commented code

This commit is contained in:
simplypower-bbj
2023-01-09 19:03:56 +01:00
parent 759e7ed7f1
commit 7b29fb0005
+4 -3
View File
@@ -1,12 +1,13 @@
# public packages
from cleantext import clean from cleantext import clean
def clean_content(text): def clean_content(text):
return clean(text, to_ascii=False) return clean(text, to_ascii=False) # avoid ascii, as it does not have æ,ø,å
def clean_content_df(df): def clean_content_df(df):
content_clean = df['content'].apply(clean_content).to_list() content_clean_list = df['content'].apply(clean_content).to_list()
id_list = df['id'].to_list() id_list = df['id'].to_list()
return content_clean, id_list return content_clean_list, id_list
def clean_content_en(text_list): def clean_content_en(text_list):
text_list_clean = list() text_list_clean = list()