graph_of_words.py 文件源码

def clean_terms(terms, stopwords=None, lemmatize=None, stem=None, only_N_J=None):
    if stopwords is not None:
        terms = [t for t in terms if t not in stopwords]
    if only_N_J is not None:  # include only nouns and verbs
        tagged = nltk.pos_tag(terms)
        terms = [t for t, pos in tagged if pos in tags]
    if lemmatize is not None:
        lem = WordNetLemmatizer()
        terms = [lem.lemmatize(t) for t in terms]
    if stem is not None:
        stem = PorterStemmer()
        terms = [stem.stem(t) for t in terms]
    return terms