spark算子

1.map

一条一条读取

def map(): Unit ={

    val list = List("张无忌", "赵敏", "周芷若")

    val listRDD = sc.parallelize(list)

    val nameRDD = listRDD.map(name => "Hello " + name)

    nameRDD.foreach(name => println(name))

  }

2.flatMap

扁平化

def flatMap(): Unit ={

    val list = List("张无忌 赵敏","宋青书 周芷若")

    val listRDD = sc.parallelize(list)

    val nameRDD = listRDD.flatMap(line => line.split(" ")).map(name => "Hello " + name)

    nameRDD.foreach(name => println(name))

  }

3.mapPartitions

一次读取一个分区数据

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 2, 3, 4, 5, 6)

    val rdd = spark.parallelize(list, 2)

    rdd.foreach(println)

    val rdd2 = rdd.mapPartitions(iterator => {

      val newList = new ListBuffer[String]

      while (iterator.hasNext) {

        newList.append("hello" + iterator.next())

      }

      newList.toIterator

    })

    rdd2.foreach(name => println(name))

  }

}

4.mapPartitionsWithIndex

一次读取一个分区数据，并且知道是哪个分区的

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 2, 3, 4, 5, 6)

    val rdd = spark.parallelize(list, 2)

    val rdd2 = rdd.mapPartitionsWithIndex((index, iterator) => {

      val newList = new ListBuffer[String]

      while (iterator.hasNext) {

        newList.append(index + "_" + iterator.next())

      }

      newList.toIterator

    })

    rdd2.foreach(name => println(name))

  }

}

5.reduce

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 2, 3, 4, 5, 6)

    val rdd = spark.parallelize(list)

    val result = rdd.reduce((x, y) => x + y)

    println(result)

  }

}

6.reduceBykey

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(("武当", 99), ("少林", 97), ("武当", 89), ("少林", 77))

    val rdd = spark.parallelize(list)

    val rdd2 = rdd.reduceByKey(_ + _)

    rdd2.foreach(tuple => println(tuple._1 + ":" + tuple._2))

  }

}

7.union

合并，但不去重

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List(1,2,3,4)

    val list2 = List(3,4,5,6)

    val rdd1 = spark.parallelize(list1)

    val rdd2 = spark.parallelize(list2)

    rdd1.union(rdd2).foreach(println)

  }

}

8.join

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List((1, "东方不败"), (2, "令狐冲"), (3, "林平之"))

    val list2 = List((1, 99), (2, 98), (3, 97))

    val rdd1 = spark.parallelize(list1)

    val rdd2 = spark.parallelize(list2)

    val rdd3 = rdd1.join(rdd2)

    rdd3.foreach(tuple => {

      val id = tuple._1

      val new_tuple = tuple._2

      val name = new_tuple._1

      val score = new_tuple._2

      println("学号：" + id + " 姓名：" + name + " 成绩:" + score)

    })

  }

}

9.groupbyKey

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(("武当", "张三丰"), ("峨眉", "灭绝师太"), ("武当", "宋青书"), ("峨眉", "周芷若"))

    val rdd1 = spark.parallelize(list)

    val rdd2 = rdd1.groupByKey()

    rdd2.foreach(t => {

      val menpai = t._1

      val iterator = t._2.iterator

      var people = ""

      while (iterator.hasNext) people = people + iterator.next + " "

      println("门派:" + menpai + "人员:" + people)

    })

  }

}

10.cartesian

笛卡尔积

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List("A", "B")

    val list2 = List(1, 2, 3)

    val list1RDD = spark.parallelize(list1)

    val list2RDD = spark.parallelize(list2)

    list1RDD.cartesian(list2RDD).foreach(t => println(t._1 + "->" + t._2))

  }

}

11.filter

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,2,3,4,5,6,7,8,9,10)

    val listRDD = spark.parallelize(list)

    listRDD.filter(num => num % 2 ==0).foreach(print(_))

  }

}

12.distinct

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,1,2,2,3,3,4,5)

    val rdd = spark.parallelize(list)

    rdd.distinct().foreach(println)

