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

多版本python及多版本pip使用
最近做一些网站的发布程序,要用到python3,所以又安装了python3. www.qlrx.netwww.393662.comwww.qnpx.netwww.393225.com ...
ADO.NET中的五大内置对象
ADO.NET中的五大内置对象学习链接:https://blog.csdn.net/wxr15732623310/article/details/51828677
自动化运维工具Ansible介绍
一个由 Python 编写的强大的配置管理解决方案.尽管市面上已经有很多可供选择的配置管理解决方案,但他们各有优劣,而 ansible 的特点就在于它的简洁. 让 ansible 在主流的配置管理系统 ...
jdbc封装模拟用户登录
dao层接口 package com.qu.dao; public interface ILoginDAO { /** * 模拟用户登录 * 验证用户名密码是否正确 * select * from ...
GO语言系列（五）- 结构体和接口
结构体(Struct) Go中struct的特点 1. 用来自定义复杂数据结构 2. struct里面可以包含多个字段(属性) 3. struct类型可以定义方法,注意和函数的区分 4. struct ...
openstack项目【day23】：glance基础
本节内容一什么是glance 二为何要有glance 三 glance的功能四 glance的两个版本五镜像的数据存放六镜像的访问权限七镜像及任务的各种状态八 glance包含的 ...
ZooKeeper-API CURD
ZooKeeper Java API pom.xml 依赖 <?xml version="1.0" encoding="UTF-8"?> <p ...
C++回顾day03---<模板>
一:函数模板建立一个通用函数,其函数类型和形参类型不具体指定,用一个虚拟的类型来代表.这个通用函数就称为函数模板.凡是函数体相同的函数都可以用这个模板来代替,不必定义多个函数,只需要在模板中定义一次 ...
dom4j,json,pattern性能对比【原】
报文大概2000字节,对比时为只取其中某个节点的值即可. 以下对比可知取少量节点时pattern性能是远大于dom4j,和json的, 但取大量的时候就不能这么以偏概全了. dom4j和pattern ...
js介绍，js三种引入方式，js选择器，js四种调试方式，js操作页面文档DOM（修改文本，修改css样式,修改属性）
js介绍 js运行编写在浏览器上的脚本语言(外挂,具有逻辑性) 脚本语言:运行在浏览器上的独立的代码块(具有逻辑性) 操作BOM 浏览器对象盒子操作DOM 文本对象 js三种引入方式 (1)行间式: ...

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