Merge branch 'online_srv' into online_srv_blin

qlib/data/data.py

@@ -522,6 +522,9 @@ class LocalCalendarProvider(CalendarProvider):
             # if future calendar not exists, return current calendar
             if not os.path.exists(fname):
                 get_module_logger("data").warning(f"{freq}_future.txt not exists, return current calendar!")
+                get_module_logger("data").warning(
+                    "You can get future calendar by referring to the following document: https://github.com/microsoft/qlib/blob/main/scripts/data_collector/contrib/README.md"
+                )
                 fname = self._uri_cal.format(freq)
         else:
             fname = self._uri_cal.format(freq)
@@ -1016,7 +1019,8 @@ class ClientProvider(BaseProvider):
         self.logger = get_module_logger(self.__class__.__name__)
         if isinstance(Cal, ClientCalendarProvider):
             Cal.set_conn(self.client)
-        Inst.set_conn(self.client)
+        if isinstance(Inst, ClientInstrumentProvider):
+            Inst.set_conn(self.client)
         if hasattr(DatasetD, "provider"):
             DatasetD.provider.set_conn(self.client)
         else:

qlib/data/dataset/__init__.py

@@ -27,7 +27,7 @@ class Dataset(Serializable):
         - setup data
             - The data related attributes' names should start with '_' so that it will not be saved on disk when serializing.
 
-        The data could specify the info to caculate the essential data for preparation
+        The data could specify the info to calculate the essential data for preparation
         """
         self.setup_data(**kwargs)
         super().__init__()
@@ -92,7 +92,7 @@ class DatasetH(Dataset):
         handler : Union[dict, DataHandler]
             handler could be:
 
-            - insntance of `DataHandler`
+            - instance of `DataHandler`
 
             - config of `DataHandler`.  Please refer to `DataHandler`
 
@@ -124,7 +124,7 @@ class DatasetH(Dataset):
         Parameters
         ----------
         handler_kwargs : dict
-            Config of DataHanlder, which could include the following arguments:
+            Config of DataHandler, which could include the following arguments:
 
             - arguments of DataHandler.conf_data, such as 'instruments', 'start_time' and 'end_time'.
 
@@ -148,11 +148,11 @@ class DatasetH(Dataset):
         Parameters
         ----------
         handler_kwargs : dict
-            init arguments of DataHanlder, which could include the following arguments:
+            init arguments of DataHandler, which could include the following arguments:
 
             - init_type : Init Type of Handler
 
-            - enable_cache : wheter to enable cache
+            - enable_cache : whether to enable cache
 
         """
         super().setup_data(**kwargs)
@@ -238,7 +238,7 @@ class TSDataSampler:
     (T)ime-(S)eries DataSampler
     This is the result of TSDatasetH
 
-    It works like `torch.data.utils.Dataset`, it provides a very convient interface for constructing time-series
+    It works like `torch.data.utils.Dataset`, it provides a very convenient interface for constructing time-series
     dataset based on tabular data.
 
     If user have further requirements for processing data, user could process them based on `TSDataSampler` or create
@@ -310,7 +310,7 @@ class TSDataSampler:
 
         self.start_idx, self.end_idx = self.data_index.slice_locs(start=pd.Timestamp(start), end=pd.Timestamp(end))
         self.idx_arr = np.array(self.idx_df.values, dtype=np.float64)  # for better performance
-        
+
         del self.data  # save memory
 
     @staticmethod
@@ -472,7 +472,7 @@ class TSDatasetH(DatasetH):
     (T)ime-(S)eries Dataset (H)andler
 
 
-    Covnert the tabular data to Time-Series data
+    Convert the tabular data to Time-Series data
 
     Requirements analysis
 

qlib/data/dataset/handler.py

@@ -36,7 +36,7 @@ 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 be implied in the data).
+    Any order of the index level can be supported (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:
@@ -77,7 +77,7 @@ class DataHandler(Serializable):
         data_loader : Tuple[dict, str, DataLoader]
             data loader to load the data.
         init_data :
-            intialize the original data in the constructor.
+            initialize the original data in the constructor.
         fetch_orig : bool
             Return the original data instead of copy if possible.
         """
@@ -128,7 +128,7 @@ class DataHandler(Serializable):
 
     def setup_data(self, enable_cache: bool = False):
         """
-        Set Up the data in case of running intialization for multiple time
+        Set Up the data in case of running initialization for multiple time
 
         It is responsible for maintaining following variable
         1) self._data
@@ -453,7 +453,7 @@ class DataHandlerLP(DataHandler):
 
     def setup_data(self, init_type: str = IT_FIT_SEQ, **kwargs):
         """
-        Set up the data in case of running intialization for multiple time
+        Set up the data in case of running initialization for multiple time
 
         Parameters
         ----------

qlib/data/dataset/processor.py

@@ -130,7 +130,7 @@ class FilterCol(Processor):
 
 
 class TanhProcess(Processor):
-    """ Use tanh to process noise data"""
+    """Use tanh to process noise data"""
 
     def __call__(self, df):
         def tanh_denoise(data):
@@ -145,7 +145,7 @@ class TanhProcess(Processor):
 
 
 class ProcessInf(Processor):
-    """Process infinity  """
+    """Process infinity"""
 
     def __call__(self, df):
         def replace_inf(data):