Package org.apache.mahout.common

Examples of org.apache.mahout.common.StringTuple

59
60
61
62
63
64
65
66
67
    String label = key.stringAt(1);

    reporter.setStatus("Bayes Theta Normalizer Mapper: " + label);
   
    double weight = Math.log((value.get() + alpha_i) / (labelWeightSum.get(label) + vocabCount));
    StringTuple thetaNormalizerTuple = new StringTuple(BayesConstants.LABEL_THETA_NORMALIZER);
    thetaNormalizerTuple.add(label);
    output.collect(thetaNormalizerTuple, new DoubleWritable(weight));
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
    return theSequenceFileOutputFormat.getRecordWriter(fs, job, name, arg3);
  }

  @Override
  protected String generateFileNameForKeyValue(WritableComparable<?> k, Writable v, String name) {
    StringTuple key = (StringTuple) k;
    if(key.length() == 3)
    {
      if(key.stringAt(0).equals(BayesConstants.WEIGHT))
        return "trainer-wordFreq/" + name;
      else if(key.stringAt(0).equals(BayesConstants.DOCUMENT_FREQUENCY))
        return "trainer-termDocCount/" + name;
    }
    else if(key.length() == 2)
    {
      if(key.stringAt(0).equals(BayesConstants.FEATURE_COUNT))
        return "trainer-featureCount/" + name;
      else if(key.stringAt(0).equals(BayesConstants.LABEL_COUNT))
        return "trainer-docCount/" + name;
    }
    throw new RuntimeException("Unrecognized Tuple: " + key);   
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
  }

  public static void loadWeightMatrix(InMemoryBayesDatastore datastore,
      FileSystem fs, Path pathPattern, Configuration conf) throws IOException {

    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      log.info("{}", path);
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);

      // the key is label,feature
      while (reader.next(key, value)) {

        datastore.loadFeatureWeight(key.stringAt(2), key.stringAt(1), value
            .get());

      }
    }
  }
View Full Code Here
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
  }

  public static void loadFeatureWeights(InMemoryBayesDatastore datastore,
      FileSystem fs, Path pathPattern, Configuration conf) throws IOException {

    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      log.info("{}", path);
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);

      // the key is either _label_ or label,feature
      long count = 0;
      while (reader.next(key, value)) {

        if (key.stringAt(0).equals(BayesConstants.FEATURE_SUM)) { // Sum of
                                                                  // weights for
                                                                  // a Feature
          datastore.setSumFeatureWeight(key.stringAt(1), value.get());
          count++;
          if (count % 50000 == 0) {
            log.info("Read {} feature weights", count);
          }
        }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
  }

  public static void loadLabelWeights(InMemoryBayesDatastore datastore,
      FileSystem fs, Path pathPattern, Configuration conf) throws IOException {

    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      log.info("{}", path);
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);

      long count = 0;
      while (reader.next(key, value)) {
        if (key.stringAt(0).equals(BayesConstants.LABEL_SUM)) { // Sum of
                                                                // weights in a
                                                                // Label
          datastore.setSumLabelWeight(key.stringAt(1), value.get());
          count++;
          if (count % 10000 == 0) {
            log.info("Read {} label weights", count);
          }
        }
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
  }

  public static void loadThetaNormalizer(InMemoryBayesDatastore datastore,
      FileSystem fs, Path pathPattern, Configuration conf) throws IOException {

    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      log.info("{}", path);
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);

      long count = 0;
      while (reader.next(key, value)) {
        if (key.stringAt(0).equals(BayesConstants.LABEL_THETA_NORMALIZER)) { // Sum
                                                                             // of
                                                                             // weights
                                                                             // in
                                                                             // a
                                                                             // Label
          datastore.setThetaNormalizer(key.stringAt(1), value.get());
          count++;
          if (count % 50000 == 0) {
            log.info("Read {} theta norms", count);
          }
        }
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
  }

  public static void loadSumWeight(InMemoryBayesDatastore datastore,
      FileSystem fs, Path pathPattern, Configuration conf) throws IOException {

    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      log.info("{}", path);
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);

      // the key is _label
      while (reader.next(key, value)) {

        if (key.stringAt(0).equals(BayesConstants.TOTAL_SUM)) { // Sum of
                                                                // weights for
          // all Features and all Labels
          datastore.setSigma_jSigma_k(value.get());
          log.info("{}", value.get());
        }
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
  }

  public static Map<String, Double> readLabelSums(FileSystem fs,
      Path pathPattern, Configuration conf) throws IOException {
    Map<String, Double> labelSum = new HashMap<String, Double>();
    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);

    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
      // the key is either _label_ or label,feature
      while (reader.next(key, value)) {
        if (key.stringAt(0).equals(BayesConstants.LABEL_SUM)) { // Sum of counts
                                                                // of labels
          labelSum.put(key.stringAt(1), value.get());
        }

      }
    }
View Full Code Here
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
  }

  public static Map<String, Double> readLabelDocumentCounts(FileSystem fs,
      Path pathPattern, Configuration conf) throws IOException {
    Map<String, Double> labelDocumentCounts = new HashMap<String, Double>();
    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
      // the key is either _label_ or label,feature
      while (reader.next(key, value)) {
        if (key.stringAt(0).equals(BayesConstants.LABEL_COUNT)) { // Count of
                                                                  // Documents
                                                                  // in a Label
          labelDocumentCounts.put(key.stringAt(1), value.get());
        }

      }
    }
View Full Code Here
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
  }

  public static double readSigma_jSigma_k(FileSystem fs, Path pathPattern,
      Configuration conf) throws IOException {
    Map<String, Double> weightSum = new HashMap<String, Double>();
    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();

    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
      // the key is *
      while (reader.next(key, value)) {
        if (weightSum.size() > 1) {
          throw new IOException("Incorrect Sum File");
        } else if (key.stringAt(0).equals(BayesConstants.TOTAL_SUM)) {
          weightSum.put(BayesConstants.TOTAL_SUM, value.get());
        }

      }
    }
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.