Examples with IterativeDataSet org.apache.flink.api.java.operators.IterativeDataSet used on opensource projects

Example 1 with IterativeDataSet

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

the class DataSetAllroundTestProgram method main.

@SuppressWarnings("Convert2Lambda")
public static void main(String[] args) throws Exception {
    // get parameters
    ParameterTool params = ParameterTool.fromArgs(args);
    int loadFactor = Integer.parseInt(params.getRequired("loadFactor"));
    String outputPath = params.getRequired("outputPath");
    boolean infinite = params.getBoolean("infinite", false);
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    int numKeys = loadFactor * 128 * 1024;
    DataSet<Tuple2<String, Integer>> x1Keys;
    DataSet<Tuple2<String, Integer>> x2Keys = env.createInput(Generator.generate(numKeys * 32, 2)).setParallelism(4);
    DataSet<Tuple2<String, Integer>> x8Keys = env.createInput(Generator.generate(numKeys, 8)).setParallelism(4);
    if (infinite) {
        x1Keys = env.createInput(Generator.generateInfinitely(numKeys)).setParallelism(4);
    } else {
        x1Keys = env.createInput(Generator.generate(numKeys, 1)).setParallelism(4);
    }
    DataSet<Tuple2<String, Integer>> joined = x2Keys.map(x -> Tuple4.of("0-0", 0L, 1, x.f0)).returns(Types.TUPLE(Types.STRING, Types.LONG, Types.INT, Types.STRING)).join(x8Keys).where(3).equalTo(0).with((l, r) -> Tuple2.of(l.f3, 1)).returns(Types.TUPLE(Types.STRING, Types.INT)).groupBy(new KeySelector<Tuple2<String, Integer>, String>() {

        @Override
        public String getKey(Tuple2<String, Integer> value) {
            return value.f0;
        }
    }).reduce((value1, value2) -> Tuple2.of(value1.f0, value1.f1 + value2.f1));
    // co-group two datasets on their primary keys.
    // we filter both inputs such that only 6.25% of the keys overlap.
    // result: (key, cnt), #keys records with unique keys, cnt = (6.25%: 2, 93.75%: 1)
    DataSet<Tuple2<String, Integer>> coGrouped = x1Keys.filter(x -> x.f1 > 59).coGroup(x1Keys.filter(x -> x.f1 < 68)).where("f0").equalTo("f0").with((CoGroupFunction<Tuple2<String, Integer>, Tuple2<String, Integer>, Tuple2<String, Integer>>) (l, r, out) -> {
        int cnt = 0;
        String key = "";
        for (Tuple2<String, Integer> t : l) {
            cnt++;
            key = t.f0;
        }
        for (Tuple2<String, Integer> t : r) {
            cnt++;
            key = t.f0;
        }
        out.collect(Tuple2.of(key, cnt));
    }).returns(Types.TUPLE(Types.STRING, Types.INT));
    // join datasets on keys (1-1 join) and replicate by 16 (previously computed count)
    // result: (key, cnt), 16 * #keys records, all keys preserved, cnt = (6.25%: 2, 93.75%: 1)
    DataSet<Tuple2<String, Integer>> joined2 = joined.join(coGrouped, JoinOperatorBase.JoinHint.REPARTITION_SORT_MERGE).where(0).equalTo("f0").flatMap((FlatMapFunction<Tuple2<Tuple2<String, Integer>, Tuple2<String, Integer>>, Tuple2<String, Integer>>) (p, out) -> {
        for (int i = 0; i < p.f0.f1; i++) {
            out.collect(Tuple2.of(p.f0.f0, p.f1.f1));
        }
    }).returns(Types.TUPLE(Types.STRING, Types.INT));
    // iteration. double the count field until all counts are at 32 or more
    // result: (key, cnt), 16 * #keys records, all keys preserved, cnt = (6.25%: 64, 93.75%: 32)
    IterativeDataSet<Tuple2<String, Integer>> initial = joined2.iterate(16);
    DataSet<Tuple2<String, Integer>> iteration = initial.map(x -> Tuple2.of(x.f0, x.f1 * 2)).returns(Types.TUPLE(Types.STRING, Types.INT));
    DataSet<Boolean> termination = iteration.flatMap((FlatMapFunction<Tuple2<String, Integer>, Boolean>) (x, out) -> {
        if (x.f1 < 32) {
            out.collect(false);
        }
    }).returns(Types.BOOLEAN);
    DataSet<Tuple2<Integer, Integer>> result = initial.closeWith(iteration, termination).groupBy(1).reduceGroup((GroupReduceFunction<Tuple2<String, Integer>, Tuple2<Integer, Integer>>) (g, out) -> {
        int key = 0;
        int cnt = 0;
        for (Tuple2<String, Integer> r : g) {
            key = r.f1;
            cnt++;
        }
        out.collect(Tuple2.of(key, cnt));
    }).returns(Types.TUPLE(Types.INT, Types.INT)).map(x -> Tuple2.of(x.f0, x.f1 / (loadFactor * 128))).returns(Types.TUPLE(Types.INT, Types.INT));
    // sort and emit result
    result.sortPartition(0, Order.ASCENDING).setParallelism(1).writeAsText(outputPath, FileSystem.WriteMode.OVERWRITE).setParallelism(1);
    env.execute();
}

