org.apache.flink.graph.library.ConnectedComponents Java Examples

The following examples show how to use org.apache.flink.graph.library.ConnectedComponents. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: SpargelCompilerTest.java    From Flink-CEPplus with Apache License 2.0 4 votes vote down vote up 
@SuppressWarnings("serial")
@Test
public void testSpargelCompiler() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program
	DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(
		new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L))
		.map(new Tuple2ToVertexMap<>());

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L))
		.map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

			public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
				return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
			}
		});

	Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);

	DataSet<Vertex<Long, Long>> result = graph.runScatterGatherIteration(
		new ConnectedComponents.CCMessenger<>(BasicTypeInfo.LONG_TYPE_INFO),
		new ConnectedComponents.CCUpdater<>(), 100)
		.getVertices();

	result.output(new DiscardingOutputFormat<>());

	Plan p = env.createProgramPlan("Spargel Connected Components");
	OptimizedPlan op = compileNoStats(p);

	// check the sink
	SinkPlanNode sink = op.getDataSinks().iterator().next();
	assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
	assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());

	// check the iteration
	WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());

	// check the solution set join and the delta
	PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
	assertTrue(ssDelta instanceof DualInputPlanNode); // this is only true if the update functions preserves the partitioning

	DualInputPlanNode ssJoin = (DualInputPlanNode) ssDelta;
	assertEquals(DEFAULT_PARALLELISM, ssJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, ssJoin.getInput1().getShipStrategy());
	assertEquals(new FieldList(0), ssJoin.getInput1().getShipStrategyKeys());

	// check the workset set join
	DualInputPlanNode edgeJoin = (DualInputPlanNode) ssJoin.getInput1().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput1().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput1().getShipStrategyKeys());

	// check that the initial partitioning is pushed out of the loop
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput2().getShipStrategy());
	assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
	assertEquals(new FieldList(0), iteration.getInput2().getShipStrategyKeys());

	// check that the initial workset sort is outside the loop
	assertEquals(LocalStrategy.SORT, iteration.getInput2().getLocalStrategy());
	assertEquals(new FieldList(0), iteration.getInput2().getLocalStrategyKeys());
}
Example #2
Source File: SpargelCompilerTest.java    From Flink-CEPplus with Apache License 2.0 4 votes vote down vote up 
@SuppressWarnings("serial")
@Test
public void testSpargelCompilerWithBroadcastVariable() {
	final String broadcastVariableName = "broadcast variable";

	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program

	DataSet<Long> bcVar = env.fromElements(1L);

	DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(
		new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L))
		.map(new Tuple2ToVertexMap<>());

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L))
		.map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

			public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
				return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
			}
		});

	Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);

	ScatterGatherConfiguration parameters = new ScatterGatherConfiguration();
	parameters.addBroadcastSetForScatterFunction(broadcastVariableName, bcVar);
	parameters.addBroadcastSetForGatherFunction(broadcastVariableName, bcVar);

	DataSet<Vertex<Long, Long>> result = graph.runScatterGatherIteration(
		new ConnectedComponents.CCMessenger<>(BasicTypeInfo.LONG_TYPE_INFO),
		new ConnectedComponents.CCUpdater<>(), 100)
		.getVertices();

	result.output(new DiscardingOutputFormat<>());

	Plan p = env.createProgramPlan("Spargel Connected Components");
	OptimizedPlan op = compileNoStats(p);

	// check the sink
	SinkPlanNode sink = op.getDataSinks().iterator().next();
	assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
	assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());

	// check the iteration
	WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());

	// check the solution set join and the delta
	PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
	assertTrue(ssDelta instanceof DualInputPlanNode); // this is only true if the update functions preserves the partitioning

	DualInputPlanNode ssJoin = (DualInputPlanNode) ssDelta;
	assertEquals(DEFAULT_PARALLELISM, ssJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, ssJoin.getInput1().getShipStrategy());
	assertEquals(new FieldList(0), ssJoin.getInput1().getShipStrategyKeys());

	// check the workset set join
	DualInputPlanNode edgeJoin = (DualInputPlanNode) ssJoin.getInput1().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput1().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput1().getShipStrategyKeys());

