Package eu.stratosphere.api.java.record.operators

Examples of eu.stratosphere.api.java.record.operators.ReduceOperator

65
66
67
68
69
70
71
72
73
74
75
    BulkIteration iteration = new BulkIteration("Loop");
    iteration.setInput(initialInput);
    iteration.setMaximumNumberOfIterations(5);
    Assert.assertTrue(iteration.getMaximumNumberOfIterations() > 1);

    ReduceOperator sumReduce = ReduceOperator.builder(new SumReducer())
        .input(iteration.getPartialSolution())
        .name("Compute sum (Reduce)")
        .build();
   
    iteration.setNextPartialSolution(sumReduce);
View Full Code Here
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
    String edgeInput = (args.length > 1 ? args[1] : "");
    String output    = (args.length > 2 ? args[2] : "");

    FileDataSource edges = new FileDataSource(new EdgeInFormat(), edgeInput, "BTC Edges");
   
    ReduceOperator buildTriads = ReduceOperator.builder(new BuildTriads(), StringValue.class, 0)
      .name("Build Triads")
      .build();

    JoinOperator closeTriads = JoinOperator.builder(new CloseTriads(), StringValue.class, 1, 0)
      .keyField(StringValue.class, 2, 1)
      .name("Close Triads")
      .build();
    closeTriads.setParameter("INPUT_LEFT_SHIP_STRATEGY", "SHIP_REPARTITION_HASH");
    closeTriads.setParameter("INPUT_RIGHT_SHIP_STRATEGY", "SHIP_REPARTITION_HASH");
    closeTriads.setParameter("LOCAL_STRATEGY", "LOCAL_STRATEGY_HASH_BUILD_SECOND");

    FileDataSink triangles = new FileDataSink(new CsvOutputFormat(), output, "Output");
    CsvOutputFormat.configureRecordFormat(triangles)
      .recordDelimiter('\n')
      .fieldDelimiter(' ')
      .field(StringValue.class, 0)
      .field(StringValue.class, 1)
      .field(StringValue.class, 2);

    triangles.setInput(closeTriads);
    closeTriads.setSecondInput(edges);
    closeTriads.setFirstInput(buildTriads);
    buildTriads.setInput(edges);

    Plan plan = new Plan(triangles, "Enumerate Triangles");
    plan.setDefaultParallelism(numSubTasks);
    return plan;
  }
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
    // create DataSourceContract for Orders input
    @SuppressWarnings("unchecked")
    CsvInputFormat format1 = new CsvInputFormat('|', IntValue.class, IntValue.class);
    FileDataSource input1 = new FileDataSource(format1, input1Path, "Input 1");
   
    ReduceOperator aggInput1 = ReduceOperator.builder(DummyReduce.class, IntValue.class, 0)
      .input(input1)
      .name("AggOrders")
      .build();

   
    // create DataSourceContract for Orders input
    @SuppressWarnings("unchecked")
    CsvInputFormat format2 = new CsvInputFormat('|', IntValue.class, IntValue.class);
    FileDataSource input2 = new FileDataSource(format2, input2Path, "Input 2");
    input2.setDegreeOfParallelism(numSubtasksInput2);

    ReduceOperator aggInput2 = ReduceOperator.builder(DummyReduce.class, IntValue.class, 0)
      .input(input2)
      .name("AggLines")
      .build();
    aggInput2.setDegreeOfParallelism(numSubtasksInput2);
   
    // create JoinOperator for joining Orders and LineItems
    JoinOperator joinLiO = JoinOperator.builder(JoinInputs.class, IntValue.class, 0, 0)
      .input1(aggInput1)
      .input2(aggInput2)
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
        BulkIteration iteration = new BulkIteration("Loop");
        iteration.setInput(initialInput);
        iteration.setMaximumNumberOfIterations(2);

        ReduceOperator dummyReduce = ReduceOperator.builder(new DummyReducer(), IntValue.class, 0)
                .input(iteration.getPartialSolution())
                .name("Reduce something")
                .build();

View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
      .field(IntValue.class, 1)
      .field(DoubleValue.class, 2);
   
    // create ReduceOperator for aggregating the result
    // the reducer has a composite key, consisting of the fields 0 and 1
    @SuppressWarnings("unchecked")
    ReduceOperator aggLiO = ReduceOperator.builder(new AggLiO())
      .keyField(LongValue.class, 0)
      .keyField(StringValue.class, 1)
      .input(joinLiO, partJoin2, partJoin1)
      .name("AggLio")
View Full Code Here
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
    JoinOperator joinNCOL = JoinOperator.builder(JoinNCOL.class, IntValue.class, 4, 0)
      .name("JoinNCOL")
      .build();

    ReduceOperator reduce = ReduceOperator.builder(Sum.class)
      .keyField(IntValue.class, 0)
      .keyField(StringValue.class, 1)
      .keyField(StringValue.class, 3)
      .keyField(StringValue.class, 4)
      .keyField(StringValue.class, 5)
      .keyField(StringValue.class, 6)
      .keyField(StringValue.class, 7)
      .name("Reduce")
      .build();

