Package org.apache.mahout.math

Examples of org.apache.mahout.math.NamedVector

18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
    @Override
    protected void reduce(LongWritable id, Iterable<VectorWritable> vectors,
            Context context) throws IOException, InterruptedException {
        for (VectorWritable nextVectorWritable : vectors) {
            NamedVector nextVectorizedDocument = (NamedVector) nextVectorWritable
                    .get();
            String docLabel = nextVectorizedDocument.getName();
            String[] parts = docLabel.split(",");
            String docName = parts[0];
            String label = parts[1];

            log.debug("Writing out " + vectorCount + "th vector of doc: "
                    + docName);
            context.write(
                    new Text(docName),
                    new VectorWritable(new NamedVector(nextVectorizedDocument
                            .getDelegate(), label)));
        }
    }
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
    String docLabel = ((NamedVector) nextVectorizedDocument).getName();
    String[] parts = docLabel.split(",");
    String docName = parts[0];
    String label = parts[1];

    writer.append(new Text(docName), new VectorWritable(new NamedVector(
      nextVectorizedDocument, label)));
      }
      log.info("Sequence file written to HDFS successfully. Docs written: " + index);
  } finally {
      IOUtils.closeStream(writer);
View Full Code Here
62
63
64
65
66
67
68
        Vector vector = new SequentialAccessSparseVector(cardinality);
        vector.assign(features);
        log.debug(String.format("Vector: label:%s Fields: %d", docLabel,
                vector.size()));

        return new NamedVector(vector, docLabel);
    }
View Full Code Here
226
227
228
229
230
231
232
233
234
235
236
    SequenceFile.Writer seqWriter =
        new SequenceFile.Writer(fs, conf, outputPath, IntWritable.class, VectorWritable.class);
    IntWritable iw = new IntWritable();
    for (int i = 0; i < numEigenVectors; i++) {
      // Persist eigenvectors sorted by eigenvalues in descending order\
      NamedVector v = new NamedVector(state.getRightSingularVector(numEigenVectors - 1 - i),
          "eigenVector" + i + ", eigenvalue = " + state.getSingularValue(numEigenVectors - 1 - i));
      Writable vw = new VectorWritable(v);
      iw.set(i);
      seqWriter.append(iw, vw);
    }
View Full Code Here
140
141
142
143
144
145
146
147
148
149
150
151
152
        name = indexReader.document(doc, idFieldSelector).get(idField);
      } else {
        name = String.valueOf(doc);
      }
      if (normPower == LuceneIterable.NO_NORMALIZING) {
        result = new NamedVector(result, name);
      } else {
        result = new NamedVector(result.normalize(normPower), name);
      }
      return result;
    } catch (IOException ioe) {
      throw new IllegalStateException(ioe);
    }
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
  }

  @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
    ClusterDumper clusterDumper =
        new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
View Full Code Here
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
  }

  @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
    ClusterDumper clusterDumper =
        new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
    Configuration conf = new Configuration();
    Collection<Double> newEigenValues = new ArrayList<Double>();

    int i = 0;
    for (VectorWritable value : new SequenceFileValueIterable<VectorWritable>(cleanEigenvectors, conf)) {
      NamedVector v = (NamedVector) value.get();
      eigenVectors.assignRow(i, v);
      log.info(v.getName());
      if(EigenVector.getCosAngleError(v.getName()) < 1e-3) {
        eigenvalues.add(EigenVector.getEigenValue(v.getName()));
      }
      i++;
    }
    assertEquals("number of clean eigenvectors", 23, i);

    i = 0;
    for (VectorWritable value : new SequenceFileValueIterable<VectorWritable>(cleanEigenvectors2, conf)) {
      NamedVector v = (NamedVector) value.get();
      log.info(v.getName());
      eigenVectors2.assignRow(i, v);
      newEigenValues.add(EigenVector.getEigenValue(v.getName()));
      i++;
    }

    Collection<Integer> oldEigensFound = new ArrayList<Integer>();
    for(int row = 0; row < eigenVectors.numRows(); row++) {
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
    Iterable<Vector> iterable = new LuceneIterable(reader, "id", "content", mapper);

    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
94
95
96
97
98
99
100
101
102
103
104
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }

    if (namedVector) {
      vector = new NamedVector(vector, key.toString());
    }

    // if the vector has no nonZero entries (nothing in the dictionary), let's not waste space sending it to disk.
    if (vector.getNumNondefaultElements() > 0) {
      VectorWritable vectorWritable = new VectorWritable(vector);
View Full Code Here
TOP

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

  • com.fujitsu.ca.fic.dataloaders.bns.corpus.BnsCorpusLineParser
  • com.fujitsu.ca.fic.dataloaders.bns.corpus.BnsCorpusVectorizer
  • com.fujitsu.ca.fic.dataloaders.bns.corpus.sequence.mapreduce.BnsPigOutputToVectorMapperTest
  • com.fujitsu.ca.fic.dataloaders.bns.corpus.sequence.mapreduce.VectorToSequenceReducer
  • com.fujitsu.ca.fic.dataloaders.bns.corpus.sequence.mapreduce.VectorToSequenceReducerTest
  • com.mozilla.grouperfish.mahout.clustering.display.kmeans.OriginalText
  • com.mozilla.grouperfish.pig.storage.MahoutVectorStorage
  • com.mozilla.grouperfish.transforms.coclustering.display.WriteCoClusteringOutput
  • com.mozilla.grouperfish.transforms.coclustering.pig.storage.KMeansOutputLoader
  • com.mozilla.grouperfish.transforms.coclustering.pig.storage.MahoutVectorStorage
    • 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.