Java Code Examples for org.apache.flink.api.java.DataSet#map()

@SuppressWarnings("serial")
public static void main(String[] args) throws Exception {
	if (args.length < 2) {
		System.err.println("Usage: TestOptimizerPlan <input-file-path> <output-file-path>");
		return;
	}

	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<Tuple2<Long, Long>> input = env.readCsvFile(args[0])
			.fieldDelimiter("\t").types(Long.class, Long.class);

	DataSet<Tuple2<Long, Long>> result = input.map(
			new MapFunction<Tuple2<Long, Long>, Tuple2<Long, Long>>() {
				public Tuple2<Long, Long> map(Tuple2<Long, Long> value){
					return new Tuple2<Long, Long>(value.f0, value.f1 + 1);
				}
			});
	result.writeAsCsv(args[1], "\n", "\t");
	env.execute();
}
 

@Override
protected void testProgram() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	DataSet<Long> vertexIds = env.generateSequence(1, NUM_VERTICES);
	DataSet<String> edgeString = env.fromElements(ConnectedComponentsData.getRandomOddEvenEdges(NUM_EDGES, NUM_VERTICES, SEED).split("\n"));

	DataSet<Edge<Long, NullValue>> edges = edgeString.map(new EdgeParser());

	DataSet<Vertex<Long, Long>> initialVertices = vertexIds.map(new IdAssigner());

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

	DataSet<Vertex<Long, Long>> result = graph.run(new ConnectedComponents<>(100));

	result.writeAsCsv(resultPath, "\n", " ");
	env.execute();
}
 

@Override
protected void testProgram() throws Exception {
	final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<Long> longs = env.generateSequence(0, 100000);

	DataSet<Tuple1<Long>> longT1 = longs.map(new TupleWrapper());
	DataSet<Tuple1<Long>> longT2 = longT1.project(0);
	DataSet<Tuple1<Long>> longT3 = longs.map(new TupleWrapper());

	longT2.join(longT3).where(0).equalTo(0).projectFirst(0)
			.join(longT1).where(0).equalTo(0).projectFirst(0)
			.writeAsText(resultPath);

	env.execute();
}
 

@Test
public void testCreatePlanAfterGetExecutionPlan() {
	ExecutionEnvironment env = new LocalEnvironment();

	DataSet<Integer> baseSet = env.fromElements(1, 2);

	DataSet<Integer> result = baseSet.map(new MapFunction<Integer, Integer>() {
		@Override public Integer map(Integer value) throws Exception {
			return value * 2;
		}});
	result.output(new DiscardingOutputFormat<Integer>());

	try {
		env.getExecutionPlan();
		env.createProgramPlan();
	} catch (Exception e) {
		e.printStackTrace();
		fail("Cannot run both #getExecutionPlan and #execute. Message: " + e.getMessage());
	}
}
 

private static DataSet<String> analyze(DataSet<String> input, DataSet<String> stats, int branches) {
	for (int i = 0; i < branches; i++) {
		final int ii = i;

		if (stats != null) {
			input = input.map(
				new RichMapFunction<String, String>() {
					@Override
					public String map(String value) {
						return value;
					}
			}).withBroadcastSet(stats.map(s -> "(" + s + ").map"), "stats");
		}

		DataSet<String> branch = input
			.map(s -> new Tuple2<>(0, s + ii)).returns(Types.TUPLE(Types.STRING, Types.INT))
			.groupBy(0)
			.minBy(1)
			.map(kv -> kv.f1).returns(Types.STRING);
		if (stats == null) {
			stats = branch;
		} else {
			stats = stats.union(branch);
		}
	}
	return stats.map(s -> "(" + s + ").stats");
}
 

private static void runConnectedComponents(ExecutionEnvironment env) throws Exception {

		env.setParallelism(PARALLELISM);
		env.getConfig().disableSysoutLogging();

		// read vertex and edge data
		DataSet<Long> vertices = ConnectedComponentsData.getDefaultVertexDataSet(env)
				.rebalance();

		DataSet<Tuple2<Long, Long>> edges = ConnectedComponentsData.getDefaultEdgeDataSet(env)
				.rebalance()
				.flatMap(new ConnectedComponents.UndirectEdge());

