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

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

258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
  @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
67
68
69
70
71
72
73
74
75
76
77
78
    KMeansBroadcast kmi = new KMeansBroadcast();
    Plan p = kmi.getPlan(String.valueOf(DEFAULT_PARALLELISM), IN_FILE, IN_FILE, OUT_FILE, String.valueOf(20));
   
    // set the statistics
    OperatorResolver cr = getContractResolver(p);
    FileDataSource pointsSource = cr.getNode(DATAPOINTS);
    FileDataSource centersSource = cr.getNode(CENTERS);
    setSourceStatistics(pointsSource, 100l*1024*1024*1024, 32f);
    setSourceStatistics(centersSource, 1024*1024, 32f);
   
    OptimizedPlan plan = compileWithStats(p);
    checkPlan(plan);
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
  @Override
  protected JobGraph getFailingJobGraph() throws Exception {
   
    // init data source
    FileDataSource input = new FileDataSource(new ContractITCaseInputFormat(), inputPath);

    // init failing map task
    MapOperator testMapper = MapOperator.builder(FailingMapper.class).build();

    // init data sink
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
  @Override
  protected JobGraph getJobGraph() throws Exception {
   
    // init data source
    FileDataSource input = new FileDataSource(new ContractITCaseInputFormat(), inputPath);

    // init (working) map task
    MapOperator testMapper = MapOperator.builder(TestMapper.class).build();

    // init data sink
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
  }

  @Override
  protected Plan getTestJob() {

    FileDataSource input_left = new FileDataSource(
        new ContractITCaseInputFormat(), leftInPath);
    DelimitedInputFormat.configureDelimitedFormat(input_left)
      .recordDelimiter('\n');
    input_left.setDegreeOfParallelism(config.getInteger("CrossTest#NoSubtasks", 1));

    FileDataSource input_right = new FileDataSource(
        new ContractITCaseInputFormat(), rightInPath);
    DelimitedInputFormat.configureDelimitedFormat(input_right)
      .recordDelimiter('\n');
    input_right.setDegreeOfParallelism(config.getInteger("CrossTest#NoSubtasks", 1));

    CrossOperator testCross = CrossOperator.builder(new TestCross()).build();
    testCross.setDegreeOfParallelism(config.getInteger("CrossTest#NoSubtasks", 1));
    testCross.getParameters().setString(PactCompiler.HINT_LOCAL_STRATEGY,
        config.getString("CrossTest#LocalStrategy", ""));
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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
     * 1: DOCUMENT_TEXT
     */
    // Create DataSourceContract for documents relation
    @SuppressWarnings("unchecked")
    CsvInputFormat docsFormat = new CsvInputFormat('|', StringValue.class, StringValue.class);
    FileDataSource docs = new FileDataSource(docsFormat, docsInput, "Docs Input");
   
    /*
     * Output Format:
     * 0: URL
     * 1: RANK
     * 2: AVG_DURATION
     */
    // Create DataSourceContract for ranks relation
    FileDataSource ranks = new FileDataSource(new CsvInputFormat(), ranksInput, "Ranks input");
    CsvInputFormat.configureRecordFormat(ranks)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(StringValue.class, 1)
      .field(IntValue.class, 0)
      .field(IntValue.class, 2);

    /*
     * Output Format:
     * 0: URL
     * 1: DATE
     */
    // Create DataSourceContract for visits relation
    @SuppressWarnings("unchecked")
    CsvInputFormat visitsFormat = new CsvInputFormat('|', null, StringValue.class, StringValue.class);
    FileDataSource visits = new FileDataSource(visitsFormat, visitsInput, "Visits input:q");

    // Create MapOperator for filtering the entries from the documents
    // relation
    MapOperator filterDocs = MapOperator.builder(new FilterDocs())
      .input(docs)
View Full Code Here
199
200
201
202
203
204
205
206
207
208
209
210
    final String edgeInput = args.length > 1 ? args[1] : "";
    final String output    = args.length > 2 ? args[2] : "";
    final char delimiter   = args.length > 3 ? (char) Integer.parseInt(args[3]) : ',';
   

    FileDataSource edges = new FileDataSource(new EdgeInputFormat(), edgeInput, "Input Edges");
    edges.setParameter(EdgeInputFormat.ID_DELIMITER_CHAR, delimiter);
   
    MapOperator projectEdge = MapOperator.builder(new ProjectEdge())
      .input(edges).name("Project Edge").build();
   
    ReduceOperator edgeCounter = ReduceOperator.builder(new CountEdges(), IntValue.class, 0)
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
    return toParameterList(config1);
  }
 
  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(NUM_ITERATIONS);
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
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.