GroupByKey

package sparkcore

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

object Demo07GroupByKey {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("GroupByKey").setMaster("local")

    val sc = new SparkContext(conf)

    val linesRDD: RDD[String] = sc.textFile("data/words.txt")
    //flatmap将数据进行切分，一行切成多行
    val wordsRDD: RDD[String] = linesRDD.flatMap(_.split(","))

    //    wordsRDD.foreach(println)
    //将切好的一个个单词进行map，转换成kv格式
    val kvRDD: RDD[(String, Int)] = wordsRDD.map(word => (word, 1))

    /**
      * groupByKey：通过key进行分组，将value放在迭代器中
      * groupBy：指定一个分组的列
      *
      * 都会产生shuffle
      */
    val groupByKeyRDD: RDD[(String, Iterable[Int])] = kvRDD.groupByKey()

    val countRDD: RDD[(String, Int)] =groupByKeyRDD.map {
      case (word: String, values: Iterable[Int]) =>
        (word, values.sum)
    }
    countRDD.foreach(println)

    val groupByRDD: RDD[(String, Iterable[(String, Int)])] = kvRDD.groupBy(kv => kv._1)

    groupByRDD.foreach(println)
  }

}