Search in sources :

Example 1 with DeltaIterationResultSet

use of org.apache.flink.api.java.operators.DeltaIterationResultSet in project flink by apache.

the class PregelTranslationTest method testTranslationPlainEdges.

@Test
public void testTranslationPlainEdges() {
    try {
        final String ITERATION_NAME = "Test Name";
        final String AGGREGATOR_NAME = "AggregatorName";
        final String BC_SET_NAME = "borat messages";
        final int NUM_ITERATIONS = 13;
        final int ITERATION_parallelism = 77;
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Long> bcVar = env.fromElements(1L);
        DataSet<Vertex<String, Double>> result;
        // ------------ construct the test program ------------------
        {
            DataSet<Tuple2<String, Double>> initialVertices = env.fromElements(new Tuple2<>("abc", 3.44));
            DataSet<Tuple2<String, String>> edges = env.fromElements(new Tuple2<>("a", "c"));
            Graph<String, Double, NullValue> graph = Graph.fromTupleDataSet(initialVertices, edges.map(new MapFunction<Tuple2<String, String>, Tuple3<String, String, NullValue>>() {

                public Tuple3<String, String, NullValue> map(Tuple2<String, String> edge) {
                    return new Tuple3<>(edge.f0, edge.f1, NullValue.getInstance());
                }
            }), env);
            VertexCentricConfiguration parameters = new VertexCentricConfiguration();
            parameters.addBroadcastSet(BC_SET_NAME, bcVar);
            parameters.setName(ITERATION_NAME);
            parameters.setParallelism(ITERATION_parallelism);
            parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
            result = graph.runVertexCentricIteration(new MyCompute(), null, NUM_ITERATIONS, parameters).getVertices();
            result.output(new DiscardingOutputFormat<Vertex<String, Double>>());
        }
        // ------------- 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());
        TwoInputUdfOperator<?, ?, ?, ?> computationCoGroup = (TwoInputUdfOperator<?, ?, ?, ?>) ((SingleInputUdfOperator<?, ?, ?>) resultSet.getNextWorkset()).getInput();
        // validate that the broadcast sets are forwarded
        assertEquals(bcVar, computationCoGroup.getBroadcastSets().get(BC_SET_NAME));
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getMessage());
    }
}
Also used : Vertex(org.apache.flink.graph.Vertex) ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) DataSet(org.apache.flink.api.java.DataSet) LongSumAggregator(org.apache.flink.api.common.aggregators.LongSumAggregator) DeltaIterationResultSet(org.apache.flink.api.java.operators.DeltaIterationResultSet) TwoInputUdfOperator(org.apache.flink.api.java.operators.TwoInputUdfOperator) DiscardingOutputFormat(org.apache.flink.api.java.io.DiscardingOutputFormat) Graph(org.apache.flink.graph.Graph) Tuple2(org.apache.flink.api.java.tuple.Tuple2) Tuple3(org.apache.flink.api.java.tuple.Tuple3) Test(org.junit.Test)

Example 2 with DeltaIterationResultSet

use of org.apache.flink.api.java.operators.DeltaIterationResultSet in project flink by apache.

the class SpargelTranslationTest method testTranslationPlainEdgesWithForkedBroadcastVariable.

@Test
public void testTranslationPlainEdgesWithForkedBroadcastVariable() {
    try {
        final String ITERATION_NAME = "Test Name";
        final String AGGREGATOR_NAME = "AggregatorName";
        final String BC_SET_MESSAGES_NAME = "borat messages";
        final String BC_SET_UPDATES_NAME = "borat updates";
        final int NUM_ITERATIONS = 13;
        final int ITERATION_parallelism = 77;
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Long> bcVar = env.fromElements(1L);
        DataSet<Vertex<String, Double>> result;
        // ------------ construct the test program ------------------
        {
            DataSet<Tuple2<String, Double>> initialVertices = env.fromElements(new Tuple2<>("abc", 3.44));
            DataSet<Tuple2<String, String>> edges = env.fromElements(new Tuple2<>("a", "c"));
            Graph<String, Double, NullValue> graph = Graph.fromTupleDataSet(initialVertices, edges.map(new MapFunction<Tuple2<String, String>, Tuple3<String, String, NullValue>>() {

