fix typo, staticmethod etc. (microsoft#1402)

* config.py: fix typo; static method

* fix typo in qlib/utils/paral

* 1) limit numpy version as numba support for 1.24+ has not been released; 2) no need to use custom numba version for pytest.

* remove useless argument

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>

qlib/config.py

@@ -75,7 +75,8 @@ def update(self, *args, **kwargs):
     def set_conf_from_C(self, config_c):
         self.update(**config_c.__dict__["_config"])
 
-    def register_from_C(self, config, skip_register=True):
+    @staticmethod
+    def register_from_C(config, skip_register=True):
         from .utils import set_log_with_config  # pylint: disable=C0415
 
         if C.registered and skip_register:
@@ -202,7 +203,7 @@ def register_from_C(self, config, skip_register=True):
         "task_url": "mongodb://localhost:27017/",
         "task_db_name": "default_task_db",
     },
-    # Shift minute for highfreq minite data, used in backtest
+    # Shift minute for highfreq minute data, used in backtest
     # if min_data_shift == 0, use default market time [9:30, 11:29, 1:00, 2:59]
     # if min_data_shift != 0, use shifted market time [9:30, 11:29, 1:00, 2:59] - shift*minute
     "min_data_shift": 0,

qlib/contrib/report/data/ana.py

@@ -139,8 +139,8 @@ def plot_single(self, col, ax):
 
 class FeaSkewTurt(NumFeaAnalyser):
     def calc_stat_values(self):
-        self._skew = datetime_groupby_apply(self._dataset, "skew", skip_group=True)
-        self._kurt = datetime_groupby_apply(self._dataset, pd.DataFrame.kurt, skip_group=True)
+        self._skew = datetime_groupby_apply(self._dataset, "skew")
+        self._kurt = datetime_groupby_apply(self._dataset, pd.DataFrame.kurt)
 
     def plot_single(self, col, ax):
         self._skew[col].plot(ax=ax, label="skew")

qlib/utils/paral.py

@@ -24,7 +24,7 @@ def __init__(self, *args, **kwargs):
 
 
 def datetime_groupby_apply(
-    df, apply_func: Union[Callable, Text], axis=0, level="datetime", resample_rule="M", n_jobs=-1, skip_group=False
+    df, apply_func: Union[Callable, Text], axis=0, level="datetime", resample_rule="M", n_jobs=-1
 ):
     """datetime_groupby_apply
     This function will apply the `apply_func` on the datetime level index.
@@ -116,7 +116,7 @@ def wrapper(self, *args, **kwargs):
 # The code are for implementing following workflow
 # - Construct complex data structure nested with delayed joblib tasks
 #      - For example,  {"job": [<delayed_joblib_task>,  {"1": <delayed_joblib_task>}]}
-# - executing all the tasks and replace all the <deplayed_joblib_task> with its return value
+# - executing all the tasks and replace all the <delayed_joblib_task> with its return value
 
 # This will make it easier to convert some existing code to a parallel one
 
@@ -160,7 +160,7 @@ class DelayedDict(DelayedTask):
     It is designed for following feature:
     Converting following existing code to parallel
     - constructing a dict
-    - key can be get instantly
+    - key can be gotten instantly
     - computation of values tasks a lot of time.
         - AND ALL the values are calculated in a SINGLE function
     """
@@ -280,7 +280,7 @@ def complex_parallel(paral: Parallel, complex_iter):
 
 class call_in_subproc:
     """
-    When we repeating run functions, it is hard to avoid memory leakage.
+    When we repeatedly run functions, it is hard to avoid memory leakage.
     So we run it in the subprocess to ensure it is OK.
 
     NOTE: Because local object can't be pickled. So we can't implement it via closure.