Package org.apache.flink.api.java.record.operators

Examples of org.apache.flink.api.java.record.operators.FileDataSource

101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
 
  @SuppressWarnings("unchecked")
  public static Plan getPlan(int numSubTasks, String verticesInput, String edgeInput, String output, int maxIterations, boolean extraMap) {

    // data source for initial vertices
    FileDataSource initialVertices = new FileDataSource(new CsvInputFormat(' ', LongValue.class), verticesInput, "Vertices");
   
    MapOperator verticesWithId = MapOperator.builder(DuplicateLongMap.class).input(initialVertices).name("Assign Vertex Ids").build();
   
    // the loop takes the vertices as the solution set and changed vertices as the workset
    // initially, all vertices are changed
    DeltaIteration iteration = new DeltaIteration(0, "Connected Components Iteration");
    iteration.setInitialSolutionSet(verticesWithId);
    iteration.setInitialWorkset(verticesWithId);
    iteration.setMaximumNumberOfIterations(maxIterations);
   
    // data source for the edges
    FileDataSource edges = new FileDataSource(new CsvInputFormat(' ', LongValue.class, LongValue.class), edgeInput, "Edges");

    // join workset (changed vertices) with the edges to propagate changes to neighbors
    JoinOperator joinWithNeighbors = JoinOperator.builder(new NeighborWithComponentIDJoin(), LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(edges)
View Full Code Here
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
    final String edgeInput = (args.length > 2 ? args[2] : "");
    final String output = (args.length > 3 ? args[3] : "");
    final int maxIterations = (args.length > 4 ? Integer.parseInt(args[4]) : 1);

    // data source for initial vertices
    FileDataSource initialVertices = new FileDataSource(new CsvInputFormat(' ', LongValue.class), verticesInput, "Vertices");
   
    MapOperator verticesWithId = MapOperator.builder(DuplicateLongMap.class).input(initialVertices).name("Assign Vertex Ids").build();
   
    // the loop takes the vertices as the solution set and changed vertices as the workset
    // initially, all vertices are changed
    DeltaIteration iteration = new DeltaIteration(0, "Connected Components Iteration");
    iteration.setInitialSolutionSet(verticesWithId);
    iteration.setInitialWorkset(verticesWithId);
    iteration.setMaximumNumberOfIterations(maxIterations);
   
    // data source for the edges
    FileDataSource edges = new FileDataSource(new CsvInputFormat(' ', LongValue.class, LongValue.class), edgeInput, "Edges");

    // join workset (changed vertices) with the edges to propagate changes to neighbors
    JoinOperator joinWithNeighbors = JoinOperator.builder(new NeighborWithComponentIDJoin(), LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(edges)
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
      this.degreeOfParallelism = Integer.parseInt(args[0]);
      this.lineItemInputPath = args[1];
      this.outputPath = args[2];
    }
   
    FileDataSource lineItems =
      new FileDataSource(new IntTupleDataInFormat(), this.lineItemInputPath, "LineItems");
    lineItems.setDegreeOfParallelism(this.degreeOfParallelism);
   
    FileDataSink result =
      new FileDataSink(new StringTupleDataOutFormat(), this.outputPath, "Output");
    result.setDegreeOfParallelism(this.degreeOfParallelism);
   
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
  @Override
  protected Plan getTestJob() {
    String input1Path = config.getString("UnionTest#Input1Path", "").equals("empty") ? emptyInPath : inPath;
    String input2Path = config.getString("UnionTest#Input2Path", "").equals("empty") ? emptyInPath : inPath;

    FileDataSource input1 = new FileDataSource(
      new ContractITCaseInputFormat(), input1Path);
    DelimitedInputFormat.configureDelimitedFormat(input1)
      .recordDelimiter('\n');
    input1.setDegreeOfParallelism(config.getInteger("UnionTest#NoSubtasks", 1));
   
    FileDataSource input2 = new FileDataSource(
        new ContractITCaseInputFormat(), input2Path);
    DelimitedInputFormat.configureDelimitedFormat(input2)
      .recordDelimiter('\n');
    input2.setDegreeOfParallelism(config.getInteger("UnionTest#NoSubtasks", 1));
   
    MapOperator testMapper = MapOperator.builder(new TestMapper()).build();
    testMapper.setDegreeOfParallelism(config.getInteger("UnionTest#NoSubtasks", 1));

    FileDataSink output = new FileDataSink(
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
    return getTestPlanPlan(DOP, dataPath, resultPath);
  }
 
  private static Plan getTestPlanPlan(int numSubTasks, String input, String output) {

    FileDataSource initialInput = new FileDataSource(TextInputFormat.class, input, "input");
   
