Package org.apache.mahout.common

Examples of org.apache.mahout.common.StringTuple

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)) {
        // Sum of weights for a Feature
        if (key.stringAt(0).equals(BayesConstants.FEATURE_SUM)) {
          datastore.setSumFeatureWeight(key.stringAt(1), value.get());
          count++;
          if (count % 50000 == 0) {
            log.info("Read {} feature weights", count);
          }
        }
View Full Code Here
33
34
35
36
37
38
39
                        Context context) throws IOException, InterruptedException {
    Set<String> outputValues = new HashSet<String>();
    for (StringTuple value : values) {
      outputValues.addAll(value.getEntries());
    }
    context.write(key, new StringTuple(outputValues));
  }
View Full Code Here
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
        @Override
        public boolean apply(String label, double sigmaJ) {
          double weight = Math.log((value.get() + alphaI) / (sigmaJSigmaK - sigmaJ + vocabCount));
         
          reporter.setStatus("Complementary Bayes Theta Normalizer Mapper: " + label + " => " + weight);
          StringTuple normalizerTuple = new StringTuple(BayesConstants.LABEL_THETA_NORMALIZER);
          normalizerTuple.add(label);
          try {
            output.collect(normalizerTuple, new DoubleWritable(weight));
          } catch (IOException e) {
            throw new IllegalStateException(e);
          } // output Sigma_j
          return true;
        }
      });
     
    } else {
      String label = key.stringAt(1);
     
      double dIJ = value.get();
      double denominator = 0.5 * (sigmaJSigmaK / vocabCount + dIJ * this.labelWeightSum.size());
      double weight = Math.log(1.0 - dIJ / denominator);
     
      reporter.setStatus("Complementary Bayes Theta Normalizer Mapper: " + label + " => " + weight);
     
      StringTuple normalizerTuple = new StringTuple(BayesConstants.LABEL_THETA_NORMALIZER);
      normalizerTuple.add(label);
     
      // output -D_ij
      output.collect(normalizerTuple, new DoubleWritable(weight));
     
    }
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
  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)) {
        // Sum of weights in a Label
        if (key.stringAt(0).equals(BayesConstants.LABEL_SUM)) {
          datastore.setSumLabelWeight(key.stringAt(1), value.get());
          count++;
          if (count % 10000 == 0) {
            log.info("Read {} label weights", count);
          }
        }
View Full Code Here
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
  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)) {
        // Sum of weights in a Label
        if (key.stringAt(0).equals(BayesConstants.LABEL_THETA_NORMALIZER)) {
          datastore.setThetaNormalizer(key.stringAt(1), value.get());
          count++;
          if (count % 50000 == 0) {
            log.info("Read {} theta norms", count);
          }
        }
View Full Code Here
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
  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.setSigmaJSigmaK(value.get());
          log.info("{}", value.get());
        }
View Full Code Here
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
 
  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
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
 
  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)) {
        // Count of Documents in a Label
        if (key.stringAt(0).equals(BayesConstants.LABEL_COUNT)) {
          labelDocumentCounts.put(key.stringAt(1), value.get());
        }
       
      }
    }
   
View Full Code Here
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
    return labelDocumentCounts;
  }
 
  public static double readSigmaJSigmaK(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);
      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
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
    return weightSum.get(BayesConstants.TOTAL_SUM);
  }
 
  public static double readVocabCount(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);
      while (reader.next(key, value)) {
        if (weightSum.size() > 1) {
          throw new IOException("Incorrect vocabCount File");
        }
        if (key.stringAt(0).equals(BayesConstants.FEATURE_SET_SIZE)) {
          weightSum.put(BayesConstants.FEATURE_SET_SIZE, 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.