org.apache.flink.graph.utils.Tuple3ToEdgeMap Java Examples

private static DataSet<Edge<Long, Double>> getEdgeDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.fieldDelimiter("\t")
				.lineDelimiter("\n")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgesDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.lineDelimiter("\n")
				.fieldDelimiter("\t")
				.ignoreComments("%")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgesDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.lineDelimiter("\n")
				.fieldDelimiter("\t")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgesDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.lineDelimiter("\n")
				.fieldDelimiter("\t")
				.ignoreComments("%")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgeDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.fieldDelimiter("\t")
				.lineDelimiter("\n")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgesDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.lineDelimiter("\n")
				.fieldDelimiter("\t")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgesDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.lineDelimiter("\n")
				.fieldDelimiter("\t")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgeDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.fieldDelimiter("\t")
				.lineDelimiter("\n")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

private static DataSet<Edge<Long, Double>> getEdgesDataSet(ExecutionEnvironment env) {
	if (fileOutput) {
		return env.readCsvFile(edgesInputPath)
				.lineDelimiter("\n")
				.fieldDelimiter("\t")
				.ignoreComments("%")
				.types(Long.class, Long.class, Double.class)
				.map(new Tuple3ToEdgeMap<>());
	} else {
		return SingleSourceShortestPathsData.getDefaultEdgeDataSet(env);
	}
}
 

@Test
public void testGSACompiler() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple3<>(
		1L, 2L, NullValue.getInstance())).map(new Tuple3ToEdgeMap<>());

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

	DataSet<Vertex<Long, Long>> result = graph.runGatherSumApplyIteration(
		new GatherNeighborIds(), new SelectMinId(),
		new UpdateComponentId(), 100).getVertices();

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

	Plan p = env.createProgramPlan("GSA 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());
	assertEquals(PartitioningProperty.HASH_PARTITIONED, sink.getGlobalProperties().getPartitioning());

	// 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 function 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
	SingleInputPlanNode sumReducer = (SingleInputPlanNode) ssJoin.getInput1().getSource();
	SingleInputPlanNode gatherMapper = (SingleInputPlanNode) sumReducer.getInput().getSource();
	DualInputPlanNode edgeJoin = (DualInputPlanNode) gatherMapper.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	// input1 is the workset
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput1().getShipStrategy());
	// input2 is the edges
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput2().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput2().getShipStrategyKeys());
}
 

@Test
public void testTranslation() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<Long> bcGather = env.fromElements(1L);
	DataSet<Long> bcSum = env.fromElements(1L);
	DataSet<Long> bcApply = env.fromElements(1L);

	DataSet<Vertex<Long, Long>> result;

	// ------------ construct the test program ------------------

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple3<>(
		1L, 2L, NullValue.getInstance())).map(new Tuple3ToEdgeMap<>());

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

	GSAConfiguration parameters = new GSAConfiguration();

	parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
	parameters.setName(ITERATION_NAME);
	parameters.setParallelism(ITERATION_parallelism);
	parameters.addBroadcastSetForGatherFunction(BC_SET_GATHER_NAME, bcGather);
	parameters.addBroadcastSetForSumFunction(BC_SET_SUM_NAME, bcSum);
	parameters.addBroadcastSetForApplyFunction(BC_SET_APLLY_NAME, bcApply);

	result = graph.runGatherSumApplyIteration(
		new GatherNeighborIds(), new SelectMinId(),
		new UpdateComponentId(), NUM_ITERATIONS, parameters).getVertices();

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

	// ------------- validate the java program ----------------

	assertTrue(result instanceof DeltaIterationResultSet);

	DeltaIterationResultSet<?, ?> resultSet = (DeltaIterationResultSet<?, ?>) result;
	DeltaIteration<?, ?> iteration = resultSet.getIterationHead();

	// check the basic iteration properties
	assertEquals(NUM_ITERATIONS, resultSet.getMaxIterations());
	assertArrayEquals(new int[]{0}, resultSet.getKeyPositions());
	assertEquals(ITERATION_parallelism, iteration.getParallelism());
	assertEquals(ITERATION_NAME, iteration.getName());

	assertEquals(AGGREGATOR_NAME, iteration.getAggregators().getAllRegisteredAggregators().iterator().next().getName());

