scala WordCount案例

数据样例：

java,spark,hadoop,python,datax
java,spark,hadoop,spark,python,datax
java,spark,hadoop,python,datax
java,spark,hadoop,spark,python
java,spark,hadoop,spark,python,datax
java,spark,hadoop,python,datax
java,spark,hadoop,python,datax
java,spark,hadoop,spark,python,datax
java,spark,hadoop,python,datax
java,spark,hadoop,spark,python,datax
hadoop,spark,spark,python

package com.shujia
 
import scala.io.Source
 
object Test1wordcount {
  def main(args: Array[String]): Unit = {
//读取文件，并将转换成list集合
    val list: List[String] = Source.fromFile("data/words.txt").getLines().toList
  //将list集合按照分隔键进行展开
  val words: List[String] = list.flatMap((lines: String) => lines.split(","))
    //分组
    val groupBy: Map[String, List[String]] = words.groupBy((word: String) =>word)
    //统计单词数量
    val wordCount: Map[String, Int] = groupBy.map((kv: (String, List[String])) => {
      //分组单词
      val word: String = kv._1
      //组内所有单词
      val value: List[String] = kv._2
      //求出数组内的长度
      val count: Int = value.length
      //返回单词的数量
      (word, count)
    })
wordCount.foreach(println)
 
  }
 
}
输出结果：

F:\soft\java\jdk\bin\java.exe "-javaagent:F:\soft\IDEA\IntelliJ
(datax,36)
(java,40)
(hadoop,44)
(spark,68)
(python,44)
 
Process finished with exit code 0