  }

}

13.intersection

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List(1,2,3,4)

    val list2 = List(3,4,5,6)

    val list1RDD = spark.parallelize(list1)

    val list2RDD = spark.parallelize(list2)

    list1RDD.intersection(list2RDD).foreach(println(_))

  }

}

14.coalesce

分区有多-->少

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,2,3,4,5)

    spark.parallelize(list,3).coalesce(1).foreach(println(_))

  }

}

15.repartition

进行重分区

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1,2,3,4)

    val listRDD = spark.parallelize(list,1)

    listRDD.repartition(2).foreach(println(_))

  }

}

16.repartitionAndSortWithinPartitions

在给定的partitioner内部进行排序，性能比repartition要高。

import org.apache.spark.{HashPartitioner, SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List(1, 4, 55, 66, 33, 48, 23)

    val listRDD = spark.parallelize(list, 1)

    listRDD.map(num => (num, num))

      .repartitionAndSortWithinPartitions(new HashPartitioner(2))

      .mapPartitionsWithIndex((index, iterator) => {

        val listBuffer: ListBuffer[String] = new ListBuffer

        while (iterator.hasNext) {

          listBuffer.append(index + "_" + iterator.next())

        }

        listBuffer.iterator

      }, false)

      .foreach(println(_))

  }

}

17.cogroup

import org.apache.spark.{HashPartitioner, SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list1 = List((1, "www"), (2, "bbs"))

    val list2 = List((1, "cnblog"), (2, "cnblog"), (3, "very"))

    val list3 = List((1, "com"), (2, "com"), (3, "good"))

    val list1RDD = spark.parallelize(list1)

    val list2RDD = spark.parallelize(list2)

    val list3RDD = spark.parallelize(list3)

    list1RDD.cogroup(list2RDD,list3RDD).foreach(tuple =>

      println(tuple._1 + " " + tuple._2._1 + " " + tuple._2._2 + " " + tuple._2._3))

  }

}

18.sortByKey

import org.apache.spark.{HashPartitioner, SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List((99, "张三丰"), (96, "东方不败"), (66, "林平之"), (98, "聂风"))

    spark.parallelize(list).sortByKey(false).foreach(tuple => println(tuple._2 + "->" + tuple._1))

  }

}

19.aggregateByKey

import org.apache.spark.{HashPartitioner, SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {

  val conf = new SparkConf().setAppName("Demo").setMaster("local");

  //  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()

  val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {

    val list = List("you,jump", "i,jump")

    spark.parallelize(list)

      .flatMap(_.split(","))

      .map((_, 1))

      .aggregateByKey(0)(_ + _, _ + _)

      .foreach(tuple => println(tuple._1 + "->" + tuple._2))

  }

}

apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.SparkSession

import scala.collection.mutable.ListBuffer

object Demo {
  val conf = new SparkConf().setAppName("Demo").setMaster("local");
//  val spark = SparkSession.builder().config(conf).enableHiveSupport().getOrCreate()
val spark = new SparkContext(conf)

  def main(args: Array[String]): Unit = {
    val list = List(("武当", "张三丰"), ("峨眉", "灭绝师太"), ("武当", "宋青书"), ("峨眉", "周芷若"))
    val rdd1 = spark.parallelize(list)
    val rdd2 = rdd1.groupByKey()
    rdd2.foreach(t => {
      val menpai = t._1
      val iterator = t._2.iterator
      var people = ""
while (iterator.hasNext) people = people + iterator.next + " "
println("门派:" + menpai + "人员:" + people)
    })
  }
}

