Fix pylint (#888)

* add_pylint_to_workflow

* fix-pylint

* fix_pylinterror

* fix-issue

qlib/data/dataset/__init__.py

@@ -52,7 +52,6 @@ class Dataset(Serializable):
 
         - User prepare data for model based on previous status.
         """
-        pass
 
     def prepare(self, **kwargs) -> object:
         """
@@ -68,7 +67,6 @@ class Dataset(Serializable):
         object:
             return the object
         """
-        pass
 
 
 class DatasetH(Dataset):
@@ -348,7 +346,7 @@ class TSDataSampler:
             flt_data = flt_data.reindex(self.data_index).fillna(False).astype(np.bool)
             self.flt_data = flt_data.values
             self.idx_map = self.flt_idx_map(self.flt_data, self.idx_map)
-            self.data_index = self.data_index[np.where(self.flt_data == True)[0]]
+            self.data_index = self.data_index[np.where(self.flt_data is True)[0]]
         self.idx_map = self.idx_map2arr(self.idx_map)
 
         self.start_idx, self.end_idx = self.data_index.slice_locs(

qlib/data/dataset/handler.py

@@ -2,24 +2,16 @@
 # Licensed under the MIT License.
 
 # coding=utf-8
-import abc
-import bisect
-import logging
 import warnings
-from inspect import getfullargspec
 from typing import Callable, Union, Tuple, List, Iterator, Optional
 
 import pandas as pd
-import numpy as np
 
 from ...log import get_module_logger, TimeInspector
-from ...data import D
-from ...config import C
-from ...utils import parse_config, transform_end_date, init_instance_by_config
+from ...utils import init_instance_by_config
 from ...utils.serial import Serializable
 from .utils import fetch_df_by_index, fetch_df_by_col
 from ...utils import lazy_sort_index
-from pathlib import Path
 from .loader import DataLoader
 
 from . import processor as processor_module
@@ -228,7 +220,7 @@ class DataHandler(Serializable):
         proc_func: Callable = None,
     ):
         # This method is extracted for sharing in subclasses
-        from .storage import BaseHandlerStorage
+        from .storage import BaseHandlerStorage  # pylint: disable=C0415
 
         # Following conflictions may occurs
         # - Does [20200101", "20210101"] mean selecting this slice or these two days?
@@ -627,7 +619,6 @@ class DataHandlerLP(DataHandler):
         -------
         pd.DataFrame:
         """
-        from .storage import BaseHandlerStorage
 
         return self._fetch_data(
             data_storage=self._get_df_by_key(data_key),

qlib/data/dataset/loader.py

@@ -51,7 +51,6 @@ class DataLoader(abc.ABC):
         pd.DataFrame:
             data load from the under layer source
         """
-        pass
 
 
 class DLWParser(DataLoader):
@@ -129,7 +128,6 @@ class DLWParser(DataLoader):
         pd.DataFrame:
             the queried dataframe.
         """
-        pass
 
     def load(self, instruments=None, start_time=None, end_time=None) -> pd.DataFrame:
         if self.is_group:
@@ -308,7 +306,7 @@ class DataLoaderDH(DataLoader):
             is_group will be used to describe whether the key of handler_config is group
 
         """
-        from qlib.data.dataset.handler import DataHandler
+        from qlib.data.dataset.handler import DataHandler  # pylint: disable=C0415
 
         if is_group:
             self.handlers = {

qlib/data/dataset/processor.py

@@ -42,7 +42,6 @@ class Processor(Serializable):
             processor, i.e. `df`.
 
