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

Examples of org.apache.flink.api.java.record.operators.DeltaIteration$SolutionSetPlaceHolder

72
73
74
75
76
77
78
79
80
81
82
    if (vertexKey == null || vertexValue == null || messageType == null || edgeValue == null) {
      throw new RuntimeException();
    }
 
    // instantiate the data flow
    this.iteration = new DeltaIteration(0, name);
   
    this.messager = CoGroupOperator.builder(MessagingDriver.class, vertexKey, 0, 0)
      .input2(iteration.getWorkset())
      .name("Message Sender")
      .build();
View Full Code Here
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
    FileDataSource initialDeltaSet = new FileDataSource(new CsvInputFormat(' ', LongValue.class, DoubleValue.class), deltasInput, "Initial DeltaSet");
       
    // create DataSourceContract for the edges
    FileDataSource dependencySet = new FileDataSource(new CsvInputFormat(' ', LongValue.class, LongValue.class, LongValue.class), dependencySetInput, "Dependency Set");
   
    DeltaIteration iteration = new DeltaIteration(0, "Delta PageRank");
    iteration.setInitialSolutionSet(initialSolutionSet);
    iteration.setInitialWorkset(initialDeltaSet);
    iteration.setMaximumNumberOfIterations(maxIterations);
   
    JoinOperator dependenciesMatch = JoinOperator.builder(PRDependenciesComputationMatchDelta.class,
        LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(dependencySet)
        .name("calculate dependencies")
        .build();
   
    ReduceOperator updateRanks = ReduceOperator.builder(UpdateRankReduceDelta.class, LongValue.class, 0)
        .input(dependenciesMatch)
        .name("update ranks")
        .build();
   
    JoinOperator oldRankComparison = JoinOperator.builder(RankComparisonMatch.class, LongValue.class, 0, 0)
        .input1(updateRanks)
        .input2(iteration.getSolutionSet())
        .name("comparison with old ranks")
        .build();

    iteration.setNextWorkset(updateRanks);
    iteration.setSolutionSetDelta(oldRankComparison);
   
    // create DataSinkContract for writing the final ranks
    FileDataSink result = new FileDataSink(CsvOutputFormat.class, output, iteration, "Final Ranks");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
View Full Code Here
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
    // 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)
        .name("Join Candidate Id With Neighbor")
        .build();

    // create ReduceOperator for finding the nearest cluster centers
    ReduceOperator minCandidateId = ReduceOperator.builder(new MinimumComponentIDReduce(), LongValue.class, 0)
        .input(joinWithNeighbors)
        .name("Find Minimum Candidate Id")
        .build();
   
    // create CrossOperator for distance computation
    JoinOperator updateComponentId = JoinOperator.builder(new UpdateComponentIdMatchMirrored(), LongValue.class, 0, 0)
        .input1(iteration.getSolutionSet())
        .input2(minCandidateId)
        .name("Update Component Id")
        .build();
   
    iteration.setNextWorkset(updateComponentId);
    iteration.setSolutionSetDelta(updateComponentId);

    // create DataSinkContract for writing the new cluster positions
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
View Full Code Here
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
151
152
153
154
155
156
157
    // 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)
        .name("Join Candidate Id With Neighbor")
        .build();

    CoGroupOperator minAndUpdate = CoGroupOperator.builder(new MinIdAndUpdate(), LongValue.class, 0, 0)
        .input1(joinWithNeighbors)
        .input2(iteration.getSolutionSet())
        .name("Min Id and Update")
        .build();
   
    iteration.setNextWorkset(minAndUpdate);
    iteration.setSolutionSetDelta(minAndUpdate);

    // create DataSinkContract for writing the new cluster positions
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
    // 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)
        .name("Join Candidate Id With Neighbor")
        .build();

    CoGroupOperator minAndUpdate = CoGroupOperator.builder(new MinIdAndUpdate(), LongValue.class, 0, 0)
        .input1(joinWithNeighbors)
        .input2(iteration.getSolutionSet())
        .name("Min Id and Update")
        .build();
   
    iteration.setNextWorkset(minAndUpdate);
    iteration.setSolutionSetDelta(minAndUpdate);

    // create DataSinkContract for writing the new cluster positions
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
View Full Code Here
107
108
109
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
143
144
145
146
147
148
149
150
151
152
   
    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)
        .name("Join Candidate Id With Neighbor")
        .build();

    // find for each neighbor the smallest of all candidates
    ReduceOperator minCandidateId = ReduceOperator.builder(new MinimumComponentIDReduce(), LongValue.class, 0)
        .input(joinWithNeighbors)
        .name("Find Minimum Candidate Id")
        .build();
   
    // join candidates with the solution set and update if the candidate component-id is smaller
    JoinOperator updateComponentId = JoinOperator.builder(new UpdateComponentIdMatchNonPreserving(), LongValue.class, 0, 0)
        .input1(minCandidateId)
        .input2(iteration.getSolutionSet())
        .name("Update Component Id")
        .build();
   
    if (extraMap) {
      MapOperator mapper = MapOperator.builder(IdentityMap.class).input(updateComponentId).name("idmap").build();
      iteration.setSolutionSetDelta(mapper);
    } else {
      iteration.setSolutionSetDelta(updateComponentId);
    }
   
    iteration.setNextWorkset(updateComponentId);

    // sink is the iteration result
    FileDataSink result = new FileDataSink(new CsvOutputFormat("\n", " ", LongValue.class, LongValue.class), output, iteration, "Result");

    // return the PACT plan
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
   
    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)
        .name("Join Candidate Id With Neighbor")
        .build();

    // find for each neighbor the smallest of all candidates
    ReduceOperator minCandidateId = ReduceOperator.builder(new MinimumComponentIDReduce(), LongValue.class, 0)
        .input(joinWithNeighbors)
        .name("Find Minimum Candidate Id")
        .build();
   