spark算子的更多相关文章

(转)Spark 算子系列文章
http://lxw1234.com/archives/2015/07/363.htm Spark算子:RDD基本转换操作(1)–map.flagMap.distinct Spark算子:RDD创建操 ...
Spark算子总结及案例
spark算子大致上可分三大类算子: 1.Value数据类型的Transformation算子,这种变换不触发提交作业,针对处理的数据项是Value型的数据. 2.Key-Value数据类型的Tran ...
UserView--第二种方式（避免第一种方式Set饱和），基于Spark算子的java代码实现
UserView--第二种方式(避免第一种方式Set饱和),基于Spark算子的java代码实现测试数据 java代码 package com.hzf.spark.study; import ...
UserView--第一种方式set去重，基于Spark算子的java代码实现
UserView--第一种方式set去重,基于Spark算子的java代码实现测试数据 java代码 package com.hzf.spark.study; import java.util.Ha ...
spark算子之DataFrame和DataSet
前言传统的RDD相对于mapreduce和storm提供了丰富强大的算子.在spark慢慢步入DataFrame到DataSet的今天,在算子的类型基本不变的情况下,这两个数据集提供了更为强大的的功 ...
Spark算子总结（带案例）
Spark算子总结(带案例) spark算子大致上可分三大类算子: 1.Value数据类型的Transformation算子,这种变换不触发提交作业,针对处理的数据项是Value型的数据. 2.Key ...
Spark算子---实战应用
Spark算子实战应用数据集 :http://grouplens.org/datasets/movielens/ MovieLens 1M Datase 相关数据文件 : users.dat --- ...
spark算子集锦
Spark 是大数据领域的一大利器,花时间总结了一下 Spark 常用算子,正所谓温故而知新. Spark 算子按照功能分,可以分成两大类:transform 和 action.Transform 不 ...
Spark算子使用
一.spark的算子分类转换算子和行动算子转换算子:在使用的时候,spark是不会真正执行,直到需要行动算子之后才会执行.在spark中每一个算子在计算之后就会产生一个新的RDD. 二.在编写sp ...
Spark：常用transformation及action，spark算子详解
常用transformation及action介绍,spark算子详解一.常用transformation介绍 1.1 transformation操作实例二.常用action介绍 2.1 act ...

随机推荐

shell之数学运算
let #!/bin/bash no1=1; no2=5; let result=no1+no2 ##不能留空格 echo $result #自加 let no++ #自减 let no-- #简写 ...
Java【第五篇】基本语法之--数组
数组概述数组是多个相同类型数据的组合,实现对这些数据的统一管理数组属引用类型,数组型数据是对象(Object),数组中的每个元素相当于该对象的成员变量数组中的元素可以是任何数据类型,包括基本类型和引 ...
LoadRunner【第一篇】下载、安装、破解
loadrunner11下载 loadrunner11大小有4g多,相对另外一款开源的性能测试工具jmeter来说,是非常笨重的了,网上很多,大家可以搜索,也可以点击右侧加群获取安装包. loadru ...
nginx设置目录浏览及解决中文乱码问题
在Nginx下默认是不允许列出整个目录的.如需开启此功能,先打开nginx.conf文件,在location server 或 http段中加入相关参数. http { include mime.ty ...
OSU! on tree
dsu on tree 好吧,这个毒瘤...... 树剖和启发式合并的杂合体. 用于解决静态子树问题,复杂度O(nlogn * insert时间) 因为dsu是并查集的意思所以算法名字大概就是什么树上 ...
Python的编码和解码
Python的编码和解码在不同的国家,存在不同的文字,由于现在的软件都要做到国际化通用,所以必须要有一种语言或编码方式,来实现各种编码的解码,然后重新编码. 在西方国家,没有汉字,只有英文,所以最开 ...
MYSQL 企业常用架构与调优经验分享
一.选择Percona Server.MariaDB还是MYSQL mysql应用源码:http://www.jinhusns.com/Products/Download/?type=xcj 1.M ...
js深拷贝
// 判断是否为对象 function isObject(o) { return (typeof o === 'object' || typeof o === 'function') &&am ...
APPLE-SA-2019-3-25-6 iCloud for Windows 7.11
APPLE-SA-2019-3-25-6 iCloud for Windows 7.11 iCloud for Windows 7.11 is now available and addresses ...
C#利用VUDP.cs开发网络通讯应用例程
VClassLib-CS项目Github地址:https://github.com/velscode/VClassLib-CS VUDP文档地址:https://github.com/velscode ...

spark算子

1.map

2.flatMap

3.mapPartitions

4.mapPartitionsWithIndex

5.reduce

6.reduceBykey

7.union

8.join

9.groupbyKey

10.cartesian

11.filter

12.distinct

13.intersection

14.coalesce

15.repartition

16.repartitionAndSortWithinPartitions

17.cogroup

18.sortByKey

19.aggregateByKey

spark算子的更多相关文章

随机推荐

热门专题