Package com.datasalt.pangool.tuplemr

Examples of com.datasalt.pangool.tuplemr.TupleMRBuilder.createJob()

131
132
133
134
135
136
137
138
139
140
141
    // 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());

    mr.createJob().waitForCompletion(true);

    return 1;
  }
 
  public static void main(String[] args) throws Exception {
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
        }
      };
    });

    job.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    job.createJob().waitForCompletion(true);
    delete(input);
    return 0;
  }

  public GameOfLifeJob() {
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
    mr.setOrderBy(new OrderBy().add("url", Order.ASC).addSchemaOrder(Order.ASC));
    mr.setTupleReducer(new Handler());
    mr.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    mr.addInput(new Path(input1), new HadoopInputFormat(TextInputFormat.class), new UrlMapProcessor());
    mr.addInput(new Path(input2), new HadoopInputFormat(TextInputFormat.class), new UrlProcessor());
    mr.createJob().waitForCompletion(true);

    return 1;
  }
 
  public static void main(String[] args) throws Exception {
View Full Code Here
228
229
230
231
232
233
234
235
236
237
238
    // 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());

    mr.createJob().waitForCompletion(true);

    return 1;
  }
 
  public static void main(String[] args) throws Exception {
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
    builder.setOrderBy(new OrderBy().add("first",Order.ASC).add("second",Order.ASC));
    // Input / output and such
    builder.setTupleReducer(new Handler());
    builder.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    builder.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class), new IProcessor());
    builder.createJob().waitForCompletion(true);

    return 1;
  }
 
  public static void main(String args[]) throws Exception {
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
    mr.setTupleReducer(new Handler());
    mr.setOutput(new Path(output), new TupleTextOutputFormat(getURLRegisterSchema(), false, '\t',
        NO_QUOTE_CHARACTER, NO_ESCAPE_CHARACTER), ITuple.class, NullWritable.class);

    try {
      mr.createJob().waitForCompletion(true);
    } finally {
      mr.cleanUpInstanceFiles();
    }

    return 1;
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
    mr.setOrderBy(new OrderBy().add("url", Order.ASC).add("date", Order.ASC));
    // Input / output and such
    mr.setTupleReducer(new MovingAverageHandler(nDaysAverage));
    mr.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    mr.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class), new URLVisitsProcessor());
    mr.createJob().waitForCompletion(true);
    return 1;
  }
 
  public static void main(String args[]) throws Exception {
    ToolRunner.run(new MovingAverage(), args);
View Full Code Here
171
172
173
174
175
176
177
178
179
180
181
    mr.setRollupFrom("date");
    // Input / output and such
    mr.setTupleReducer(new TweetsHandler(n));
    mr.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    mr.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class), new TweetsProcessor());
    mr.createJob().waitForCompletion(true);
    return 0;
  }
 
  public static void main(String[] args) throws Exception {
    ToolRunner.run(new TopNHashTags(), args);
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
     */
    builder.setTupleOutput(new Path(args[1]), TopicalWordCount.getSchema());
    builder.addNamedTupleOutput(OUTPUT_TOTALCOUNT, getOutputCountSchema());
    builder.setTupleReducer(new TopNWords(n));

    builder.createJob().waitForCompletion(true);

    return 1;
  }
 
  public static void main(String[] args) throws Exception {
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
    // Input / output and such
    mr.setTupleCombiner(new CountCombinerHandler());
    mr.setTupleReducer(new NormalizingHandler());
    mr.setOutput(new Path(output), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    mr.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class), new UserActivityProcessor());
    mr.createJob().waitForCompletion(true);
   
    return 1;
  }
 
  public UserActivityNormalizer() {
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.