	// check that the initial partitioning is pushed out of the loop
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput2().getShipStrategy());
	assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
	assertEquals(new FieldList(0), iteration.getInput2().getShipStrategyKeys());
}
Example #3
Source File: SpargelCompilerTest.java    From flink with Apache License 2.0 4 votes vote down vote up 
@SuppressWarnings("serial")
@Test
public void testSpargelCompiler() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program
	DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(
		new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L))
		.map(new Tuple2ToVertexMap<>());

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L))
		.map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

			public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
				return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
			}
		});

	Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);

	DataSet<Vertex<Long, Long>> result = graph.runScatterGatherIteration(
		new ConnectedComponents.CCMessenger<>(BasicTypeInfo.LONG_TYPE_INFO),
		new ConnectedComponents.CCUpdater<>(), 100)
		.getVertices();

	result.output(new DiscardingOutputFormat<>());

	Plan p = env.createProgramPlan("Spargel Connected Components");
	OptimizedPlan op = compileNoStats(p);

	// check the sink
	SinkPlanNode sink = op.getDataSinks().iterator().next();
	assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
	assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());

	// check the iteration
	WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());

	// check the solution set join and the delta
	PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
	assertTrue(ssDelta instanceof DualInputPlanNode); // this is only true if the update functions preserves the partitioning

	DualInputPlanNode ssJoin = (DualInputPlanNode) ssDelta;
	assertEquals(DEFAULT_PARALLELISM, ssJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, ssJoin.getInput1().getShipStrategy());
	assertEquals(new FieldList(0), ssJoin.getInput1().getShipStrategyKeys());

	// check the workset set join
	DualInputPlanNode edgeJoin = (DualInputPlanNode) ssJoin.getInput1().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput1().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput1().getShipStrategyKeys());

	// check that the initial partitioning is pushed out of the loop
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput2().getShipStrategy());
	assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
	assertEquals(new FieldList(0), iteration.getInput2().getShipStrategyKeys());

	// check that the initial workset sort is outside the loop
	assertEquals(LocalStrategy.SORT, iteration.getInput2().getLocalStrategy());
	assertEquals(new FieldList(0), iteration.getInput2().getLocalStrategyKeys());
}
Example #4
Source File: SpargelCompilerTest.java    From flink with Apache License 2.0 4 votes vote down vote up 
@SuppressWarnings("serial")
@Test
public void testSpargelCompilerWithBroadcastVariable() {
	final String broadcastVariableName = "broadcast variable";

	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program

	DataSet<Long> bcVar = env.fromElements(1L);

	DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(
		new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L))
		.map(new Tuple2ToVertexMap<>());

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L))
		.map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

			public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
				return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
			}
		});

	Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);

	ScatterGatherConfiguration parameters = new ScatterGatherConfiguration();
	parameters.addBroadcastSetForScatterFunction(broadcastVariableName, bcVar);
	parameters.addBroadcastSetForGatherFunction(broadcastVariableName, bcVar);

	DataSet<Vertex<Long, Long>> result = graph.runScatterGatherIteration(
		new ConnectedComponents.CCMessenger<>(BasicTypeInfo.LONG_TYPE_INFO),
		new ConnectedComponents.CCUpdater<>(), 100)
		.getVertices();

	result.output(new DiscardingOutputFormat<>());

	Plan p = env.createProgramPlan("Spargel Connected Components");
	OptimizedPlan op = compileNoStats(p);

	// check the sink
	SinkPlanNode sink = op.getDataSinks().iterator().next();
	assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
	assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());

	// check the iteration
	WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());

	// check the solution set join and the delta
	PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
	assertTrue(ssDelta instanceof DualInputPlanNode); // this is only true if the update functions preserves the partitioning

	DualInputPlanNode ssJoin = (DualInputPlanNode) ssDelta;
	assertEquals(DEFAULT_PARALLELISM, ssJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, ssJoin.getInput1().getShipStrategy());
	assertEquals(new FieldList(0), ssJoin.getInput1().getShipStrategyKeys());

	// check the workset set join
	DualInputPlanNode edgeJoin = (DualInputPlanNode) ssJoin.getInput1().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput1().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput1().getShipStrategyKeys());

