Question

我有一个简单的脚本，试图将csv数据文件转换为工具svm_light可以接受的表单。这是代码：

    import csv
import sys
import numpy as np
from sklearn.cross_validation import train_test_split

def svm_light_conversion(row):
    conv_row = row[len(row) - 1] + ' '

    for i in xrange(len(row) - 1):
        conv_row = conv_row + str(i + 1) + ':' + str(row[i]) + ' '

    return conv_row

def reaData(inputfile):

    with open(inputfile, 'r') as inFile: 
        reader = csv.reader(inFile)
        my_content = list(reader)

    my_content = my_content[0:len(my_content) - 1]

    return my_content

def converToSVMLiteFormat(outputfile, train, test):

    train_file = outputfile + '_train.dat'
    test_file = outputfile + '_test.dat'
    #svm_light conversion for training data
    with open(train_file, 'wb') as txtfile:
        for i in xrange(len(train)):
            converted_row = svm_light_conversion(train[i]) + '\n'

            txtfile.write(converted_row)

    txtfile.close()

    #svm_light conversion for test data#
    with open(test_file, 'wb') as txtfile:
        for i in xrange(len(test)):
            converted_row = svm_light_conversion(test[i]) + '\n'

            txtfile.write(converted_row)

    txtfile.close()



def main():

    inputfile = sys.argv[1]
    outputfile = sys.argv[2]

    content = reaData(inputfile)

    train, test = train_test_split(content, train_size = 0.8) #split data
    converToSVMLiteFormat(outputfile, train, test)



if __name__ == "__main__":
    main()

之前它的工作非常好，但现在却突然发出错误：

(env)fieldsofgold@fieldsofgold-VirtualBox:~/new$ python prac.py data.csv outt
Traceback (most recent call last):
  File "prac.py", line 4, in <module>
    from sklearn.cross_validation import train_test_split
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/sklearn/cross_validation.py", line 32, in <module>
    from .metrics.scorer import check_scoring
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/sklearn/metrics/__init__.py", line 7, in <module>
    from .ranking import auc
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/sklearn/metrics/ranking.py", line 30, in <module>
    from ..utils.stats import rankdata
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/sklearn/utils/stats.py", line 2, in <module>
    from scipy.stats import rankdata as _sp_rankdata
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/scipy/stats/__init__.py", line 338, in <module>
    from .stats import *
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/scipy/stats/stats.py", line 189, in <module>
    from . import distributions
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/scipy/stats/distributions.py", line 10, in <module>
    from ._distn_infrastructure import (entropy, rv_discrete, rv_continuous,
  File "/home/fieldsofgold/new/env/local/lib/python2.7/site-packages/scipy/stats/_distn_infrastructure.py", line 44, in <module>
    from new import instancemethod
  File "/home/fieldsofgold/new/new.py", line 10, in <module>
    response2 = urllib2.urlopen(row[12])
  File "/usr/lib/python2.7/urllib2.py", line 127, in urlopen
    return _opener.open(url, data, timeout)
  File "/usr/lib/python2.7/urllib2.py", line 396, in open
    protocol = req.get_type()
  File "/usr/lib/python2.7/urllib2.py", line 258, in get_type
    raise ValueError, "unknown url type: %s" % self.__original
ValueError: unknown url type: 0.0

有人可以帮我解析错误吗？似乎错误发生在sklearn的某处，但我完全不明白可能出错的地方。感谢。

ValueError：未知的url类型：sklearn中的0.0错误

0 个答案: