Files
twitter_scraper/code/clean_data.py
T

9 lines
251 B
Python

from cleantext import clean
def clean_content(text):
return clean(text, to_ascii=False)
def clean_content_df(df):
content_clean = df['content'].apply(clean_content).to_list()
id_list = df['id'].to_list()
return content_clean, id_list