本文整理了Java中org.apache.spark.api.java.JavaPairRDD.groupBy()方法的一些代码示例，展示了JavaPairRDD.groupBy()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.groupBy()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：groupBy

JavaPairRDD.groupBy介绍

暂无

代码示例

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

@Test
public void groupByOnPairRDD() {
 // Regression test for SPARK-4459
 JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 1, 2, 3, 5, 8, 13));
 Function<Tuple2<Integer, Integer>, Boolean> areOdd =
  x -> (x._1() % 2 == 0) && (x._2() % 2 == 0);
 JavaPairRDD<Integer, Integer> pairRDD = rdd.zip(rdd);
 JavaPairRDD<Boolean, Iterable<Tuple2<Integer, Integer>>> oddsAndEvens = pairRDD.groupBy(areOdd);
 assertEquals(2, oddsAndEvens.count());
 assertEquals(2, Iterables.size(oddsAndEvens.lookup(true).get(0)));  // Evens
 assertEquals(5, Iterables.size(oddsAndEvens.lookup(false).get(0))); // Odds
 oddsAndEvens = pairRDD.groupBy(areOdd, 1);
 assertEquals(2, oddsAndEvens.count());
 assertEquals(2, Iterables.size(oddsAndEvens.lookup(true).get(0)));  // Evens
 assertEquals(5, Iterables.size(oddsAndEvens.lookup(false).get(0))); // Odds
}

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

@Test
public void groupByOnPairRDD() {
 // Regression test for SPARK-4459
 JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 1, 2, 3, 5, 8, 13));
 Function<Tuple2<Integer, Integer>, Boolean> areOdd =
  x -> (x._1() % 2 == 0) && (x._2() % 2 == 0);
 JavaPairRDD<Integer, Integer> pairRDD = rdd.zip(rdd);
 JavaPairRDD<Boolean, Iterable<Tuple2<Integer, Integer>>> oddsAndEvens = pairRDD.groupBy(areOdd);
 assertEquals(2, oddsAndEvens.count());
 assertEquals(2, Iterables.size(oddsAndEvens.lookup(true).get(0)));  // Evens
 assertEquals(5, Iterables.size(oddsAndEvens.lookup(false).get(0))); // Odds
 oddsAndEvens = pairRDD.groupBy(areOdd, 1);
 assertEquals(2, oddsAndEvens.count());
 assertEquals(2, Iterables.size(oddsAndEvens.lookup(true).get(0)));  // Evens
 assertEquals(5, Iterables.size(oddsAndEvens.lookup(false).get(0))); // Odds
}

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

@Test
public void groupByOnPairRDD() {
 // Regression test for SPARK-4459
 JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 1, 2, 3, 5, 8, 13));
 Function<Tuple2<Integer, Integer>, Boolean> areOdd =
  x -> (x._1() % 2 == 0) && (x._2() % 2 == 0);
 JavaPairRDD<Integer, Integer> pairRDD = rdd.zip(rdd);
 JavaPairRDD<Boolean, Iterable<Tuple2<Integer, Integer>>> oddsAndEvens = pairRDD.groupBy(areOdd);
 assertEquals(2, oddsAndEvens.count());
 assertEquals(2, Iterables.size(oddsAndEvens.lookup(true).get(0)));  // Evens
 assertEquals(5, Iterables.size(oddsAndEvens.lookup(false).get(0))); // Odds
 oddsAndEvens = pairRDD.groupBy(areOdd, 1);
 assertEquals(2, oddsAndEvens.count());
 assertEquals(2, Iterables.size(oddsAndEvens.lookup(true).get(0)));  // Evens
 assertEquals(5, Iterables.size(oddsAndEvens.lookup(false).get(0))); // Odds
}