import org.apache.spark.{SparkConf, SparkContext}
/**
* Created by liupeng on 2017/6/16.
*/
object T_groupByKey {
System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("groupByKey_test").setMaster("local")
val sc = new SparkContext(conf)
val scoreMap = List("liupeng" -> 150, "liupeng" -> 50, "liusi" -> 120, "xiaoma" -> 100)
//groupByKey把相同的key的元素放到一起去
val rdd = sc.parallelize(scoreMap)
val result = rdd.groupByKey()
result.foreach(x => println(x._1 + ":" + x._2))
}
}
运行结果:
liusi:CompactBuffer(120)
liupeng:CompactBuffer(150, 50)
xiaoma:CompactBuffer(100)
liupeng:CompactBuffer(150, 50)
xiaoma:CompactBuffer(100)