RDD的詳解、建立及其操作

lmandcc發表於2021-11-10

RDD的詳解


RDD:彈性分散式資料集,是Spark中最基本的資料抽象,用來表示分散式集合,支援分散式操作!

RDD的建立

RDD中的資料可以來源於2個地方:本地集合或外部資料來源

RDD操作

分類

轉換運算元

Map

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

object Demo03Map {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf()
    conf.setAppName("Demo03Map").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    //讀取檔案資料
    val linesRDD: RDD[String] = sc.textFile("spark/data/words.txt")
    //對資料進行扁平化處理
    val flatRDD: RDD[String] = linesRDD.flatMap(_.split(","))


    //按照單詞分組
    val groupRDD: RDD[(String, Iterable[String])] = flatRDD.groupBy(w => w)
    //聚合
    val wordsRDD: RDD[String] = groupRDD.map(kv => {
      val key: String = kv._1
      val words: Iterable[String] = kv._2
      key + "," + words.size
    })


    //分組+聚合
    val mapRDD1: RDD[(String, Int)] = flatRDD.map((_, 1))
    val words1: RDD[(String, Int)] = mapRDD1.reduceByKey(_ + _)

    ////分組+聚合
    val mapRDD2: RDD[(String, Int)] = flatRDD.map((_, 1))
    val words2: RDD[(String, Iterable[Int])] = mapRDD2.groupByKey()
    val wordSum: RDD[(String, Int)] = words2.mapValues(_.size)
    wordSum.foreach(println)

    //輸出
    wordsRDD.foreach(println)
    words1.foreach(println)
  }
}

flatMap(資料扁平化處理)

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

object Demo04FlatMap {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo04FlatMap").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)

    val linesRDD: RDD[String] = sc.parallelize(List("java,scala,python", "map,java,scala"))
    //扁平化處理
    val flatRDD: RDD[String] = linesRDD.flatMap(_.split(","))
    flatRDD.foreach(println)
  }
}

Mappartitions

map和mapPartitions區別

1)map:每次處理一條資料
2)mapPartitions:每次處理一個分割槽資料

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

object Demo05MapPartition {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo05MapPartition").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    val stuRDD: RDD[String] = sc.textFile("spark/data/words.txt",3)
    stuRDD.mapPartitions(rdd => {
      println("map partition")
      // 按分割槽去處理資料
      rdd.map(line => line.split(",")(1))
    }).foreach(println)
  }
}

fliter 過濾

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

object Demo06Filter {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo05MapPartition").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    val linesRDD: RDD[Int] = sc.parallelize(List(1, 2, 3, 4, 5))
    //過濾,轉換運算元
    linesRDD.filter(kv => {
      kv % 2 == 1
    }).foreach(println)
  }
}

sample 取樣

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

object Demo07Sample {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo05MapPartition").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    /**
     * sample:對資料取樣
     * withReplacement 有無放回
     * fraction 抽樣比例
     * withReplacement:表示抽出樣本後是否在放回去,true表示會放回去
     * 這也就意味著抽出的樣本可能有重複
     * fraction :抽出多少,這是一個double型別的引數,0-1之間,eg:0.3表示抽出30%
     */
    val stuRDD: RDD[String] = sc.textFile("spark/data/students.txt",3)
    stuRDD.sample(withReplacement = true,0.1).foreach(println)
  }
}

union 將相同結結構的資料連線到一起

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

object Demo08Union {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo05MapPartition").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)

    /**union
     * 將兩個相同結構的資料連線在一起
     */
    val lineRDD1: RDD[String] = sc.parallelize(List("java,scala", "data,python"))
    val lineRDD2: RDD[String] = sc.parallelize(List("spark,scala", "java,python"))
    println(lineRDD1.getNumPartitions)
    val unionRDD: RDD[String] = lineRDD1.union(lineRDD2)
    println(unionRDD.getNumPartitions)
    unionRDD.foreach(println)
  }
}

mappatitionWIthindex

    //mapPartitionsWithIndex也是一個轉換運算元
    // 會在處理每一個分割槽的時候獲得一個index
    //可以選擇的執行的分割槽
    stuRDD.mapPartitionsWithIndex((index, rdd) => {
      println("當前遍歷的分割槽:" + index)
      // 按分割槽去處理資料
      rdd.map(line => line.split(",")(1))
    }).foreach(println)

join 將資料按照相同key進行關聯(資料必須是(K,V))

import java.io

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

object Demo09Join {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo05MapPartition").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    // 構建K-V格式的RDD
    val tuple2RDD1: RDD[(String, String)] = sc.parallelize(List(("001", "張三"), "002" -> "小紅", "003" -> "小明"))
    val tuple2RDD2: RDD[(String, Int)] = sc.parallelize(List(("001", 20), "002" -> 22, "003" -> 21))
    val tuple2RDD3: RDD[(String, String)] = sc.parallelize(List(("001", "男"), "002" -> "女"))
    //將檔案進行join
    val joinRDD: RDD[(String, (String, Int))] = tuple2RDD1.join(tuple2RDD2)
    joinRDD.map(kv => {
      val i: String = kv._1
      val j: String = kv._2._1
      val k: Int = kv._2._2
      i + "," + j + "," + k
    }).foreach(println)