Example 2 with IterativeDataSet

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

the class BulkIterationTranslationTest method testCorrectTranslation.

@Test
public void testCorrectTranslation() {
    final String jobName = "Test JobName";
    final int numIterations = 13;
    final int defaultParallelism = 133;
    final int iterationParallelism = 77;
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    // ------------ construct the test program ------------------
    {
        env.setParallelism(defaultParallelism);
        @SuppressWarnings("unchecked") DataSet<Tuple3<Double, Long, String>> initialDataSet = env.fromElements(new Tuple3<>(3.44, 5L, "abc"));
        IterativeDataSet<Tuple3<Double, Long, String>> bulkIteration = initialDataSet.iterate(numIterations);
        bulkIteration.setParallelism(iterationParallelism);
        // test that multiple iteration consumers are supported
        DataSet<Tuple3<Double, Long, String>> identity = bulkIteration.map(new IdentityMapper<Tuple3<Double, Long, String>>());
        DataSet<Tuple3<Double, Long, String>> result = bulkIteration.closeWith(identity);
        result.output(new DiscardingOutputFormat<Tuple3<Double, Long, String>>());
        result.writeAsText("/dev/null");
    }
    Plan p = env.createProgramPlan(jobName);
    // ------------- validate the plan ----------------
    BulkIterationBase<?> iteration = (BulkIterationBase<?>) p.getDataSinks().iterator().next().getInput();
    assertEquals(jobName, p.getJobName());
    assertEquals(defaultParallelism, p.getDefaultParallelism());
    assertEquals(iterationParallelism, iteration.getParallelism());
}

Example 3 with IterativeDataSet

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

the class BulkIterationTranslationTest method testCorrectTranslation.

