Package org.apache.mahout.math

Examples of org.apache.mahout.math.Vector

64
65
66
67
68
69
70
71
72
73
74
75
    for (int i = 0; i < dotval.length; i++) {
      this.model.timesDelta(i, dotval[i]);
    }

    double[] valuesFalse = {1.0, 0.0, 1.0, 0.0, 1.0};
    Vector dataPointFalse = new DenseVector(valuesFalse);
    assertTrue(this.model.classify(dataPointFalse));

    double[] valuesTrue = {0.0, 1.0, 0.0, 1.0, 0.0};
    Vector dataPointTrue = new DenseVector(valuesTrue);
    assertFalse(this.model.classify(dataPointTrue));
  }
View Full Code Here
58
59
60
61
62
63
64
65
66
   * @param corpus
   * @return
   */
  @Override
  protected Vector getInitialVector(VectorIterable corpus) {
    Vector initialVector = new DenseVector(corpus.numCols());
    initialVector.assign(1/Math.sqrt(corpus.numCols()));
    return initialVector;
  }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
    FileSystem fs = FileSystem.get(conf);
    SequenceFile.Writer seqWriter = new SequenceFile.Writer(fs, conf, path, IntWritable.class, VectorWritable.class);
    VectorWritable vw = new VectorWritable();
    IntWritable iw = new IntWritable();
    for(int i=0; i<eigenVectors.numRows() - 1; i++) {
      Vector v = eigenVectors.getRow(i);
      v.setName("eigenVector" + i + ", eigenvalue = " + eigenValues.get(i));
      vw.set(v);
      iw.set(i);
      seqWriter.append(iw, vw);
    }
    seqWriter.close();
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
    trainer = new PerceptronTrainer(3, 0.5, 0.1, 1.0, 1.0);
  }

  public void testUpdate() throws TrainingException {
    double[] labels = { 1.0, 1.0, 1.0, 0.0 };
    Vector labelset = new DenseVector(labels);
    double[][] values = new double[3][4];
    for (int i = 0; i < 3; i++) {
      values[i][0] = 1.0;
      values[i][1] = 1.0;
      values[i][2] = 1.0;
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
    Model<O>[] newModels = modelFactory.sampleFromPosterior(state.getModels());
   
    // iterate over the samples, assigning each to a model
    for (O x : sampleData) {
      // compute normalized vector of probabilities that x is described by each model
      Vector pi = normalizedProbabilities(state, x);
      // then pick one cluster by sampling a Multinomial distribution based upon them
      // see: http://en.wikipedia.org/wiki/Multinomial_distribution
      int k = UncommonDistributions.rMultinom(pi);
      // ask the selected model to observe the datum
      newModels[k].observe(x);
View Full Code Here
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
   * @param x
   *          an Observation
   * @return the Vector of probabilities
   */
  private Vector normalizedProbabilities(DirichletState<O> state, O x) {
    Vector pi = new DenseVector(numClusters);
    double max = 0;
    for (int k = 0; k < numClusters; k++) {
      double p = state.adjustedProbability(x, k);
      pi.set(k, p);
      if (max < p) {
        max = p;
      }
    }
    // normalize the probabilities by largest observed value
    pi.assign(new TimesFunction(), 1.0 / max);
    return pi;
  }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
 
  @Override
  public Model<VectorWritable>[] sampleFromPrior(int howMany) {
    Model<VectorWritable>[] result = new NormalModel[howMany];
    for (int i = 0; i < howMany; i++) {
      Vector prototype = getModelPrototype().get();
      result[i] = new NormalModel(prototype.like(), 1);
    }
    return result;
  }
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
      }
    }
   
    @Override
    public Vector next() {
      Vector result;
      int doc = termDocs.doc();
      //
      try {
        indexReader.getTermFreqVector(doc, field, mapper);
        mapper.setDocumentNumber(doc);
        result = mapper.getVector();
        if (result == null) {
          return null;
        }
        if (idField != null) {
          String id = indexReader.document(doc, idFieldSelector).get(idField);
          result.setName(id);
        } else {
          result.setName(String.valueOf(doc));
        }
        if (normPower != NO_NORMALIZING) {
          result = result.normalize(normPower);
        }
      } catch (IOException e) {
        // Log?
        throw new IllegalStateException(e);
      }
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
  @Override
  public void map(WritableComparable<?> key,
                  VectorWritable value,
                  OutputCollector<IntWritable,LongWritable> output,
                  Reporter reporter) throws IOException {
    Vector vector = value.get();
    Iterator<Element> it = vector.iterateNonZero();
   
    while (it.hasNext()) {
      Element e = it.next();
      output.collect(new IntWritable(e.index()), ONE);
    }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
    if (values.hasNext() == false) {
      return;
    }
    StringTuple value = values.next();
   
    Vector vector = new RandomAccessSparseVector(key.toString(), dimension, value.length()); // guess at
                                                                                             // initial size
   
    if (maxNGramSize >= 2) {
      ShingleFilter sf = new ShingleFilter(new IteratorTokenStream(value.getEntries().iterator()),
          maxNGramSize);
     
      do {
        String term = ((TermAttribute) sf.getAttribute(TermAttribute.class)).term();
        if (term.length() > 0) { // ngram
          if (dictionary.containsKey(term) == false) {
            continue;
          }
          int termId = dictionary.get(term);
          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      } while (sf.incrementToken());
     
      sf.end();
      sf.close();
    } else {
      for (String term : value.getEntries()) {
        if (term.length() > 0) { // unigram
          if (dictionary.containsKey(term) == false) {
            continue;
          }
          int termId = dictionary.get(term);
          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      }
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    // 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.set(vector);
      output.collect(key, vectorWritable);
    } else {
      reporter.incrCounter("TFParticalVectorReducer", "emptyVectorCount", 1);
    }
View Full Code Here
TOP

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

  • com.fujitsu.ca.fic.dataloaders.bns.corpus.BnsCorpusLineParserTest
  • mia.classifier.ch16.train.TrainNewsGroups
  • mia.clustering.ch07.SimpleKMeansClustering
  • org.apache.mahout.cf.taste.hadoop.als.ALS
  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJob
  • org.apache.mahout.cf.taste.hadoop.item.AggregateAndRecommendReducer
  • org.apache.mahout.cf.taste.hadoop.item.RecommenderJobTest
  • org.apache.mahout.cf.taste.hadoop.item.UserVectorSplitterMapper
  • org.apache.mahout.cf.taste.impl.recommender.svd.ALSWRFactorizerTest
  • org.apache.mahout.cf.taste.impl.recommender.svd.ParallelSGDFactorizerTest
    • 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.