add ops_warning_log to config (#685)

examples/data_demo/data_cache_demo.py

@@ -40,13 +40,13 @@ if __name__ == "__main__":
     # 3) create new task with handler cache
     new_task_config = deepcopy(task_config)
     new_task_config["task"]["dataset"]["kwargs"]["handler"] = f"file://{hd_path}"
-    new_task_config
+    new_task_config["sys"] = {"path": [str(config_path.parent.resolve())]}
     new_task_path = DIRNAME / "new_task.yaml"
     print("The location of the new task", new_task_path)
 
     # save new task
     with new_task_path.open("w") as f:
-        yaml.safe_dump(new_task_config, f)
+        yaml.safe_dump(new_task_config, f, indent=4, sort_keys=False)
 
     # 4) train model with new task
     with TimeInspector.logt("The time for task with handler cache:"):

qlib/config.py

@@ -176,6 +176,8 @@ _default_config = {
     # if min_data_shift == 0, use default market time [9:30, 11:29, 1:00, 2:59]
     # if min_data_shift != 0, use shifted market time [9:30, 11:29, 1:00, 2:59] - shift*minute
     "min_data_shift": 0,
+    # whether to display the ops warning log, default False
+    "ops_warning_log": False,
 }
 
 MODE_CONF = {

qlib/data/data.py

@@ -38,6 +38,7 @@ from ..utils import (
     hash_args,
     normalize_cache_fields,
     code_to_fname,
+    set_log_with_config,
 )
 from ..utils.paral import ParallelExt
 
@@ -586,6 +587,8 @@ class DatasetProvider(abc.ABC):
         # NOTE: This place is compatible with windows, windows multi-process is spawn
         if not C.registered:
             C.set_conf_from_C(g_config)
+            if C.logging_config:
+                set_log_with_config(C.logging_config)
             C.register()
 
         obj = dict()

qlib/data/ops.py

@@ -14,6 +14,8 @@ from typing import Union, List, Type
 from scipy.stats import percentileofscore
 
 from .base import Expression, ExpressionOps, Feature
+
+from ..config import C
 from ..log import get_module_logger
 from ..utils import get_callable_kwargs
 
@@ -325,7 +327,7 @@ class NpPairOperator(PairOperator):
             get_module_logger("ops").error(warning_info)
             raise ValueError(f"{str(e)}. \n\t{warning_info}")
         else:
-            if check_length and len(series_left) != len(series_right):
+            if check_length and len(series_left) != len(series_right) and C.ops_warning_log:
                 get_module_logger("ops").warning(warning_info)
         return res