笔记:scala:WordCount

 WordCount入门案例

object WordCount {
  def main(args: Array[String]): Unit = {
    val lines = List("hadoop spark fink tomcat hive ", "hadoop scala scala spark zookeeper", "scala spark")
    //val result = lines.flatMap(_.split(" ")).map((_, 1)).groupBy(_._1).map(t => (t._1, t._2.length)).toList.sortBy(_._2).reverse
    /*切分lines里的每个元素
    val words: immutable.Seq[Array[String]] = lines.map(x => x.split(" "))
    val flatten = words.flatten
    println(flatten)*/
    //替换flatMap
    val flatten = lines.flatMap(x => x.split(" "))
    // 对flatten的元素操作  (hadoop,1)...
    val tuples = flatten.map(x => (x, 1))
    // 分组 Map(fink -> List((fink,1)), hadoop -> List((hadoop,1), (hadoop,1))...
    val grouped = tuples.groupBy(x => x._1)
    //println(grouped)
    // 获取统计结果
    /**
     * 这里不能使用_  ,需要2个_  ,表示成2个参数,是错误的
     * val map = grouped.map(_._1,_._2.size))
     */
    val map = grouped.map(x => (x._1, x._2.size))
    //println(map)
    // 根据按照次数排序
    val result = map.toList.sortBy(x => x._2).reverse
    println(result)

  }
}