本文整理了Java中org.apache.spark.api.java.JavaPairRDD.aggregateByKey()方法的一些代码示例，展示了JavaPairRDD.aggregateByKey()的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。JavaPairRDD.aggregateByKey()方法的具体详情如下：
包路径：org.apache.spark.api.java.JavaPairRDD
类名称：JavaPairRDD
方法名：aggregateByKey

JavaPairRDD.aggregateByKey介绍

暂无

代码示例

代码示例来源：origin: org.apache.spark/spark-core_2.11

@SuppressWarnings("unchecked")
@Test
public void aggregateByKey() {
 JavaPairRDD<Integer, Integer> pairs = sc.parallelizePairs(
  Arrays.asList(
   new Tuple2<>(1, 1),
   new Tuple2<>(1, 1),
   new Tuple2<>(3, 2),
   new Tuple2<>(5, 1),
   new Tuple2<>(5, 3)), 2);
 Map<Integer, HashSet<Integer>> sets = pairs.aggregateByKey(new HashSet<Integer>(),
   (a, b) -> {
    a.add(b);
    return a;
   },
   (a, b) -> {
    a.addAll(b);
    return a;
   }).collectAsMap();
 assertEquals(3, sets.size());
 assertEquals(new HashSet<>(Arrays.asList(1)), sets.get(1));
 assertEquals(new HashSet<>(Arrays.asList(2)), sets.get(3));
 assertEquals(new HashSet<>(Arrays.asList(1, 3)), sets.get(5));
}

代码示例来源：origin: org.apache.spark/spark-core_2.10

@SuppressWarnings("unchecked")
@Test
public void aggregateByKey() {
 JavaPairRDD<Integer, Integer> pairs = sc.parallelizePairs(
  Arrays.asList(
   new Tuple2<>(1, 1),
   new Tuple2<>(1, 1),
   new Tuple2<>(3, 2),
   new Tuple2<>(5, 1),
   new Tuple2<>(5, 3)), 2);
 Map<Integer, HashSet<Integer>> sets = pairs.aggregateByKey(new HashSet<Integer>(),
   (a, b) -> {
    a.add(b);
    return a;
   },
   (a, b) -> {
    a.addAll(b);
    return a;
   }).collectAsMap();
 assertEquals(3, sets.size());
 assertEquals(new HashSet<>(Arrays.asList(1)), sets.get(1));
 assertEquals(new HashSet<>(Arrays.asList(2)), sets.get(3));
 assertEquals(new HashSet<>(Arrays.asList(1, 3)), sets.get(5));
}

代码示例来源：origin: org.apache.spark/spark-core

@SuppressWarnings("unchecked")
@Test
public void aggregateByKey() {
 JavaPairRDD<Integer, Integer> pairs = sc.parallelizePairs(
  Arrays.asList(
   new Tuple2<>(1, 1),
   new Tuple2<>(1, 1),
   new Tuple2<>(3, 2),
   new Tuple2<>(5, 1),
   new Tuple2<>(5, 3)), 2);
 Map<Integer, HashSet<Integer>> sets = pairs.aggregateByKey(new HashSet<Integer>(),
   (a, b) -> {
    a.add(b);
    return a;
   },
   (a, b) -> {
    a.addAll(b);
    return a;
   }).collectAsMap();
 assertEquals(3, sets.size());
 assertEquals(new HashSet<>(Arrays.asList(1)), sets.get(1));
 assertEquals(new HashSet<>(Arrays.asList(2)), sets.get(3));
 assertEquals(new HashSet<>(Arrays.asList(1, 3)), sets.get(5));
}

代码示例来源：origin: DataSystemsLab/GeoSpark

private static <U extends Geometry, T extends Geometry> JavaPairRDD<U, Long> countGeometriesByKey(JavaPairRDD<U, T> input)
{
  return input.aggregateByKey(
      0L,
      new Function2<Long, T, Long>()
      {
        @Override
        public Long call(Long count, T t)
            throws Exception
        {
          return count + 1;
        }
      },
      new Function2<Long, Long, Long>()
      {
        @Override
        public Long call(Long count1, Long count2)
            throws Exception
        {
          return count1 + count2;
        }
      });
}

代码示例来源：origin: org.datasyslab/geospark

private static <U extends Geometry, T extends Geometry> JavaPairRDD<U, Long> countGeometriesByKey(JavaPairRDD<U, T> input)
{
  return input.aggregateByKey(
      0L,
      new Function2<Long, T, Long>()
      {
        @Override
        public Long call(Long count, T t)
            throws Exception
        {
          return count + 1;
        }
      },
      new Function2<Long, Long, Long>()
      {
        @Override
        public Long call(Long count1, Long count2)
            throws Exception
        {
          return count1 + count2;
        }
      });
}

代码示例来源：origin: org.datasyslab/geospark

private static <U extends Geometry, T extends Geometry> JavaPairRDD<U, HashSet<T>> collectGeometriesByKey(JavaPairRDD<U, T> input)
{
  return input.aggregateByKey(
      new HashSet<T>(),
      new Function2<HashSet<T>, T, HashSet<T>>()
      {
        @Override
        public HashSet<T> call(HashSet<T> ts, T t)
            throws Exception
        {
          ts.add(t);
          return ts;
        }
      },
      new Function2<HashSet<T>, HashSet<T>, HashSet<T>>()
      {
        @Override
        public HashSet<T> call(HashSet<T> ts, HashSet<T> ts2)
            throws Exception
        {
          ts.addAll(ts2);
          return ts;
        }
      });
}

代码示例来源：origin: DataSystemsLab/GeoSpark

private static <U extends Geometry, T extends Geometry> JavaPairRDD<U, HashSet<T>> collectGeometriesByKey(JavaPairRDD<U, T> input)
{
  return input.aggregateByKey(
      new HashSet<T>(),
      new Function2<HashSet<T>, T, HashSet<T>>()
      {
        @Override
        public HashSet<T> call(HashSet<T> ts, T t)
            throws Exception
        {
          ts.add(t);
          return ts;
        }
      },
      new Function2<HashSet<T>, HashSet<T>, HashSet<T>>()
      {
        @Override
        public HashSet<T> call(HashSet<T> ts, HashSet<T> ts2)
            throws Exception
        {
          ts.addAll(ts2);
          return ts;
        }
      });
}

代码示例来源：origin: edu.usc.ir/age-predictor-cli

JavaPairRDD<String, Integer> totalMap = validSamples.aggregateByKey(0,
  new Function2<Integer, String, Integer>() {
  @Override
JavaPairRDD<String, Integer> correctMap = correct.aggregateByKey(0,
  new Function2<Integer, String, Integer>() {
  @Override

代码示例来源：origin: org.datavec/datavec-spark

currentWritables = pair.aggregateByKey(reducer.aggregableReducer(),
        new Function2<IAggregableReduceOp<List<Writable>, List<Writable>>, List<Writable>, IAggregableReduceOp<List<Writable>, List<Writable>>>() {
          @Override

代码示例来源：origin: org.datavec/datavec-spark_2.11

currentWritables = pair.aggregateByKey(reducer.aggregableReducer(),
        new Function2<IAggregableReduceOp<List<Writable>, List<Writable>>, List<Writable>, IAggregableReduceOp<List<Writable>, List<Writable>>>() {
          @Override