Package com.datasalt.pangool.io

Examples of com.datasalt.pangool.io.Tuple

102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
    // Define the input and its associated mapper
    // The mapper will just emit the (min, max) pairs to the reduce stage
    job.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class),
        new TupleMapper<LongWritable, Text>() {

          Tuple tuple = new Tuple(schema);

          @Override
          public void map(LongWritable key, Text value, TupleMRContext context, Collector collector)
              throws IOException, InterruptedException {
            String[] fields = value.toString().split("\t");
            tuple.set("min", Integer.parseInt(fields[0]));
            tuple.set("max", Integer.parseInt(fields[1]));
            collector.write(tuple);
          }
        });

    // Define the reducer
View Full Code Here
112
113
114
115
116
117
118
    private Tuple tuple;

    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      tuple = new Tuple(context.getTupleMRConfig().getIntermediateSchema("my_schema"));
    }
View Full Code Here
62
63
64
65
66
67
68
    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      jsonMapper = new ObjectMapper();
      jsonMapper.configure(DeserializationConfig.Feature.FAIL_ON_UNKNOWN_PROPERTIES, false);
      tuple = new Tuple(context.getTupleMRConfig().getIntermediateSchema("my_schema"));
    }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
    // Use a HashSet to calculate the total vocabulary size
    Set<String> vocabulary = new HashSet<String>();
    // Read tuples from generate job
    for(FileStatus fileStatus : fileSystem.globStatus(generatedModel)) {
      TupleFile.Reader reader = new TupleFile.Reader(fileSystem, conf, fileStatus.getPath());
      Tuple tuple = new Tuple(reader.getSchema());
      while(reader.next(tuple)) {
        // Read Tuple
        Integer count = (Integer) tuple.get("count");
        Category category = (Category) tuple.get("category");
        String word = tuple.get("word").toString();
        vocabulary.add(word);
        tokensPerCategory.put(category, MapUtils.getInteger(tokensPerCategory, category, 0) + count);
        wordCountPerCategory.get(category).put(word, count);
      }
      reader.close();
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
    @Override
    public void map(LongWritable key, Text value, TupleMRContext context, Collector collector)
        throws IOException, InterruptedException {
      if(tuple == null) {
        tuple = new Tuple(context.getTupleMRConfig().getIntermediateSchema(0));
      }

      String[] fields = value.toString().trim().split("\t");
      tuple.set("intField", Integer.parseInt(fields[0]));
      tuple.set("strField", fields[1]);
View Full Code Here
56
57
58
59
60
61
62
      this.n = n;
    }

    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException, TupleMRException {
      outputCountTuple = new Tuple(getOutputCountSchema());
    };
View Full Code Here
64
65
66
67
68
69
70
    private Tuple tuple;

    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      tuple = new Tuple(context.getTupleMRConfig().getIntermediateSchema("tweet"));
    };
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
95
96
97
    job.addIntermediateSchema(INTERMEDIATE_SCHEMA);
    // perform per-category word count mapping
    job.addInput(new Path(inputExamples), new HadoopInputFormat(TextInputFormat.class),
        new TupleMapper<LongWritable, Text>() {

          ITuple tuple = new Tuple(INTERMEDIATE_SCHEMA);

          @Override
          public void map(LongWritable toIgnore, Text value, TupleMRContext context, Collector collector)
              throws IOException, InterruptedException {

            Category category = Category.valueOf(value.toString().split("\t")[0]);
            StringTokenizer itr = new StringTokenizer(value.toString().split("\t")[1]);
            tuple.set("category", category);
            tuple.set("count", 1);
            while(itr.hasMoreTokens()) {
              tuple.set("word", normalizeWord(itr.nextToken()));
              collector.write(tuple);
            }
          }
        });

    TupleReducer countReducer = new TupleReducer<ITuple, NullWritable>() {

      public void reduce(ITuple group, Iterable<ITuple> tuples, TupleMRContext context,
          Collector collector) throws IOException, InterruptedException, TupleMRException {
        int count = 0;
        ITuple outputTuple = null;
        for(ITuple tuple : tuples) {
          count += (Integer) tuple.get("count");
          outputTuple = tuple;
        }
        outputTuple.set("count", count);
        collector.write(outputTuple, NullWritable.get());
      }
View Full Code Here
82
83
84
85
86
87
88
  private static class RetweetsMapper extends TupleMapper<LongWritable, Text> {
    private Tuple tuple;

    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      tuple = new Tuple(context.getTupleMRConfig().getIntermediateSchema("retweet"));
    };
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
95
    @Override
    public void map(LongWritable key, Text value, TupleMRContext context, Collector collector)
        throws IOException, InterruptedException {

      // Just parsing the text input and emitting a Tuple
      Tuple tuple = new Tuple(schema);
      String[] fields = value.toString().trim().split("\t");
      tuple.set("url", fields[0]);
      tuple.set("date", fields[1]);
      tuple.set("visits", Integer.parseInt(fields[2]));
      collector.write(tuple);
    }
View Full Code Here
TOP

Related Classes of com.datasalt.pangool.io.Tuple

  • com.datasalt.pangool.examples.avro.AvroCustomSerializationJob$TokenizeMapper
  • com.datasalt.pangool.examples.avro.AvroTopicalWordCount$TokenizeMapper
  • com.datasalt.pangool.examples.avro.AvroTweetsJoin$RetweetsMapper
  • com.datasalt.pangool.examples.avro.AvroTweetsJoin$TweetsMapper
  • com.datasalt.pangool.examples.avro.TestAvroTopicalWordCount
  • com.datasalt.pangool.examples.gameoflife.GameOfLifeJob
  • com.datasalt.pangool.examples.movingaverage.MovingAverage$URLVisitsProcessor
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesClassifier
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate
  • com.datasalt.pangool.examples.secondarysort.SecondarySort$IProcessor
    • 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.