Package org.apache.mahout.math

Examples of org.apache.mahout.math.RandomAccessSparseVector$AllIterator

154
155
156
157
158
159
160
161
162
163
164
                       Iterator<VectorWritable> it,
                       OutputCollector<IntWritable,VectorWritable> out,
                       Reporter reporter) throws IOException {
      Vector accumulator;
      if(it.hasNext()) {
        accumulator = new RandomAccessSparseVector(it.next().get());
      } else {
        return;
      }
      while(it.hasNext()) {
        Vector row = it.next().get();
View Full Code Here
173
174
175
176
177
178
179
180
181
182
183
        if(!(inputVector instanceof SequentialAccessSparseVector || inputVector instanceof DenseVector)) {
          inputVector = new SequentialAccessSparseVector(inputVector);
        }
        int outDim = conf.getInt(OUTPUT_VECTOR_DIMENSION, Integer.MAX_VALUE);
        outputVector = conf.getBoolean(IS_SPARSE_OUTPUT, false)
                     ? new RandomAccessSparseVector(outDim, 10)
                     : new DenseVector(outDim);
      } catch (IOException ioe) {
        throw new IllegalStateException(ioe);
      }
    }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
 
  public static List<VectorWritable> getPointsWritable(double[][] raw) {
    List<VectorWritable> points = new ArrayList<VectorWritable>();
    int i = 0;
    for (double[] fr : raw) {
      Vector vec = new RandomAccessSparseVector(String.valueOf(i++), fr.length);
      vec.assign(fr);
      points.add(new VectorWritable(vec));
    }
    return points;
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
 
  private static List<VectorWritable> getPointsWritable(double[][] raw) {
    List<VectorWritable> points = new ArrayList<VectorWritable>();
    int i = 0;
    for (double[] fr : raw) {
      Vector vec = new RandomAccessSparseVector(String.valueOf(i++), fr.length);
      vec.assign(fr);
      points.add(new VectorWritable(vec));
    }
    return points;
  }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
 
  private static List<Vector> getPoints(double[][] raw) {
    List<Vector> points = new ArrayList<Vector>();
    int i = 0;
    for (double[] fr : raw) {
      Vector vec = new RandomAccessSparseVector(String.valueOf(i++), fr.length);
      vec.assign(fr);
      points.add(vec);
    }
    return points;
  }
View Full Code Here
228
229
230
231
232
233
234
235
    @Override
    public void configure(JobConf conf) {
      int outputDimension = conf.getInt(OUTPUT_VECTOR_DIMENSION, Integer.MAX_VALUE);
      outputVector = conf.getBoolean(IS_SPARSE_OUTPUT, false)
                   ? new RandomAccessSparseVector(outputDimension, 10)
                   : new DenseVector(outputDimension);
    }
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
 
  private static List<VectorWritable> getPoints(double[][] raw) {
    List<VectorWritable> points = new ArrayList<VectorWritable>();
    int i = 0;
    for (double[] fr : raw) {
      Vector vec = new RandomAccessSparseVector(String.valueOf(i++), fr.length);
      vec.assign(fr);
      points.add(new VectorWritable(vec));
    }
    return points;
  }
View Full Code Here
55
56
57
58
59
60
61
62
  }
 
  @Override
  public void setExpectations(String field, int numTerms, boolean storeOffsets, boolean storePositions) {
    this.field = field;
    vector = new RandomAccessSparseVector(termInfo.totalTerms(field));
    this.numTerms = numTerms;
  }
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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
  public void reduce(WritableComparable<?> key,
                     Iterator<VectorWritable> values,
                     OutputCollector<WritableComparable<?>,VectorWritable> output,
                     Reporter reporter) throws IOException {
   
    Vector vector = new RandomAccessSparseVector(key.toString(), dimension, 10);
    while (values.hasNext()) {
      VectorWritable value = values.next();
      value.get().addTo(vector);
    }
    if (normPower != PartialVectorMerger.NO_NORMALIZING) {
      vector = vector.normalize(normPower);
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    vectorWritable.set(vector);
View Full Code Here
TOP

Related Classes of org.apache.mahout.math.RandomAccessSparseVector$AllIterator

  • com.mozilla.grouperfish.pig.storage.MahoutVectorStorage
  • com.mozilla.grouperfish.transforms.coclustering.pig.storage.MahoutVectorStorage
  • com.twitter.elephantbird.pig.mahout.VectorWritableConverter
  • org.apache.mahout.benchmark.VectorBenchmarks
  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJob$AverageRatingMapper
  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJob$ItemRatingVectorsMapper
  • org.apache.mahout.cf.taste.hadoop.item.AggregateAndRecommendReducer
  • org.apache.mahout.cf.taste.hadoop.item.ItemFilterAsVectorAndPrefsReducer
  • org.apache.mahout.cf.taste.hadoop.item.RecommenderJobTest
  • org.apache.mahout.cf.taste.hadoop.item.RecommenderMapper
    • 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.