Initialization is split into: set_config and config_based_on_C

qlib/__init__.py

@@ -6,88 +6,48 @@ __version__ = "0.6.0.dev"
 
 
 import os
-import re
-import sys
-import copy
 import yaml
 import logging
 import platform
 import subprocess
-from pathlib import Path
 
-from .utils import can_use_cache, init_instance_by_config, get_module_by_module_path
-from .workflow.utils import experiment_exit_handler
+from .utils import set_config, config_based_on_c
+
 
 # init qlib
 def init(default_conf="client", **kwargs):
-    from .config import C, REG_CN, REG_US, QlibConfig
-    from .data.data import register_all_wrappers
-    from .log import get_module_logger, set_log_with_config
+    from .config import C
+    from .log import get_module_logger
     from .data.cache import H
-    from .workflow import R, QlibRecorder
 
-    C.reset()
     H.clear()
 
-    _logging_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
-    LOG = get_module_logger("Initialization", level=logging.INFO)
-    LOG.info(f"default_conf: {default_conf}.")
+    logger = get_module_logger("Initialization", level=logging.INFO)
 
-    C.set_mode(default_conf)
-    C.set_region(kwargs.get("region", C["region"] if "region" in C else REG_CN))
-
-    for k, v in kwargs.items():
-        C[k] = v
-        if k not in C:
-            LOG.warning("Unrecognized config %s" % k)
-
-    C.resolve_path()
-
-    if not (C["expression_cache"] is None and C["dataset_cache"] is None):
-        # check redis
-        if not can_use_cache():
-            LOG.warning(
-                f"redis connection failed(host={C['redis_host']} port={C['redis_port']}), cache will not be used!"
-            )
-            C["expression_cache"] = None
-            C["dataset_cache"] = None
+    set_config(C, default_conf, **kwargs)
 
     # check path if server/local
-    if C.get_uri_type() == QlibConfig.LOCAL_URI:
+    if C.get_uri_type() == C.LOCAL_URI:
         if not os.path.exists(C["provider_uri"]):
             if C["auto_mount"]:
-                LOG.error(
+                logger.error(
                     f"Invalid provider uri: {C['provider_uri']}, please check if a valid provider uri has been set. This path does not exist."
                 )
             else:
-                LOG.warning(f"auto_path is False, please make sure {C['mount_path']} is mounted")
-    elif C.get_uri_type() == QlibConfig.NFS_URI:
+                logger.warning(f"auto_path is False, please make sure {C['mount_path']} is mounted")
+    elif C.get_uri_type() == C.NFS_URI:
         _mount_nfs_uri(C)
     else:
         raise NotImplementedError(f"This type of URI is not supported")
 
-    LOG.info("qlib successfully initialized based on %s settings." % default_conf)
-    register_all_wrappers()
-
-    LOG.info(f"data_path={C.get_data_path()}")
-
     if "flask_server" in C:
-        LOG.info(f"flask_server={C['flask_server']}, flask_port={C['flask_port']}")
+        logger.info(f"flask_server={C['flask_server']}, flask_port={C['flask_port']}")
 
-    # set up QlibRecorder
-    exp_manager = init_instance_by_config(C["exp_manager"])
-    qr = QlibRecorder(exp_manager)
-    R.register(qr)
-    # clean up experiment when python program ends
-    experiment_exit_handler()
+    config_based_on_c(C)
+
+    logger.info("qlib successfully initialized based on %s settings." % default_conf)
+    logger.info(f"data_path={C.get_data_path()}")
 
 
 def _mount_nfs_uri(C):

qlib/config.py

@@ -59,6 +59,9 @@ class Config:
     def update(self, *args, **kwargs):
         self.__dict__["_config"].update(*args, **kwargs)
 
+    def set_conf_from_C(self, config_c):
+        self.update(**config_c.__dict__["_config"])
+
 
 # REGION CONST
 REG_CN = "cn"

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
+from ..utils import Wrapper, init_instance_by_config, register_wrapper, get_module_by_module_path, config_based_on_c
 
 
 class CalendarProvider(abc.ABC):
@@ -481,11 +481,10 @@ 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
-        global C
-        C = g_config
         # NOTE: This place is compatible with windows, windows multi-process is spawn
         if getattr(ExpressionD, "_provider", None) is None:
-            register_all_wrappers()
+            C.set_conf_from_C(g_config)
+            config_based_on_c(g_config)
 
         obj = dict()
         for field in column_names:
@@ -1043,7 +1042,7 @@ DatasetD = Wrapper()
 D = Wrapper()
 
 
-def register_all_wrappers():
+def register_all_wrappers(C):
     """register_all_wrappers"""
     logger = get_module_logger("data")
     module = get_module_by_module_path("qlib.data")

qlib/utils/__init__.py

@@ -15,6 +15,7 @@ import bisect
 import shutil
 import difflib
 import hashlib
+import logging
 import datetime
 import requests
 import tempfile
@@ -26,8 +27,9 @@ import pandas as pd
 from pathlib import Path
 from typing import Union, Tuple
 
-from ..config import C
-from ..log import get_module_logger
+from ..config import C, REG_CN
+from ..log import get_module_logger, set_log_with_config
+
 
 log = get_module_logger("utils")
 
@@ -728,3 +730,53 @@ 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.data import register_all_wrappers
+    from ..workflow import R, QlibRecorder
+    from ..workflow.utils import experiment_exit_handler
+
+    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()