data2tensor.py 文件源码

def __generate_tensor(self, is_review, reverse=False):
        """

        :param is_review:
        :param reverse:
        :return:
        """
        seq_length = self.review_max_words if is_review else self.summary_max_words
        total_rev_summary_pairs = self.rev_sum_pair.shape[0]
        data_tensor = np.zeros([total_rev_summary_pairs,seq_length])

        sample = self.rev_sum_pair[0::, 0] if is_review else self.rev_sum_pair[0::, 1]

        for index, entry in enumerate(sample.tolist()):
            index_lst = np.array([self.map[word.lower()] for word in wordpunct_tokenize(entry)])
            # reverse if want to get backward form
            if reverse:
                index_lst = index_lst[::-1]
            # Pad the list
            if len(index_lst) <= seq_length:
                index_lst = np.lib.pad(index_lst, (0,seq_length - index_lst.size), 'constant', constant_values=(0, 0))
            else:
                index_lst = index_lst[0:seq_length]

            data_tensor[index] = index_lst

        return data_tensor