ERROR - qlib.workflow - [utils.py:41] - An exception has been raised[KeyError: 'PRED'].

🐛 Bug Description

cd examples && qrun .\benchmarks\Linear\workflow_config_linear_Alpha158.yaml
and it output error:
[5468:MainThread](2023-09-03 19:15:58,118) INFO - qlib.Initialization - [config.py:417] - default_conf: client.
[5468:MainThread](2023-09-03 19:15:58,124) INFO - qlib.Initialization - [init.py:74] - qlib successfully initialized based on client settings.
[5468:MainThread](2023-09-03 19:15:58,125) INFO - qlib.Initialization - [init.py:76] - data_path={'__DEFAULT_FREQ': WindowsPath('C:/Users/hsz/.qlib/qlib_data/cn_data')}
[5468:MainThread](2023-09-03 19:15:58,129) INFO - qlib.workflow - [exp.py:258] - Experiment 1 starts running ...
[5468:MainThread](2023-09-03 19:15:58,506) INFO - qlib.workflow - [recorder.py:341] - Recorder fef59cb8c44b4c2da1422e3df21ee0e3 starts running under Experiment 1 ...
[5468:MainThread](2023-09-03 19:17:10,487) INFO - qlib.timer - [log.py:128] - Time cost: 66.236s | Loading data Done
C:\Program Files\Python39\lib\site-packages\numpy\lib\nanfunctions.py:1096: RuntimeWarning: All-NaN slice encountered
result = np.apply_along_axis(_nanmedian1d, axis, a, overwrite_input)
[5468:MainThread](2023-09-03 19:17:32,525) INFO - qlib.timer - [log.py:128] - Time cost: 21.523s | RobustZScoreNorm Done
[5468:MainThread](2023-09-03 19:17:33,175) INFO - qlib.timer - [log.py:128] - Time cost: 0.648s | Fillna Done
[5468:MainThread](2023-09-03 19:17:33,604) INFO - qlib.timer - [log.py:128] - Time cost: 0.259s | DropnaLabel Done
C:\Program Files\Python39\lib\site-packages\qlib\data\dataset\processor.py:360: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
df[cols] = t
[5468:MainThread](2023-09-03 19:17:34,136) INFO - qlib.timer - [log.py:128] - Time cost: 0.531s | CSRankNorm Done
[5468:MainThread](2023-09-03 19:17:34,167) INFO - qlib.timer - [log.py:128] - Time cost: 23.679s | fit & process data Done
[5468:MainThread](2023-09-03 19:17:34,168) INFO - qlib.timer - [log.py:128] - Time cost: 89.917s | Init data Done
[5468:MainThread](2023-09-03 19:17:37,246) INFO - qlib.timer - [log.py:128] - Time cost: 0.000s | waiting async_log Done
[5468:MainThread](2023-09-03 19:17:37,253) ERROR - qlib.workflow - [utils.py:41] - An exception has been raised[KeyError: 'PRED'].
File "C:\Program Files\Python39\lib\runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Program Files\Python39\lib\runpy.py", line 87, in run_code
exec(code, run_globals)
File "C:\Program Files\Python39\Scripts\qrun.exe_main.py", line 7, in
sys.exit(run())
File "C:\Program Files\Python39\lib\site-packages\qlib\workflow\cli.py", line 115, in run
fire.Fire(workflow)
File "C:\Program Files\Python39\lib\site-packages\fire\core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "C:\Program Files\Python39\lib\site-packages\fire\core.py", line 475, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "C:\Program Files\Python39\lib\site-packages\fire\core.py", line 691, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "C:\Program Files\Python39\lib\site-packages\qlib\workflow\cli.py", line 109, in workflow
recorder = task_train(config.get("task"), experiment_name=experiment_name)
File "C:\Program Files\Python39\lib\site-packages\qlib\model\trainer.py", line 127, in task_train
exe_task(task_config)
File "C:\Program Files\Python39\lib\site-packages\qlib\model\trainer.py", line 56, in exe_task
task_config = fill_placeholder(task_config, placehorder_value)
File "C:\Program Files\Python39\lib\site-packages\qlib\utils_init.py", line 930, in fill_placeholder
now_item[key] = get_item_from_obj(config, m.groupdict()["name_path"])
File "C:\Program Files\Python39\lib\site-packages\qlib\utils_init.py", line 875, in get_item_from_obj
cur_cfg = cur_cfg[k]
KeyError: 'PRED'

To Reproduce

Steps to reproduce the behavior:

1.cd examples && qrun .\benchmarks\Linear\workflow_config_linear_Alpha158.yaml
1.
1.

Expected Behavior

Screenshot

Environment

Note: User could run cd scripts && python collect_info.py all under project directory to get system information
and paste them here directly.

• Qlib version:pyqlib-0.9.3.99
• Python version:python3.9
• OS (Windows, Linux, MacOS):Windows
• Commit number (optional, please provide it if you are using the dev version):

Additional Notes

Any workflow configuration that contains PREV will report an error.

Start with examples/benchmarks/Linear/workflow_config_linear_Alpha158.yaml and trace the PREV placeholder through qlib/model/trainer.py and qlib/utils/init.py, especially fill_placeholder and get_item_from_obj. Reproduce the command from the issue, then verify that workflow configurations containing PREV no longer fail with KeyError: 'PRED'.