Spark排序之SortBy

1、例子1：按照value进行降序排序

def sortBy[K]( f: (T) => K,

      ascending: Boolean = true, // 默认为正序排列，从小到大,false:倒序

      numPartitions: Int = this.partitions.length)

      (implicit ord: Ordering[K], ctag: classtag[K]): RDD[T]

返回值是T，数字不会变

package  com.test.spark
import  org.apache.spark.{SparkConf, SparkContext}
 
/**
   * @author admin
   * SortBy是SortByKey的增强版
   * 按照value进行排序
   */
object  SparkSortByApplication {
 
   def  main(args :  Array[String]) :  Unit  =  {
     val  conf  =  new  SparkConf().setAppName( "SortSecond" ).setMaster( "local[1]" )
     val  sc  =  new  SparkContext(conf)
     val  datas  =  sc.parallelize(Array(( "cc" , 12 ),( "bb" , 32 ),( "cc" , 22 ),( "aa" , 18 ),( "bb" , 16 ),( "dd" , 16 ),( "ee" , 54 ),( "cc" , 1 ),( "ff" , 13 ),( "gg" , 32 ),( "bb" , 4 )))
     // 统计key出现的次数
     val  counts  =  datas.reduceByKey( _ + _ )
     // 按照value进行降序排序
     val  sorts  =  counts.sortBy( _ . _ 2 , false )
     sorts.collect().foreach(println) 
     sc.stop()
   }   
}

输出结果：

(ee,54)
(bb,52)
(cc,35)
(gg,32)
(aa,18)
(dd,16)
(ff,13)

2、例子2：先按照第一个元素升序排序，如果第一个元素相同，再进行第三个元素进行升序排序

package  com.sudiyi.spark
import  org.apache.spark.{SparkConf, SparkContext}
 
/**
   * @author xubiao
   * SortBy是SortByKey的增强版
   * 先按照第一个，再按照第三个元素进行升序排序
   */
object  SparkSortByApplication {
 
   def  main(args :  Array[String]) :  Unit  =  {    
     val  conf  =  new  SparkConf().setAppName( "SortSecond" ).setMaster( "local[1]" )
     val  sc  =  new  SparkContext(conf)
     val  arr  =  Array(( 1 ,  6 ,  3 ), ( 2 ,  3 ,  3 ), ( 1 ,  1 ,  2 ), ( 1 ,  3 ,  5 ), ( 2 ,  1 ,  2 ))
     val  datas 2  =  sc.parallelize(arr)
     val  sorts 2  =  datas 2 .sortBy(e  = > (e. _ 1 ,e. _ 2 ))
     sorts 2 .collect().foreach(println)
     sc.stop()
   }
}

输出结果：

(1,1,2)
(1,3,5)
(1,6,3)
(2,1,2)
(2,3,3)