本文實例為大家分享了python實現txt文件格式轉換為arff格式的具體代碼，供大家參考，具體內容如下
將文件讀取出來的時候默認都是字符型的，所以有轉換出來有點問題，但是還是可以用的。
文件要求第一行是你對應的屬性名，之后是數字。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|
import sys import re relationname = "" filename = "" if (len(sys.argv)<2): print("Usage:\npython arff.py MyRelationName filename.txt") else: relationname = sys.argv[1] filename = sys.argv[2] class Arff: def __init__(self, r, f): self.relationname = r if r is not "" else "MachineLearning" f = f if f is not "" else "MMG_data.txt" self.file1 = open(f, 'r') self.data = [] self.names = [] self.parseData() self.writeToFile() def parseData(self): firstLine = True for line in self.file1.readlines(): if not firstLine: try: line = line.replace("\n", "") words = line.split(" ") except ValueError: print("cant parse file!!") self.data.append(words) else: firstLine = False line = line.replace("\n", "") words = line.split(" ") self.names = words def getType(self, value): v = "" if(type(value) == type(1)): v = "numeric" elif(type(value) == type(1.0)): v = "numeric" elif(re.match("[0-9]{4}\-[0-9]{2}\-[0-9]{2}\s[0-9]{2}\:[0-9]{2}\:[0-9]{2}", value)): v = "date " + "yyyy-MM-dd HH:mm:ss" elif(type(value) == type("string")): v = "string" elif(v == ""): print("Data type "+value+" not supported yet.") return v def writeToFile(self): values = self.data[0] file2 = open("Dexhunter_test_result.arff", 'w+' ) self.relationname+="\n" relationString = '@RELATION ' + self.relationname file2.write(''+relationString+'') for i in range(len(self.names)): str2 = "@ATTRIBUTE " + self.names[i] + " " + self.getType( values[i] ) + "\n" file2.write(''+str2+'') file2.write('''''@DATA\n''') for line in self.data: try: file2.write(",".join(line)+"\n") except UnicodeEncodeError: print("cant write Data to file!!") Arff(relationname, filename) |
以上就是本文的全部內容，希望對大家的學習有所幫助，也希望大家多多支持服務器之家。
原文鏈接：https://blog.csdn.net/chichoxian/article/details/41937581
