Question

我有下面的代码找到并替换。我试图调试代码，但我找不到任何帮助。

import pandas as pd
import re

##### Build test set of sentences to be cleaned
#dataframe to be cleaned
dat = pd.read_csv("H:\\Find Replace Tool\\Find_Replace_in_this_v1.csv")
#clean
dat.currentTitle=dat.currentTitle.str.replace(r"[^a-zA-Z0-9`~!|@#%&_}={:\"\];<>,./. -]",r'')
dat.currentTitle=dat.currentTitle.str.replace('\s+', ' ')
dat.currentTitle=dat.currentTitle.str.lower()
#create list of column
test_sentences = dat.currentTitle.tolist()

##### Create search and replace patterns
#list element of of each row like this [('word0','repl0'),('word1','repl1'),('word2','repl2')]
#dataframe with lookup
dat2 = pd.read_csv("H:\\Find Replace Tool\\Find_Replace_v1.csv")

patterns = list(zip(dat2.keyword, dat2.lookupId))
#convert list into dictionary
patterns_dict = dict(patterns)
#for value of first and second column in the list: return (first_column with regex) and second_column
patterns_comp = [ (re.compile("\\b"+search+"\\b"), repl) for search, repl in patterns ]
del dat2

def replace4( sentences ):
    #pass dictionary index to get value. not sure what is done here
    pd = patterns_dict.get
    #m could be group of all regex matches
    def repl(m):
        #group() is used for assigning out of many regex, which one you want to use
        w = m.group()
        return pd(w,w)
    for n, sentence in enumerate( sentences ):
        sentence = re.sub(r"\w+", repl, sentence)
    dat['cleanedTitle'] = sentence

replace4(test_sentences)

当我执行此操作时，我遇到错误。可能是什么原因，我该如何解决？我还没有找到任何解决方案

error                                     Traceback (most recent call last)
<ipython-input-104-43c08b4ceffa> in <module>()
      2 #for value of first and second column in the list: return (first_column with regex) and second_column
      3 for search, repl in patterns:
----> 4     a = (re.compile(r'\b'+ search + r'\b'), repl)
      5     #if j <5:
      6         #print search,repl

c:\python27\lib\re.pyc in compile(pattern, flags)
    192 def compile(pattern, flags=0):
    193     "Compile a regular expression pattern, returning a pattern object."
--> 194     return _compile(pattern, flags)
    195 
    196 def purge():

c:\python27\lib\re.pyc in _compile(*key)
    249         p = sre_compile.compile(pattern, flags)
    250     except error, v:
--> 251         raise error, v # invalid expression
    252     if not bypass_cache:
    253         if len(_cache) >= _MAXCACHE:

error: unbalanced parenthesis

Python中的不平衡括号错误

0 个答案: