RecBole icon indicating copy to clipboard operation
RecBole copied to clipboard

关于原子数据的问题

Open lovedididi opened this issue 1 year ago • 2 comments

在运行过程中发现你们给出的原子文件处理有异常值,例如23年的亚马逊sports数据中在item文件中的price有‘-’,导致无法正常运行 报错如下: Traceback (most recent call last): File "/home/yy/.conda/envs/recbole/lib/python3.10/site-packages/pandas/io/parsers/base_parser.py", line 848, in _cast_types values = astype_array(values, cast_type, copy=True) File "/home/yy/.conda/envs/recbole/lib/python3.10/site-packages/pandas/core/dtypes/astype.py", line 182, in astype_array values = _astype_nansafe(values, dtype, copy=copy) File "/home/yy/.conda/envs/recbole/lib/python3.10/site-packages/pandas/core/dtypes/astype.py", line 133, in _astype_nansafe return arr.astype(dtype, copy=True) ValueError: could not convert string to float: '—' 当我用代码希望用None替换这个异常数据的时候,会出现另一个错误。 我的代码如下: df['price'] = df['price'].replace('-', None)

lovedididi avatar Dec 05 '24 14:12 lovedididi

这是我上面替换数据后,出现的错误。 Traceback (most recent call last): File "/home/yy/FDSA/RecBole-master/run_recbole.py", line 49, in run( File "/home/yy/FDSA/RecBole-master/recbole/quick_start/quick_start.py", line 52, in run res = run_recbole( File "/home/yy/FDSA/RecBole-master/recbole/quick_start/quick_start.py", line 129, in run_recbole dataset = create_dataset(config) File "/home/yy/FDSA/RecBole-master/recbole/data/utils.py", line 72, in create_dataset dataset = dataset_class(config) File "/home/yy/FDSA/RecBole-master/recbole/data/dataset/sequential_dataset.py", line 36, in init super().init(config) File "/home/yy/FDSA/RecBole-master/recbole/data/dataset/dataset.py", line 108, in init self._from_scratch() File "/home/yy/FDSA/RecBole-master/recbole/data/dataset/dataset.py", line 118, in _from_scratch self._load_data(self.dataset_name, self.dataset_path) File "/home/yy/FDSA/RecBole-master/recbole/data/dataset/dataset.py", line 272, in _load_data self.item_feat = self._load_user_or_item_feat( File "/home/yy/FDSA/RecBole-master/recbole/data/dataset/dataset.py", line 340, in _load_user_or_item_feat feat = self._load_feat(feat_path, source) File "/home/yy/FDSA/RecBole-master/recbole/data/dataset/dataset.py", line 462, in _load_feat field, ftype = field_type.split(":") ValueError: not enough values to unpack (expected 2, got 1)

lovedididi avatar Dec 05 '24 14:12 lovedididi

你好,请问解决了吗?我用ml-20m也有一样的问题。

Jary-lrj avatar Oct 03 '25 15:10 Jary-lrj