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

The following examples show how to use org.apache.flink.api.java.DataSet#count() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: CountCollectITCase.java    From Flink-CEPplus with Apache License 2.0 6 votes vote down vote up 
@Test
public void testSimple() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	Integer[] input = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};

	DataSet<Integer> data = env.fromElements(input);

	// count
	long numEntries = data.count();
	assertEquals(10, numEntries);

	// collect
	ArrayList<Integer> list = (ArrayList<Integer>) data.collect();
	assertArrayEquals(input, list.toArray());
}
Example 2
Source File: CountCollectITCase.java    From flink with Apache License 2.0 6 votes vote down vote up 
@Test
public void testSimple() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	Integer[] input = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};

	DataSet<Integer> data = env.fromElements(input);

	// count
	long numEntries = data.count();
	assertEquals(10, numEntries);

	// collect
	ArrayList<Integer> list = (ArrayList<Integer>) data.collect();
	assertArrayEquals(input, list.toArray());
}
Example 3
Source File: CountCollectITCase.java    From flink with Apache License 2.0 6 votes vote down vote up 
@Test
public void testSimple() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	Integer[] input = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};

	DataSet<Integer> data = env.fromElements(input);

	// count
	long numEntries = data.count();
	assertEquals(10, numEntries);

	// collect
	ArrayList<Integer> list = (ArrayList<Integer>) data.collect();
	assertArrayEquals(input, list.toArray());
}
Example 4
Source File: CountCollectITCase.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void testAdvanced() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.getConfig().disableObjectReuse();

	DataSet<Integer> data = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);
	DataSet<Integer> data2 = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);

	DataSet<Tuple2<Integer, Integer>> data3 = data.cross(data2);

	// count
	long numEntries = data3.count();
	assertEquals(100, numEntries);

	// collect
	ArrayList<Tuple2<Integer, Integer>> list = (ArrayList<Tuple2<Integer, Integer>>) data3.collect();

	// set expected entries in a hash map to true
	HashMap<Tuple2<Integer, Integer>, Boolean> expected = new HashMap<Tuple2<Integer, Integer>, Boolean>();
	for (int i = 1; i <= 10; i++) {
		for (int j = 1; j <= 10; j++) {
			expected.put(new Tuple2<Integer, Integer>(i, j), true);
		}
	}

	// check if all entries are contained in the hash map
	for (int i = 0; i < 100; i++) {
		Tuple2<Integer, Integer> element = list.get(i);
		assertEquals(expected.get(element), true);
		expected.remove(element);
	}
}
Example 5
Source File: CountCollectITCase.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testAdvanced() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.getConfig().disableObjectReuse();

	DataSet<Integer> data = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);
	DataSet<Integer> data2 = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);

	DataSet<Tuple2<Integer, Integer>> data3 = data.cross(data2);

	// count
	long numEntries = data3.count();
	assertEquals(100, numEntries);

	// collect
	ArrayList<Tuple2<Integer, Integer>> list = (ArrayList<Tuple2<Integer, Integer>>) data3.collect();

	// set expected entries in a hash map to true
	HashMap<Tuple2<Integer, Integer>, Boolean> expected = new HashMap<Tuple2<Integer, Integer>, Boolean>();
	for (int i = 1; i <= 10; i++) {
		for (int j = 1; j <= 10; j++) {
			expected.put(new Tuple2<Integer, Integer>(i, j), true);
		}
	}

	// check if all entries are contained in the hash map
	for (int i = 0; i < 100; i++) {
		Tuple2<Integer, Integer> element = list.get(i);
		assertEquals(expected.get(element), true);
		expected.remove(element);
	}
}
Example 6
Source File: CountCollectITCase.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testAdvanced() throws Exception {
	ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
	env.getConfig().disableObjectReuse();

	DataSet<Integer> data = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);
	DataSet<Integer> data2 = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);

	DataSet<Tuple2<Integer, Integer>> data3 = data.cross(data2);

	// count
	long numEntries = data3.count();
	assertEquals(100, numEntries);