                public Tuple3<String, String, NullValue> map(Tuple2<String, String> edge) {
                    return new Tuple3<>(edge.f0, edge.f1, NullValue.getInstance());
                }
            }), env);
            ScatterGatherConfiguration parameters = new ScatterGatherConfiguration();
            parameters.addBroadcastSetForScatterFunction(BC_SET_MESSAGES_NAME, bcVar);
            parameters.addBroadcastSetForGatherFunction(BC_SET_UPDATES_NAME, bcVar);
            parameters.setName(ITERATION_NAME);
            parameters.setParallelism(ITERATION_parallelism);
            parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
            result = graph.runScatterGatherIteration(new MessageFunctionNoEdgeValue(), new UpdateFunction(), NUM_ITERATIONS, parameters).getVertices();
            result.output(new DiscardingOutputFormat<Vertex<String, Double>>());
        }
        // ------------- 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));
        TwoInputUdfOperator<?, ?, ?, ?> edgesJoin = (TwoInputUdfOperator<?, ?, ?, ?>) solutionSetJoin.getInput1();
        // validate that the broadcast sets are forwarded
        assertEquals(bcVar, solutionSetJoin.getBroadcastSets().get(BC_SET_UPDATES_NAME));
        assertEquals(bcVar, edgesJoin.getBroadcastSets().get(BC_SET_MESSAGES_NAME));
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getMessage());
    }
}
Also used : Vertex(org.apache.flink.graph.Vertex) ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) DataSet(org.apache.flink.api.java.DataSet) LongSumAggregator(org.apache.flink.api.common.aggregators.LongSumAggregator) DeltaIterationResultSet(org.apache.flink.api.java.operators.DeltaIterationResultSet) TwoInputUdfOperator(org.apache.flink.api.java.operators.TwoInputUdfOperator) DiscardingOutputFormat(org.apache.flink.api.java.io.DiscardingOutputFormat) Graph(org.apache.flink.graph.Graph) Tuple2(org.apache.flink.api.java.tuple.Tuple2) Tuple3(org.apache.flink.api.java.tuple.Tuple3) Test(org.junit.Test)

Example 3 with DeltaIterationResultSet

use of org.apache.flink.api.java.operators.DeltaIterationResultSet in project flink by apache.

the class GSATranslationTest method testTranslation.

@Test
public void testTranslation() {
    try {
        final String ITERATION_NAME = "Test Name";
        final String AGGREGATOR_NAME = "AggregatorName";
        final String BC_SET_GATHER_NAME = "gather messages";
        final String BC_SET_SUM_NAME = "sum updates";
        final String BC_SET_APLLY_NAME = "apply updates";
        final int NUM_ITERATIONS = 13;
        final int ITERATION_parallelism = 77;
        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<Long, NullValue>());
            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<Vertex<Long, Long>>());
        }
        // ------------- 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));
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getMessage());
    }
}
Also used : Vertex(org.apache.flink.graph.Vertex) ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) DataSet(org.apache.flink.api.java.DataSet) LongSumAggregator(org.apache.flink.api.common.aggregators.LongSumAggregator) DeltaIterationResultSet(org.apache.flink.api.java.operators.DeltaIterationResultSet) TwoInputUdfOperator(org.apache.flink.api.java.operators.TwoInputUdfOperator) DiscardingOutputFormat(org.apache.flink.api.java.io.DiscardingOutputFormat) NullValue(org.apache.flink.types.NullValue) SingleInputUdfOperator(org.apache.flink.api.java.operators.SingleInputUdfOperator) Graph(org.apache.flink.graph.Graph) Tuple3ToEdgeMap(org.apache.flink.graph.utils.Tuple3ToEdgeMap) Test(org.junit.Test)

Example 4 with DeltaIterationResultSet

use of org.apache.flink.api.java.operators.DeltaIterationResultSet in project flink by apache.

the class SpargelTranslationTest method testTranslationPlainEdges.

