utils.py 文件源码

def lemmatizer(text):
    # '''Description: This function takes in the string of descriptions and return string with all words lemmatized
    #   Parameters: String of descriptions
    #   Output: String with all words lemmatized (ex. "meeting" to "meeting" if noun and "meet" if verb)'''
    lemmatizer = WordNetLemmatizer()
    lis = unicode(str(text), 'utf-8').split(" ")
    lemm_words = [lemmatizer.lemmatize(word) for word in lis]
    return " ".join(lemm_words)