add register in config

qlib/__init__.py

@@ -11,8 +11,6 @@ import logging
 import platform
 import subprocess
 
-from .utils import set_config, config_based_on_c
-
 
 # init qlib
 def init(default_conf="client", **kwargs):
@@ -25,7 +23,7 @@ def init(default_conf="client", **kwargs):
     # FIXME: this logger ignored the level in config
     logger = get_module_logger("Initialization", level=logging.INFO)
 
-    set_config(C, default_conf, **kwargs)
+    C.set(default_conf, **kwargs)
 
     # check path if server/local
     if C.get_uri_type() == C.LOCAL_URI:
@@ -44,7 +42,7 @@ def init(default_conf="client", **kwargs):
     if "flask_server" in C:
         logger.info(f"flask_server={C['flask_server']}, flask_port={C['flask_port']}")
 
-    config_based_on_c(C)
+    C.register()
 
     logger.info("qlib successfully initialized based on %s settings." % default_conf)
     logger.info(f"data_path={C.get_data_path()}")

qlib/config.py

@@ -11,11 +11,12 @@ Two modes are supported
 
 """
 
-import copy
-from pathlib import Path
-import re
 import os
+import re
+import copy
+import logging
 import multiprocessing
+from pathlib import Path
 
 
 class Config:
@@ -212,6 +213,10 @@ class QlibConfig(Config):
     LOCAL_URI = "local"
     NFS_URI = "nfs"
 
+    def __init__(self, default_conf):
+        super().__init__(default_conf)
+        self._registered = False
+
     def set_mode(self, mode):
         # raise KeyError
         self.update(MODE_CONF[mode])
@@ -248,6 +253,64 @@ class QlibConfig(Config):
         else:
             raise NotImplementedError(f"This type of uri is not supported")
 
+    def set(self, default_conf="client", **kwargs):
+        from .utils import set_log_with_config, get_module_logger, can_use_cache
+
+        self.reset()
+
+        _logging_config = self.logging_config
+        if "logging_config" in kwargs:
+            _logging_config = kwargs["logging_config"]
+
+        # set global config
+        if _logging_config:
+            set_log_with_config(_logging_config)
+
+        # FIXME: this logger ignored the level in config
+        logger = get_module_logger("Initialization", level=logging.INFO)
+        logger.info(f"default_conf: {default_conf}.")
+
+        self.set_mode(default_conf)
+        self.set_region(kwargs.get("region", self["region"] if "region" in self else REG_CN))
+
+        for k, v in kwargs.items():
+            if k not in self:
+                logger.warning("Unrecognized config %s" % k)
+            self[k] = v
+
+        self.resolve_path()
+
+        if not (self["expression_cache"] is None and self["dataset_cache"] is None):
+            # check redis
+            if not can_use_cache():
+                logger.warning(
+                    f"redis connection failed(host={self['redis_host']} port={self['redis_port']}), cache will not be used!"
+                )
+                self["expression_cache"] = None
+                self["dataset_cache"] = None
+
+    def register(self):
+        from .utils import init_instance_by_config
+        from .data.ops import register_custom_ops
+        from .data.data import register_all_wrappers
+        from .workflow import R, QlibRecorder
+        from .workflow.utils import experiment_exit_handler
+
+        register_custom_ops(self)
+        register_all_wrappers(self)
+        # set up QlibRecorder
+        exp_manager = init_instance_by_config(self["exp_manager"])
+        qr = QlibRecorder(exp_manager)
+        R.register(qr)
+        # clean up experiment when python program ends
+        experiment_exit_handler()
+
+        self._registered = True
+
+    @property
+    def registered(self):
+        return self._registered
+
 
 # global config
 C = QlibConfig(_default_config)

qlib/data/data.py

@@ -25,7 +25,7 @@ from ..log import get_module_logger
 from ..utils import parse_field, read_bin, hash_args, normalize_cache_fields
 from .base import Feature
 from .cache import DiskDatasetCache, DiskExpressionCache
-from ..utils import Wrapper, init_instance_by_config, register_wrapper, get_module_by_module_path, config_based_on_c
+from ..utils import Wrapper, init_instance_by_config, register_wrapper, get_module_by_module_path
 
 
 class CalendarProvider(abc.ABC):
@@ -486,9 +486,9 @@ class DatasetProvider(abc.ABC):
         """
         # FIXME: Windows OS or MacOS using spawn: https://docs.python.org/3.8/library/multiprocessing.html?highlight=spawn#contexts-and-start-methods
         # NOTE: This place is compatible with windows, windows multi-process is spawn
-        if getattr(ExpressionD, "_provider", None) is None:
+        if not C.registered:
             C.set_conf_from_C(g_config)
-            config_based_on_c(g_config)
+            C.register()
 
         obj = dict()
         for field in column_names:

qlib/utils/__init__.py

@@ -744,55 +744,3 @@ def load_dataset(path_or_obj):
     elif extension == ".csv":
         return pd.read_csv(path_or_obj, parse_dates=True, index_col=[0, 1])
     raise ValueError(f"unsupported file type `{extension}`")
-
-
-def set_config(config_c, default_conf="client", **kwargs):
-
-    config_c.reset()
-
-    _logging_config = config_c.logging_config
-    if "logging_config" in kwargs:
-        _logging_config = kwargs["logging_config"]
-
-    # set global config
-    if _logging_config:
-        set_log_with_config(_logging_config)
-
-    # FIXME: this logger ignored the level in config
-    logger = get_module_logger("Initialization", level=logging.INFO)
-    logger.info(f"default_conf: {default_conf}.")
-
-    config_c.set_mode(default_conf)
-    config_c.set_region(kwargs.get("region", config_c["region"] if "region" in config_c else REG_CN))
-
-    for k, v in kwargs.items():
-        if k not in config_c:
-            logger.warning("Unrecognized config %s" % k)
-        config_c[k] = v
-
-    config_c.resolve_path()
-
-    if not (config_c["expression_cache"] is None and config_c["dataset_cache"] is None):
-        # check redis
-        if not can_use_cache():
-            logger.warning(
-                f"redis connection failed(host={config_c['redis_host']} port={config_c['redis_port']}), cache will not be used!"
-            )
-            config_c["expression_cache"] = None
-            config_c["dataset_cache"] = None
-
-
-def config_based_on_c(config_c):
-    from ..data.ops import register_custom_ops
-    from ..data.data import register_all_wrappers
-    from ..workflow import R, QlibRecorder
-    from ..workflow.utils import experiment_exit_handler
-
-    register_custom_ops(config_c)
-    register_all_wrappers(config_c)
-    # set up QlibRecorder
-    exp_manager = init_instance_by_config(config_c["exp_manager"])
-    qr = QlibRecorder(exp_manager)
-    R.register(qr)
-    # clean up experiment when python program ends
-    experiment_exit_handler()