spark本地体验WordCount

一、流程分析

二、代码部分

package wc

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

object Spark_WordCount {

  def main(args: Array[String]): Unit = {
    //建立和spark框架的连接
    val sparConf = new SparkConf().setMaster("local").setAppName("WordCount")
    val sc = new SparkContext(sparConf)

    //执行业务操作
    //1.读取文件，获取一行一行的数据
    //hello world
    val lines:RDD[String] = sc.textFile("datas")

    //2.将一行一行的数据进行拆分，形成一个一个的单词（分词）
    //扁平化：将整体拆分成个体的操作
    //"hello world"=>hello,world
    val words: RDD[String] = lines.flatMap(_.split(" "))

    //3.将数据根据单词进行分组，便于统计
    //(hello,hello,hello),(world,world)
    val wordGroup: RDD[(String, Iterable[String])] = words.groupBy(word => word)

    //4.对分组后的数据进行转换
    //(hello,hello,hello),(world,world)=>(hello,3),(world,2)
    val wordToCount = wordGroup.map{
      case (word,list)=>{
        (word,list.size)
      }
    }

    //5.将转换结果采集到控制台打印出来
    val array: Array[(String, Int)] = wordToCount.collect()
    array.foreach(println)
    //关闭连接
    sc.stop()
  }
}

三、运行结果

 -------------------------------------------------------------------------------------分割线----------------------------------------------------------------------------------------------

另一种方式：

一、流程变化

 二、代码

package wc

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

object Spark_WordCount02 {

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

    val sparConf = new SparkConf().setMaster("local").setAppName("WordCount")
    val sc = new SparkContext(sparConf)

    val lines:RDD[String] = sc.textFile("datas")

    val words: RDD[String] = lines.flatMap(_.split(" "))

    val wordToOne: RDD[(String, Int)] = words.map(
      word => (word, 1)
    )

    val wordGroup: RDD[(String, Iterable[(String, Int)])] = wordToOne.groupBy(
      t => t._1
    )

    val wordToCount: RDD[(String, Int)] = wordGroup.map {
      case (word, list) => {
        list.reduce(
          (t1, t2) => {
            (t1._1, t1._2 + t2._2)
          }
        )
      }
    }
    //5.将转换结果采集到控制台打印出来
    val array: Array[(String, Int)] = wordToCount.collect()
    array.foreach(println)
    //关闭连接
    sc.stop()
  }
}

  -------------------------------------------------------------------------------------分割线----------------------------------------------------------------------------------------------

spark提供了更多的功能，可以将分组和聚合用一个方法来实现

package wc

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

object Spark_WordCount03 {

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

    val sparConf = new SparkConf().setMaster("local").setAppName("WordCount")
    val sc = new SparkContext(sparConf)

    val lines:RDD[String] = sc.textFile("datas")

    val words: RDD[String] = lines.flatMap(_.split(" "))

    val wordToOne: RDD[(String, Int)] = words.map(
      word => (word, 1)
    )

    //spark提供了更多的功能，可以将分组和聚合用一个方法来实现
    //reduceByKey：对相同的key的数据，可以对value进行reduce整合
    val wordToCount=wordToOne.reduceByKey(_+_)

    val array: Array[(String, Int)] = wordToCount.collect()
    array.foreach(println)
    //关闭连接
    sc.stop()
  }
}

 -------------------------------------------------------------------------------------分割线--------------------------------------------------------------------------------------------------------

cmd中运行wordCount

sc.textFile("data/word.txt").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).collect