knock72.py 文件源码

def preprocessor_words(words):
    stopwords_set = set(stopwords.words('english'))
    stemmer = stem.LancasterStemmer()

    words_preprocessed = []
    for word in words:
        if word in stopwords_set:
            continue
        lemmatized = stemmer.stem(word)
        words_preprocessed.append(lemmatized)

    return words_preprocessed