Package eu.stratosphere.api.java

Examples of eu.stratosphere.api.java.ExecutionEnvironment

86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
   * A mapper that preserves fields 0, 1, 2 of a tuple data set.
   */
  @Test
  public void translateUnaryFunctionAnnotationTuples() {
    try {
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
     
      @SuppressWarnings("unchecked")
      DataSet<Tuple3<Long, String, Integer>> input = env.fromElements(new Tuple3<Long, String, Integer>(3l, "test", 42));
      input.map(new IndividualConstantMapper<Long, String, Integer>()).print();
     
      Plan plan = env.createProgramPlan();
     
      GenericDataSinkBase<?> sink = plan.getDataSinks().iterator().next();
      MapOperatorBase<?, ?, ?> mapper = (MapOperatorBase<?, ?, ?>) sink.getInput();
     
      SingleInputSemanticProperties semantics = mapper.getSemanticProperties();
View Full Code Here
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
   * A join that preserves tuple fields from both sides.
   */
  @Test
  public void translateBinaryFunctionAnnotationTuples() {
    try {
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
     
      @SuppressWarnings("unchecked")
      DataSet<Tuple2<Long, String>> input1 = env.fromElements(new Tuple2<Long, String>(3l, "test"));
      @SuppressWarnings("unchecked")
      DataSet<Tuple2<Long, Double>> input2 = env.fromElements(new Tuple2<Long, Double>(3l, 3.1415));
     
      input1.join(input2).where(0).equalTo(0).with(new ForwardingTupleJoin<Long, String, Long, Double>())
        .print();
     
      Plan plan = env.createProgramPlan();
     
      GenericDataSinkBase<?> sink = plan.getDataSinks().iterator().next();
      JoinOperatorBase<?, ?, ?, ?> join = (JoinOperatorBase<?, ?, ?, ?>) sink.getInput();
     
      DualInputSemanticProperties semantics = join.getSemanticProperties();
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
public class GroupReduceCompilationTest extends CompilerTestBase implements java.io.Serializable {

  @Test
  public void testAllGroupReduceNoCombiner() {
    try {
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
      env.setDegreeOfParallelism(8);
     
      DataSet<Double> data = env.fromElements(0.2, 0.3, 0.4, 0.5).name("source");
     
      data.reduceGroup(new GroupReduceFunction<Double, Double>() {
        public void reduce(Iterator<Double> values, Collector<Double> out) {}
      }).name("reducer")
      .print().name("sink");
     
      Plan p = env.createProgramPlan();
      OptimizedPlan op = compileNoStats(p);
     
      OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(op);
     
     
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
  @Test
  public void translateNonGroupedReduce() {
    try {
      final int DOP = 8;
      ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment(DOP);
     
      DataSet<Tuple3<Double, StringValue, LongValue>> initialData = getSourceDataSet(env);
     
      initialData.reduce(new ReduceFunction<Tuple3<Double,StringValue,LongValue>>() {
        public Tuple3<Double, StringValue, LongValue> reduce(Tuple3<Double, StringValue, LongValue> value1, Tuple3<Double, StringValue, LongValue> value2) {
          return value1;
        }
      }).print();
     
      Plan p = env.createProgramPlan();
     
      GenericDataSinkBase<?> sink = p.getDataSinks().iterator().next();
     
      ReduceOperatorBase<?, ?> reducer = (ReduceOperatorBase<?, ?>) sink.getInput();
     
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 
  @Test
  public void translateGroupedReduceNoMapper() {
    try {
      final int DOP = 8;
      ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment(DOP);
     
      DataSet<Tuple3<Double, StringValue, LongValue>> initialData = getSourceDataSet(env);
     
      initialData
        .groupBy(2)
        .reduce(new ReduceFunction<Tuple3<Double,StringValue,LongValue>>() {
          public Tuple3<Double, StringValue, LongValue> reduce(Tuple3<Double, StringValue, LongValue> value1, Tuple3<Double, StringValue, LongValue> value2) {
            return value1;
          }
        })
        .print();
     
      Plan p = env.createProgramPlan();
     
      GenericDataSinkBase<?> sink = p.getDataSinks().iterator().next();
     
      ReduceOperatorBase<?, ?> reducer = (ReduceOperatorBase<?, ?>) sink.getInput();
     
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
public class SpargelCompilerTest extends CompilerTestBase {

//  @Test
  public void testSpargelCompiler() {
    try {
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
      env.setDegreeOfParallelism(DEFAULT_PARALLELISM);
      // compose test program
      {
        DataSet<Long> vertexIds = env.generateSequence(1, 2);
       
        @SuppressWarnings("unchecked")
        DataSet<Tuple2<Long, Long>> edges = env.fromElements(new Tuple2<Long, Long>(1L, 2L));
       
        DataSet<Tuple2<Long, Long>> initialVertices = vertexIds.map(new IdAssigner());
        DataSet<Tuple2<Long, Long>> result = initialVertices.runOperation(VertexCentricIteration.withPlainEdges(edges, new CCUpdater(), new CCMessager(), 100));
       
        result.print();
      }
     
      Plan p = env.createProgramPlan("Spargel Connected Components");
      OptimizedPlan op = compileNoStats(p);
     