		// assign the initial components (equal to the vertex id)
		DataSet<Tuple2<Long, Long>> verticesWithInitialId = vertices
				.map(new ConnectedComponents.DuplicateValue<Long>());

		// open a delta iteration
		DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
				verticesWithInitialId.iterateDelta(verticesWithInitialId, 100, 0);

		// apply the step logic: join with the edges, select the minimum neighbor,
		// update if the component of the candidate is smaller
		DataSet<Tuple2<Long, Long>> changes = iteration.getWorkset().join(edges)
				.where(0).equalTo(0)
				.with(new ConnectedComponents.NeighborWithComponentIDJoin())

				.groupBy(0).aggregate(Aggregations.MIN, 1)

				.join(iteration.getSolutionSet())
				.where(0).equalTo(0)
				.with(new ConnectedComponents.ComponentIdFilter());

		// close the delta iteration (delta and new workset are identical)
		DataSet<Tuple2<Long, Long>> result = iteration.closeWith(changes, changes);

		result.output(new DiscardingOutputFormat<Tuple2<Long, Long>>());

		env.execute();
	}
 

private static DataSet<String> analyze(DataSet<String> input, DataSet<String> stats, int branches) {
	for (int i = 0; i < branches; i++) {
		final int ii = i;

		if (stats != null) {
			input = input.map(
				new RichMapFunction<String, String>() {
					@Override
					public String map(String value) {
						return value;
					}
			}).withBroadcastSet(stats.map(s -> "(" + s + ").map"), "stats");
		}

		DataSet<String> branch = input
			.map(s -> new Tuple2<>(0, s + ii)).returns(Types.TUPLE(Types.STRING, Types.INT))
			.groupBy(0)
			.minBy(1)
			.map(kv -> kv.f1).returns(Types.STRING);
		if (stats == null) {
			stats = branch;
		} else {
			stats = stats.union(branch);
		}
	}
	return stats.map(s -> "(" + s + ").stats");
}
 

@Test
public void testTypeConversionMapperCustomToTuple() throws Exception {
	/*
	 * Test type conversion mapper (Custom -> Tuple)
	 */

	final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<CustomType> ds = CollectionDataSets.getCustomTypeDataSet(env);
	DataSet<Tuple3<Integer, Long, String>> typeConversionMapDs = ds.
			map(new Mapper3());

	List<Tuple3<Integer, Long, String>> result = typeConversionMapDs.collect();

	String expected = "1,0,Hi\n" +
			"2,1,Hello\n" +
			"2,2,Hello world\n" +
			"3,3,Hello world, how are you?\n" +
			"3,4,I am fine.\n" +
			"3,5,Luke Skywalker\n" +
			"4,6,Comment#1\n" +
			"4,7,Comment#2\n" +
			"4,8,Comment#3\n" +
			"4,9,Comment#4\n" +
			"5,10,Comment#5\n" +
			"5,11,Comment#6\n" +
			"5,12,Comment#7\n" +
			"5,13,Comment#8\n" +
			"5,14,Comment#9\n" +
			"6,15,Comment#10\n" +
			"6,16,Comment#11\n" +
			"6,17,Comment#12\n" +
			"6,18,Comment#13\n" +
			"6,19,Comment#14\n" +
			"6,20,Comment#15\n";

	compareResultAsTuples(result, expected);
}
 

public static void main(String[] args) throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.getConfig().disableSysoutLogging();

	// read vertex and edge data
	DataSet<Long> vertices = ConnectedComponentsData.getDefaultVertexDataSet(env)
			.rebalance();

	DataSet<Tuple2<Long, Long>> edges = ConnectedComponentsData.getDefaultEdgeDataSet(env)
			.rebalance()
			.flatMap(new ConnectedComponents.UndirectEdge());

	// assign the initial components (equal to the vertex id)
	DataSet<Tuple2<Long, Long>> verticesWithInitialId = vertices
			.map(new ConnectedComponents.DuplicateValue<>());

	// open a delta iteration
	DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
			verticesWithInitialId.iterateDelta(verticesWithInitialId, 100, 0);