    // join candidates with the solution set and update if the candidate component-id is smaller
    JoinOperator updateComponentId = JoinOperator.builder(new UpdateComponentIdMatch(), LongValue.class, 0, 0)
        .input1(minCandidateId)
        .input2(iteration.getSolutionSet())
        .name("Update Component Id")
        .build();
   
    iteration.setNextWorkset(updateComponentId);
    iteration.setSolutionSetDelta(updateComponentId);

    // sink is the iteration result
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
View Full Code Here
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
143
144
145
146
147
148
149
150
151
    // 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)
        .name("Join Candidate Id With Neighbor")
        .build();

    // create ReduceOperator for finding the nearest cluster centers
    ReduceOperator minCandidateId = ReduceOperator.builder(new MinimumComponentIDReduce(), LongValue.class, 0)
        .input(joinWithNeighbors)
        .name("Find Minimum Candidate Id")
        .build();
   
    // create CrossOperator for distance computation
    JoinOperator updateComponentId = JoinOperator.builder(new UpdateComponentIdMatchMirrored(), LongValue.class, 0, 0)
        .input1(iteration.getSolutionSet())
        .input2(minCandidateId)
        .name("Update Component Id")
        .build();
   
    iteration.setNextWorkset(updateComponentId);
    iteration.setSolutionSetDelta(updateComponentId);

    // create DataSinkContract for writing the new cluster positions
    FileDataSink result = new FileDataSink(new CsvOutputFormat(), output, iteration, "Result");
    CsvOutputFormat.configureRecordFormat(result)
      .recordDelimiter('\n')
View Full Code Here
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
    FileDataSource solutionSetInput = new FileDataSource(new DummyInputFormat(), IN_FILE, "Solution Set");
    FileDataSource worksetInput = new FileDataSource(new DummyInputFormat(), IN_FILE, "Workset");
   
    FileDataSource invariantInput = new FileDataSource(new DummyInputFormat(), IN_FILE, "Invariant Input");
   
    DeltaIteration iteration = new DeltaIteration(0, ITERATION_NAME);
    iteration.setInitialSolutionSet(solutionSetInput);
    iteration.setInitialWorkset(worksetInput);
    iteration.setMaximumNumberOfIterations(100);

    JoinOperator joinWithInvariant = JoinOperator.builder(new DummyMatchStub(), LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(invariantInput)
        .name(JOIN_WITH_INVARIANT_NAME)
        .build();

    JoinOperator joinWithSolutionSet = JoinOperator.builder(
        joinPreservesSolutionSet ? new DummyMatchStub() : new DummyNonPreservingMatchStub(), LongValue.class, 0, 0)
        .input1(iteration.getSolutionSet())
        .input2(joinWithInvariant)
        .name(JOIN_WITH_SOLUTION_SET)
        .build();
   
    ReduceOperator nextWorkset = ReduceOperator.builder(new IdentityReduce(), LongValue.class, 0)
        .input(joinWithSolutionSet)
        .name(NEXT_WORKSET_REDUCER_NAME)
        .build();
   
    if (mapBeforeSolutionDelta) {
      MapOperator mapper = MapOperator.builder(new IdentityMap())
        .input(joinWithSolutionSet)
        .name(SOLUTION_DELTA_MAPPER_NAME)
        .build();
      iteration.setSolutionSetDelta(mapper);
    } else {
      iteration.setSolutionSetDelta(joinWithSolutionSet);
    }
   
    iteration.setNextWorkset(nextWorkset);

    FileDataSink sink = new FileDataSink(new DummyOutputFormat(), OUT_FILE, iteration, "Sink");
   
    Plan plan = new Plan(sink);
    plan.setDefaultParallelism(DEFAULT_PARALLELISM);
View Full Code Here
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
    FileDataSource sourceC = new FileDataSource(DummyInputFormat.class, IN_FILE, "Source 3");

    FileDataSink sink1 = new FileDataSink(DummyOutputFormat.class, OUT_FILE, sourceA, "Sink 1");
    FileDataSink sink2 = new FileDataSink(DummyOutputFormat.class, OUT_FILE, sourceC, "Sink 2");

    DeltaIteration iteration = new DeltaIteration(0, "Loop");
    iteration.setInitialSolutionSet(sourceA);
    iteration.setInitialWorkset(sourceB);
    iteration.setMaximumNumberOfIterations(10);

    CrossOperator nextWorkset = CrossOperator.builder(DummyCrossStub.class).name("Next workset").
        input1(iteration.getWorkset()).
        input2(sourceC).
        build();

    JoinOperator solutionSetDelta = JoinOperator.builder(DummyMatchStub.class, LongValue.class,0,0).
        name("Next solution set.").
        input1(nextWorkset).
        input2(iteration.getSolutionSet()).
        build();

    iteration.setNextWorkset(nextWorkset);
    iteration.setSolutionSetDelta(solutionSetDelta);

    FileDataSink sink3 = new FileDataSink(DummyOutputFormat.class, OUT_FILE, iteration, "Sink 3");

    List<FileDataSink> sinks = new ArrayList<FileDataSink>();
    sinks.add(sink1);
View Full Code Here
TOP

Related Classes of org.apache.flink.api.java.record.operators.DeltaIteration$SolutionSetPlaceHolder

  • eu.stratosphere.api.java.typeutils.RecordTypeInfo
  • org.apache.flink.api.java.typeutils.RecordTypeInfo
  • org.apache.flink.compiler.BranchingPlansCompilerTest
  • org.apache.flink.compiler.WorksetIterationsRecordApiCompilerTest
  • org.apache.flink.spargel.java.record.SpargelIteration
  • 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.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.