    //第二種方式
    joinRDD.map {
      case (id: String, (name: String, age: Int)) => id + "*" + name + "*" + age
    }.foreach(println)

    val leftJoinRDD: RDD[(String, (String, Option[String]))] = tuple2RDD1.leftOuterJoin(tuple2RDD3)
    leftJoinRDD.map {
          //存在關聯
      case (id: String, (name: String, Some(gender))) => 
        id + "*" + name + "*" + gender
        //不存在關聯
      case (id: String, (name: String, None)) =>
        id + "*" + name + "*" + "_"
    }
  }
}

groupByKey 將kv格式的資料進行key的聚合

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

object Demo10GroupByKey {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo10GroupByKey").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    /**
     * groupBy 指定分組的欄位進行分組
     */

    // 統計班級人數
    val linesRDD: RDD[String] = sc.textFile("spark/data/students.txt")
    linesRDD.groupBy(word => word.split(",")(4))
      .map(kv => {
        val key = kv._1
        val wordsCnt = kv._2.size
        key + "," + wordsCnt
      }).foreach(println)

    val linesMap: RDD[(String, String)] = linesRDD.map(lines => (lines.split(",")(4), lines))
    //按照key進行分組
    linesMap.groupByKey()
      .map(lines=>{
        val key = lines._1
        val wordsCnt: Int = lines._2.size
        key+","+wordsCnt
      }).foreach(println)

  }
}

ReduceByKey
reduceByKey 需要接收一個聚合函式
首先會對資料按key分組 然後在組內進行聚合(一般是加和,也可以是Max、Min之類的操作)
相當於 MR 中的combiner
可以在Map端進行預聚合,減少shuffle過程需要傳輸的資料量,以此提高效率
相對於groupByKey來說,效率更高,但功能更弱
冪等操作
y = f(x) = f(y) = f(f(x))
reducebyKey與groupbykey的區別
reduceByKey:具有預聚合操作
groupByKey:沒有預聚合
在不影響業務邏輯的前提下,優先採用reduceByKey。

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

object Demo11ReduceByKey {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo11ReduceByKey").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    val linesRDD: RDD[String] = sc.textFile("spark/data/students.txt")
    //統計班級人數
    linesRDD.map(lines => (lines.split(",")(4), lines))
      .groupByKey()
      .map(kv => {
        val key = kv._1
        val cnt = kv._2.size
        key + "" + cnt
      }).foreach(println)


    //ReduceByKey
    /**
     * reduceByKey 需要接收一個聚合函式
     * 首先會對資料按key分組 然後在組內進行聚合(一般是加和,也可以是Max、Min之類的操作)
     * 相當於 MR 中的combiner
     * 可以在Map端進行預聚合,減少shuffle過程需要傳輸的資料量,以此提高效率
     * 相對於groupByKey來說,效率更高,但功能更弱
     * 冪等操作
     * y = f(x) = f(y) = f(f(x))
     */
    linesRDD.map(lines=>(lines.split(",")(4),1))
      .reduceByKey(_+_)
      .foreach(println)
  }
}

sort 排序,預設升序

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

object Demo12Sort {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("Demo12Sort").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    val linesRDD: RDD[String] = sc.textFile("spark/data/students.txt")

    /**
     * sortBy 轉換運算元
     * 指定按什麼排序 預設升序
     *
     * sortByKey 轉換運算元
     * 需要作用在KV格式的RDD上,直接按key排序 預設升序
     */
    linesRDD.sortBy(lines => lines.split(",")(2), ascending = false) //按照年紀降序
      .take(10) //轉換運算元列印十行
      .foreach(println)

    val mapRDD: RDD[(String, String)] = linesRDD.map(l => (l.split(",")(2), l))
    mapRDD.sortByKey(ascending = false)
      .take(10)
      .foreach(println)
  }
}

Mapvalue

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

object Demo13MapValue {
  def main(args: Array[String]): Unit = {
    /**
     * mapValues 轉換運算元
     * 需要作用在K—V格式的RDD上
     * 傳入一個函式f
     * 將RDD的每一條資料的value傳給函式f,key保持不變
     * 資料規模也不會改變
     */
    val conf: SparkConf = new SparkConf().setAppName("Demo13MapValue").setMaster("local")
    val sc: SparkContext = new SparkContext(conf)
    val linesRDD: RDD[(String, Int)] = sc.parallelize(List(("zs", 10), ("zzw", 34), ("lm", 18)))
    linesRDD.mapValues(lines=>lines*2)
      .foreach(println)
  }

行為運算元

相關文章