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

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

224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
   
    FileDataSource lineItems =
      new FileDataSource(new IntTupleDataInFormat(), this.lineItemInputPath, "LineItems");
    lineItems.setDegreeOfParallelism(this.degreeOfParallelism);
   
    FileDataSink result =
        new FileDataSink(new StringTupleDataOutFormat(), this.outputPath, "Output");
    result.setDegreeOfParallelism(degreeOfParallelism);
   
    MapOperator lineFilter =
        MapOperator.builder(LiFilter.class)
      .name("LineItemFilter")
      .build();
    lineFilter.setDegreeOfParallelism(degreeOfParallelism);
   
    MapOperator ordersFilter =
        MapOperator.builder(OFilter.class)
      .name("OrdersFilter")
      .build();
    ordersFilter.setDegreeOfParallelism(degreeOfParallelism);
   
    JoinOperator join =
        JoinOperator.builder(JoinLiO.class, IntValue.class, 0, 0)
      .name("OrdersLineitemsJoin")
      .build();
      join.setDegreeOfParallelism(degreeOfParallelism);
   
    ReduceOperator aggregation =
        ReduceOperator.builder(CountAgg.class, StringValue.class, 0)
      .name("AggregateGroupBy")
      .build();
    aggregation.setDegreeOfParallelism(this.degreeOfParallelism);
   
    lineFilter.setInput(lineItems);
    ordersFilter.setInput(orders);
    join.setFirstInput(ordersFilter);
    join.setSecondInput(lineFilter);
    aggregation.setInput(join);
    result.setInput(aggregation);
   
     
    return new Plan(result, "TPC-H 4");
  }
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
        .name("Close Triads")
        .build();
    closeTriads.setParameter("INPUT_SHIP_STRATEGY", "SHIP_REPARTITION_HASH");
    closeTriads.setParameter("LOCAL_STRATEGY", "LOCAL_STRATEGY_HASH_BUILD_SECOND");

    FileDataSink triangles = new FileDataSink(new TriangleOutputFormat(), output, closeTriads, "Triangles");

    Plan p = new Plan(triangles, "Enumerate Triangles");
    p.setDefaultParallelism(numSubTasks);
    return p;
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
  @Test
  public void testReduce() {
    // construct the plan
    FileDataSource source = new FileDataSource(new DummyInputFormat(), IN_FILE, "Source");
    ReduceOperator reduce1 = ReduceOperator.builder(new IdentityReduce()).name("Reduce1").input(source).build();
    FileDataSink sink = new FileDataSink(new DummyOutputFormat(), OUT_FILE, "Sink");
    sink.setInput(reduce1);
    Plan plan = new Plan(sink, "AllReduce Test");
    plan.setDefaultParallelism(DEFAULT_PARALLELISM);
   
   
    try {
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
   
    iteration.setNextWorkset(updateComponentId);
    iteration.setSolutionSetDelta(updateComponentId);

    // create DataSinkContract for writing the new cluster positions
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
      .fieldDelimiter(' ')
      .field(LongValue.class, 0)
      .field(LongValue.class, 1);
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
   
    ReduceOperator reduce = ReduceOperator.builder(new IdentityReduce()).keyField(IntValue.class, 2).name("Reduce").input(source).build();
    Ordering groupOrder = new Ordering(5, StringValue.class, Order.DESCENDING);
    reduce.setGroupOrder(groupOrder);
   
    FileDataSink sink = new FileDataSink(new DummyOutputFormat(), OUT_FILE, reduce, "Sink");
   
   
    Plan plan = new Plan(sink, "Test Temp Task");
    plan.setDefaultParallelism(DEFAULT_PARALLELISM);
   
View Full Code Here
111
112
113
114
115
116
117
118
119
120
121
    Ordering groupOrder2 = new Ordering(1, StringValue.class, Order.DESCENDING);
    groupOrder2.appendOrdering(4, DoubleValue.class, Order.ASCENDING);
    coGroup.setGroupOrderForInputOne(groupOrder1);
    coGroup.setGroupOrderForInputTwo(groupOrder2);
   
    FileDataSink sink = new FileDataSink(new DummyOutputFormat(), OUT_FILE, coGroup, "Sink");
   
    Plan plan = new Plan(sink, "Reduce Group Order Test");
    plan.setDefaultParallelism(DEFAULT_PARALLELISM);
   
    OptimizedPlan oPlan;
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
        .input1(buildTriads).input2(projectOutCounts)
        .name("Close Triads").build();
    closeTriads.setParameter("INPUT_SHIP_STRATEGY", "SHIP_REPARTITION_HASH");
    closeTriads.setParameter("LOCAL_STRATEGY", "LOCAL_STRATEGY_HASH_BUILD_SECOND");

    FileDataSink triangles = new FileDataSink(new TriangleOutputFormat(), output, closeTriads, "Triangles");

    Plan p = new Plan(triangles, "Enumerate Triangles");
    p.setDefaultParallelism(numSubTasks);
    return p;
  }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
    CollectionDataSource source2 = new CollectionDataSource(tmp, "test_collection");

    JoinOperator join = JoinOperator.builder(Join.class, IntValue.class, 0, 0)
      .input1(source).input2(source2).build();

    FileDataSink out = new FileDataSink(new CsvOutputFormat(), output, join, "Collection Join");
    CsvOutputFormat.configureRecordFormat(out)
      .recordDelimiter('\n')
      .fieldDelimiter(' ')
      .field(StringValue.class, 0)
      .field(IntValue.class, 1);
View Full Code Here
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
      .name("AggCo")
      .build();
    aggCO.setDegreeOfParallelism(numSubtasks);

    // create DataSinkContract for writing the result
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, "Output");
    result.setDegreeOfParallelism(numSubtasks);
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(IntValue.class, 0)
      .field(StringValue.class, 1);

    // assemble the plan
    result.setInput(aggCO);
    aggCO.setInput(joinCO);
    joinCO.setFirstInput(orders);
    joinCO.setSecondInput(customers);

    return new Plan(result, "TPCH Asterix");
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
   
    iteration.setNextWorkset(minAndUpdate);
    iteration.setSolutionSetDelta(minAndUpdate);

    // create DataSinkContract for writing the new cluster positions
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
      .fieldDelimiter(' ')
      .field(LongValue.class, 0)
      .field(LongValue.class, 1);
View Full Code Here
TOP

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

  • eu.stratosphere.addons.hbase.example.HBaseReadExample
  • eu.stratosphere.api.java.typeutils.RecordTypeInfo
  • eu.stratosphere.hadoopcompatibility.example.WordCount
  • eu.stratosphere.pact.compiler.AdditionalOperatorsTest
  • 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
    • 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.