Examples of DoubleWritable

Examples of org.apache.hadoop.io.DoubleWritable

72
73
74
75
76
77
78
79
        bu.add(Bytes.toBytes(BayesConstants.HBASE_COLUMN_FAMILY), Bytes.toBytes(label), Bytes
            .toBytes(weightSumPerLabel));
        table.put(bu);
      }
    }
    output.collect(key, new DoubleWritable(weightSumPerLabel));
   
  }
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

143
144
145
146
147
148
149
150
151
152
153
    } else {
      CollocDriver.generateAllGrams(inputPath.toString(), dictionaryJobPath.toString(), maxNGramSize,
        minSupport, minLLRValue, numReducers);
      dictionaryChunks = createDictionaryChunks(minSupport, new Path(
          output + DICTIONARY_JOB_FOLDER, CollocDriver.NGRAM_OUTPUT_DIRECTORY), output,
        chunkSizeInMegabytes, new DoubleWritable(), maxTermDimension);
    }
   
    int partialVectorIndex = 0;
    List<Path> partialVectorPaths = new ArrayList<Path>();
    for (Path dictionaryChunk : dictionaryChunks) {
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

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
         
          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

Examples of org.apache.hadoop.io.DoubleWritable

198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
    FileSystem fs = new Path(dir).getFileSystem(job);
   
    List<PriorityQueue<StringDoublePair>> queues = new ArrayList<PriorityQueue<StringDoublePair>>();
   
    IntPairWritable key = new IntPairWritable();
    DoubleWritable value = new DoubleWritable();
    for (FileStatus status : fs.globStatus(new Path(dir, "*"))) {
      Path path = status.getPath();
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, job);
      while (reader.next(key, value)) {
        int topic = key.getFirst();
        int word = key.getSecond();
       
        ensureQueueSize(queues, topic);
        if (word >= 0 && topic >= 0) {
          double score = value.get();
          String realWord = wordList.get(word);
          maybeEnqueue(queues.get(topic), realWord, score, numWordsToPrint);
        }
      }
      reader.close();
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

73
74
75
76
77
78
79
80
        bu.add(Bytes.toBytes(BayesConstants.HBASE_COLUMN_FAMILY), Bytes.toBytes(label), Bytes
            .toBytes(weightSumPerLabel));
        table.put(bu);
      }
    }
    output.collect(key, new DoubleWritable(weightSumPerLabel));
   
  }
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

164
165
166
167
168
169
170
171
172
173
        totalScore += freqBigram.getFrequency();
      }
      // normalize the co-occurrence based counts.
      for (Bigram.Frequency freqBigram : freqBigrams) {
        key = freqBigram.getBigram();
        value = new DoubleWritable(freqBigram.getFrequency() / totalScore);
        output.collect(key, value);
      }
      freqBigrams.clear();
    }
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

120
121
122
123
124
125
126
127
128
129
130
        try {
          StringTuple tuple = new StringTuple();
          tuple.add(BayesConstants.WEIGHT);
          tuple.add(label);
          tuple.add(token);
          DoubleWritable f = new DoubleWritable(Math.log(1.0 + dKJ) / lengthNormalisation);
          output.collect(tuple, f);
        } catch (IOException e) {
          throw new IllegalStateException(e);
        }
        return true;
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

69
70
71
72
73
74
75
    reporter.setStatus("Bayes Theta Normalizer Mapper: " + label);
   
    double weight = Math.log((value.get() + alphaI) / (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

Examples of org.apache.hadoop.io.DoubleWritable

43
44
45
46
47
48
49
    while (values.hasNext()) {
      reporter.setStatus("Feature Reducer:" + key);
      sum += values.next().get();
    }
    reporter.setStatus("Bayes Feature Reducer: " + key + " => " + sum);
    output.collect(key, new DoubleWritable(sum));
  }
View Full Code Here

Examples of org.apache.hadoop.io.DoubleWritable

91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
                                           Path pathPattern,
                                           Configuration conf,
                                           Parameters params) throws IOException {
   
    StringTuple key = new StringTuple();
    DoubleWritable value = new DoubleWritable();
    String defaultLabel = params.get("defaultCat");
    FileStatus[] outputFiles = fs.globStatus(pathPattern);
    Map<String,Map<String,Integer>> confusionMatrix = new HashMap<String,Map<String,Integer>>();
   
    for (FileStatus fileStatus : outputFiles) {
      Path path = fileStatus.getPath();
      SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
      while (reader.next(key, value)) {
        String correctLabel = key.stringAt(1);
        String classifiedLabel = key.stringAt(2);
        Map<String,Integer> rowMatrix = confusionMatrix.get(correctLabel);
        if (rowMatrix == null) {
          rowMatrix = new HashMap<String,Integer>();
        }
        Integer count = Double.valueOf(value.get()).intValue();
        rowMatrix.put(classifiedLabel, count);
        confusionMatrix.put(correctLabel, rowMatrix);
       
      }
    }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.