utils.py 文件源码

def nonenglish(string):
    # '''Description: This function takes in the string of descriptions and return the string with nonenglish words removed (useful for course syllabi)
    #   Parameters: String of descriptions
    #   Output: the string with nonenglish words removed'''
    words = set(nltk.corpus.words.words())
    result=[w for w in nltk.wordpunct_tokenize(string) if w.lower() in words]
    return " ".join(result)