	// apply the step logic: join with the edges, select the minimum neighbor,
	// update if the component of the candidate is smaller
	DataSet<Tuple2<Long, Long>> changes = iteration.getWorkset().join(edges)
			.where(0).equalTo(0)
			.with(new ConnectedComponents.NeighborWithComponentIDJoin())

			.groupBy(0).aggregate(Aggregations.MIN, 1)

			.join(iteration.getSolutionSet())
			.where(0).equalTo(0)
			.with(new ConnectedComponents.ComponentIdFilter());

	// close the delta iteration (delta and new workset are identical)
	DataSet<Tuple2<Long, Long>> result = iteration.closeWith(changes, changes);

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

	env.execute();
}
 

private static DataSet<Long>
getMinSupportCnt(DataSet<Long> transactionsCnt,
                 final int minSupportCount, final double minSupportPercent) {
    return transactionsCnt.map(new MapFunction<Long, Long>() {
        @Override
        public Long map(Long value) throws Exception {
            if (minSupportCount >= 0) {
                return (long) minSupportCount;
            } else {
                return (long) (Math.floor(value * minSupportPercent));
            }
        }
    });
}
 

@Override
protected void testProgram() throws Exception {
	// set up execution environment
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	// read vertex and edge data
	DataSet<Tuple1<Long>> vertices = env.readCsvFile(verticesPath).types(Long.class);

	DataSet<Tuple2<Long, Long>> edges = env.readCsvFile(edgesPath).fieldDelimiter(" ").types(Long.class, Long.class)
			.flatMap(new ConnectedComponents.UndirectEdge());

	// assign the initial components (equal to the vertex id)
	DataSet<Tuple2<Long, Long>> verticesWithInitialId = vertices.map(new DuplicateValue<Long>());

	// open a delta iteration
	DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
			verticesWithInitialId.iterateDelta(verticesWithInitialId, 100, 0);

	// apply the step logic: join with the edges, select the minimum neighbor, update if the component of the candidate is smaller
	DataSet<Tuple2<Long, Long>> changes = iteration.getWorkset().join(edges).where(0).equalTo(0).with(new ConnectedComponents.NeighborWithComponentIDJoin())
			.groupBy(0).aggregate(Aggregations.MIN, 1)
			.join(iteration.getSolutionSet()).where(0).equalTo(0)
			.with(new ConnectedComponents.ComponentIdFilter());

	// close the delta iteration (delta and new workset are identical)
	DataSet<Tuple2<Long, Long>> result = iteration.closeWith(changes, changes);

	result.writeAsCsv(resultPath, "\n", " ");

	// execute program
	env.execute("Connected Components Example");
}
 

/**
 * <pre>
 *             +---------Iteration-------+
 *             |                         |
 *    /--map--< >----\                   |
 *   /         |      \         /-------< >---sink
 * src-map     |     join------/         |
 *   \         |      /                  |
 *    \        +-----/-------------------+
 *     \            /
 *      \--reduce--/
 * </pre>
 */
@Test
public void testIterationWithStaticInput() {
	try {
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
		env.setParallelism(100);

		DataSet<Long> source = env.generateSequence(1, 1000000);

		DataSet<Long> mapped = source.map(new IdentityMapper<Long>());

		DataSet<Long> reduced = source.groupBy(new IdentityKeyExtractor<Long>()).reduce(new SelectOneReducer<Long>());

		IterativeDataSet<Long> iteration = mapped.iterate(10);
		iteration.closeWith(
				iteration.join(reduced)
						.where(new IdentityKeyExtractor<Long>())
						.equalTo(new IdentityKeyExtractor<Long>())
						.with(new DummyFlatJoinFunction<Long>()))
				.output(new DiscardingOutputFormat<Long>());

		compileNoStats(env.createProgramPlan());
	}
	catch(Exception e){
		e.printStackTrace();
		fail(e.getMessage());
	}
}
 

@Override
protected void testProgram() throws Exception {
	// set up execution environment
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	// read vertex and edge data
	DataSet<Tuple1<Long>> vertices = env.readCsvFile(verticesPath).types(Long.class);

