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

Examples of org.apache.flink.api.java.record.io.CsvInputFormat

108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
  @SuppressWarnings("unchecked")
  private static Plan getPlanForWorksetConnectedComponentsWithSolutionSetAsFirstInput(
      int numSubTasks, String verticesInput, String edgeInput, String output, int maxIterations)
  {
    // 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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
    final String ordersPath    = (args.length > 1 ? args[1] : "");
    final String lineitemsPath = (args.length > 2 ? args[2] : "");
    final String output        = (args.length > 3 ? args[3] : "");

    // create DataSourceContract for Orders input
    FileDataSource orders = new FileDataSource(new CsvInputFormat(), ordersPath, "Orders");
    CsvInputFormat.configureRecordFormat(orders)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)    // order id
      .field(IntValue.class, 7)     // ship prio
      .field(StringValue.class, 2, 2)  // order status
      .field(StringValue.class, 4, 10)  // order date
      .field(StringValue.class, 5, 8);  // order prio

    // create DataSourceContract for LineItems input
    FileDataSource lineitems = new FileDataSource(new CsvInputFormat(), lineitemsPath, "LineItems");
    CsvInputFormat.configureRecordFormat(lineitems)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)    // order id
      .field(DoubleValue.class, 5);  // extended price
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
    String output = (args.length > 3 ? args[3] : "");
    int numIterations = (args.length > 4 ? Integer.parseInt(args[4]) : 2);

    // data source data point input
    @SuppressWarnings("unchecked")
    FileDataSource pointsSource = new FileDataSource(new CsvInputFormat('|', IntValue.class, DoubleValue.class, DoubleValue.class, DoubleValue.class), dataPointInput, "Data Points");

    // data source for cluster center input
    @SuppressWarnings("unchecked")
    FileDataSource clustersSource = new FileDataSource(new CsvInputFormat('|', IntValue.class, DoubleValue.class, DoubleValue.class, DoubleValue.class), clusterInput, "Centers");
   
    MapOperator dataPoints = MapOperator.builder(new PointBuilder()).name("Build data points").input(pointsSource).build();
   
    MapOperator clusterPoints = MapOperator.builder(new PointBuilder()).name("Build cluster points").input(clustersSource).build();
   
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
  @SuppressWarnings("unchecked")
  public static Plan getPlan(int numSubTasks, String verticesInput, String edgeInput, String output, int maxIterations) {

    // 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
TOP

Related Classes of org.apache.flink.api.java.record.io.CsvInputFormat

  • org.apache.flink.api.common.operators.CompilerHints
  • org.apache.flink.test.broadcastvars.BroadcastBranchingITCase
  • org.apache.flink.test.broadcastvars.BroadcastVarsNepheleITCase
  • org.apache.flink.test.broadcastvars.KMeansIterativeNepheleITCase
  • org.apache.flink.test.compiler.iterations.ConnectedComponentsTest
  • org.apache.flink.test.iterative.CoGroupConnectedComponentsITCase
  • org.apache.flink.test.iterative.ConnectedComponentsWithDeferredUpdateITCase
  • org.apache.flink.test.iterative.ConnectedComponentsWithSolutionSetFirstITCase
  • org.apache.flink.test.iterative.nephele.ConnectedComponentsNepheleITCase
  • org.apache.flink.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.