Scala zip 拉链操作

1. 
   
2. import scala.runtime._
   
3. 
   
4. 
   
5. scala> val year = List(2010, 2010, 2010, 2016, 2016)
   
6. year: List[Int] = List(2010, 2010, 2010, 2016, 2016)
   
7. 
   
8. scala>
   
9. 
   
10. scala> val month = List(1, 2, 3, 9, 10)
    
11. month: List[Int] = List(1, 2, 3, 9, 10)
    
12. 
    
13. scala>
    
14. 
    
15. scala> val price = List(13.8, 32, 62.9, 66, 88, 99)
    
16. price: List[Double] = List(13.8, 32.0, 62.9, 66.0, 88.0, 99.0)
    
17. 
    
18. scala>
    
19. 
    
20. scala> val profit = List(1.1, 2.2, 3.3, 4.4, 5.5)
    
21. profit: List[Double] = List(1.1, 2.2, 3.3, 4.4, 5.5)
    
22. 
    
23. scala>
    
24. 
    
25. scala> val res1 = year zip month
    
26. res1: List[(Int, Int)] = List((2010,1), (2010,2), (2010,3), (2016,9), (2016,10))
    
27. 
    
28. scala> res1.foreach(println)
    
29. (2010,1)
    
30. (2010,2)
    
31. (2010,3)
    
32. (2016,9)
    
33. (2016,10)
    
34. 
    
35. scala>
    
36. 
    
37. scala> val res2 = price zip profit
    
38. 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))
    
39. 
    
40. scala> res2.foreach(println)
    
41. (13.8,1.1)
    
42. (32.0,2.2)
    
43. (62.9,3.3)
    
44. (66.0,4.4)
    
45. (88.0,5.5)
    
46. 
    
47. scala>
    
48. 
    
49. scala> val res3 = res1 zip res2
    
50. 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)))
    
51. 
    
52. scala> res3.foreach(println)
    
53. ((2010,1),(13.8,1.1))
    
54. ((2010,2),(32.0,2.2))
    
55. ((2010,3),(62.9,3.3))
    
56. ((2016,9),(66.0,4.4))
    
57. ((2016,10),(88.0,5.5))
    
58. 
    
59. scala>
    
60. 
    
61. scala> val spark1 = List("Vector", "Feature")
    
62. spark1: List[String] = List(Vector, Feature)
    
63. 
    
64. scala>
    
65. 
    
66. scala> val spark2 = List("Scala", "SQL", "MLlib", "GraphX", "Streaming")
    
67. spark2: List[String] = List(Scala, SQL, MLlib, GraphX, Streaming)
    
68. 
    
69. scala>
    
70. 
    
71. scala> val res4 = spark1 zip spark2
    
72. res4: List[(String, String)] = List((Vector,Scala), (Feature,SQL))
    
73. 
    
74. scala> res4.foreach(println)
    
75. (Vector,Scala)
    
76. (Feature,SQL)
    
77. 
    
78. scala>
    
79. 
    
80. scala> // a.zipAll(b, thisElem, thatElem),a短，用thisElem填补；b短，用thatElem填补
    
81. 
    
82. scala> val res5 = spark1.zipAll(spark2, "DataFrame", "Pipeline")
    
83. res5: List[(String, String)] = List((Vector,Scala), (Feature,SQL), (DataFrame,MLlib), (DataFrame,GraphX), (DataFrame,Streaming))
    
84. 
    
85. scala> res5.foreach(println)
    
86. (Vector,Scala)
    
87. (Feature,SQL)
    
88. (DataFrame,MLlib)
    
89. (DataFrame,GraphX)
    
90. (DataFrame,Streaming)
    
91. 
    
92. scala>
    
93. 
    
94. scala> val res6 = spark2.zipAll(spark1, "DataFrame", "Pipeline")
    
95. res6: List[(String, String)] = List((Scala,Vector), (SQL,Feature), (MLlib,Pipeline), (GraphX,Pipeline), (Streaming,Pipeline))
    
96. 
    
97. scala> res6.foreach(println)
    
98. (Scala,Vector)
    
99. (SQL,Feature)
    
100. (MLlib,Pipeline)
     
101. (GraphX,Pipeline)
     
102. (Streaming,Pipeline)
     
103. 
     
104. scala> res6.par.foreach(println)
     
105. (Scala,Vector)
     
106. (SQL,Feature)
     
107. (MLlib,Pipeline)
     
108. (GraphX,Pipeline)
     
109. (Streaming,Pipeline)
     
110. 
     
111. 
     
112. 
     
113. scala> val res7 = res6.zipWithIndex
     
114. res7: List[((String, String), Int)] = List(((Scala,Vector),0), ((SQL,Feature),1), ((MLlib,Pipeline),2), ((GraphX,Pipeline),3), ((Streaming,Pipeline),4))
     
115. 
     
116. scala> res7.foreach(println)
     
117. ((Scala,Vector),0)
     
118. ((SQL,Feature),1)
     
119. ((MLlib,Pipeline),2)
     
120. ((GraphX,Pipeline),3)
     
121. ((Streaming,Pipeline),4)
     
122. 
     
123. 
     
124. 
     
125. scala> val a = Array(
     
126.      | (1, 10),
     
127.      | (2, 11),
     
128.      | (3, 12),
     
129.      | (4, 13),
     
130.      | (5, 14))
     
131. a: Array[(Int, Int)] = Array((1,10), (2,11), (3,12), (4,13), (5,14))
     
132. 
     
133. 
     
134. 
     
135. scala> val b = a.unzip
     
136. b: (Array[Int], Array[Int]) = (Array(1, 2, 3, 4, 5),Array(10, 11, 12, 13, 14))
     
137. 
     
138. 
     
139. 
     
140. scala> val c = List(
     
141.      | (1, 10, "a"),
     
142.      | (2, 11, "b"),
     
143.      | (3, 12, "c"),
     
144.      | (4, 13, "d"),
     
145.      | (5, 14, "e"))
     
146. c: List[(Int, Int, String)] = List((1,10,a), (2,11,b), (3,12,c), (4,13,d), (5,14,e))
     
147. 
     
148. 
     
149. 
     
150. scala> val d = c.unzip3
     
151. 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))
     
152. 
     
153.  
     
154. 
     
155. scala> d._3.par.foreach(println)
     
156. a
     
157. c
     
158. b
     
159. d
     
160. e

来自 “ ITPUB博客 ” ，链接：http://blog.itpub.net/29070860/viewspace-2127856/，如需转载，请注明出处，否则将追究法律责任。

转载于:http://blog.itpub.net/29070860/viewspace-2127856/