val list = List(23, 54, 68, 91, 15)
(1)获取集合长度
println(list.length)
(2)获取集合大小
println(list.size)
(3)循环遍历
for( elem <- list ) print(elem + "\t")
list.foreach( elem => print(elem + "\t") )
(4)迭代器
val iter = list.iterator
while(iter.hasNext) print(iter.next() + "\t")
for( elem <- list.iterator ) print(elem + "\t")
(5)生成字符串
println(list.mkString("--"))
(6)是否包含
println(list.contains(23))
val list1 = List(23, 54, 68, 91, 15)
val list2 = List(35, 48, 69, 54, 23, 91, 102, 68, 23, 56)
(1)获取集合的头
println(list1.head)
(2)获取集合的尾(不是头的就是尾)
println(list1.tail)
(3)集合最后一个数据
println(list1.last)
(4)集合初始数据(不包含最后一个)
println(list1.init)
(5)反转
println(list1.reverse)
(6)取前(后)n个元素
println(list2.take(5))
//println(list2.reverse.take(3).reverse)
println(list2.takeRight(3))
(7)去掉前(后)n个元素
println(list2.drop(2))
println(list2.dropRight(5))
(8)并集
println(list1.union(list2))
(9)交集
println(list1.intersect(list2))
(10)差集
println(list1.diff(list2))
(11)拉链
println(list1.zip(list2))
(12)滑窗
list2.sliding(3).foreach( println )
list2.sliding(5, 3).foreach( println )
3、集合计算的初级函数
(1)求和
println(list.sum)
(2)求乘积
println(list.product)
(3)最大值
println(list.max)
(4)最小值
println(list.min)
(5)排序
// (5.1)按照元素大小排序
println(list.sortBy(x => x))
// (5.2)按照元素的绝对值大小排序
println(list.sortBy(x => x.abs))
// (5.3)按元素大小升序排序
println(list.sortWith((x, y) => x < y))
// (5.4)按元素大小降序排序
println(list.sortWith((x, y) => x > y))
//(1)过滤
println(list.filter(x => x % 2 == 0))
//(2)转化/映射
println(list.map(x => x + 1))
//(3)扁平化
println(nestedList.flatten)
//(4)扁平化+映射 注:flatMap相当于先进行map操作,在进行flatten操作
println(wordList.flatMap(x => x.split(" ")))
//(5)分组
println(list.groupBy(x => x % 2))
reduce方法
val list = List(1,2,3,4)
// 将数据两两结合,实现运算规则
val i: Int = list.reduce( (x,y) => x-y )
println("i = " + i)
// 从源码的角度,reduce底层调用的其实就是reduceLeft
//val i1 = list.reduceLeft((x,y) => x-y)
// ((4-3)-2-1) = -2
val i2 = list.reduceRight((x,y) => x-y)
println(i2)
Fold方法
val list = List(1,2,3,4)
// fold方法使用了函数柯里化,存在两个参数列表
// 第一个参数列表为 : 零值(初始值)
// 第二个参数列表为: 简化规则
// fold底层其实为foldLeft
val i = list.foldLeft(1)((x,y)=>x-y)
val i1 = list.foldRight(10)((x,y)=>x-y)
println(i)
println(i1)
// 两个Map的数据合并
val map1 = mutable.Map("a"->1, "b"->2, "c"->3)
val map2 = mutable.Map("a"->4, "b"->5, "d"->6)
val map3: mutable.Map[String, Int] = map2.foldLeft(map1) {
(map, kv) => {
val k = kv._1
val v = kv._2
map(k) = map.getOrElse(k, 0) + v
map
}
}
println(map3)
def main(args: Array[String]): Unit = {
// 单词计数:将集合中出现的相同的单词,进行计数,取计数排名前三的结果
val stringList = List("Hello Scala Hbase kafka", "Hello Scala Hbase", "Hello Scala", "Hello")
// 1) 将每一个字符串转换成一个一个单词
val wordList: List[String] = stringList.flatMap(str=>str.split(" "))
//println(wordList)
// 2) 将相同的单词放置在一起
val wordToWordsMap: Map[String, List[String]] = wordList.groupBy(word=>word)
//println(wordToWordsMap)
// 3) 对相同的单词进行计数
// (word, list) => (word, count)
val wordToCountMap: Map[String, Int] = wordToWordsMap.map(tuple=>(tuple._1, tuple._2.size))
// 4) 对计数完成后的结果进行排序(降序)
val sortList: List[(String, Int)] = wordToCountMap.toList.sortWith {
(left, right) => {
left._2 > right._2
}
}
// 5) 对排序后的结果取前3名
val resultList: List[(String, Int)] = sortList.take(3)
println(resultList)
}
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)
}
==================================
//方式二
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)
*/
}