用scala统计单词个数一步一步详解

怼烎@ 2022-05-29 11:10 257阅读 0赞

val lines = List("hello tom hello jerry", "hello jerry", "hello kitty")

![70][]

//先按空格切分

val lines\_1 = lines.map(\_.split(" "))

![70 1][]

//压平

val lines\_2 = lines\_1.flatten

![70 2][]

//用flatMap 两步合并成一步

val words= lines.flatMap(\_.split(" "))

//将每一个单词映射为元组  
val wordToOne = lines\_3.map(x=>(x,1)）

val wordToOne = lines\_3.map((\_,1))

![70 3][]

//分组

val grouped = wordToOne.groupBy(\_.\_1)

![70 4][]

组内求和

val grouped\_1 = grouped.map(t => (t.\_1,t.\_2.size))

![70 5][]

//将map转化成List

val result = grouped\_1.toList

![70 6][]

//排序

val result\_1 = result.sortBy(\_.\_2).reverse

![70 7][]

合并为一句  
  
  
val words = lines.flatMap(\_.split(" ")).map((\_,1)).groupBy(\_.\_1).map(t=>(t.\_1,t.\_2.size)).toList.sortBy(\_.\_2).reverse  
  
  
val words = lines.flatMap(\_.split(" ")).map((\_,1)).groupBy(\_.\_1).mapValues(\_.size).toList.sortBy(\_.\_2).reverse

val words = lines.flatMap(\_.split(" ")).map((\_,1)).groupBy(\_.\_1).mapValues(\_.foldLeft(0)

(\_+\_.\_2)).toList.sortBy(\_.\_2).reverse

从本地读取文件

package main.count
    
    import scala.io.Source
    object WordCounts {
      /*
      * 从本地读取文件统计个数
      * */
      def main(args: Array[String]): Unit = {
        val  lines=Source.fromFile("d:\\words.txt").getLines().toBuffer
        //val lines=lines.map(_.split(" ")).flatten.map(t=>(t,1)).groupBy(_._1).map(x=>(x._1,x._2.size)).toList.sortBy(_._2).reverse
        val lines1=lines.flatMap(_.split(" ")).map((_,1)).groupBy(_._1).map(t=>(t._1,t._2.size)).toList.sortBy(_._2).reverse
    
        println(lines1)
      }
    }

[70]: /images/20220529/2f0e44e38d78410fba85e12bded5477b.png
[70 1]: /images/20220529/2923d5a548a74afa86055910ee0a5380.png
[70 2]: /images/20220529/69e98ed44ad54999853840396d0e78ae.png
[70 3]: /images/20220529/edfb4ef2bc7a4db99e54b49a2839aa69.png
[70 4]: /images/20220529/d3fc5191ecfb4a0ba6866ef5c2e7a061.png
[70 5]: /images/20220529/5b2dfcaa9e864207a793b61ba0cbc641.png
[70 6]: /images/20220529/88e0aaf4912147a888de756eb944095f.png
[70 7]: /images/20220529/b3b3f7dc7b294116bc96bc64155288d5.png