Update repr for dataset/workflow classes and add uri kwarg for QlibRecorder

.gitignore

@@ -34,3 +34,5 @@ tags
 
 .pytest_cache/
 .vscode/
+
+*.swp

qlib/data/dataset/__init__.py

@@ -1,5 +1,5 @@
 from ...utils.serial import Serializable
-from typing import Union, List, Tuple
+from typing import Union, List, Tuple, Dict, Text, Optional
 from ...utils import init_instance_by_config, np_ffill
 from ...log import get_module_logger
 from .handler import DataHandler, DataHandlerLP
@@ -76,7 +76,7 @@ class DatasetH(Dataset):
     - The processing is related to data split.
     """
 
-    def __init__(self, handler: Union[dict, DataHandler], segments: dict):
+    def __init__(self, handler: Union[Dict, DataHandler], segments: Dict):
         """
         Parameters
         ----------
@@ -87,7 +87,7 @@ def __init__(self, handler: Union[dict, DataHandler], segments: dict):
         """
         super().__init__(handler, segments)
 
-    def init(self, handler_kwargs: dict = None, segment_kwargs: dict = None):
+    def init(self, handler_kwargs: Optional[Dict] = None, segment_kwargs: Optional[Dict] = None):
         """
         Initialize the DatasetH
 
@@ -124,7 +124,7 @@ def init(self, handler_kwargs: dict = None, segment_kwargs: dict = None):
                 raise TypeError(f"param handler_kwargs must be type dict, not {type(segment_kwargs)}")
             self.segments = segment_kwargs.copy()
 
-    def setup_data(self, handler: Union[dict, DataHandler], segments: dict):
+    def setup_data(self, handler: Union[Dict, DataHandler], segments: Dict[Text, Tuple]):
         """
         Setup the underlying data.
 
@@ -156,6 +156,11 @@ def setup_data(self, handler: Union[dict, DataHandler], segments: dict):
         self.handler = init_instance_by_config(handler, accept_types=DataHandler)
         self.segments = segments.copy()
 
+    def __repr__(self):
+        return "{name}(handler={handler}, segments={segments})".format(
+            name=self.__class__.__name__, handler=self.handler, segments=self.segments
+        )
+
     def _prepare_seg(self, slc: slice, **kwargs):
         """
         Give a slice, retrieve the according data
@@ -168,7 +173,7 @@ def _prepare_seg(self, slc: slice, **kwargs):
 
     def prepare(
         self,
-        segments: Union[List[str], Tuple[str], str, slice],
+        segments: Union[List[Text], Tuple[Text], Text, slice],
         col_set=DataHandler.CS_ALL,
         data_key=DataHandlerLP.DK_I,
         **kwargs,
@@ -178,7 +183,7 @@ def prepare(
 
         Parameters
         ----------
-        segments : Union[List[str], Tuple[str], str, slice]
+        segments : Union[List[Text], Tuple[Text], Text, slice]
             Describe the scope of the data to be prepared
             Here are some examples:
 

qlib/data/dataset/handler.py

@@ -35,7 +35,7 @@ class DataHandler(Serializable):
     The data handler try to maintain a handler with 2 level.
     `datetime` & `instruments`.
 
-    Any order of the index level can be suported(The order will implied in the data).
+    Any order of the index level can be suported (The order will be implied in the data).
     The order  <`datetime`, `instruments`> will be used when the dataframe index name is missed.
 
     Example of the data:
@@ -47,8 +47,8 @@ class DataHandler(Serializable):
                                 $close     $volume  Ref($close, 1)  Mean($close, 3)  $high-$low  LABEL0
         datetime   instrument
         2010-01-04 SH600000    81.807068  17145150.0       83.737389        83.016739    2.741058  0.0032
-                SH600004    13.313329  11800983.0       13.313329        13.317701    0.183632  0.0042
-                SH600005    37.796539  12231662.0       38.258602        37.919757    0.970325  0.0289
+                   SH600004    13.313329  11800983.0       13.313329        13.317701    0.183632  0.0042
+                   SH600005    37.796539  12231662.0       38.258602        37.919757    0.970325  0.0289
 
     """
 

qlib/workflow/__init__.py

@@ -16,8 +16,11 @@ class QlibRecorder:
     def __init__(self, exp_manager):
         self.exp_manager = exp_manager
 
+    def __repr__(self):
+        return "{name}(manager={manager})".format(name=self.__class__.__name__, manager=self.exp_manager)
+
     @contextmanager
-    def start(self, experiment_name=None, recorder_name=None):
+    def start(self, experiment_name=None, recorder_name=None, uri=None):
         """
         Method to start an experiment. This method can only be called within a Python's `with` statement. Here is the example code:
 
@@ -34,8 +37,11 @@ def start(self, experiment_name=None, recorder_name=None):
             name of the experiment one wants to start.
         recorder_name : str
             name of the recorder under the experiment one wants to start.
+        uri : str
+            the tracking uri of the experiment, where all the artifacts/metrics etc. will be stored.
+            The default uri are set in the qlib.config.
         """
-        run = self.start_exp(experiment_name, recorder_name)
+        run = self.start_exp(experiment_name, recorder_name, uri)
         try:
             yield run
         except Exception as e:

qlib/workflow/expm.py

@@ -25,6 +25,9 @@ def __init__(self, uri, default_exp_name):
         self.default_exp_name = default_exp_name
         self.active_experiment = None  # only one experiment can active each time
 
+    def __repr__(self):
+        return "{name}(uri={uri})".format(name=self.__class__.__name__, uri=self.uri)
+
     def start_exp(self, experiment_name=None, recorder_name=None, uri=None, **kwargs):
         """
         Start an experiment. This method includes first get_or_create an experiment, and then