utils.py 文件源码

def master_clean(df, column, html, email, punc, non_ascii, stopwords, number, remove_nonenglish, stemorlem):
    if punc:
        df[column] = df[column].apply(remove_punc).to_frame()
    if html:
        df[column] = df[column].apply(remove_html).to_frame()
    if email:
        df[column] = df[column].apply(remove_email).to_frame()
    if non_ascii:
        df[column] = df[column].apply(remove_non_ascii).to_frame()
    if stopwords:
        df[column] = df[column].apply(remove_stop).to_frame()
    if number:
        df[column] = df[column].apply(remove_numbers).to_frame()
    if nonenglish:
        df[column] = df[column].apply(nonenglish).to_frame()
    if stemorlem == 'stem':
        df[column] = df[column].apply(stemmer).to_frame()
    elif stemorlem == 'lem':
        df[column] = df[column].apply(lemmatizer).to_frame()

    return df