Package org.apache.mahout.common

Examples of org.apache.mahout.common.StringTuple

62
63
64
65
66
67
68
69
    List<String> oValue = new ArrayList<String>();
    for (int selectedField : selectedFields) {
      oValue.add(fields[selectedField]);
    }
   
    context.write(new Text(oKey.toString()), new StringTuple(oValue));
   
  }
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
    Text key = new Text();
    key.set("dummy-key");
   
    String[] input = {"the", "best", "of", "times", "the", "worst", "of",
    "times"};
    StringTuple inputTuple = new StringTuple();
    for (String i : input) {
      inputTuple.add(i);
    }
   
    String[][] values = { {"h_the", "the best"},
                          {"t_best", "the best"},
                          {"h_of", "of times"},
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
    Text key = new Text();
    key.set("dummy-key");
   
    String[] input = {"the", "best", "of", "times", "the", "worst", "of",
    "times"};
    StringTuple inputTuple = new StringTuple();
    for (String i : input) {
      inputTuple.add(i);
    }
   
    String[][] values = {{"h_the", "the best"},
                                         {"t_best", "the best"},
                                         {"h_of", "of times"},
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
  protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
    TokenStream stream = analyzer.tokenStream(key.toString(), new StringReader(value.toString()));
    stream.reset();
    CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
    stream.reset();
    StringTuple document = new StringTuple();
    while (stream.incrementToken()) {
      if (termAtt.length() > 0) {
        document.add(new String(termAtt.buffer(), 0, termAtt.length()));
      }
    }
    stream.end();
    Closeables.close(stream, true);
    context.write(key, document);
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
    }
   
    for (NamedVector seedVector : seedVectors) {
      double distance = measure.distance(seedVector, valVec);
      if (!usesThreshold || distance <= maxDistance) {
        StringTuple outKey = new StringTuple();
        outKey.add(seedVector.getName());
        outKey.add(keyName);
        context.write(outKey, new DoubleWritable(distance));
      }
    }
  }
View Full Code Here
33
34
35
36
37
38
39
40
41
  private static final VarIntWritable ONE = new VarIntWritable(1);

  @Override
  protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
    StringTuple tuple = new StringTuple(key.toString());
    tuple.add(value.toString());
    context.write(tuple, ONE);
  }
View Full Code Here
63
64
65
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
    throws IOException, InterruptedException {
    Iterator<StringTuple> it = values.iterator();
    if (!it.hasNext()) {
      return;
    }
    StringTuple value = it.next();

    Vector vector = new RandomAccessSparseVector(dimension, value.length()); // guess at initial size

    if (maxNGramSize >= 2) {
      ShingleFilter sf = new ShingleFilter(new IteratorTokenStream(value.getEntries().iterator()), maxNGramSize);
      sf.reset();
      try {
        do {
          String term = sf.getAttribute(CharTermAttribute.class).toString();
          if (!term.isEmpty() && dictionary.containsKey(term)) { // ngram
            int termId = dictionary.get(term);
            vector.setQuick(termId, vector.getQuick(termId) + 1);
          }
        } while (sf.incrementToken());

        sf.end();
      } finally {
        Closeables.close(sf, true);
      }
    } else {
      for (String term : value.getEntries()) {
        if (!term.isEmpty() && dictionary.containsKey(term)) { // unigram
          int termId = dictionary.get(term);
          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      }
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
    Text key = new Text();
    key.set("dummy-key");
   
    String[] input = {"the", "best", "of", "times", "the", "worst", "of",
    "times"};
    StringTuple inputTuple = new StringTuple();
    for (String i : input) {
      inputTuple.add(i);
    }
   
    String[][] values = { {"h_the", "the best"},
                          {"t_best", "the best"},
                          {"h_of", "of times"},
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
    Text key = new Text();
    key.set("dummy-key");
   
    String[] input = {"the", "best", "of", "times", "the", "worst", "of",
    "times"};
    StringTuple inputTuple = new StringTuple();
    for (String i : input) {
      inputTuple.add(i);
    }
   
    String[][] values = {{"h_the", "the best"},
                                         {"t_best", "the best"},
                                         {"h_of", "of times"},
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
  @Test
  public void testVectorDistanceMapper() throws Exception {
    Mapper<WritableComparable<?>, VectorWritable, StringTuple, DoubleWritable>.Context context =
            EasyMock.createMock(Mapper.Context.class);
    StringTuple tuple = new StringTuple();
    tuple.add("foo");
    tuple.add("123");
    context.write(tuple, new DoubleWritable(Math.sqrt(2.0)));
    tuple = new StringTuple();
    tuple.add("foo2");
    tuple.add("123");
    context.write(tuple, new DoubleWritable(1));

    EasyMock.replay(context);

    Vector vector = new RandomAccessSparseVector(2);
View Full Code Here
TOP

Related Classes of org.apache.mahout.common.StringTuple

  • com.digitalpebble.behemoth.mahout.BehemothTokenizerMapper
  • com.digitalpebble.behemoth.mahout.LuceneTokenizerMapper
  • org.apache.hadoop.io.Text
  • org.apache.mahout.classifier.bayes.io.SequenceFileModelReader
  • org.apache.mahout.classifier.bayes.mapreduce.bayes.BayesClassifierDriver
  • org.apache.mahout.classifier.bayes.mapreduce.bayes.BayesClassifierMapper
  • org.apache.mahout.classifier.bayes.mapreduce.bayes.BayesThetaNormalizerMapper
  • org.apache.mahout.classifier.bayes.mapreduce.cbayes.CBayesThetaNormalizerMapper
  • org.apache.mahout.classifier.bayes.mapreduce.common.BayesFeatureMapper
  • org.apache.mahout.classifier.bayes.mapreduce.common.BayesFeatureOutputFormat
    • 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.