         """
-        pass
 
     @abc.abstractmethod
     def __call__(self, df: pd.DataFrame):
@@ -57,7 +56,6 @@ class Processor(Serializable):
         df : pd.DataFrame
             The raw_df of handler or result from previous processor.
         """
-        pass
 
     def is_for_infer(self) -> bool:
         """
@@ -201,7 +199,7 @@ class MinMaxNorm(Processor):
         self.fit_end_time = fit_end_time
         self.fields_group = fields_group
 
-    def fit(self, df):
+    def fit(self, df: pd.DataFrame = None):
         df = fetch_df_by_index(df, slice(self.fit_start_time, self.fit_end_time), level="datetime")
         cols = get_group_columns(df, self.fields_group)
         self.min_val = np.nanmin(df[cols].values, axis=0)
@@ -232,7 +230,7 @@ class ZScoreNorm(Processor):
         self.fit_end_time = fit_end_time
         self.fields_group = fields_group
 
-    def fit(self, df):
+    def fit(self, df: pd.DataFrame = None):
         df = fetch_df_by_index(df, slice(self.fit_start_time, self.fit_end_time), level="datetime")
         cols = get_group_columns(df, self.fields_group)
         self.mean_train = np.nanmean(df[cols].values, axis=0)
@@ -272,7 +270,7 @@ class RobustZScoreNorm(Processor):
         self.fields_group = fields_group
         self.clip_outlier = clip_outlier
 
-    def fit(self, df):
+    def fit(self, df: pd.DataFrame = None):
         df = fetch_df_by_index(df, slice(self.fit_start_time, self.fit_end_time), level="datetime")
         self.cols = get_group_columns(df, self.fields_group)
         X = df[self.cols].values
@@ -351,6 +349,6 @@ class HashStockFormat(Processor):
     """Process the storage of from df into hasing stock format"""
 
     def __call__(self, df: pd.DataFrame):
-        from .storage import HasingStockStorage
+        from .storage import HasingStockStorage  # pylint: disable=C0415
 
         return HasingStockStorage.from_df(df)

qlib/data/dataset/storage.py

@@ -2,7 +2,7 @@ import pandas as pd
 import numpy as np
 
 from .handler import DataHandler
-from typing import Tuple, Union, List, Callable
+from typing import Union, List, Callable
 
 from .utils import get_level_index, fetch_df_by_index, fetch_df_by_col
 
@@ -109,7 +109,7 @@ class HasingStockStorage(BaseHandlerStorage):
                 stock_selector = selector[self.stock_level]
             elif isinstance(selector, (list, str)) and self.stock_level == 0:
                 stock_selector = selector
-        elif level == "instrument" or level == self.stock_level:
+        elif level in ("instrument", self.stock_level):
             if isinstance(selector, tuple):
                 stock_selector = selector[0]
             elif isinstance(selector, (list, str)):

qlib/data/dataset/utils.py

@@ -63,7 +63,7 @@ def fetch_df_by_index(
     Data of the given index.
     """
     # level = None -> use selector directly
-    if level == None:
+    if level is None:
         return df.loc(axis=0)[selector]
     # Try to get the right index
     idx_slc = (selector, slice(None, None))
@@ -75,7 +75,7 @@ def fetch_df_by_index(
                 return df.loc[
                     pd.IndexSlice[idx_slc],
                 ]
-        else:
+        else:  # pylint: disable=W0120
             return df
     else:
         return df.loc[
@@ -84,7 +84,7 @@ def fetch_df_by_index(
 
 
 def fetch_df_by_col(df: pd.DataFrame, col_set: Union[str, List[str]]) -> pd.DataFrame:
-    from .handler import DataHandler
+    from .handler import DataHandler  # pylint: disable=C0415
 
     if not isinstance(df.columns, pd.MultiIndex) or col_set == DataHandler.CS_RAW:
         return df
@@ -136,7 +136,7 @@ def init_task_handler(task: dict) -> Union[DataHandler, None]:
         returns
     """
     # avoid recursive import
-    from .handler import DataHandler
+    from .handler import DataHandler  # pylint: disable=C0415
 
     h_conf = task["dataset"]["kwargs"].get("handler")
     if h_conf is not None:

qlib/data/dataset/weight.py

@@ -1,13 +1,6 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 
-import pandas as pd
-import numpy as np
-from typing import Union, List, Tuple
-from ...data.dataset import TSDataSampler
-from ...data.dataset.utils import get_level_index
-from ...utils import lazy_sort_index
-
 
 class Reweighter:
     def __init__(self, *args, **kwargs):