlet.models.DistributionDescription

  • org.apache.mahout.clustering.cdbw.TestCDbwEvaluator
  • org.apache.mahout.clustering.dirichlet.DirichletDriver
  • org.apache.mahout.clustering.dirichlet.DirichletMapper
  • org.apache.mahout.clustering.dirichlet.TestDirichletClustering
  • org.apache.mahout.clustering.dirichlet.TestL1ModelClustering
  • org.apache.mahout.clustering.dirichlet.TestMapReduce
  • org.apache.mahout.clustering.display.DisplayDirichlet
  • org.apache.mahout.clustering.syntheticcontrol.dirichlet.Job
  • org.apache.mahout.clustering.TestClusterDumper
  • org.apache.mahout.clustering.TestClusterEvaluator
    • 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.