FilesExpand file tree

 python-2.7

/

python2libsvm.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

52 lines (39 loc) · 1.38 KB

 python-2.7

/

python2libsvm.py

Copy path

Top

File metadata and controls

• Code
• Blame

52 lines (39 loc) · 1.38 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

#!/usr/bin/python

# coding:utf8

import os

import sklearn.datasets as datasets

def get_data(file_input, separator='\t'):

if 'libsvm' not in file_input:

file_input = other2libsvm(file_input, separator)

data = datasets.load_svmlight_file(file_input)

return data[0], data[1]

def other2libsvm(file_name, separator='\t'):

libsvm_name = file_name.replace('.txt', '.libsvm_tmp')

libsvm_data = open(libsvm_name, 'w')

file_data = open(file_name, 'r')

for line in file_data.readlines():

features = line.strip().split(separator)

# print len(features)

class_data = features[-1]

svm_format = ''

for i in range(len(features)-1):

svm_format += " %d:%s" % (i+1, features[i])

# print svm_format

svm_format = "%s%s\n" % (class_data, svm_format)

# print svm_format

libsvm_data.write(svm_format)

file_data.close()

libsvm_data.close()

return libsvm_name

def dump_data(x, y, file_output):

datasets.dump_svmlight_file(x, y, file_output)

os.remove("%s_tmp" % file_output)

if __name__ == "__main__":

file_input = "input/7.AdaBoost/horseColicTest2.txt"

file_output = "input/7.AdaBoost/horseColicTest2.libsvm"

# 获取数据集

x, y = get_data(file_input, separator='\t')

print x[3, :]

print y

# 导出数据为 libsvm

dump_data(x, y, file_output)