preprocess.py 文件源码

def fourterms(words, join_string):
        """
            Input: a list of words, e.g., ["I", "am", "Denny", "boy", "ha"]
            Output: a list of fourterm, e.g., ["I_am_Denny_boy", "I_am_Denny_ha", "I_am_boy_ha", "I_Denny_boy_ha", "am_Denny_boy_ha"]
        """
        assert type(words) == list
        L = len(words)
        if L > 3:
            lst = []
            for i in xrange(L - 3):
                for j in xrange(i + 1, L - 2):
                    for k in xrange(j + 1, L - 1):
                        for l in xrange(k + 1, L):
                            lst.append(join_string.join([words[i], words[j], words[k], words[l]]))
        else:
            # set it as triterm
            lst = NgramUtil.triterms(words, join_string)
        return lst