contexts.py 文件源码

def tag_contexts(doc_id):

    global tags
    if not tags :
        tags = nltk.data.load("help/tagsets/upenn_tagset.pickle")

    words = defaultdict(Counter)
    count = Counter()
    for context in get_contexts(doc_id) :
        for word, tag in nltk.pos_tag(tokenize(context)) :
            words[tag].update([word])

            count.update([tag])


    tag_common_words = {tag : ' '.join(zip(*tag_words.most_common(10))[0]) for tag, tag_words in words.items() }

    for tag, freq in count.most_common(15) :
        print "%4d\t%45s\t%s" % (freq, tags[tag][0], tag_common_words[tag])