def load_data_from_file()

in recommenders/models/deeprec/io/sequential_iterator.py [0:0]

• 90 lines of code
• 10 McCabe index (conditional complexity)

    def load_data_from_file(self, infile, batch_num_ngs=0, min_seq_length=1):
        """Read and parse data from a file.

        Args:
            infile (str): Text input file. Each line in this file is an instance.
            batch_num_ngs (int): The number of negative sampling here in batch.
                0 represents that there is no need to do negative sampling here.
            min_seq_length (int): The minimum number of a sequence length.
                Sequences with length lower than min_seq_length will be ignored.

        Yields:
            object: An iterator that yields parsed results, in the format of graph `feed_dict`.
        """
        label_list = []
        user_list = []
        item_list = []
        item_cate_list = []
        item_history_batch = []
        item_cate_history_batch = []
        time_list = []
        time_diff_list = []
        time_from_first_action_list = []
        time_to_now_list = []

        cnt = 0

        if infile not in self.iter_data:
            lines = self.parse_file(infile)
            self.iter_data[infile] = lines
        else:
            lines = self.iter_data[infile]

        if batch_num_ngs > 0:
            random.shuffle(lines)

        for line in lines:
            if not line:
                continue

            (
                label,
                user_id,
                item_id,
                item_cate,
                item_history_sequence,
                item_cate_history_sequence,
                current_time,
                time_diff,
                time_from_first_action,
                time_to_now,
            ) = line
            if len(item_history_sequence) < min_seq_length:
                continue

            label_list.append(label)
            user_list.append(user_id)
            item_list.append(item_id)
            item_cate_list.append(item_cate)
            item_history_batch.append(item_history_sequence)
            item_cate_history_batch.append(item_cate_history_sequence)
            time_list.append(current_time)
            time_diff_list.append(time_diff)
            time_from_first_action_list.append(time_from_first_action)
            time_to_now_list.append(time_to_now)

            cnt += 1
            if cnt == self.batch_size:
                res = self._convert_data(
                    label_list,
                    user_list,
                    item_list,
                    item_cate_list,
                    item_history_batch,
                    item_cate_history_batch,
                    time_list,
                    time_diff_list,
                    time_from_first_action_list,
                    time_to_now_list,
                    batch_num_ngs,
                )
                batch_input = self.gen_feed_dict(res)
                yield batch_input if batch_input else None
                label_list = []
                user_list = []
                item_list = []
                item_cate_list = []
                item_history_batch = []
                item_cate_history_batch = []
                time_list = []
                time_diff_list = []
                time_from_first_action_list = []
                time_to_now_list = []
                cnt = 0
        if cnt > 0:
            res = self._convert_data(
                label_list,
                user_list,
                item_list,
                item_cate_list,
                item_history_batch,
                item_cate_history_batch,
                time_list,
                time_diff_list,
                time_from_first_action_list,
                time_to_now_list,
                batch_num_ngs,
            )
            batch_input = self.gen_feed_dict(res)
            yield batch_input if batch_input else None