	// collect
	ArrayList<Tuple2<Integer, Integer>> list = (ArrayList<Tuple2<Integer, Integer>>) data3.collect();

	// set expected entries in a hash map to true
	HashMap<Tuple2<Integer, Integer>, Boolean> expected = new HashMap<Tuple2<Integer, Integer>, Boolean>();
	for (int i = 1; i <= 10; i++) {
		for (int j = 1; j <= 10; j++) {
			expected.put(new Tuple2<Integer, Integer>(i, j), true);
		}
	}

	// check if all entries are contained in the hash map
	for (int i = 0; i < 100; i++) {
		Tuple2<Integer, Integer> element = list.get(i);
		assertEquals(expected.get(element), true);
		expected.remove(element);
	}
}
Example 7
Source File: FlinkCubingByLayer.java    From kylin-on-parquet-v2 with Apache License 2.0 4 votes vote down vote up 
@Override
protected void execute(OptionsHelper optionsHelper) throws Exception {
    String metaUrl = optionsHelper.getOptionValue(OPTION_META_URL);
    String hiveTable = optionsHelper.getOptionValue(OPTION_INPUT_TABLE);
    String inputPath = optionsHelper.getOptionValue(OPTION_INPUT_PATH);
    String cubeName = optionsHelper.getOptionValue(OPTION_CUBE_NAME);
    String segmentId = optionsHelper.getOptionValue(OPTION_SEGMENT_ID);
    String outputPath = optionsHelper.getOptionValue(OPTION_OUTPUT_PATH);
    String enableObjectReuseOptValue = optionsHelper.getOptionValue(OPTION_ENABLE_OBJECT_REUSE);

    boolean enableObjectReuse = false;
    if (enableObjectReuseOptValue != null && !enableObjectReuseOptValue.isEmpty()) {
        enableObjectReuse = true;
    }

    Job job = Job.getInstance();
    FileSystem fs = HadoopUtil.getWorkingFileSystem();
    HadoopUtil.deletePath(job.getConfiguration(), new Path(outputPath));

    final SerializableConfiguration sConf = new SerializableConfiguration(job.getConfiguration());
    KylinConfig envConfig = AbstractHadoopJob.loadKylinConfigFromHdfs(sConf, metaUrl);

    final CubeInstance cubeInstance = CubeManager.getInstance(envConfig).getCube(cubeName);
    final CubeDesc cubeDesc = cubeInstance.getDescriptor();
    final CubeSegment cubeSegment = cubeInstance.getSegmentById(segmentId);

    logger.info("DataSet input path : {}", inputPath);
    logger.info("DataSet output path : {}", outputPath);

    int countMeasureIndex = 0;
    for (MeasureDesc measureDesc : cubeDesc.getMeasures()) {
        if (measureDesc.getFunction().isCount() == true) {
            break;
        } else {
            countMeasureIndex++;
        }
    }

    final CubeStatsReader cubeStatsReader = new CubeStatsReader(cubeSegment, envConfig);
    boolean[] needAggr = new boolean[cubeDesc.getMeasures().size()];
    boolean allNormalMeasure = true;
    for (int i = 0; i < cubeDesc.getMeasures().size(); i++) {
        needAggr[i] = !cubeDesc.getMeasures().get(i).getFunction().getMeasureType().onlyAggrInBaseCuboid();
        allNormalMeasure = allNormalMeasure && needAggr[i];
    }

    logger.info("All measure are normal (agg on all cuboids) ? : " + allNormalMeasure);

    boolean isSequenceFile = JoinedFlatTable.SEQUENCEFILE.equalsIgnoreCase(envConfig.getFlatTableStorageFormat());

    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    if (enableObjectReuse) {
        env.getConfig().enableObjectReuse();
    }
    env.getConfig().registerKryoType(PercentileCounter.class);
    env.getConfig().registerTypeWithKryoSerializer(PercentileCounter.class, PercentileCounterSerializer.class);