	// validate that the semantic properties are set as they should
	TwoInputUdfOperator<?, ?, ?, ?> solutionSetJoin = (TwoInputUdfOperator<?, ?, ?, ?>) resultSet.getNextWorkset();
	assertTrue(solutionSetJoin.getSemanticProperties().getForwardingTargetFields(0, 0).contains(0));
	assertTrue(solutionSetJoin.getSemanticProperties().getForwardingTargetFields(1, 0).contains(0));

	SingleInputUdfOperator<?, ?, ?> sumReduce = (SingleInputUdfOperator<?, ?, ?>) solutionSetJoin.getInput1();
	SingleInputUdfOperator<?, ?, ?> gatherMap = (SingleInputUdfOperator<?, ?, ?>) sumReduce.getInput();

	// validate that the broadcast sets are forwarded
	assertEquals(bcGather, gatherMap.getBroadcastSets().get(BC_SET_GATHER_NAME));
	assertEquals(bcSum, sumReduce.getBroadcastSets().get(BC_SET_SUM_NAME));
	assertEquals(bcApply, solutionSetJoin.getBroadcastSets().get(BC_SET_APLLY_NAME));
}
 

@Test
public void testGSACompiler() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple3<>(
		1L, 2L, NullValue.getInstance())).map(new Tuple3ToEdgeMap<>());

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

	DataSet<Vertex<Long, Long>> result = graph.runGatherSumApplyIteration(
		new GatherNeighborIds(), new SelectMinId(),
		new UpdateComponentId(), 100).getVertices();

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

	Plan p = env.createProgramPlan("GSA 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());
	assertEquals(PartitioningProperty.HASH_PARTITIONED, sink.getGlobalProperties().getPartitioning());

	// 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 function 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
	SingleInputPlanNode sumReducer = (SingleInputPlanNode) ssJoin.getInput1().getSource();
	SingleInputPlanNode gatherMapper = (SingleInputPlanNode) sumReducer.getInput().getSource();
	DualInputPlanNode edgeJoin = (DualInputPlanNode) gatherMapper.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	// input1 is the workset
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput1().getShipStrategy());
	// input2 is the edges
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput2().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput2().getShipStrategyKeys());
}
 

@Test
public void testTranslation() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<Long> bcGather = env.fromElements(1L);
	DataSet<Long> bcSum = env.fromElements(1L);
	DataSet<Long> bcApply = env.fromElements(1L);

	DataSet<Vertex<Long, Long>> result;

	// ------------ construct the test program ------------------

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple3<>(
		1L, 2L, NullValue.getInstance())).map(new Tuple3ToEdgeMap<>());

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

	GSAConfiguration parameters = new GSAConfiguration();

	parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
	parameters.setName(ITERATION_NAME);
	parameters.setParallelism(ITERATION_parallelism);
	parameters.addBroadcastSetForGatherFunction(BC_SET_GATHER_NAME, bcGather);
	parameters.addBroadcastSetForSumFunction(BC_SET_SUM_NAME, bcSum);
	parameters.addBroadcastSetForApplyFunction(BC_SET_APLLY_NAME, bcApply);

	result = graph.runGatherSumApplyIteration(
		new GatherNeighborIds(), new SelectMinId(),
		new UpdateComponentId(), NUM_ITERATIONS, parameters).getVertices();

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

	// ------------- validate the java program ----------------

	assertTrue(result instanceof DeltaIterationResultSet);

	DeltaIterationResultSet<?, ?> resultSet = (DeltaIterationResultSet<?, ?>) result;
	DeltaIteration<?, ?> iteration = resultSet.getIterationHead();

	// check the basic iteration properties
	assertEquals(NUM_ITERATIONS, resultSet.getMaxIterations());
	assertArrayEquals(new int[]{0}, resultSet.getKeyPositions());
	assertEquals(ITERATION_parallelism, iteration.getParallelism());
	assertEquals(ITERATION_NAME, iteration.getName());

	assertEquals(AGGREGATOR_NAME, iteration.getAggregators().getAllRegisteredAggregators().iterator().next().getName());

