added functions to clean content

code/clean_data.py

@@ -0,0 +1,9 @@
+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