	DataSet<Tuple2<Long, Long>> edges = env.readCsvFile(edgesPath).fieldDelimiter(" ").types(Long.class, Long.class)
			.flatMap(new ConnectedComponents.UndirectEdge());

	// assign the initial components (equal to the vertex id)
	DataSet<Tuple2<Long, Long>> verticesWithInitialId = vertices.map(new ConnectedComponentsITCase.DuplicateValue<Long>());

	// open a delta iteration
	DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
			verticesWithInitialId.iterateDelta(verticesWithInitialId, 100, 0);

	// apply the step logic: join with the edges, select the minimum neighbor, update if the component of the candidate is smaller
	DataSet<Tuple2<Long, Long>> minNeighbor = iteration.getWorkset()
			.join(edges).where(0).equalTo(0).with(new ConnectedComponents.NeighborWithComponentIDJoin())
			.groupBy(0).aggregate(Aggregations.MIN, 1);

	DataSet<Tuple2<Long, Long>> updatedIds = iteration.getSolutionSet()
			.join(minNeighbor).where(0).equalTo(0).with(new UpdateComponentIdMatchMirrored());

	// close the delta iteration (delta and new workset are identical)
	DataSet<Tuple2<Long, Long>> result = iteration.closeWith(updatedIds, updatedIds);

	result.writeAsCsv(resultPath, "\n", " ");

	// execute program
	env.execute("Connected Components Example");
}
 

@Override
protected void testProgram() throws Exception {

	// set up execution environment
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	// read vertex and edge data
	DataSet<Long> vertices = env.fromElements(ConnectedComponentsData.getEnumeratingVertices(NUM_VERTICES).split("\n"))
			.map(new VertexParser());

	DataSet<Tuple2<Long, Long>> edges = env.fromElements(ConnectedComponentsData.getRandomOddEvenEdges(NUM_EDGES, NUM_VERTICES, SEED).split("\n"))
			.flatMap(new EdgeParser());

	// assign the initial components (equal to the vertex id)
	DataSet<Tuple2<Long, Long>> verticesWithInitialId = vertices.map(new DuplicateValue<Long>());

	// open a delta iteration
	DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
			verticesWithInitialId.iterateDelta(verticesWithInitialId, 100, 0);

	// apply the step logic: join with the edges, select the minimum neighbor, update if the component of the candidate is smaller
	DataSet<Tuple2<Long, Long>> changes = iteration
			.getWorkset().join(edges).where(0).equalTo(0).with(new NeighborWithComponentIDJoin())
			.coGroup(iteration.getSolutionSet()).where(0).equalTo(0)
			.with(new MinIdAndUpdate());

	// close the delta iteration (delta and new workset are identical)
	DataSet<Tuple2<Long, Long>> result = iteration.closeWith(changes, changes);

	// emit result
	List<Tuple2<Long, Long>> resutTuples = new ArrayList<>();
	result.output(new LocalCollectionOutputFormat<>(resutTuples));

	env.execute();
}
 

/**
 * Tests whether the kryo serializer is forwarded via the ExecutionConfig.
 * @throws Exception
 */
@Test
public void testRegisterTypeWithKryoSerializer() throws Exception {
	int numElements = 10;
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	env.registerTypeWithKryoSerializer(TestClass.class, new TestClassSerializer());

	DataSet<Long> input = env.generateSequence(0, numElements - 1);

	DataSet<TestClass> mapped = input.map(new MapFunction<Long, TestClass>() {
		private static final long serialVersionUID = -529116076312998262L;

		@Override
		public TestClass map(Long value) throws Exception {
			return new TestClass(value);
		}
	});

	List<TestClass> expected = new ArrayList<>(numElements);

	for (int i = 0; i < numElements; i++) {
		expected.add(new TestClass(42));
	}

	compareResultCollections(expected, mapped.collect(), new Comparator<TestClass>() {
		@Override
		public int compare(TestClass o1, TestClass o2) {
			return (int) (o1.getValue() - o2.getValue());
		}
	});
}
 