    BulkIteration iteration = new BulkIteration("Loop");
    iteration.setInput(initialInput);
    iteration.setMaximumNumberOfIterations(5);
    Assert.assertTrue(iteration.getMaximumNumberOfIterations() > 1);
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
  public Plan getPlan(String... args) {
    int numSubTasks = (args.length > 0 ? Integer.parseInt(args[0]) : 1);
    String dataInput = (args.length > 1 ? args[1] : "");
    String output = (args.length > 2 ? args[2] : "");

    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();
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
   
    int dop = this.config.getInteger("GroupOrderTest#NumSubtasks", 1);
   
    @SuppressWarnings("unchecked")
    CsvInputFormat format = new CsvInputFormat(',', IntValue.class, IntValue.class);
    FileDataSource source = new FileDataSource(format, this.textPath, "Source");
   
    ReduceOperator reducer = ReduceOperator.builder(CheckingReducer.class)
      .keyField(IntValue.class, 0)
      .input(source)
      .name("Ordered Reducer")
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
    }
  }

  @Override
  protected Plan getTestJob() {
    FileDataSource input = new FileDataSource(
        new ContractITCaseInputFormat(), inPath);
    DelimitedInputFormat.configureDelimitedFormat(input)
      .recordDelimiter('\n');
    input.setDegreeOfParallelism(config.getInteger("MapTest#NoSubtasks", 1));

    MapOperator testMapper = MapOperator.builder(new TestMapper()).build();
    testMapper.setDegreeOfParallelism(config.getInteger("MapTest#NoSubtasks", 1));

    FileDataSink output = new FileDataSink(
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
  }

 
  private static Plan getTestPlanPlan(int numSubTasks, String input, String output) {

    FileDataSource initialInput = new FileDataSource(TextInputFormat.class, input, "input");
   
    BulkIteration iteration = new BulkIteration("Loop");
    iteration.setInput(initialInput);
    iteration.setMaximumNumberOfIterations(5);
   
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
    final String clusterInput = (args.length > 2 ? args[2] : "");
    final String output = (args.length > 3 ? args[3] : "");
    final int numIterations = (args.length > 4 ? Integer.parseInt(args[4]) : 1);

    // create DataSourceContract for cluster center input
    FileDataSource initialClusterPoints = new FileDataSource(new PointInFormat(), clusterInput, "Centers");
    initialClusterPoints.setDegreeOfParallelism(1);
   
    BulkIteration iteration = new BulkIteration("K-Means Loop");
    iteration.setInput(initialClusterPoints);
    iteration.setMaximumNumberOfIterations(numIterations);
   
    // create DataSourceContract for data point input
    FileDataSource dataPoints = new FileDataSource(new PointInFormat(), dataPointInput, "Data Points");

    // create CrossOperator for distance computation
    CrossOperator computeDistance = CrossOperator.builder(new ComputeDistance())
        .input1(dataPoints)
        .input2(iteration.getPartialSolution())
        .name("Compute Distances")
        .build();

    // create ReduceOperator for finding the nearest cluster centers
    ReduceOperator findNearestClusterCenters = ReduceOperator.builder(new FindNearestCenter(), IntValue.class, 0)
        .input(computeDistance)
        .name("Find Nearest Centers")
        .build();

    // create ReduceOperator for computing new cluster positions
    ReduceOperator recomputeClusterCenter = ReduceOperator.builder(new RecomputeClusterCenter(), IntValue.class, 0)
        .input(findNearestClusterCenters)
        .name("Recompute Center Positions")
        .build();
    iteration.setNextPartialSolution(recomputeClusterCenter);
   
    // create DataSourceContract for data point input
    FileDataSource dataPoints2 = new FileDataSource(new PointInFormat(), dataPointInput, "Data Points 2");
   
    // compute distance of points to final clusters
    CrossOperator computeFinalDistance = CrossOperator.builder(new ComputeDistance())
        .input1(dataPoints2)
        .input2(iteration)
View Full Code Here
TOP

Related Classes of org.apache.flink.api.java.record.operators.FileDataSource

  • org.apache.flink.compiler.AdditionalOperatorsTest
  • org.apache.flink.compiler.BranchingPlansCompilerTest
  • org.apache.flink.compiler.DOPChangeTest
  • org.apache.flink.compiler.GroupOrderTest
  • org.apache.flink.compiler.HardPlansCompilationTest
  • org.apache.flink.compiler.ReduceAllTest
  • org.apache.flink.compiler.UnionPropertyPropagationTest
  • org.apache.flink.compiler.WorksetIterationsRecordApiCompilerTest
  • org.apache.flink.test.accumulators.AccumulatorIterativeITCase
  • org.apache.flink.test.broadcastvars.BroadcastBranchingITCase
    • 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.