    DataSet<String[]> hiveDataSet = FlinkUtil.readHiveRecords(isSequenceFile, env, inputPath, hiveTable, job);

    DataSet<Tuple2<ByteArray, Object[]>> encodedBaseDataSet = hiveDataSet.mapPartition(
            new EncodeBaseCuboidMapPartitionFunction(cubeName, segmentId, metaUrl, sConf));

    Long totalCount = 0L;
    if (envConfig.isFlinkSanityCheckEnabled()) {
        totalCount = encodedBaseDataSet.count();
    }

    final BaseCuboidReduceGroupFunction baseCuboidReducerFunction = new BaseCuboidReduceGroupFunction(cubeName, metaUrl, sConf);

    BaseCuboidReduceGroupFunction reducerFunction = baseCuboidReducerFunction;
    if (!allNormalMeasure) {
        reducerFunction = new CuboidReduceGroupFunction(cubeName, metaUrl, sConf, needAggr);
    }

    final int totalLevels = cubeSegment.getCuboidScheduler().getBuildLevel();
    DataSet<Tuple2<ByteArray, Object[]>>[] allDataSets = new DataSet[totalLevels + 1];
    int level = 0;

    // aggregate to calculate base cuboid
    allDataSets[0] = encodedBaseDataSet.groupBy(0).reduceGroup(baseCuboidReducerFunction);

    sinkToHDFS(allDataSets[0], metaUrl, cubeName, cubeSegment, outputPath, 0, Job.getInstance(), envConfig);

    CuboidMapPartitionFunction mapPartitionFunction = new CuboidMapPartitionFunction(cubeName, segmentId, metaUrl, sConf);

    for (level = 1; level <= totalLevels; level++) {
        allDataSets[level] = allDataSets[level - 1].mapPartition(mapPartitionFunction).groupBy(0).reduceGroup(reducerFunction);
        if (envConfig.isFlinkSanityCheckEnabled()) {
            sanityCheck(allDataSets[level], totalCount, level, cubeStatsReader, countMeasureIndex);
        }
        sinkToHDFS(allDataSets[level], metaUrl, cubeName, cubeSegment, outputPath, level, Job.getInstance(), envConfig);
    }

    env.execute("Cubing for : " + cubeName + " segment " + segmentId);
    logger.info("Finished on calculating all level cuboids.");
    logger.info("HDFS: Number of bytes written=" + FlinkBatchCubingJobBuilder2.getFileSize(outputPath, fs));
}
Example 8
Source File: FlinkCubingByLayer.java    From kylin with Apache License 2.0 4 votes vote down vote up 
@Override
protected void execute(OptionsHelper optionsHelper) throws Exception {
    String metaUrl = optionsHelper.getOptionValue(OPTION_META_URL);
    String hiveTable = optionsHelper.getOptionValue(OPTION_INPUT_TABLE);
    String inputPath = optionsHelper.getOptionValue(OPTION_INPUT_PATH);
    String cubeName = optionsHelper.getOptionValue(OPTION_CUBE_NAME);
    String segmentId = optionsHelper.getOptionValue(OPTION_SEGMENT_ID);
    String outputPath = optionsHelper.getOptionValue(OPTION_OUTPUT_PATH);
    String enableObjectReuseOptValue = optionsHelper.getOptionValue(OPTION_ENABLE_OBJECT_REUSE);

    boolean enableObjectReuse = false;
    if (enableObjectReuseOptValue != null && !enableObjectReuseOptValue.isEmpty()) {
        enableObjectReuse = true;
    }

