preprocess.py 文件源码

def triterms(words, join_string):
        """
            Input: a list of words, e.g., ["I", "am", "Denny", "boy"]
            Output: a list of triterm, e.g., ["I_am_Denny", "I_am_boy", "I_Denny_boy", "am_Denny_boy"]
        """
        assert type(words) == list
        L = len(words)
        if L > 2:
            lst = []
            for i in xrange(L - 2):
                for j in xrange(i + 1, L - 1):
                    for k in xrange(j + 1, L):
                        lst.append(join_string.join([words[i], words[j], words[k]]))
        else:
            # set it as biterm
            lst = NgramUtil.biterms(words, join_string)
        return lst