@Test
public void testTranslationPlainEdges() {
    try {
        final String ITERATION_NAME = "Test Name";
        final String AGGREGATOR_NAME = "AggregatorName";
        final String BC_SET_MESSAGES_NAME = "borat messages";
        final String BC_SET_UPDATES_NAME = "borat updates";
        final int NUM_ITERATIONS = 13;
        final int ITERATION_parallelism = 77;
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Long> bcMessaging = env.fromElements(1L);
        DataSet<Long> bcUpdate = env.fromElements(1L);
        DataSet<Vertex<String, Double>> result;
        // ------------ construct the test program ------------------
        {
            DataSet<Tuple2<String, Double>> initialVertices = env.fromElements(new Tuple2<>("abc", 3.44));
            DataSet<Tuple2<String, String>> edges = env.fromElements(new Tuple2<>("a", "c"));
            Graph<String, Double, NullValue> graph = Graph.fromTupleDataSet(initialVertices, edges.map(new MapFunction<Tuple2<String, String>, Tuple3<String, String, NullValue>>() {

                public Tuple3<String, String, NullValue> map(Tuple2<String, String> edge) {
                    return new Tuple3<>(edge.f0, edge.f1, NullValue.getInstance());
                }
            }), env);
            ScatterGatherConfiguration parameters = new ScatterGatherConfiguration();
            parameters.addBroadcastSetForScatterFunction(BC_SET_MESSAGES_NAME, bcMessaging);
            parameters.addBroadcastSetForGatherFunction(BC_SET_UPDATES_NAME, bcUpdate);
            parameters.setName(ITERATION_NAME);
            parameters.setParallelism(ITERATION_parallelism);
            parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
            result = graph.runScatterGatherIteration(new MessageFunctionNoEdgeValue(), new UpdateFunction(), NUM_ITERATIONS, parameters).getVertices();
            result.output(new DiscardingOutputFormat<Vertex<String, Double>>());
        }
        // ------------- 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));
        TwoInputUdfOperator<?, ?, ?, ?> edgesJoin = (TwoInputUdfOperator<?, ?, ?, ?>) solutionSetJoin.getInput1();
        // validate that the broadcast sets are forwarded
        assertEquals(bcUpdate, solutionSetJoin.getBroadcastSets().get(BC_SET_UPDATES_NAME));
        assertEquals(bcMessaging, edgesJoin.getBroadcastSets().get(BC_SET_MESSAGES_NAME));
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getMessage());
    }
}
Also used : Vertex(org.apache.flink.graph.Vertex) ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) DataSet(org.apache.flink.api.java.DataSet) LongSumAggregator(org.apache.flink.api.common.aggregators.LongSumAggregator) DeltaIterationResultSet(org.apache.flink.api.java.operators.DeltaIterationResultSet) TwoInputUdfOperator(org.apache.flink.api.java.operators.TwoInputUdfOperator) DiscardingOutputFormat(org.apache.flink.api.java.io.DiscardingOutputFormat) Graph(org.apache.flink.graph.Graph) Tuple2(org.apache.flink.api.java.tuple.Tuple2) Tuple3(org.apache.flink.api.java.tuple.Tuple3) Test(org.junit.Test)

Aggregations

LongSumAggregator (org.apache.flink.api.common.aggregators.LongSumAggregator)4 DataSet (org.apache.flink.api.java.DataSet)4 ExecutionEnvironment (org.apache.flink.api.java.ExecutionEnvironment)4 DiscardingOutputFormat (org.apache.flink.api.java.io.DiscardingOutputFormat)4 DeltaIterationResultSet (org.apache.flink.api.java.operators.DeltaIterationResultSet)4 TwoInputUdfOperator (org.apache.flink.api.java.operators.TwoInputUdfOperator)4 Graph (org.apache.flink.graph.Graph)4 Vertex (org.apache.flink.graph.Vertex)4 Test (org.junit.Test)4 Tuple2 (org.apache.flink.api.java.tuple.Tuple2)3 Tuple3 (org.apache.flink.api.java.tuple.Tuple3)3 SingleInputUdfOperator (org.apache.flink.api.java.operators.SingleInputUdfOperator)1 Tuple3ToEdgeMap (org.apache.flink.graph.utils.Tuple3ToEdgeMap)1 NullValue (org.apache.flink.types.NullValue)1