@Test
public void test() throws Exception {
	/*
	 * Test mapper if UDF returns input object - increment first field of a tuple
	 */

	final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	DataSet<Tuple3<Integer, Long, String>> ds = CollectionDataSets.get3TupleDataSet(env);
	DataSet<Tuple3<Integer, Long, String>> inputObjMapDs = ds.
			map(new Mapper7());

	List<Tuple3<Integer, Long, String>> result = inputObjMapDs.collect();

	String expected = "2,1,Hi\n" +
			"3,2,Hello\n" +
			"4,2,Hello world\n" +
			"5,3,Hello world, how are you?\n" +
			"6,3,I am fine.\n" +
			"7,3,Luke Skywalker\n" +
			"8,4,Comment#1\n" +
			"9,4,Comment#2\n" +
			"10,4,Comment#3\n" +
			"11,4,Comment#4\n" +
			"12,5,Comment#5\n" +
			"13,5,Comment#6\n" +
			"14,5,Comment#7\n" +
			"15,5,Comment#8\n" +
			"16,5,Comment#9\n" +
			"17,6,Comment#10\n" +
			"18,6,Comment#11\n" +
			"19,6,Comment#12\n" +
			"20,6,Comment#13\n" +
			"21,6,Comment#14\n" +
			"22,6,Comment#15\n";

	compareResultAsTuples(result, expected);
}
 

public static void main(String[] args) throws Exception {

		ParameterTool params = ParameterTool.fromArgs(args);

		final int numPages = params.getInt("numPages", PageRankData.getNumberOfPages());
		final int maxIterations = params.getInt("iterations", 10);

		// set up execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		// make the parameters available to the web ui
		env.getConfig().setGlobalJobParameters(params);

		// get input data
		DataSet<Long> pagesInput = getPagesDataSet(env, params);
		DataSet<Tuple2<Long, Long>> linksInput = getLinksDataSet(env, params);

		// assign initial rank to pages
		DataSet<Tuple2<Long, Double>> pagesWithRanks = pagesInput.
				map(new RankAssigner((1.0d / numPages)));

		// build adjacency list from link input
		DataSet<Tuple2<Long, Long[]>> adjacencyListInput =
				linksInput.groupBy(0).reduceGroup(new BuildOutgoingEdgeList());

		// set iterative data set
		IterativeDataSet<Tuple2<Long, Double>> iteration = pagesWithRanks.iterate(maxIterations);

		DataSet<Tuple2<Long, Double>> newRanks = iteration
				// join pages with outgoing edges and distribute rank
				.join(adjacencyListInput).where(0).equalTo(0).flatMap(new JoinVertexWithEdgesMatch())
				// collect and sum ranks
				.groupBy(0).aggregate(SUM, 1)
				// apply dampening factor
				.map(new Dampener(DAMPENING_FACTOR, numPages));

		DataSet<Tuple2<Long, Double>> finalPageRanks = iteration.closeWith(
				newRanks,
				newRanks.join(iteration).where(0).equalTo(0)
				// termination condition
				.filter(new EpsilonFilter()));

		// emit result
		if (params.has("output")) {
			finalPageRanks.writeAsCsv(params.get("output"), "\n", " ");
			// execute program
			env.execute("Basic Page Rank Example");
		} else {
			System.out.println("Printing result to stdout. Use --output to specify output path.");
			finalPageRanks.print();
		}
	}
 

public static void main(String[] args) throws Exception {

		// Checking input parameters
		final ParameterTool params = ParameterTool.fromArgs(args);

		// set up execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		// make parameters available in the web interface
		env.getConfig().setGlobalJobParameters(params);

		// read input data
		DataSet<Edge> edges;
		if (params.has("edges")) {
			edges = env.readCsvFile(params.get("edges"))
					.fieldDelimiter(" ")
					.includeFields(true, true)
					.types(Integer.class, Integer.class)
					.map(new TupleEdgeConverter());
		} else {
			System.out.println("Executing EnumTriangles example with default edges data set.");
			System.out.println("Use --edges to specify file input.");
			edges = EnumTrianglesData.getDefaultEdgeDataSet(env);
		}

		// project edges by vertex id
		DataSet<Edge> edgesById = edges
				.map(new EdgeByIdProjector());