      // check the sink
      SinkPlanNode sink = op.getDataSinks().iterator().next();
      assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
 
  @Test
  public void translateGroupedReduceWithkeyExtractor() {
    try {
      final int DOP = 8;
      ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment(DOP);
     
      DataSet<Tuple3<Double, StringValue, LongValue>> initialData = getSourceDataSet(env);
     
      initialData
        .groupBy(new KeySelector<Tuple3<Double,StringValue,LongValue>, StringValue>() {
          public StringValue getKey(Tuple3<Double, StringValue, LongValue> value) {
            return value.f1;
          }
        })
        .reduce(new ReduceFunction<Tuple3<Double,StringValue,LongValue>>() {
          public Tuple3<Double, StringValue, LongValue> reduce(Tuple3<Double, StringValue, LongValue> value1, Tuple3<Double, StringValue, LongValue> value2) {
            return value1;
          }
        }).setParallelism(4)
        .print();
     
      Plan p = env.createProgramPlan();
     
      GenericDataSinkBase<?> sink = p.getDataSinks().iterator().next();
     
     
      MapOperatorBase<?, ?, ?> keyProjector = (MapOperatorBase<?, ?, ?>) sink.getInput();
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
  }
 
  @Test
  public void testAllReduceWithCombiner() {
    try {
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
      env.setDegreeOfParallelism(8);
     
      DataSet<Long> data = env.generateSequence(1, 8000000).name("source");
     
      ReduceGroupOperator<Long, Long> reduced = data.reduceGroup(new GroupReduceFunction<Long, Long>() {
        public void reduce(Iterator<Long> values, Collector<Long> out) {}
      }).name("reducer");
     
      reduced.setCombinable(true);
      reduced.print().name("sink");
     
      Plan p = env.createProgramPlan();
      OptimizedPlan op = compileNoStats(p);
     
      OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(op);
     
      // get the original nodes
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
  public void testSpargelCompilerWithBroadcastVariable() {
    try {
      final String BC_VAR_NAME = "borat variable";
     
     
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
      env.setDegreeOfParallelism(DEFAULT_PARALLELISM);
      // compose test program
      {
        DataSet<Long> bcVar = env.fromElements(1L);
       
        DataSet<Long> vertexIds = env.generateSequence(1, 2);
       
        @SuppressWarnings("unchecked")
        DataSet<Tuple2<Long, Long>> edges = env.fromElements(new Tuple2<Long, Long>(1L, 2L));
       
        DataSet<Tuple2<Long, Long>> initialVertices = vertexIds.map(new IdAssigner());
       
        VertexCentricIteration<Long, Long, Long, ?> vcIter = VertexCentricIteration.withPlainEdges(edges, new CCUpdater(), new CCMessager(), 100);
        vcIter.addBroadcastSetForMessagingFunction(BC_VAR_NAME, bcVar);
        vcIter.addBroadcastSetForUpdateFunction(BC_VAR_NAME, bcVar);
       
        DataSet<Tuple2<Long, Long>> result = initialVertices.runOperation(vcIter);
       
        result.print();
      }
     
      Plan p = env.createProgramPlan("Spargel Connected Components");
      OptimizedPlan op = compileNoStats(p);
     
      // check the sink
      SinkPlanNode sink = op.getDataSinks().iterator().next();
      assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
View Full Code Here
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
 
 
  @Test
  public void testGroupedReduceWithFieldPositionKeyNonCombinable() {
    try {
      ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
      env.setDegreeOfParallelism(8);
     
      DataSet<Tuple2<String, Double>> data = env.readCsvFile("file:///will/never/be/read").types(String.class, Double.class)
        .name("source").setParallelism(6);
     
      data
        .groupBy(1)
        .reduceGroup(new GroupReduceFunction<Tuple2<String, Double>, Tuple2<String, Double>>() {
        public void reduce(Iterator<Tuple2<String, Double>> values, Collector<Tuple2<String, Double>> out) {}
      }).name("reducer")
      .print().name("sink");
     
      Plan p = env.createProgramPlan();
      OptimizedPlan op = compileNoStats(p);
     
      OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(op);
     
      // get the original nodes
View Full Code Here
TOP

Related Classes of eu.stratosphere.api.java.ExecutionEnvironment

  • $.Job
  • $.WordCountJob
  • eu.stratosphere.api.avro.testjar.AvroExternalJarProgram
  • eu.stratosphere.api.java.functions.SemanticPropertiesTranslationTest
  • eu.stratosphere.api.java.io.CsvReader
  • eu.stratosphere.api.java.io.jdbc.example.JDBCExample
  • eu.stratosphere.api.java.io.TextInputFormat
  • eu.stratosphere.api.java.io.TextValueInputFormat
  • eu.stratosphere.api.java.operator.AggregateOperatorTest
  • eu.stratosphere.api.java.operator.CoGroupOperatorTest
    • 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.