DoJerryChen
commented
4 months ago 解决了 数据格式是 user_id Item_id yaml里面是field_separator: "\t" 粗心了 改成field_separator: " " 就解决了
Open DoJerryChen opened 4 months ago
DoJerryChen
commented
4 months ago 解决了 数据格式是 user_id Item_id yaml里面是field_separator: "\t" 粗心了 改成field_separator: " " 就解决了
yunshanlucky
commented
2 months ago @DoJerryChen ，请问您是用自己的数据集然后转化为KG的形式嘛，由于网络相应的学习资源匮乏，能否请教下具体转化的详细操作，非常感谢并期待您的回复
目前进行的研究是对数据集进行处理，需要应用到大量的基础模型进行测试数据集 但是转换成原子文件后还是不能运行 转换后atuo数据格式如 user_id Item_id 随机生成的时间戳 运行报错为 dataset = create_dataset(config) File "F:\Anaconda\envs\recbole\lib\site-packages\recbole\data\utils.py", line 70, in create_dataset dataset = dataset_class(config) File "F:\Anaconda\envs\recbole\lib\site-packages\recbole\data\dataset\dataset.py", line 108, in init self._from_scratch() File "F:\Anaconda\envs\recbole\lib\site-packages\recbole\data\dataset\dataset.py", line 118, in _from_scratch self._load_data(self.dataset_name, self.dataset_path) File "F:\Anaconda\envs\recbole\lib\site-packages\recbole\data\dataset\dataset.py", line 268, in _load_data self._load_inter_feat(token, dataset_path) File "F:\Anaconda\envs\recbole\lib\site-packages\recbole\data\dataset\dataset.py", line 295, in _load_inter_feat inter_feat = self._load_feat(inter_feat_path, FeatureSource.INTERACTION) File "F:\Anaconda\envs\recbole\lib\site-packages\recbole\data\dataset\dataset.py", line 462, in _load_feat field, ftype = field_type.split(":") ValueError: too many values to unpack (expected 2)
求帮助