有没有办法在NLTK中交换依赖于检测到的语言的语料库？

Question

我已经得到了以下脚本，它将根据停用词的数量来检测语言。然后，它将调用另一个脚本进行标记。但是，我似乎无法弄清楚如何交换正在加载的语料库（目前是它的棕色）：

tagger = UnigramTagger(nltk.corpus.brown.tagged_sents())，具体取决于检测到的语言。有没有我可以打电话的方法？或者是在初始设置时打开输入，还是为每种语言设置了多个进程？

＃！/ usr / bin / env python     #coding：UTF_8

"""
Imports
"""
import sys
import getopt
import socket
import select
import pprint
import json
import subprocess

try:
    from nltk import wordpunct_tokenize
    from nltk.tag import UnigramTagger
    from nltk.corpus import stopwords
except ImportError:
    print '[!] Missing NLTK packages. Attempting to install. This may take a while!'
    subprocess.call('python scripts/SetupNltk.py', shell=True)

"""
Globals
"""

"""
Definitions
"""
def _calculate_languages_ratio(text):
    languages_ratios = {}
    tokens = wordpunct_tokenize(text)
    words = [word.lower() for word in tokens]
    for language in stopwords.fileids():
        stopwords_set = set(stopwords.words(language))
        words_set = set(words)
        common_elements = words_set.intersection(stopwords_set)
        languages_ratios[language] = len(common_elements)

    return languages_ratios


def detect_language(text):
    ratios = _calculate_languages_ratio(text)
    return max(ratios, key=ratios.get)


"""
Main entry point
"""
if __name__ == '__main__':
    language = detect_language(text)
    print language