第 7 章 集合-----Scala集合继承图

7.1.1 不可变集合继承图

7.1.2 可变集合继承图

7.2.3 不可变数组与可变数组的转换

7.7.6 复杂 WordCount 案例

1）方式一

object TestWordCount {
 def main(args: Array[String]): Unit = {
 // 第一种方式（不通用）
 val tupleList = List(("Hello Scala Spark World ", 4), ("Hello 
Scala Spark", 3), ("Hello Scala", 2), ("Hello", 1))
 val stringList: List[String] = tupleList.map(t=>(t._1 + " 
") * t._2)
 //val words: List[String] = 
stringList.flatMap(s=>s.split(" "))
 val words: List[String] = stringList.flatMap(_.split(" "))
//在 map 中，如果传进来什么就返回什么，不要用_省略
 val groupMap: Map[String, List[String]] = 
words.groupBy(word=>word)
 //val groupMap: Map[String, List[String]] = 
words.groupBy(_)
 // (word, list) => (word, count)
 val wordToCount: Map[String, Int] = groupMap.map(t=>(t._1, 
t._2.size))
 val wordCountList: List[(String, Int)] = 
wordToCount.toList.sortWith {
 (left, right) => {
 left._2 > right._2
 }
 }.take(3)
 //tupleList.map(t=>(t._1 + " ") * t._2).flatMap(_.split(" 
")).groupBy(word=>word).map(t=>(t._1, t._2.size))
 println(wordCountList)
 }
}

2）方式二

object TestWordCount {
 def main(args: Array[String]): Unit = {
 val tuples = List(("Hello Scala Spark World", 4), ("Hello 
Scala Spark", 3), ("Hello Scala", 2), ("Hello", 1))
 // (Hello,4),(Scala,4),(Spark,4),(World,4)
 // (Hello,3),(Scala,3),(Spark,3)
 // (Hello,2),(Scala,2)
 // (Hello,1)
 val wordToCountList: List[(String, Int)] = tuples.flatMap 
{
 t => {
 val strings: Array[String] = t._1.split(" ")
 strings.map(word => (word, t._2))
 }
 }
 // Hello, List((Hello,4), (Hello,3), (Hello,2), (Hello,1))
 // Scala, List((Scala,4), (Scala,3), (Scala,2)
 // Spark, List((Spark,4), (Spark,3)
 // Word, List((Word,4))
 val wordToTupleMap: Map[String, List[(String, Int)]] = 
wordToCountList.groupBy(t=>t._1)
 val stringToInts: Map[String, List[Int]] = 
wordToTupleMap.mapValues {
 datas => datas.map(t => t._2)
 }
 stringToInts

 val wordToCountMap: Map[String, List[Int]] = 
wordToTupleMap.map {
 t => {
 (t._1, t._2.map(t1 => t1._2))
 }
 }
 val wordToTotalCountMap: Map[String, Int] = 
wordToCountMap.map(t=>(t._1, t._2.sum))
 println(wordToTotalCountMap)
 
 }
}