spark rdd实现WordCount的八种方法

最新推荐文章于 2022-08-05 17:43:32 发布

南辰x

最新推荐文章于 2022-08-05 17:43:32 发布

阅读量355

点赞数 3

文章标签： spark scala big data

本文链接：https://blog.csdn.net/weixin_60578371/article/details/125193843

版权


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

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


    //创建spark环境
    val sparkconf = new SparkConf().setAppName("wordcount").setMaster("local[*]")
    val sc = new SparkContext(sparkconf)

    //读取文件
    val value: RDD[String] = sc.textFile("E:\\idea\\IdeaProjects\\Spark-Project\\Spark-Core\\src\\main\\resources\\data.txt")


    //map + groupByKey + mapValues
    val value1: RDD[String] = value.flatMap(_.split(" "))
    val value2: RDD[(String, Int)] = value1.map((_,1))

    val value3: RDD[(String, Iterable[Int])] = value2.groupByKey()
    val res: RDD[(String, Int)] = value3.mapValues(_.size)


    //groupby + mapvalue

    val value4: RDD[String] = value.flatMap(_.split(" "))
    val value5: RDD[(String, Iterable[String])] = value4.groupBy((data: String) => data)

    val res2 = value5.mapValues(_.size)


    val value6: RDD[String] = value.flatMap(_.split(" "))
    val value7: RDD[(String, Int)] = value6.map((_,1))


    //map + reduceByKey
    val res3: RDD[(String, Int)] = value7.reduceByKey(_+_)

    //map + aggregateByKey
    val res4: RDD[(String, Int)] = value7.aggregateByKey(0)(_ + _, _ + _)

    //map + foldByKey
    val res5: RDD[(String, Int)] = value7.foldByKey(0)(_ + _)

    //map + combineByKey
    val res6: RDD[(String, Int)] = value7.combineByKey(
      x => x,
      (x: Int, y: Int) => {
        x + y
      },
      (x: Int, y: Int) => {
        x + y
      }
    )

    //map + countByKey
    val res7: collection.Map[String, Long] = value7.countByKey()


    //countByValue
    val res8: collection.Map[String, Long] = value6.countByValue()


    sc.stop()

  }
}