Package eu.stratosphere.api.java.record.io

Examples of eu.stratosphere.api.java.record.io.CsvInputFormat

89
90
91
92
93
94
95
96
97
98
99
100
  // -------------------------------------------------------------------------------------------------------------
  // Job vertex builder methods
  // -------------------------------------------------------------------------------------------------------------

  private static JobInputVertex createPointsInput(JobGraph jobGraph, String pointsPath, int numSubTasks, TypeSerializerFactory<?> serializer) {
    @SuppressWarnings("unchecked")
    CsvInputFormat pointsInFormat = new CsvInputFormat('|', IntValue.class, DoubleValue.class, DoubleValue.class, DoubleValue.class);
    JobInputVertex pointsInput = JobGraphUtils.createInput(pointsInFormat, pointsPath, "[Points]", jobGraph, numSubTasks, numSubTasks);
    {
      TaskConfig taskConfig = new TaskConfig(pointsInput.getConfiguration());
      taskConfig.addOutputShipStrategy(ShipStrategyType.FORWARD);
      taskConfig.setOutputSerializer(serializer);
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
    return pointsInput;
  }

  private static JobInputVertex createCentersInput(JobGraph jobGraph, String centersPath, int numSubTasks, TypeSerializerFactory<?> serializer) {
    @SuppressWarnings("unchecked")
    CsvInputFormat modelsInFormat = new CsvInputFormat('|', IntValue.class, DoubleValue.class, DoubleValue.class, DoubleValue.class);
    JobInputVertex modelsInput = JobGraphUtils.createInput(modelsInFormat, centersPath, "[Models]", jobGraph, numSubTasks, numSubTasks);

    {
      TaskConfig taskConfig = new TaskConfig(modelsInput.getConfiguration());
      taskConfig.addOutputShipStrategy(ShipStrategyType.FORWARD);
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
  //                      /
  //    Sc3(id,y) --------
  @Override
  protected Plan getTestJob() {
    // Sc1 generates M parameters a,b,c for second degree polynomials P(x) = ax^2 + bx + c identified by id
    FileDataSource sc1 = new FileDataSource(new CsvInputFormat(), sc1Path);
    CsvInputFormat.configureRecordFormat(sc1).fieldDelimiter(' ').field(StringValue.class, 0).field(IntValue.class, 1)
        .field(IntValue.class, 2).field(IntValue.class, 3);

    // Sc2 generates N x values to be evaluated with the polynomial identified by id
    FileDataSource sc2 = new FileDataSource(new CsvInputFormat(), sc2Path);
    CsvInputFormat.configureRecordFormat(sc2).fieldDelimiter(' ').field(StringValue.class, 0).field(IntValue.class, 1);

    // Sc3 generates N y values to be evaluated with the polynomial identified by id
    FileDataSource sc3 = new FileDataSource(new CsvInputFormat(), sc3Path);
    CsvInputFormat.configureRecordFormat(sc3).fieldDelimiter(' ').field(StringValue.class, 0).field(IntValue.class, 1);

    // Jn1 matches x and y values on id and emits (id, x, y) triples
    JoinOperator jn1 = JoinOperator.builder(Jn1.class, StringValue.class, 0, 0).input1(sc2).input2(sc3).build();
View Full Code Here
219
220
221
222
223
224
225
226
227
228
229
  // Job vertex builder methods
  // -------------------------------------------------------------------------------------------------------------

  @SuppressWarnings("unchecked")
  private static JobInputVertex createPointsInput(JobGraph jobGraph, String pointsPath, int numSubTasks, TypeSerializerFactory<?> serializer) {
    CsvInputFormat pointsInFormat = new CsvInputFormat(' ', LongValue.class, LongValue.class, LongValue.class, LongValue.class);
    JobInputVertex pointsInput = JobGraphUtils.createInput(pointsInFormat, pointsPath, "Input[Points]", jobGraph, numSubTasks, numSubTasks);

    {
      TaskConfig taskConfig = new TaskConfig(pointsInput.getConfiguration());
      taskConfig.addOutputShipStrategy(ShipStrategyType.FORWARD);
View Full Code Here
233
234
235
236
237
238
239
240
241
242
243
    return pointsInput;
  }

