Numpy 从 .txt 文档中读取数组

zltzlt

1. import numpy as np
   
2. nba = np.genfromtxt("resources/nba.txt", encoding="utf-8", dtype=str)    # 设置类型为 str，编码为 utf-8
   
3. print(nba)
   
4. [['排名' '队名' '胜' '负' '胜率' '胜场差' '主场' '客场' '赛区' '东部' '得分' '失分' '净胜' '连胜/负']
   
5. ['1' '雄鹿' '46' '8' '85.2%' '0.0' '25-3' '21-5' '11-1' '28-4' '119.6'
   
6.   '107.5' '12.1' '1连败']
   
7. ['2' '猛龙' '40' '15' '72.7%' '6.5' '21-7' '19-8' '8-4' '29-8' '113.0'
   
8.   '106.6' '6.3' '1连败']
   
9. ['3' '凯尔特人' '37' '16' '69.8%' '8.5' '22-5' '15-11' '7-5' '25-9' '112.6'
   
10.   '105.7' '6.8' '1连败']
    
11. ['4' '热火' '35' '19' '64.8%' '11.0' '22-3' '13-16' '8-2' '23-7' '111.7'
    
12.   '108.4' '3.4' '1连败']
    
13. ['5' '76人' '34' '21' '61.8%' '12.5' '25-2' '9-19' '9-4' '22-14' '108.6'
    
14.   '106.2' '2.4' '3连胜']
    
15. ['6' '步行者' '32' '23' '58.2%' '14.5' '19-10' '13-13' '6-6' '20-15'
    
16.   '109.7' '107.6' '2.2' '1连胜']
    
17. ['7' '篮网' '25' '28' '47.2%' '20.5' '16-12' '9-16' '5-8' '17-16' '110.6'
    
18.   '111.0' '-0.5' '2连胜']
    
19. ['8' '魔术' '24' '31' '43.6%' '22.5' '15-13' '9-18' '8-4' '17-17' '103.9'
    
20.   '105.4' '-1.5' '2连胜']
    
21. ['9' '奇才' '20' '33' '37.7%' '25.5' '13-13' '7-20' '4-8' '14-19' '115.6'
    
22.   '119.9' '-4.2' '2连胜']
    
23. ['10' '公牛' '19' '36' '34.5%' '27.5' '11-16' '8-20' '6-8' '13-24' '106.4'
    
24.   '109.5' '-3.1' '6连败']]
    
25. print(nba[:, [4, -2]])
    
26. # 拿出胜率（04 列）和净胜（倒数 -2 ）
    
27. print(nba[:, [4, -2]])
    
28. [['胜率' '净胜']
    
29. ['85.2%' '12.1']
    
30. ['72.7%' '6.3']
    
31. ['69.8%' '6.8']
    
32. ['64.8%' '3.4']
    
33. ['61.8%' '2.4']
    
34. ['58.2%' '2.2']
    
35. ['47.2%' '-0.5']
    
36. ['43.6%' '-1.5']
    
37. ['37.7%' '-4.2']
    
38. ['34.5%' '-3.1']]
    
39. nba[:, [4, -2]][1:]
    
40. # 去掉第一行
    
41. print(nba[:, [4, -2]][1:])
    
42. [['85.2%' '12.1']
    
43. ['72.7%' '6.3']
    
44. ['69.8%' '6.8']
    
45. ['64.8%' '3.4']
    
46. ['61.8%' '2.4']
    
47. ['58.2%' '2.2']
    
48. ['47.2%' '-0.5']
    
49. ['43.6%' '-1.5']
    
50. ['37.7%' '-4.2']
    
51. ['34.5%' '-3.1']]
    
52. print(np.char.strip(nba[:, [4, -2]][1:], '%'))
    
53. # 去掉第一列的 %
    
54. print(np.char.strip(nba[:, [4, -2]][1:], '%'))
    
55. [['85.2' '12.1']
    
56. ['72.7' '6.3']
    
57. ['69.8' '6.8']
    
58. ['64.8' '3.4']
    
59. ['61.8' '2.4']
    
60. ['58.2' '2.2']
    
61. ['47.2' '-0.5']
    
62. ['43.6' '-1.5']
    
63. ['37.7' '-4.2']
    
64. ['34.5' '-3.1']]
    
65. # 将 str 类型转化为 float
    
66. print(np.char.strip(nba[:, [4, -2]][1:], '%').astype("f8"))    # f8 是 float64 的缩写
    
67. [[85.2 12.1]
    
68. [72.7  6.3]
    
69. [69.8  6.8]
    
70. [64.8  3.4]
    
71. [61.8  2.4]
    
72. [58.2  2.2]
    
73. [47.2 -0.5]
    
74. [43.6 -1.5]
    
75. [37.7 -4.2]
    
76. [34.5 -3.1]]

复制代码