TIME_FIELD: timestamp # (str) Field name of timestamp feature.
seq_len: ~ # (dict) Field name of sequence feature: maximum length of each sequence
threshold: ~ # (dict) 0/1 labels will be generated according to the pairs.
NEGPREFIX: neg # (str) Negative sampling prefix for pair-wise dataLoaders.
Sequential Model Needed
LIST_SUFFIX: _list # (str) Suffix of field names which are generated as sequences.
MAX_ITEM_LIST_LENGTH: 50 # (int) Maximum length of each generated sequence.
POSITION_FIELD: position_id # (str) Field name of the generated position sequence.
load_col: # (dict) The suffix of atomic files: (list) field names to be loaded.
inter: [user_id, product_id, timestamp]
item: [product_id, genres]
selected_features: [genres]
**报错内容**
Traceback (most recent call last):
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py", line 795, in _next_iter_line
line = next(self.data)
_csv.Error: ' ' expected after '"'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "run_recbole.py", line 46, in <module>
run(
File "/home/yxy/RecBole-master/recbole/quick_start/quick_start.py", line 52, in run
res = run_recbole(
File "/home/yxy/RecBole-master/recbole/quick_start/quick_start.py", line 129, in run_recbole
dataset = create_dataset(config)
File "/home/yxy/RecBole-master/recbole/data/utils.py", line 72, in create_dataset
dataset = dataset_class(config)
File "/home/yxy/RecBole-master/recbole/data/dataset/sequential_dataset.py", line 36, in __init__
super().__init__(config)
File "/home/yxy/RecBole-master/recbole/data/dataset/dataset.py", line 109, in __init__
self._from_scratch()
File "/home/yxy/RecBole-master/recbole/data/dataset/dataset.py", line 119, in _from_scratch
self._load_data(self.dataset_name, self.dataset_path)
File "/home/yxy/RecBole-master/recbole/data/dataset/dataset.py", line 273, in _load_data
self.item_feat = self._load_user_or_item_feat(
File "/home/yxy/RecBole-master/recbole/data/dataset/dataset.py", line 341, in _load_user_or_item_feat
feat = self._load_feat(feat_path, source)
File "/home/yxy/RecBole-master/recbole/data/dataset/dataset.py", line 487, in _load_feat
df = pd.read_csv(
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 912, in read_csv
return _read(filepath_or_buffer, kwds)
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 583, in _read
return parser.read(nrows)
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 1704, in read
) = self._engine.read( # type: ignore[attr-defined]
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py", line 251, in read
content = self._get_lines(rows)
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py", line 1130, in _get_lines
new_row = self._next_iter_line(row_num=self.pos + rows + 1)
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py", line 824, in _next_iter_line
self._alert_malformed(msg, row_num)
File "/home/yxy/miniconda3/envs/yxy/lib/python3.8/site-packages/pandas/io/parsers/python_parser.py", line 774, in _alert_malformed
raise ParserError(msg)
pandas.errors.ParserError: ' ' expected after '"'
描述这个 bug 我想在steam数据集上运行FDSA模型,steam.item文件读取错误
如何复现 复现这个 bug 的步骤:
user_inter_num_interval: "[5,inf)" item_inter_num_interval: "[5,inf)"
TIME_FIELD: timestamp # (str) Field name of timestamp feature. seq_len: ~ # (dict) Field name of sequence feature: maximum length of each sequence threshold: ~ # (dict) 0/1 labels will be generated according to the pairs. NEGPREFIX: neg # (str) Negative sampling prefix for pair-wise dataLoaders.
Sequential Model Needed
LIST_SUFFIX: _list # (str) Suffix of field names which are generated as sequences. MAX_ITEM_LIST_LENGTH: 50 # (int) Maximum length of each generated sequence.
POSITION_FIELD: position_id # (str) Field name of the generated position sequence.
load_col: # (dict) The suffix of atomic files: (list) field names to be loaded. inter: [user_id, product_id, timestamp] item: [product_id, genres] selected_features: [genres]