Spark算子：transformation之键值转换partitionBy、mapValues、flatMapValues

雨点打透心脏的1/2处 2022-05-11 07:44 212阅读 0赞

1、**partitionBy**：def partitionBy(partitioner: Partitioner): RDD\[(K, V)\]

该函数根据partitioner函数生成新的ShuffleRDD，将原RDD重新分区。

scala> var rdd1 = sc.makeRDD(Array((1,"A"),(2,"B"),(3,"C"),(4,"D")),2)
    rdd1: org.apache.spark.rdd.RDD[(Int, String)] = ParallelCollectionRDD[23] at makeRDD at :21
     
    scala> rdd1.partitions.size
    res20: Int = 2
     
    //查看rdd1中每个分区的元素
    scala> rdd1.mapPartitionsWithIndex{
         |         (partIdx,iter) => {
         |           var part_map = scala.collection.mutable.Map[String,List[(Int,String)]]()
         |             while(iter.hasNext){
         |               var part_name = "part_" + partIdx;
         |               var elem = iter.next()
         |               if(part_map.contains(part_name)) {
         |                 var elems = part_map(part_name)
         |                 elems ::= elem
         |                 part_map(part_name) = elems
         |               } else {
         |                 part_map(part_name) = List[(Int,String)]{elem}
         |               }
         |             }
         |             part_map.iterator
         |            
         |         }
         |       }.collect
    res22: Array[(String, List[(Int, String)])] = Array((part_0,List((2,B), (1,A))), (part_1,List((4,D), (3,C))))
    //(2,B),(1,A)在part_0中，(4,D),(3,C)在part_1中
     
    //使用partitionBy重分区
    scala> var rdd2 = rdd1.partitionBy(new org.apache.spark.HashPartitioner(2))
    rdd2: org.apache.spark.rdd.RDD[(Int, String)] = ShuffledRDD[25] at partitionBy at :23
     
    scala> rdd2.partitions.size
    res23: Int = 2
     
    //查看rdd2中每个分区的元素
    scala> rdd2.mapPartitionsWithIndex{
         |         (partIdx,iter) => {
         |           var part_map = scala.collection.mutable.Map[String,List[(Int,String)]]()
         |             while(iter.hasNext){
         |               var part_name = "part_" + partIdx;
         |               var elem = iter.next()
         |               if(part_map.contains(part_name)) {
         |                 var elems = part_map(part_name)
         |                 elems ::= elem
         |                 part_map(part_name) = elems
         |               } else {
         |                 part_map(part_name) = List[(Int,String)]{elem}
         |               }
         |             }
         |             part_map.iterator
         |         }
         |       }.collect
    res24: Array[(String, List[(Int, String)])] = Array((part_0,List((4,D), (2,B))), (part_1,List((3,C), (1,A))))
    //(4,D),(2,B)在part_0中，(3,C),(1,A)在part_1中

2、**mapValues**：def mapValues\[U\](f: (V) => U): RDD\[(K, U)\]

同基本转换操作中的map，只不过mapValues是针对\[K,V\]中的V值进行map操作。

scala> var rdd1 = sc.makeRDD(Array((1,"A"),(2,"B"),(3,"C"),(4,"D")),2)
    rdd1: org.apache.spark.rdd.RDD[(Int, String)] = ParallelCollectionRDD[27] at makeRDD at :21
     
    scala> rdd1.mapValues(x => x + "_").collect
    res26: Array[(Int, String)] = Array((1,A_), (2,B_), (3,C_), (4,D_))

3、**flatMapValues**：def flatMapValues\[U\](f: (V) => TraversableOnce\[U\]): RDD\[(K, U)\]

基本转换操作与flatMap类似，只不过flatMapValues是针对\[K,V\]中的V值进行flatMap操作。

scala> rdd1.flatMapValues(x => x + "_").collect
    res36: Array[(Int, Char)] = Array((1,A), (1,_), (2,B), (2,_), (3,C), (3,_), (4,D), (4,_))