gender.py 文件源码

def parse_gender(text):

    sentences = [
        [word.lower() for word in nltk.word_tokenize(sentence)]
        for sentence in nltk.sent_tokenize(text)
    ]

    sents, words = count_gender(sentences)
    total = sum(words.values())

    for gender, count in words.items():
        pcent = (count / total) * 100
        nsents = sents[gender]

        print(
            "{:0.3f}% {} ({} sentences)".format(pcent, gender, nsents)
        )