fix_typo (#790)

Signed-off-by: unknown <lv.linlang@qq.com>

qlib/data/cache.py

@@ -359,7 +359,7 @@ class ExpressionCache(BaseProviderCache):
     def update(self, cache_uri: Union[str, Path], freq: str = "day"):
         """Update expression cache to latest calendar.
 
-        Overide this method to define how to update expression cache corresponding to users' own cache mechanism.
+        Override this method to define how to update expression cache corresponding to users' own cache mechanism.
 
         Parameters
         ----------
@@ -445,7 +445,7 @@ class DatasetCache(BaseProviderCache):
     def update(self, cache_uri: Union[str, Path], freq: str = "day"):
         """Update dataset cache to latest calendar.
 
-        Overide this method to define how to update dataset cache corresponding to users' own cache mechanism.
+        Override this method to define how to update dataset cache corresponding to users' own cache mechanism.
 
         Parameters
         ----------
@@ -543,7 +543,7 @@ class DiskExpressionCache(ExpressionCache):
                 # instance
                 series = self.provider.expression(instrument, field, _calendar[0], _calendar[-1], freq)
                 if not series.empty:
-                    # This expresion is empty, we don't generate any cache for it.
+                    # This expression is empty, we don't generate any cache for it.
                     with CacheUtils.writer_lock(self.r, f"{str(C.dpm.get_data_uri(freq))}:expression-{_cache_uri}"):
                         self.gen_expression_cache(
                             expression_data=series,
@@ -858,7 +858,7 @@ class DiskDatasetCache(DatasetCache):
         """gen_dataset_cache
 
         .. note:: This function does not consider the cache read write lock. Please
-        Aquire the lock outside this function
+        Acquire the lock outside this function
 
         The format the cache contains 3 parts(followed by typical filename).
 
@@ -1035,7 +1035,7 @@ class DiskDatasetCache(DatasetCache):
                 # FIXME:
                 # Because the feature cache are stored as .bin file.
                 # So the series read from features are all float32.
-                # However, the first dataset cache is calulated based on the
+                # However, the first dataset cache is calculated based on the
                 # raw data. So the data type may be float64.
                 # Different data type will result in failure of appending data
                 if "/{}".format(DatasetCache.HDF_KEY) in store.keys():

qlib/data/client.py

@@ -58,7 +58,7 @@ class Client:
         msg_proc_func : func
             the function to process the message when receiving response, should have arg `*args`.
         msg_queue: Queue
-            The queue to pass the messsage after callback.
+            The queue to pass the message after callback.
         """
         head_info = {"version": qlib.__version__}
 

qlib/data/data.py

@@ -16,7 +16,7 @@ from multiprocessing import Pool
 from typing import Iterable, Union
 from typing import List, Union
 
-# For supporting multiprocessing in outter code, joblib is used
+# For supporting multiprocessing in outer code, joblib is used
 from joblib import delayed
 
 from .cache import H

qlib/data/dataset/__init__.py

@@ -392,7 +392,7 @@ class TSDataSampler:
                 2021-01-14    12441    12442    12443    12444    12445    12446  ...
             2) the second element:  {<original index>: <row, col>}
         """
-        # object incase of pandas converting int to flaot
+        # object incase of pandas converting int to float
         idx_df = pd.Series(range(data.shape[0]), index=data.index, dtype=object)
         idx_df = lazy_sort_index(idx_df.unstack())
         # NOTE: the correctness of `__getitem__` depends on columns sorted here

qlib/data/dataset/handler.py

@@ -70,7 +70,7 @@ class DataHandler(Serializable):
         Parameters
         ----------
         instruments :
-            The stock list to retrive.
+            The stock list to retrieve.
         start_time :
             start_time of the original data.
         end_time :

qlib/data/dataset/processor.py

@@ -75,7 +75,7 @@ class Processor(Serializable):
 
     def readonly(self) -> bool:
         """
-        Does the processor treat the input data readonly (i.e. does not write the input data) when processsing
+        Does the processor treat the input data readonly (i.e. does not write the input data) when processing
 
         Knowning the readonly information is helpful to the Handler to avoid uncessary copy
         """

qlib/data/dataset/storage.py

@@ -63,7 +63,7 @@ class HasingStockStorage(BaseHandlerStorage):
     """Hasing data storage for datahanlder
     - The default data storage pandas.DataFrame is too slow when randomly accessing one stock's data
     - HasingStockStorage hashes the multiple stocks' data(pandas.DataFrame) by the key `stock_id`.
-    - HasingStockStorage hases the pandas.DataFrame into a dict, whose key is the stock_id(str) and value this stock data(panda.DataFrame), it has the following format:
+    - HasingStockStorage hashes the pandas.DataFrame into a dict, whose key is the stock_id(str) and value this stock data(panda.DataFrame), it has the following format:
         {
             stock1_id: stock1_data,
             stock2_id: stock2_data,