@Test
public void testCorrectTranslation() {
    final String jobName = "Test JobName";
    final int numIterations = 13;
    final int defaultParallelism = 133;
    final int iterationParallelism = 77;
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    // ------------ construct the test program ------------------
    {
        env.setParallelism(defaultParallelism);
        @SuppressWarnings("unchecked") DataSet<Tuple3<Double, Long, String>> initialDataSet = env.fromElements(new Tuple3<>(3.44, 5L, "abc"));
        IterativeDataSet<Tuple3<Double, Long, String>> bulkIteration = initialDataSet.iterate(numIterations);
        bulkIteration.setParallelism(iterationParallelism);
        // test that multiple iteration consumers are supported
        DataSet<Tuple3<Double, Long, String>> identity = bulkIteration.map(new IdentityMapper<Tuple3<Double, Long, String>>());
        DataSet<Tuple3<Double, Long, String>> result = bulkIteration.closeWith(identity);
        result.output(new DiscardingOutputFormat<Tuple3<Double, Long, String>>());
        result.writeAsText("/dev/null");
    }
    Plan p = env.createProgramPlan(jobName);
    // ------------- validate the plan ----------------
    BulkIterationBase<?> iteration = (BulkIterationBase<?>) p.getDataSinks().iterator().next().getInput();
    assertEquals(jobName, p.getJobName());
    assertEquals(defaultParallelism, p.getDefaultParallelism());
    assertEquals(iterationParallelism, iteration.getParallelism());
}

Example 4 with IterativeDataSet

use of org.apache.flink.api.java.operators.IterativeDataSet in project flink-mirror by flink-ci.

the class DataSetAllroundTestProgram method main.

@SuppressWarnings("Convert2Lambda")
public static void main(String[] args) throws Exception {
    // get parameters
    ParameterTool params = ParameterTool.fromArgs(args);
    int loadFactor = Integer.parseInt(params.getRequired("loadFactor"));
    String outputPath = params.getRequired("outputPath");
    boolean infinite = params.getBoolean("infinite", false);
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    int numKeys = loadFactor * 128 * 1024;
    DataSet<Tuple2<String, Integer>> x1Keys;
    DataSet<Tuple2<String, Integer>> x2Keys = env.createInput(Generator.generate(numKeys * 32, 2)).setParallelism(4);
    DataSet<Tuple2<String, Integer>> x8Keys = env.createInput(Generator.generate(numKeys, 8)).setParallelism(4);
    if (infinite) {
        x1Keys = env.createInput(Generator.generateInfinitely(numKeys)).setParallelism(4);
    } else {
        x1Keys = env.createInput(Generator.generate(numKeys, 1)).setParallelism(4);
    }
    DataSet<Tuple2<String, Integer>> joined = x2Keys.map(x -> Tuple4.of("0-0", 0L, 1, x.f0)).returns(Types.TUPLE(Types.STRING, Types.LONG, Types.INT, Types.STRING)).join(x8Keys).where(3).equalTo(0).with((l, r) -> Tuple2.of(l.f3, 1)).returns(Types.TUPLE(Types.STRING, Types.INT)).groupBy(new KeySelector<Tuple2<String, Integer>, String>() {

