groupBy

作用：分组，按照传入函数的返回值进行分组。将相同的key对应的值放入一个迭代器。

package com.atguigu

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object Trans {
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf().setAppName("Trans").setMaster("local[*]")
    val sc = new SparkContext(conf)

    val numRDD: RDD[Int] = sc.makeRDD(List(1,4,3,2),2)

    val groupByRDD: RDD[(Int, Iterable[Int])] = numRDD.groupBy(_%2)
    groupByRDD.collect().foreach(println)
    

  }
}

(0,CompactBuffer(4, 2))
(1,CompactBuffer(1, 3))