使用Scala语言实现单词数量统计功能

最新推荐文章于 2023-07-21 11:04:15 发布

原创最新推荐文章于 2023-07-21 11:04:15 发布 · 5.4k 阅读

20 ·

CC 4.0 BY-SA版权

Scala 专栏收录该内容

1 篇文章

订阅专栏

博客介绍了使用Scala语言实现单词数量统计功能。给出一个包含字符串及对应数字的集合，需统计集合中单词出现次数，再按次数降序排列并取前3，还提及了两种实现方式。

使用Scala语言实现单词数量统计功能：
List( ("Hello Scala World", 4), ("Hello World", 3), ("Hello Hadoop", 2), ("Hello Hbase", 1) )
将上面集合中的单词统计出现次数并按照次数降序排列取前3.

方式一

object  WordCount {

    def main(args: Array[String]): Unit = {

        val linesList = List(("Hello Scala World", 4), ("Hello World", 3), ("Hello Hadoop", 2), ("Hello Hbase", 1))

        // 将一行一行的数据拆分成一个一个的单词数据
        // ("Hello Scala World", 4)
        // =>[ (Hello), (Scala), (World) ]
        // =>[ (Hello,4), (Scala,4), (World,4) ]
        val flatMapList: List[(String, Int)] = linesList.flatMap(t => {
            val line: String = t._1
            val words = line.split(" ")
            words.map(w => (w, t._2))
        })

        // 将单词进行分组
        // Hello -> List((Hello,4), (Hello,3), (Hello,2), (Hello,1))
        // ==> List((4), (3), (2), (1))
        // ==> list.sum
        val groupWordMap: Map[String, List[(String, Int)]] = flatMapList.groupBy(t=>t._1)

        // 将分组后的数据进行结构的转换
        /*
        val wordToSumMap: Map[String, Int] = groupWordMap.map(t => {
            val countList: List[Int] = t._2.map(tt => tt._2)
            (t._1, countList.sum)
        })
        */
        // mapValues方法可以只针对于Map集合中的Value做操作，key保持不变
        val wordToSumMap: Map[String, Int] = groupWordMap.mapValues(datas=>datas.map(tt=>tt._2).sum)

        // 将统计的结果进行降序排列
        val sortList: List[(String, Int)] = wordToSumMap.toList.sortWith( (left, right)=> left._2 > right._2 )

        // 从排序后的集合中获取前3条
        val resultList: List[(String, Int)] = sortList.take(3)

        println(resultList)
    }
}

方式二

object WordCount {

  def main(args: Array[String]): Unit = {
    //原始数据 ("Hello Scala World", 4) 4:代表出现的次数
    val tuples: List[(String, Int)] = List( ("Hello Scala World", 4), ("Hello World", 3), ("Hello Hadoop", 2), ("Hello Hbase", 1) )

    //将("Hello Scala World", 4)还原，"Hello Scala World"*4
    //List(Hello Scala World Hello Scala World Hello Scala World Hello Scala World , Hello World Hello World Hello World )
    val strings: List[String] = tuples.map(t=>{(t._1+" ")*t._2})
    println(strings)
    //进行扁平化,将集合中的字符串按空格进行切分
    val flatMapList: List[String] = strings.flatMap(t=>{t.split(" ")})
    println(flatMapList)
    //进行分组
    val stringToStrings: Map[String, List[String]] = flatMapList.groupBy(words=>words)
    println(stringToStrings)
    //进行统计  (Hello,4), (Scala,4), (World,4)
    val stringToInt: Map[String, Int] = stringToStrings.map(t=>{(t._1,t._2.size)})
    println(stringToInt)
    //进行排序(倒序)
    println(stringToInt.toList)
    val sortWithList: List[(String, Int)] = stringToInt.toList.toList.sortWith((left, right) => {
      left._2 > right._2
    })
    println(sortWithList)
    //获取前3的数据
    val result: List[(String, Int)] = sortWithList.take(3)
    println(result)
  }
}