	// validate that the semantic properties are set as they should
	TwoInputUdfOperator<?, ?, ?, ?> solutionSetJoin = (TwoInputUdfOperator<?, ?, ?, ?>) resultSet.getNextWorkset();
	assertTrue(solutionSetJoin.getSemanticProperties().getForwardingTargetFields(0, 0).contains(0));
	assertTrue(solutionSetJoin.getSemanticProperties().getForwardingTargetFields(1, 0).contains(0));

	SingleInputUdfOperator<?, ?, ?> sumReduce = (SingleInputUdfOperator<?, ?, ?>) solutionSetJoin.getInput1();
	SingleInputUdfOperator<?, ?, ?> gatherMap = (SingleInputUdfOperator<?, ?, ?>) sumReduce.getInput();

	// validate that the broadcast sets are forwarded
	assertEquals(bcGather, gatherMap.getBroadcastSets().get(BC_SET_GATHER_NAME));
	assertEquals(bcSum, sumReduce.getBroadcastSets().get(BC_SET_SUM_NAME));
	assertEquals(bcApply, solutionSetJoin.getBroadcastSets().get(BC_SET_APLLY_NAME));
}
 

@Test
public void testGSACompiler() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	// compose test program

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple3<>(
		1L, 2L, NullValue.getInstance())).map(new Tuple3ToEdgeMap<>());

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

	DataSet<Vertex<Long, Long>> result = graph.runGatherSumApplyIteration(
		new GatherNeighborIds(), new SelectMinId(),
		new UpdateComponentId(), 100).getVertices();

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

	Plan p = env.createProgramPlan("GSA 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());
	assertEquals(PartitioningProperty.HASH_PARTITIONED, sink.getGlobalProperties().getPartitioning());

	// 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 function 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
	SingleInputPlanNode sumReducer = (SingleInputPlanNode) ssJoin.getInput1().getSource();
	SingleInputPlanNode gatherMapper = (SingleInputPlanNode) sumReducer.getInput().getSource();
	DualInputPlanNode edgeJoin = (DualInputPlanNode) gatherMapper.getInput().getSource();
	assertEquals(DEFAULT_PARALLELISM, edgeJoin.getParallelism());
	// input1 is the workset
	assertEquals(ShipStrategyType.FORWARD, edgeJoin.getInput1().getShipStrategy());
	// input2 is the edges
	assertEquals(ShipStrategyType.PARTITION_HASH, edgeJoin.getInput2().getShipStrategy());
	assertTrue(edgeJoin.getInput2().getTempMode().isCached());

	assertEquals(new FieldList(0), edgeJoin.getInput2().getShipStrategyKeys());
}
 

@Test
public void testTranslation() {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<Long> bcGather = env.fromElements(1L);
	DataSet<Long> bcSum = env.fromElements(1L);
	DataSet<Long> bcApply = env.fromElements(1L);

	DataSet<Vertex<Long, Long>> result;

	// ------------ construct the test program ------------------

	DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple3<>(
		1L, 2L, NullValue.getInstance())).map(new Tuple3ToEdgeMap<>());

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

	GSAConfiguration parameters = new GSAConfiguration();

	parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
	parameters.setName(ITERATION_NAME);
	parameters.setParallelism(ITERATION_parallelism);
	parameters.addBroadcastSetForGatherFunction(BC_SET_GATHER_NAME, bcGather);
	parameters.addBroadcastSetForSumFunction(BC_SET_SUM_NAME, bcSum);
	parameters.addBroadcastSetForApplyFunction(BC_SET_APLLY_NAME, bcApply);

	result = graph.runGatherSumApplyIteration(
		new GatherNeighborIds(), new SelectMinId(),
		new UpdateComponentId(), NUM_ITERATIONS, parameters).getVertices();

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

	// ------------- validate the java program ----------------

	assertTrue(result instanceof DeltaIterationResultSet);

	DeltaIterationResultSet<?, ?> resultSet = (DeltaIterationResultSet<?, ?>) result;
	DeltaIteration<?, ?> iteration = resultSet.getIterationHead();

	// check the basic iteration properties
	assertEquals(NUM_ITERATIONS, resultSet.getMaxIterations());
	assertArrayEquals(new int[]{0}, resultSet.getKeyPositions());
	assertEquals(ITERATION_parallelism, iteration.getParallelism());
	assertEquals(ITERATION_NAME, iteration.getName());

	assertEquals(AGGREGATOR_NAME, iteration.getAggregators().getAllRegisteredAggregators().iterator().next().getName());

