Spark Scala GroupByKey

package main.scala.scala.operator
import org.apache.spark.{SparkConf, SparkContext}

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

    //val lines = sc.textFile("hdfs://hadoop001:9000/input/test.txt",1)
    val lines = sc.textFile("file:/Users/zhudechao/gitee/bigdata/scalaSpark/input/test.txt")
    val words = lines.flatMap{line=>line.split(" ")}
    val pairs = words.map{word=>(word,1)}
    val wc = pairs.groupByKey().map((w=>(w._1,w._2.sum)))
    wc.foreach(w=>println(w._1+" "+w._2))

    sc.stop()
  }

}

输入数据

a b c
uu uu 1
h k l

输出数据

a 1
k 1
b 1
h 1
uu 2
1 1
l 1
c 1