-
-
import scala.runtime._
-
-
-
scala> val year = List(2010, 2010, 2010, 2016, 2016)
-
year: List[Int] = List(2010, 2010, 2010, 2016, 2016)
-
-
scala>
-
-
scala> val month = List(1, 2, 3, 9, 10)
-
month: List[Int] = List(1, 2, 3, 9, 10)
-
-
scala>
-
-
scala> val price = List(13.8, 32, 62.9, 66, 88, 99)
-
price: List[Double] = List(13.8, 32.0, 62.9, 66.0, 88.0, 99.0)
-
-
scala>
-
-
scala> val profit = List(1.1, 2.2, 3.3, 4.4, 5.5)
-
profit: List[Double] = List(1.1, 2.2, 3.3, 4.4, 5.5)
-
-
scala>
-
-
scala> val res1 = year zip month
-
res1: List[(Int, Int)] = List((2010,1), (2010,2), (2010,3), (2016,9), (2016,10))
-
-
scala> res1.foreach(println)
-
(2010,1)
-
(2010,2)
-
(2010,3)
-
(2016,9)
-
(2016,10)
-
-
scala>
-
-
scala> val res2 = price zip profit
-
res2: List[(Double, Double)] = List((13.8,1.1), (32.0,2.2), (62.9,3.3), (66.0,4.4), (88.0,5.5))
-
-
scala> res2.foreach(println)
-
(13.8,1.1)
-
(32.0,2.2)
-
(62.9,3.3)
-
(66.0,4.4)
-
(88.0,5.5)
-
-
scala>
-
-
scala> val res3 = res1 zip res2
-
res3: List[((Int, Int), (Double, Double))] = List(((2010,1),(13.8,1.1)), ((2010,2),(32.0,2.2)), ((2010,3),(62.9,3.3)), ((2016,9),(66.0,4.4)), ((2016,10),(88.0,5.5)))
-
-
scala> res3.foreach(println)
-
((2010,1),(13.8,1.1))
-
((2010,2),(32.0,2.2))
-
((2010,3),(62.9,3.3))
-
((2016,9),(66.0,4.4))
-
((2016,10),(88.0,5.5))
-
-
scala>
-
-
scala> val spark1 = List("Vector", "Feature")
-
spark1: List[String] = List(Vector, Feature)
-
-
scala>
-
-
scala> val spark2 = List("Scala", "SQL", "MLlib", "GraphX", "Streaming")
-
spark2: List[String] = List(Scala, SQL, MLlib, GraphX, Streaming)
-
-
scala>
-
-
scala> val res4 = spark1 zip spark2
-
res4: List[(String, String)] = List((Vector,Scala), (Feature,SQL))
-
-
scala> res4.foreach(println)
-
(Vector,Scala)
-
(Feature,SQL)
-
-
scala>
-
-
scala> // a.zipAll(b, thisElem, thatElem),a短，用thisElem填补；b短，用thatElem填补
-
-
scala> val res5 = spark1.zipAll(spark2, "DataFrame", "Pipeline")
-
res5: List[(String, String)] = List((Vector,Scala), (Feature,SQL), (DataFrame,MLlib), (DataFrame,GraphX), (DataFrame,Streaming))
-
-
scala> res5.foreach(println)
-
(Vector,Scala)
-
(Feature,SQL)
-
(DataFrame,MLlib)
-
(DataFrame,GraphX)
-
(DataFrame,Streaming)
-
-
scala>
-
-
scala> val res6 = spark2.zipAll(spark1, "DataFrame", "Pipeline")
-
res6: List[(String, String)] = List((Scala,Vector), (SQL,Feature), (MLlib,Pipeline), (GraphX,Pipeline), (Streaming,Pipeline))
-
-
scala> res6.foreach(println)
-
(Scala,Vector)
-
(SQL,Feature)
-
(MLlib,Pipeline)
-
(GraphX,Pipeline)
-
(Streaming,Pipeline)
-
-
scala> res6.par.foreach(println)
-
(Scala,Vector)
-
(SQL,Feature)
-
(MLlib,Pipeline)
-
(GraphX,Pipeline)
-
(Streaming,Pipeline)
-
-
-
-
scala> val res7 = res6.zipWithIndex
-
res7: List[((String, String), Int)] = List(((Scala,Vector),0), ((SQL,Feature),1), ((MLlib,Pipeline),2), ((GraphX,Pipeline),3), ((Streaming,Pipeline),4))
-
-
scala> res7.foreach(println)
-
((Scala,Vector),0)
-
((SQL,Feature),1)
-
((MLlib,Pipeline),2)
-
((GraphX,Pipeline),3)
-
((Streaming,Pipeline),4)
-
-
-
-
scala> val a = Array(
-
| (1, 10),
-
| (2, 11),
-
| (3, 12),
-
| (4, 13),
-
| (5, 14))
-
a: Array[(Int, Int)] = Array((1,10), (2,11), (3,12), (4,13), (5,14))
-
-
-
-
scala> val b = a.unzip
-
b: (Array[Int], Array[Int]) = (Array(1, 2, 3, 4, 5),Array(10, 11, 12, 13, 14))
-
-
-
-
scala> val c = List(
-
| (1, 10, "a"),
-
| (2, 11, "b"),
-
| (3, 12, "c"),
-
| (4, 13, "d"),
-
| (5, 14, "e"))
-
c: List[(Int, Int, String)] = List((1,10,a), (2,11,b), (3,12,c), (4,13,d), (5,14,e))
-
-
-
-
scala> val d = c.unzip3
-
d: (List[Int], List[Int], List[String]) = (List(1, 2, 3, 4, 5),List(10, 11, 12, 13, 14),List(a, b, c, d, e))
-
-
-
-
scala> d._3.par.foreach(println)
-
a
-
c
-
b
-
d
- e
来自 “ ITPUB博客 ” ，链接：https://blog.itpub.net/29070860/viewspace-2127856/ ，如需转载，请注明出处，否则将追究法律责任。
下一篇：
Scala Parallel 并行
请登录后发表评论
登录
全部评论