	// validate that the semantic properties are set as they should
	TwoInputUdfOperator<?, ?, ?, ?> solutionSetJoin = (TwoInputUdfOperator<?, ?, ?, ?>) resultSet.getNextWorkset();
	assertTrue(solutionSetJoin.getSemanticProperties().getForwardingTargetFields(0, 0).contains(0));
	assertTrue(solutionSetJoin.getSemanticProperties().getForwardingTargetFields(1, 0).contains(0));

	SingleInputUdfOperator<?, ?, ?> sumReduce = (SingleInputUdfOperator<?, ?, ?>) solutionSetJoin.getInput1();
	SingleInputUdfOperator<?, ?, ?> gatherMap = (SingleInputUdfOperator<?, ?, ?>) sumReduce.getInput();

	// validate that the broadcast sets are forwarded
	assertEquals(bcGather, gatherMap.getBroadcastSets().get(BC_SET_GATHER_NAME));
	assertEquals(bcSum, sumReduce.getBroadcastSets().get(BC_SET_SUM_NAME));
	assertEquals(bcApply, solutionSetJoin.getBroadcastSets().get(BC_SET_APLLY_NAME));
}
 

/**
 * Creates a graph from a DataSet of Tuple3 objects for edges.
 *
 * <p>Each Tuple3 will become one Edge, where the source ID will be the first field of the Tuple2,
 * the target ID will be the second field of the Tuple2
 * and the Edge value will be the third field of the Tuple3.
 *
 * <p>Vertices are created automatically and their values are initialized
 * by applying the provided vertexValueInitializer map function to the vertex IDs.
 *
 * @param edges a DataSet of Tuple3.
 * @param vertexValueInitializer the mapper function that initializes the vertex values.
 * It allows to apply a map transformation on the vertex ID to produce an initial vertex value.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, VV, EV> Graph<K, VV, EV> fromTupleDataSet(DataSet<Tuple3<K, K, EV>> edges,
		final MapFunction<K, VV> vertexValueInitializer, ExecutionEnvironment context) {

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(edgeDataSet, vertexValueInitializer, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple3 objects for edges.
 *
 * <p>The first field of the Tuple3 object will become the source ID,
 * the second field will become the target ID, and the third field will become
 * the edge value.
 *
 * <p>Vertices are created automatically and their values are set to NullValue.
 *
 * @param edges a DataSet of Tuple3 representing the edges.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, EV> Graph<K, NullValue, EV> fromTupleDataSet(DataSet<Tuple3<K, K, EV>> edges,
		ExecutionEnvironment context) {

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(edgeDataSet, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple2 objects for vertices and
 * Tuple3 objects for edges.
 *
 * <p>The first field of the Tuple2 vertex object will become the vertex ID
 * and the second field will become the vertex value.
 * The first field of the Tuple3 object for edges will become the source ID,
 * the second field will become the target ID, and the third field will become
 * the edge value.
 *
 * @param vertices a DataSet of Tuple2 representing the vertices.
 * @param edges a DataSet of Tuple3 representing the edges.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, VV, EV> Graph<K, VV, EV> fromTupleDataSet(DataSet<Tuple2<K, VV>> vertices,
		DataSet<Tuple3<K, K, EV>> edges, ExecutionEnvironment context) {

	DataSet<Vertex<K, VV>> vertexDataSet = vertices
		.map(new Tuple2ToVertexMap<>())
			.name("Type conversion");

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(vertexDataSet, edgeDataSet, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple3 objects for edges.
 *
 * <p>Each Tuple3 will become one Edge, where the source ID will be the first field of the Tuple2,
 * the target ID will be the second field of the Tuple2
 * and the Edge value will be the third field of the Tuple3.
 *
 * <p>Vertices are created automatically and their values are initialized
 * by applying the provided vertexValueInitializer map function to the vertex IDs.
 *
 * @param edges a DataSet of Tuple3.
 * @param vertexValueInitializer the mapper function that initializes the vertex values.
 * It allows to apply a map transformation on the vertex ID to produce an initial vertex value.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, VV, EV> Graph<K, VV, EV> fromTupleDataSet(DataSet<Tuple3<K, K, EV>> edges,
		final MapFunction<K, VV> vertexValueInitializer, ExecutionEnvironment context) {