  @SuppressWarnings("unchecked")
  private static JobInputVertex createModelsInput(JobGraph jobGraph, String pointsPath, int numSubTasks, TypeSerializerFactory<?> serializer) {
    CsvInputFormat modelsInFormat = new CsvInputFormat(' ', LongValue.class, LongValue.class, LongValue.class, LongValue.class);
    JobInputVertex modelsInput = JobGraphUtils.createInput(modelsInFormat, pointsPath, "Input[Models]", jobGraph, numSubTasks, numSubTasks);

    {
      TaskConfig taskConfig = new TaskConfig(modelsInput.getConfiguration());
      taskConfig.addOutputShipStrategy(ShipStrategyType.BROADCAST);
View Full Code Here
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
  @SuppressWarnings("unchecked")
  private static Plan getPlanForWorksetConnectedComponentsWithSolutionSetAsFirstInput(
      int numSubTasks, String verticesInput, String edgeInput, String output, int maxIterations)
  {
    // create DataSourceContract for the vertices
    FileDataSource initialVertices = new FileDataSource(new CsvInputFormat(' ', LongValue.class), verticesInput, "Vertices");
   
    MapOperator verticesWithId = MapOperator.builder(DuplicateLongMap.class).input(initialVertices).name("Assign Vertex Ids").build();
   
    DeltaIteration iteration = new DeltaIteration(0, "Connected Components Iteration");
    iteration.setInitialSolutionSet(verticesWithId);
    iteration.setInitialWorkset(verticesWithId);
    iteration.setMaximumNumberOfIterations(maxIterations);
   
    // create DataSourceContract for the edges
    FileDataSource edges = new FileDataSource(new CsvInputFormat(' ', LongValue.class, LongValue.class), edgeInput, "Edges");

    // create CrossOperator for distance computation
    JoinOperator joinWithNeighbors = JoinOperator.builder(new NeighborWithComponentIDJoin(), LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(edges)
View Full Code Here
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
    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();
   
    DeltaIteration iteration = new DeltaIteration(0, "Connected Components Iteration");
    iteration.setInitialSolutionSet(verticesWithId);
    iteration.setInitialWorkset(verticesWithId);
    iteration.setMaximumNumberOfIterations(maxIterations);
   
    // create DataSourceContract for the edges
    FileDataSource edges = new FileDataSource(new CsvInputFormat(' ', LongValue.class, LongValue.class), edgeInput, "Edges");

    // create CrossOperator for distance computation
    JoinOperator joinWithNeighbors = JoinOperator.builder(new NeighborWithComponentIDJoin(), LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(edges)
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
  @Override
  protected Plan getTestJob() {
   
    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)
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
    // parse job parameters
    int numSubTasks = (args.length > 0 ? Integer.parseInt(args[0]) : 1);
    String dataInput = (args.length > 1 ? args[1] : "");
    String output = (args.length > 2 ? args[2] : "");

    @SuppressWarnings("unchecked")
    CsvInputFormat format = new CsvInputFormat(' ', IntValue.class, IntValue.class);
    FileDataSource input = new FileDataSource(format, dataInput, "Input");
   
    // create the reduce contract and sets the key to the first field
    ReduceOperator sorter = ReduceOperator.builder(new IdentityReducer(), IntValue.class, 0)
      .input(input)
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
    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
TOP

Related Classes of eu.stratosphere.api.java.record.io.CsvInputFormat

  • eu.stratosphere.api.common.operators.CompilerHints
  • eu.stratosphere.test.broadcastvars.BroadcastBranchingITCase
  • eu.stratosphere.test.broadcastvars.BroadcastVarsNepheleITCase
  • eu.stratosphere.test.broadcastvars.KMeansIterativeNepheleITCase
  • eu.stratosphere.test.compiler.iterations.ConnectedComponentsTest
  • eu.stratosphere.test.iterative.CoGroupConnectedComponentsITCase
  • eu.stratosphere.test.iterative.ConnectedComponentsWithDeferredUpdateITCase
  • eu.stratosphere.test.iterative.ConnectedComponentsWithSolutionSetFirstITCase
  • eu.stratosphere.test.iterative.nephele.ConnectedComponentsNepheleITCase
  • eu.stratosphere.test.recordJobs.graph.ConnectedComponentsWithCoGroup
    • 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.