Spark算子:RDDAction操作–first/count/reduce/collect/collectAsMap

来源：互联网发布：java触发器是什么编辑：程序博客网时间：2024/05/29 16:47

first

def first(): T
first返回RDD中的第一个元素，不排序。

scala> var rdd1 = sc.makeRDD(Array(("A","1"),("B","2"),("C","3")),2)rdd1: org.apache.spark.rdd.RDD[(String, String)] = ParallelCollectionRDD[33] at makeRDD at :21 scala> rdd1.firstres14: (String, String) = (A,1) scala> var rdd1 = sc.makeRDD(Seq(10, 4, 2, 12, 3))rdd1: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[0] at makeRDD at :21 scala> rdd1.firstres8: Int = 10

count

def count(): Long

count返回RDD中的元素数量。

scala> var rdd1 = sc.makeRDD(Array(("A","1"),("B","2"),("C","3")),2)rdd1: org.apache.spark.rdd.RDD[(String, String)] = ParallelCollectionRDD[34] at makeRDD at :21 scala> rdd1.countres15: Long = 3

reduce

def reduce(f: (T, T) ⇒ T): T
根据映射函数f，对RDD中的元素进行二元计算，返回计算结果。

scala> var rdd1 = sc.makeRDD(1 to 10,2)rdd1: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[36] at makeRDD at :21 scala> rdd1.reduce(_ + _)res18: Int = 55 scala> var rdd2 = sc.makeRDD(Array(("A",0),("A",2),("B",1),("B",2),("C",1)))rdd2: org.apache.spark.rdd.RDD[(String, Int)] = ParallelCollectionRDD[38] at makeRDD at :21 scala> rdd2.reduce((x,y) => {     |       (x._1 + y._1,x._2 + y._2)     |     })res21: (String, Int) = (CBBAA,6)

collect

def collect(): Array[T]

def collect[U: ClassTag](f: PartialFunction[T, U]): RDD[U]

collect用于将一个RDD转换成数组。

scala> var rdd1 = sc.makeRDD(1 to 10,2)rdd1: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[36] at makeRDD at :21scala> rdd1.collectres23: Array[Int] = Array(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)<div class="line number10 index9 alt1" style="white-space: pre-wrap; line-height: 20.8px; border-radius: 0px !important; border: 0px !important; bottom: auto !important; float: none !important; height: auto !important; left: auto !important; margin: 0px !important; outline: 0px !important; overflow: visible !important; padding: 0px 1em 0px 0em !important; position: static !important; right: auto !important; top: auto !important; vertical-align: baseline !important; width: auto !important; box-sizing: content-box !important; direction: ltr !important; box-shadow: none !important; background: none rgb(247, 247, 247) !important;"><pre name="code" class="plain" style="font-size: 13px; font-family: Consolas, "Bitstream Vera Sans Mono", "Courier New", Courier, monospace;"><pre name="code" class="plain">scala> val one: PartialFunction[Int, String] = { case 1 => "one"; case _ => "other"}one: PartialFunction[Int,String] = <function1> scala> val data = sc.parallelize(List(2,3,1))data: org.apache.spark.rdd.RDD[Int] =　　　　ParallelCollectionRDD[11] at parallelize at <console>:12 scala> data.collect(one).collectres4: Array[String] = Array(other, other, one)

collectAsMap

def collectAsMap(): Map[K, V]

scala> val data = sc.parallelize(List((1, "www"), (1, "iteblog"), (1, "com"), 　　　　(2, "bbs"), (2, "iteblog"), (2, "com"), (3, "good")))data: org.apache.spark.rdd.RDD[(Int, String)] =　　　　ParallelCollectionRDD[26] at parallelize at <console>:12 scala> data.collectAsMapres28: scala.collection.Map[Int,String] = Map(2 -> com, 1 -> com, 3 -> good)

0 0