        @Override
        public String getKey(Tuple2<String, Integer> value) {
            return value.f0;
        }
    }).reduce((value1, value2) -> Tuple2.of(value1.f0, value1.f1 + value2.f1));
    // co-group two datasets on their primary keys.
    // we filter both inputs such that only 6.25% of the keys overlap.
    // result: (key, cnt), #keys records with unique keys, cnt = (6.25%: 2, 93.75%: 1)
    DataSet<Tuple2<String, Integer>> coGrouped = x1Keys.filter(x -> x.f1 > 59).coGroup(x1Keys.filter(x -> x.f1 < 68)).where("f0").equalTo("f0").with((CoGroupFunction<Tuple2<String, Integer>, Tuple2<String, Integer>, Tuple2<String, Integer>>) (l, r, out) -> {
        int cnt = 0;
        String key = "";
        for (Tuple2<String, Integer> t : l) {
            cnt++;
            key = t.f0;
        }
        for (Tuple2<String, Integer> t : r) {
            cnt++;
            key = t.f0;
        }
        out.collect(Tuple2.of(key, cnt));
    }).returns(Types.TUPLE(Types.STRING, Types.INT));
    // join datasets on keys (1-1 join) and replicate by 16 (previously computed count)
    // result: (key, cnt), 16 * #keys records, all keys preserved, cnt = (6.25%: 2, 93.75%: 1)
    DataSet<Tuple2<String, Integer>> joined2 = joined.join(coGrouped, JoinOperatorBase.JoinHint.REPARTITION_SORT_MERGE).where(0).equalTo("f0").flatMap((FlatMapFunction<Tuple2<Tuple2<String, Integer>, Tuple2<String, Integer>>, Tuple2<String, Integer>>) (p, out) -> {
        for (int i = 0; i < p.f0.f1; i++) {
            out.collect(Tuple2.of(p.f0.f0, p.f1.f1));
        }
    }).returns(Types.TUPLE(Types.STRING, Types.INT));
    // iteration. double the count field until all counts are at 32 or more
    // result: (key, cnt), 16 * #keys records, all keys preserved, cnt = (6.25%: 64, 93.75%: 32)
    IterativeDataSet<Tuple2<String, Integer>> initial = joined2.iterate(16);
    DataSet<Tuple2<String, Integer>> iteration = initial.map(x -> Tuple2.of(x.f0, x.f1 * 2)).returns(Types.TUPLE(Types.STRING, Types.INT));
    DataSet<Boolean> termination = iteration.flatMap((FlatMapFunction<Tuple2<String, Integer>, Boolean>) (x, out) -> {
        if (x.f1 < 32) {
            out.collect(false);
        }
    }).returns(Types.BOOLEAN);
    DataSet<Tuple2<Integer, Integer>> result = initial.closeWith(iteration, termination).groupBy(1).reduceGroup((GroupReduceFunction<Tuple2<String, Integer>, Tuple2<Integer, Integer>>) (g, out) -> {
        int key = 0;
        int cnt = 0;
        for (Tuple2<String, Integer> r : g) {
            key = r.f1;
            cnt++;
        }
        out.collect(Tuple2.of(key, cnt));
    }).returns(Types.TUPLE(Types.INT, Types.INT)).map(x -> Tuple2.of(x.f0, x.f1 / (loadFactor * 128))).returns(Types.TUPLE(Types.INT, Types.INT));
    // sort and emit result
    result.sortPartition(0, Order.ASCENDING).setParallelism(1).writeAsText(outputPath, FileSystem.WriteMode.OVERWRITE).setParallelism(1);
    env.execute();
}

Example 5 with IterativeDataSet

use of org.apache.flink.api.java.operators.IterativeDataSet in project flink-mirror by flink-ci.

the class BulkIterationTranslationTest method testCorrectTranslation.

@Test
public void testCorrectTranslation() {
    final String jobName = "Test JobName";
    final int numIterations = 13;
    final int defaultParallelism = 133;
    final int iterationParallelism = 77;
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    // ------------ construct the test program ------------------
    {
        env.setParallelism(defaultParallelism);
        @SuppressWarnings("unchecked") DataSet<Tuple3<Double, Long, String>> initialDataSet = env.fromElements(new Tuple3<>(3.44, 5L, "abc"));
        IterativeDataSet<Tuple3<Double, Long, String>> bulkIteration = initialDataSet.iterate(numIterations);
        bulkIteration.setParallelism(iterationParallelism);
        // test that multiple iteration consumers are supported
        DataSet<Tuple3<Double, Long, String>> identity = bulkIteration.map(new IdentityMapper<Tuple3<Double, Long, String>>());
        DataSet<Tuple3<Double, Long, String>> result = bulkIteration.closeWith(identity);
        result.output(new DiscardingOutputFormat<Tuple3<Double, Long, String>>());
        result.writeAsText("/dev/null");
    }
    Plan p = env.createProgramPlan(jobName);
    // ------------- validate the plan ----------------
    BulkIterationBase<?> iteration = (BulkIterationBase<?>) p.getDataSinks().iterator().next().getInput();
    assertEquals(jobName, p.getJobName());
    assertEquals(defaultParallelism, p.getDefaultParallelism());
    assertEquals(iterationParallelism, iteration.getParallelism());
}