faizhalas commited on
Commit
55e3ca3
1 Parent(s): 40f34d4

remove quotation mark on text

Browse files
Files changed (1) hide show
  1. pages/2 Topic Modeling.py +1 -0
pages/2 Topic Modeling.py CHANGED
@@ -87,6 +87,7 @@ def clean_csv(extype):
87
  paper['Abstract_pre'] = paper['Abstract'].map(lambda x: re.sub('[,:;\.!-?•=]', '', x))
88
  paper['Abstract_pre'] = paper['Abstract_pre'].map(lambda x: x.lower())
89
  paper['Abstract_pre'] = paper['Abstract_pre'].map(lambda x: re.sub('©.*', '', x))
 
90
 
91
  #===stopword removal===
92
  stop = stopwords.words('english')
 
87
  paper['Abstract_pre'] = paper['Abstract'].map(lambda x: re.sub('[,:;\.!-?•=]', '', x))
88
  paper['Abstract_pre'] = paper['Abstract_pre'].map(lambda x: x.lower())
89
  paper['Abstract_pre'] = paper['Abstract_pre'].map(lambda x: re.sub('©.*', '', x))
90
+ paper['Abstract_pre'] = paper['Abstract_pre'].str.replace('\u201c|\u201d', '', regex=True)
91
 
92
  #===stopword removal===
93
  stop = stopwords.words('english')