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(edgeDataSet, vertexValueInitializer, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple2 objects for vertices and
 * Tuple3 objects for edges.
 *
 * <p>The first field of the Tuple2 vertex object will become the vertex ID
 * and the second field will become the vertex value.
 * The first field of the Tuple3 object for edges will become the source ID,
 * the second field will become the target ID, and the third field will become
 * the edge value.
 *
 * @param vertices a DataSet of Tuple2 representing the vertices.
 * @param edges a DataSet of Tuple3 representing the edges.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, VV, EV> Graph<K, VV, EV> fromTupleDataSet(DataSet<Tuple2<K, VV>> vertices,
		DataSet<Tuple3<K, K, EV>> edges, ExecutionEnvironment context) {

	DataSet<Vertex<K, VV>> vertexDataSet = vertices
		.map(new Tuple2ToVertexMap<>())
			.name("Type conversion");

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(vertexDataSet, edgeDataSet, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple3 objects for edges.
 *
 * <p>The first field of the Tuple3 object will become the source ID,
 * the second field will become the target ID, and the third field will become
 * the edge value.
 *
 * <p>Vertices are created automatically and their values are set to NullValue.
 *
 * @param edges a DataSet of Tuple3 representing the edges.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, EV> Graph<K, NullValue, EV> fromTupleDataSet(DataSet<Tuple3<K, K, EV>> edges,
		ExecutionEnvironment context) {

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(edgeDataSet, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple3 objects for edges.
 *
 * <p>Each Tuple3 will become one Edge, where the source ID will be the first field of the Tuple2,
 * the target ID will be the second field of the Tuple2
 * and the Edge value will be the third field of the Tuple3.
 *
 * <p>Vertices are created automatically and their values are initialized
 * by applying the provided vertexValueInitializer map function to the vertex IDs.
 *
 * @param edges a DataSet of Tuple3.
 * @param vertexValueInitializer the mapper function that initializes the vertex values.
 * It allows to apply a map transformation on the vertex ID to produce an initial vertex value.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, VV, EV> Graph<K, VV, EV> fromTupleDataSet(DataSet<Tuple3<K, K, EV>> edges,
		final MapFunction<K, VV> vertexValueInitializer, ExecutionEnvironment context) {

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(edgeDataSet, vertexValueInitializer, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple3 objects for edges.
 *
 * <p>The first field of the Tuple3 object will become the source ID,
 * the second field will become the target ID, and the third field will become
 * the edge value.
 *
 * <p>Vertices are created automatically and their values are set to NullValue.
 *
 * @param edges a DataSet of Tuple3 representing the edges.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, EV> Graph<K, NullValue, EV> fromTupleDataSet(DataSet<Tuple3<K, K, EV>> edges,
		ExecutionEnvironment context) {

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(edgeDataSet, context);
}
 

/**
 * Creates a graph from a DataSet of Tuple2 objects for vertices and
 * Tuple3 objects for edges.
 *
 * <p>The first field of the Tuple2 vertex object will become the vertex ID
 * and the second field will become the vertex value.
 * The first field of the Tuple3 object for edges will become the source ID,
 * the second field will become the target ID, and the third field will become
 * the edge value.
 *
 * @param vertices a DataSet of Tuple2 representing the vertices.
 * @param edges a DataSet of Tuple3 representing the edges.
 * @param context the flink execution environment.
 * @return the newly created graph.
 */
public static <K, VV, EV> Graph<K, VV, EV> fromTupleDataSet(DataSet<Tuple2<K, VV>> vertices,
		DataSet<Tuple3<K, K, EV>> edges, ExecutionEnvironment context) {

	DataSet<Vertex<K, VV>> vertexDataSet = vertices
		.map(new Tuple2ToVertexMap<>())
			.name("Type conversion");

	DataSet<Edge<K, EV>> edgeDataSet = edges
		.map(new Tuple3ToEdgeMap<>())
			.name("Type conversion");

	return fromDataSet(vertexDataSet, edgeDataSet, context);
}