import org.apache.spark.{SparkConf, SparkContext}
/**
* Created by liupeng on 2017/6/16.
*/
object T_sortByKey {
System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("sortByKey_test").setMaster("local")
val sc = new SparkContext(conf)
val list1 = List(("liupeng", 120), ("liupeng", 120), ("liusi", 120), ("mayun", 100))
val rdd = sc.parallelize(list1)
//sortByKey方法用于针对Key做排序,默认是按照升序排序
val sum = rdd.sortByKey()
.foreach(println)
//降序排序
val sum1 = rdd.sortByKey(false)
.foreach(println)
}
}
运行结果:
(liupeng,120)
(liupeng,120)
(liusi,120)
(mayun,100)
(liupeng,120)
(liusi,120)
(mayun,100)
(mayun,100)
(liusi,120)
(liupeng,120)
(liupeng,120)
(liusi,120)
(liupeng,120)
(liupeng,120)