@Test public void testFirstNOnUngroupedDS() throws Exception { /* * First-n on ungrouped data set */ final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment(); DataSet<Tuple3<Integer, Long, String>> ds = CollectionDataSets.get3TupleDataSet(env); DataSet<Tuple1<Integer>> seven = ds.first(7).map(new OneMapper()).sum(0); List<Tuple1<Integer>> result = seven.collect(); String expected = "(7)\n"; compareResultAsText(result, expected); }
return new Tuple2<Long, Text>(value.f0.get(), value.f1); }).sum(0); sumed.writeAsText(resultPath[0]); DataSet<String> res = ds.distinct(0).map(new MapFunction<Tuple2<LongWritable, Text>, String>() {
@Test public void testReplicatedSourceToCross() throws Exception { /* * Test replicated source going into cross */ final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment(); DataSet<Tuple1<Long>> source1 = env.createInput(new ReplicatingInputFormat<Long, GenericInputSplit> (new ParallelIteratorInputFormat<Long>(new NumberSequenceIterator(0L, 1000L))), BasicTypeInfo.LONG_TYPE_INFO) .map(new ToTuple()); DataSet<Tuple1<Long>> source2 = env.generateSequence(0L, 1000L).map(new ToTuple()); DataSet<Tuple1<Long>> pairs = source1.cross(source2) .filter(new FilterFunction<Tuple2<Tuple1<Long>, Tuple1<Long>>>() { @Override public boolean filter(Tuple2<Tuple1<Long>, Tuple1<Long>> value) throws Exception { return value.f0.f0.equals(value.f1.f0); } }) .map(new MapFunction<Tuple2<Tuple1<Long>, Tuple1<Long>>, Tuple1<Long>>() { @Override public Tuple1<Long> map(Tuple2<Tuple1<Long>, Tuple1<Long>> value) throws Exception { return value.f0; } }) .sum(0); List<Tuple1<Long>> result = pairs.collect(); String expectedResult = "(500500)"; compareResultAsText(result, expectedResult); }
.setParallelism(parallelism) .name("Average score") .sum(0) .andSum(1);
.setParallelism(littleParallelism) .name("Average score") .sum(0) .andSum(1);
.setParallelism(parallelism) .name("Average score") .sum(0) .andSum(1);
.setParallelism(parallelism) .name("Average score") .sum(0) .andSum(1);