    FileDataSink result = new FileDataSink(new TupleOutputFormat(), resultPath, "Output");

    result.setInput(reduce);
   
    reduce.setInput(joinNCOL);
   
    joinNCOL.setFirstInput(joinCOL);
    joinNCOL.setSecondInput(projectN);
   
    joinCOL.setFirstInput(projectC);
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
        .input2(edges)
        .name("Join Candidate Id With Neighbor")
        .build();

    // find for each neighbor the smallest of all candidates
    ReduceOperator minCandidateId = ReduceOperator.builder(new MinimumComponentIDReduce(), LongValue.class, 0)
        .input(joinWithNeighbors)
        .name("Find Minimum Candidate Id")
        .build();
   
    // join candidates with the solution set and update if the candidate component-id is smaller
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
    FileDataSource source = new FileDataSource(new TextInputFormat(), dataInput, "Input Lines");

    MapOperator mapper = MapOperator.builder(new TokenizeLine()).input(source).name("Tokenize Lines").build();
   
    ReduceOperator reducer = ReduceOperator.builder(CountWords.class, StringValue.class, 0).input(mapper)
        .name("Count Words").build();
   
    FileDataSink out = new FileDataSink(new CsvOutputFormat(), output, reducer, "Word Counts");
   
    CsvOutputFormat.configureRecordFormat(out).recordDelimiter('\n')
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
        new ContractITCaseInputFormat(), inPath);
    DelimitedInputFormat.configureDelimitedFormat(input)
      .recordDelimiter('\n');
    input.setDegreeOfParallelism(config.getInteger("ReduceTest#NoSubtasks", 1));

    ReduceOperator testReducer = ReduceOperator.builder(new TestReducer(), StringValue.class, 0)
      .build();
    testReducer.setDegreeOfParallelism(config.getInteger("ReduceTest#NoSubtasks", 1));
    testReducer.getParameters().setString(PactCompiler.HINT_LOCAL_STRATEGY,
        config.getString("ReduceTest#LocalStrategy", ""));
    testReducer.getParameters().setString(PactCompiler.HINT_SHIP_STRATEGY,
        config.getString("ReduceTest#ShipStrategy", ""));

    FileDataSink output = new FileDataSink(
        new ContractITCaseOutputFormat(), resultPath);
    output.setDegreeOfParallelism(1);

    output.setInput(testReducer);
    testReducer.setInput(input);

    Plan plan = new Plan(output);

    PactCompiler pc = new PactCompiler(new DataStatistics());
    OptimizedPlan op = pc.compile(plan);
View Full Code Here
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
      JoinOperator.builder(PartListJoin.class, IntValue.class , 0, 0)
      .name("partlistJoin")
      .build();

    /* Aggregate sum(amount) by (nation,year): */
    ReduceOperator sumAmountAggregate =
      ReduceOperator.builder(AmountAggregate.class, StringIntPair.class, 0)
      .name("groupyBy")
      .build();

    /* Connect input filters: */
    filterPart.setInput(partInput);
    mapPartsupp.setInput(partSuppInput);
    mapOrder.setInput(ordersInput);
    mapLineItem.setInput(lineItemInput);
    mapSupplier.setInput(supplierInput);

    /* Connect equijoins: */
    partsJoin.setFirstInput(filterPart);
    partsJoin.setSecondInput(mapPartsupp);
    orderedPartsJoin.setFirstInput(mapOrder);
    orderedPartsJoin.setSecondInput(mapLineItem);
    suppliersJoin.setFirstInput(mapSupplier);
    suppliersJoin.setSecondInput(nationInput);
    filteredPartsJoin.setFirstInput(partsJoin);
    filteredPartsJoin.setSecondInput(orderedPartsJoin);
    partListJoin.setFirstInput(filteredPartsJoin);
    partListJoin.setSecondInput(suppliersJoin);

    /* Connect aggregate: */
    sumAmountAggregate.setInput(partListJoin);

    /* Connect sink: */
    FileDataSink result = new FileDataSink(new StringIntPairStringDataOutFormat(), this.outputPath, "Results sink");
    result.setInput(sumAmountAggregate);

View Full Code Here
TOP

Related Classes of eu.stratosphere.api.java.record.operators.ReduceOperator

  • eu.stratosphere.api.java.record.io.avro.example.ReflectiveAvroTypeExample
  • eu.stratosphere.hadoopcompatibility.example.WordCount
  • eu.stratosphere.hadoopcompatibility.example.WordCountWithHadoopOutputFormat
  • eu.stratosphere.pact.compiler.BranchingPlansCompilerTest
  • eu.stratosphere.pact.compiler.DOPChangeTest
  • eu.stratosphere.pact.compiler.GroupOrderTest
  • eu.stratosphere.pact.compiler.HardPlansCompilationTest
  • eu.stratosphere.pact.compiler.ReduceAllTest
  • eu.stratosphere.pact.compiler.UnionPropertyPropagationTest
  • eu.stratosphere.pact.compiler.WorksetIterationsRecordApiCompilerTest
    • 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.