	// check that the initial partitioning is pushed out of the loop
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput2().getShipStrategy());
	assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
	assertEquals(new FieldList(0), iteration.getInput2().getShipStrategyKeys());
}
Example #5
Source File: SpargelCompilerTest.java    From flink with Apache License 2.0 4 votes vote down vote up 
@SuppressWarnings("serial")
@Test
public void testSpargelCompiler() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program
	DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(
		new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L))
		.map(new Tuple2ToVertexMap<>());

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L))
		.map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

			public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
				return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
			}
		});

	Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);

	DataSet<Vertex<Long, Long>> result = graph.runScatterGatherIteration(
		new ConnectedComponents.CCMessenger<>(BasicTypeInfo.LONG_TYPE_INFO),
		new ConnectedComponents.CCUpdater<>(), 100)
		.getVertices();

	result.output(new DiscardingOutputFormat<>());

	Plan p = env.createProgramPlan("Spargel Connected Components");
	OptimizedPlan op = compileNoStats(p);

	// check the sink
	SinkPlanNode sink = op.getDataSinks().iterator().next();
	assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
	assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());

	// check the iteration
	WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());

	// check the solution set join and the delta
	PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
	assertTrue(ssDelta instanceof DualInputPlanNode); // this is only true if the update functions preserves the partitioning

	DualInputPlanNode ssJoin = (DualInputPlanNode) ssDelta;
	assertEquals(DEFAULT_PARALLELISM, ssJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, ssJoin.getInput1().getShipStrategy());
	assertEquals(new FieldList(0), ssJoin.getInput1().getShipStrategyKeys());

	// check the workset set join
	DualInputPlanNode edgeJoin = (DualInputPlanNode) ssJoin.getInput1().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput1().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput1().getShipStrategyKeys());

	// check that the initial partitioning is pushed out of the loop
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput2().getShipStrategy());
	assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
	assertEquals(new FieldList(0), iteration.getInput2().getShipStrategyKeys());

	// check that the initial workset sort is outside the loop
	assertEquals(LocalStrategy.SORT, iteration.getInput2().getLocalStrategy());
	assertEquals(new FieldList(0), iteration.getInput2().getLocalStrategyKeys());
}
Example #6
Source File: SpargelCompilerTest.java    From flink with Apache License 2.0 4 votes vote down vote up 
@SuppressWarnings("serial")
@Test
public void testSpargelCompilerWithBroadcastVariable() {
	final String broadcastVariableName = "broadcast variable";

	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program

	DataSet<Long> bcVar = env.fromElements(1L);

	DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(
		new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L))
		.map(new Tuple2ToVertexMap<>());

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L))
		.map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

			public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
				return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
			}
		});

	Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);

	ScatterGatherConfiguration parameters = new ScatterGatherConfiguration();
	parameters.addBroadcastSetForScatterFunction(broadcastVariableName, bcVar);
	parameters.addBroadcastSetForGatherFunction(broadcastVariableName, bcVar);

	DataSet<Vertex<Long, Long>> result = graph.runScatterGatherIteration(
		new ConnectedComponents.CCMessenger<>(BasicTypeInfo.LONG_TYPE_INFO),
		new ConnectedComponents.CCUpdater<>(), 100)
		.getVertices();

	result.output(new DiscardingOutputFormat<>());

	Plan p = env.createProgramPlan("Spargel Connected Components");
	OptimizedPlan op = compileNoStats(p);

	// check the sink
	SinkPlanNode sink = op.getDataSinks().iterator().next();
	assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
	assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());

	// check the iteration
	WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());

	// check the solution set join and the delta
	PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
	assertTrue(ssDelta instanceof DualInputPlanNode); // this is only true if the update functions preserves the partitioning

	DualInputPlanNode ssJoin = (DualInputPlanNode) ssDelta;
	assertEquals(DEFAULT_PARALLELISM, ssJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, ssJoin.getInput1().getShipStrategy());
	assertEquals(new FieldList(0), ssJoin.getInput1().getShipStrategyKeys());

	// check the workset set join
	DualInputPlanNode edgeJoin = (DualInputPlanNode) ssJoin.getInput1().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput1().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput1().getShipStrategyKeys());

	// check that the initial partitioning is pushed out of the loop
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
	assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput2().getShipStrategy());
	assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
	assertEquals(new FieldList(0), iteration.getInput2().getShipStrategyKeys());
}