		DataSet<Triad> triangles = edgesById
				// build triads
				.groupBy(Edge.V1).sortGroup(Edge.V2, Order.ASCENDING).reduceGroup(new TriadBuilder())
				// filter triads
				.join(edgesById).where(Triad.V2, Triad.V3).equalTo(Edge.V1, Edge.V2).with(new TriadFilter());

		// emit result
		if (params.has("output")) {
			triangles.writeAsCsv(params.get("output"), "\n", ",");
			// execute program
			env.execute("Basic Triangle Enumeration Example");
		} else {
			System.out.println("Printing result to stdout. Use --output to specify output path.");
			triangles.print();
		}
	}
 

@Override
protected void testProgram() throws Exception {
	// set up execution environment
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	// read vertex and edge data
	DataSet<Tuple1<Long>> vertices = env.readCsvFile(verticesPath).types(Long.class);

	DataSet<Tuple2<Long, Long>> edges = env.readCsvFile(edgesPath).fieldDelimiter(" ").types(Long.class, Long.class)
			.flatMap(new ConnectedComponents.UndirectEdge());

	// assign the initial components (equal to the vertex id)
	DataSet<Tuple2<Long, Long>> verticesWithInitialId = vertices.map(new ConnectedComponentsITCase.DuplicateValue<Long>());

	// open a delta iteration
	DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
			verticesWithInitialId.iterateDelta(verticesWithInitialId, 100, 0);

	// apply the step logic: join with the edges, select the minimum neighbor, update if the component of the candidate is smaller
	DataSet<Tuple2<Long, Long>> changes = iteration.getWorkset()
			.join(edges).where(0).equalTo(0).with(new ConnectedComponents.NeighborWithComponentIDJoin())
			.groupBy(0).aggregate(Aggregations.MIN, 1)
			.join(iteration.getSolutionSet()).where(0).equalTo(0)
			.with(new UpdateComponentIdMatchNonPreserving());

	DataSet<Tuple2<Long, Long>> delta;
	if (extraMapper) {
		delta = changes.map(
				// ID Mapper
				new MapFunction<Tuple2<Long, Long>, Tuple2<Long, Long>>() {
					private static final long serialVersionUID = -3929364091829757322L;

					@Override
					public Tuple2<Long, Long> map(Tuple2<Long, Long> v) throws Exception {
						return v;
					}
				});
	}
	else {
		delta = changes;
	}

	// close the delta iteration (delta and new workset are identical)
	DataSet<Tuple2<Long, Long>> result = iteration.closeWith(delta, changes);

	result.writeAsCsv(resultPath, "\n", " ");

	// execute program
	env.execute("Connected Components Example");
}
 

public static void main(String[] args) throws Exception {

		// Checking input parameters
		final ParameterTool params = ParameterTool.fromArgs(args);

		// set up execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		// make parameters available in the web interface
		env.getConfig().setGlobalJobParameters(params);

		// read input data
		DataSet<Edge> edges;
		if (params.has("edges")) {
			edges = env.readCsvFile(params.get("edges"))
					.fieldDelimiter(" ")
					.includeFields(true, true)
					.types(Integer.class, Integer.class)
					.map(new TupleEdgeConverter());
		} else {
			System.out.println("Executing EnumTriangles example with default edges data set.");
			System.out.println("Use --edges to specify file input.");
			edges = EnumTrianglesData.getDefaultEdgeDataSet(env);
		}

		// project edges by vertex id
		DataSet<Edge> edgesById = edges
				.map(new EdgeByIdProjector());

		DataSet<Triad> triangles = edgesById
				// build triads
				.groupBy(Edge.V1).sortGroup(Edge.V2, Order.ASCENDING).reduceGroup(new TriadBuilder())
				// filter triads
				.join(edgesById).where(Triad.V2, Triad.V3).equalTo(Edge.V1, Edge.V2).with(new TriadFilter());

		// emit result
		if (params.has("output")) {
			triangles.writeAsCsv(params.get("output"), "\n", ",");
			// execute program
			env.execute("Basic Triangle Enumeration Example");
		} else {
			System.out.println("Printing result to stdout. Use --output to specify output path.");
			triangles.print();
		}
	}