import pandas as pd
import re
# create a sample dataframe
df = pd.DataFrame({'text': ['hello\tworld', 'hi\nthere', 'how\rare you?']})
# define a function to search for control characters and get their position
def find_control_char(string):
# search for control characters using regular expression
pattern = re.compile(r'[\x00-\x1F\x7F]')
match = pattern.search(string)
if match:
return match.start()
else:
return None
# apply the function to the dataframe
df['control_char_pos'] = df['text'].apply(find_control_char)
print(df)
No comments:
Post a Comment