    Job job = Job.getInstance();
    FileSystem fs = HadoopUtil.getWorkingFileSystem();
    HadoopUtil.deletePath(job.getConfiguration(), new Path(outputPath));

    final SerializableConfiguration sConf = new SerializableConfiguration(job.getConfiguration());
    KylinConfig envConfig = AbstractHadoopJob.loadKylinConfigFromHdfs(sConf, metaUrl);

    final CubeInstance cubeInstance = CubeManager.getInstance(envConfig).getCube(cubeName);
    final CubeDesc cubeDesc = cubeInstance.getDescriptor();
    final CubeSegment cubeSegment = cubeInstance.getSegmentById(segmentId);

    logger.info("DataSet input path : {}", inputPath);
    logger.info("DataSet output path : {}", outputPath);

    int countMeasureIndex = 0;
    for (MeasureDesc measureDesc : cubeDesc.getMeasures()) {
        if (measureDesc.getFunction().isCount() == true) {
            break;
        } else {
            countMeasureIndex++;
        }
    }

    final CubeStatsReader cubeStatsReader = new CubeStatsReader(cubeSegment, envConfig);
    boolean[] needAggr = new boolean[cubeDesc.getMeasures().size()];
    boolean allNormalMeasure = true;
    for (int i = 0; i < cubeDesc.getMeasures().size(); i++) {
        needAggr[i] = !cubeDesc.getMeasures().get(i).getFunction().getMeasureType().onlyAggrInBaseCuboid();
        allNormalMeasure = allNormalMeasure && needAggr[i];
    }

    logger.info("All measure are normal (agg on all cuboids) ? : " + allNormalMeasure);

    boolean isSequenceFile = JoinedFlatTable.SEQUENCEFILE.equalsIgnoreCase(envConfig.getFlatTableStorageFormat());

    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    if (enableObjectReuse) {
        env.getConfig().enableObjectReuse();
    }
    env.getConfig().registerKryoType(PercentileCounter.class);
    env.getConfig().registerTypeWithKryoSerializer(PercentileCounter.class, PercentileCounterSerializer.class);

    DataSet<String[]> hiveDataSet = FlinkUtil.readHiveRecords(isSequenceFile, env, inputPath, hiveTable, job);

    DataSet<Tuple2<ByteArray, Object[]>> encodedBaseDataSet = hiveDataSet.mapPartition(
            new EncodeBaseCuboidMapPartitionFunction(cubeName, segmentId, metaUrl, sConf));

    Long totalCount = 0L;
    if (envConfig.isFlinkSanityCheckEnabled()) {
        totalCount = encodedBaseDataSet.count();
    }

    final BaseCuboidReduceGroupFunction baseCuboidReducerFunction = new BaseCuboidReduceGroupFunction(cubeName, metaUrl, sConf);

    BaseCuboidReduceGroupFunction reducerFunction = baseCuboidReducerFunction;
    if (!allNormalMeasure) {
        reducerFunction = new CuboidReduceGroupFunction(cubeName, metaUrl, sConf, needAggr);
    }

    final int totalLevels = cubeSegment.getCuboidScheduler().getBuildLevel();
    DataSet<Tuple2<ByteArray, Object[]>>[] allDataSets = new DataSet[totalLevels + 1];
    int level = 0;

    // aggregate to calculate base cuboid
    allDataSets[0] = encodedBaseDataSet.groupBy(0).reduceGroup(baseCuboidReducerFunction);

    sinkToHDFS(allDataSets[0], metaUrl, cubeName, cubeSegment, outputPath, 0, Job.getInstance(), envConfig);

    CuboidMapPartitionFunction mapPartitionFunction = new CuboidMapPartitionFunction(cubeName, segmentId, metaUrl, sConf);

    for (level = 1; level <= totalLevels; level++) {
        allDataSets[level] = allDataSets[level - 1].mapPartition(mapPartitionFunction).groupBy(0).reduceGroup(reducerFunction);
        if (envConfig.isFlinkSanityCheckEnabled()) {
            sanityCheck(allDataSets[level], totalCount, level, cubeStatsReader, countMeasureIndex);
        }
        sinkToHDFS(allDataSets[level], metaUrl, cubeName, cubeSegment, outputPath, level, Job.getInstance(), envConfig);
    }

    env.execute("Cubing for : " + cubeName + " segment " + segmentId);
    logger.info("Finished on calculating all level cuboids.");
    logger.info("HDFS: Number of bytes written=" + FlinkBatchCubingJobBuilder2.getFileSize(outputPath, fs));
}