Package com.datasalt.pangool.tuplemr.mapred.lib.input

Examples of com.datasalt.pangool.tuplemr.mapred.lib.input.HadoopInputFormat

53
54
55
56
57
58
59
60
61
62
63
    TupleMRBuilder job = new TupleMRBuilder(conf);
    job.addIntermediateSchema(schema);
    job.setGroupByFields("user_id");
    // Define the input and its associated mapper.
    // We'll just have a Mapper, reducer will be Identity
    job.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class),
        new TupleMapper<LongWritable, Text>() {

          Tuple tuple = new Tuple(schema);

          @Override
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
        .add("name", Order.ASC).add("height", Order.DESC));
    builder.setRollupFrom("country");
    builder.setTupleReducer(new IdentityRed());
    builder.setOutput(outputPath, new HadoopOutputFormat(SequenceFileOutputFormat.class), Text.class,
        Text.class);
    builder.addInput(new Path(input), new HadoopInputFormat(SequenceFileInputFormat.class), new Map());

    Job job = builder.createJob();
    try {
      job.setNumReduceTasks(1);
      assertRun(job);
View Full Code Here
273
274
275
276
277
278
279
280
281
282
283
        .add("name", Order.ASC).add("height", Order.DESC));
    builder.setRollupFrom("age");
    builder.setTupleReducer(new IdentityRed());
    builder.setOutput(outputPath, new HadoopOutputFormat(SequenceFileOutputFormat.class), Text.class,
        Text.class);
    builder.addInput(new Path(input), new HadoopInputFormat(SequenceFileInputFormat.class), new Map());

    Job job = builder.createJob();
    try {
      job.setNumReduceTasks(1);
      assertRun(job);
View Full Code Here
452
453
454
455
456
457
458
459
460
461
462
        .add("name", Order.ASC));
    builder.setRollupFrom("age");
    builder.setTupleReducer(new IdentityRed());
    builder.setOutput(outputPath, new HadoopOutputFormat(SequenceFileOutputFormat.class), Text.class,
        Text.class);
    builder.addInput(new Path(input), new HadoopInputFormat(SequenceFileInputFormat.class),
        new DoNothingMap());

    Job job = builder.createJob();
    try {
      job.setNumReduceTasks(1);
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
    final Schema schema2 = new Schema("tupleInTuple2", fields);

    builder.addIntermediateSchema(schema1);
    builder.addIntermediateSchema(schema2);

    builder.addInput(new Path(INPUT1), new HadoopInputFormat(TextInputFormat.class),
        new TupleMapper<LongWritable, Text>() {

          ITuple tupleInTuple1 = new Tuple(schema1);
          ITuple tuple1 = new Tuple(tupleSchema1);

          @Override
          public void map(LongWritable key, Text value, TupleMRContext context, Collector collector)
              throws IOException, InterruptedException {
            String[] split = value.toString().split("\t");
            tuple1.set("a", split[0]);
            tuple1.set("b", Integer.parseInt(split[1]));

            tupleInTuple1.set("partitionId", 0);
            tupleInTuple1.set("tuple1", tuple1);
            collector.write(tupleInTuple1);
          }
        });

    builder.addInput(new Path(INPUT2), new HadoopInputFormat(TextInputFormat.class),
        new TupleMapper<LongWritable, Text>() {

          ITuple tupleInTuple2 = new Tuple(schema2);
          ITuple tuple2 = new Tuple(tupleSchema2);
View Full Code Here
115
116
117
118
119
120
121
122
123
124
        value.set(value.toString() + "\t" + classify(value.toString()));
        context.write(value, NullWritable.get());
      }
    });
    job.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    job.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class));
    job.createJob().waitForCompletion(true);
   
    return 1;
  }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    deleteOutput(output);

    TupleMRBuilder job = new TupleMRBuilder(conf, "Naive Bayes Model Generator");
    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
View Full Code Here
193
194
195
196
197
198
199
200
201
202
203
    mr.addIntermediateSchema(getPangoolRetweetSchema());
    mr.setGroupByFields("tweet_id");
    mr.setOrderBy(new OrderBy().add("tweet_id",Order.ASC).addSchemaOrder(Order.ASC));
   
    mr.addInput(tweetsPath,new AvroInputFormat<Record>(getAvroTweetSchema()),new TweetsMapper());
    mr.addInput(retweetsPath, new HadoopInputFormat(TextInputFormat.class), new RetweetsMapper());
    mr.setOutput(outputPath,new AvroOutputFormat<Record>(getAvroOutputSchema()),
        AvroWrapper.class,NullWritable.class);

    mr.setTupleReducer(new Red());
View Full Code Here
218
219
220
221
222
223
224
225
226
227
228
    mr.addIntermediateSchema(getSchema());
    mr.setGroupByFields("my_avro");
    //here the custom comparator that groups by "topic,word" is used.
    MyAvroComparator customComp = new MyAvroComparator(getAvroSchema(),"topic","word");
    mr.setOrderBy(new OrderBy().add("my_avro",Order.ASC,customComp));
    mr.addInput(new Path(args[0]), new HadoopInputFormat(TextInputFormat.class), new TokenizeMapper());
    // We'll use a TupleOutputFormat with the same schema than the intermediate schema
    mr.setTupleOutput(new Path(args[1]), getSchema());
    mr.setTupleReducer(new CountReducer());
    mr.setTupleCombiner(new CountReducer());
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
    MapOnlyJobBuilder job = new MapOnlyJobBuilder(conf);
    TableSpec tableSpec = new TableSpec(schema, schema.getFields().get(1));
   
    job.setOutput(new Path(out, "store"), new SploutSQLProxyOutputFormat(new SQLite4JavaOutputFormat(1000000, tableSpec)), ITuple.class,
        NullWritable.class);
    job.addInput(input, new HadoopInputFormat(TextInputFormat.class), new MapOnlyMapper<LongWritable, Text, ITuple, NullWritable>() {

      ITuple metaTuple = new Tuple(schema);

      protected void map(LongWritable key, Text value, Context context) throws IOException,
          InterruptedException {
View Full Code Here
TOP

Related Classes of com.datasalt.pangool.tuplemr.mapred.lib.input.HadoopInputFormat

  • com.datasalt.pangool.examples.avro.AvroCustomSerializationJob
  • com.datasalt.pangool.examples.avro.AvroTopicalWordCount
  • com.datasalt.pangool.examples.avro.AvroTweetsJoin
  • com.datasalt.pangool.examples.gameoflife.GameOfLifeJob
  • com.datasalt.pangool.examples.Grep
  • com.datasalt.pangool.examples.mongo.QypeScrapper
  • com.datasalt.pangool.examples.movingaverage.MovingAverage
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesClassifier
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate
  • com.datasalt.pangool.examples.secondarysort.SecondarySort
    • 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.