liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-17 01:14:35 +08:00
Code Activity

[930] Fix typo HasingStockStorage to HashingStockStorage. (#947)

Browse Source
This commit is contained in:
Chia-hung Tai
2022-03-04 12:40:04 +08:00
committed by GitHub
parent ea4fb33ff2
commit 07f0d4f599
4 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
qlib/data/dataset/handler.py
View File

@@ -257,7 +257,7 @@ class DataHandler(Serializable):
selector=selector, level=level, col_set=col_set, fetch_orig=self.fetch_orig, proc_func=proc_func selector=selector, level=level, col_set=col_set, fetch_orig=self.fetch_orig, proc_func=proc_func
) )
else: else:
raise TypeError(f"data_storage should be pd.DataFrame|HasingStockStorage, not {type(data_storage)}") raise TypeError(f"data_storage should be pd.DataFrame|HashingStockStorage, not {type(data_storage)}")
if squeeze: if squeeze:
# squeeze columns # squeeze columns

4
qlib/data/dataset/processor.py
View File

@@ -349,6 +349,6 @@ class HashStockFormat(Processor):
"""Process the storage of from df into hasing stock format""" """Process the storage of from df into hasing stock format"""
def __call__(self, df: pd.DataFrame): def __call__(self, df: pd.DataFrame):
from .storage import HasingStockStorage # pylint: disable=C0415 from .storage import HashingStockStorage # pylint: disable=C0415
return HasingStockStorage.from_df(df) return HashingStockStorage.from_df(df)

12
qlib/data/dataset/storage.py
View File

@@ -59,11 +59,11 @@ class BaseHandlerStorage:
raise NotImplementedError("is_proc_func_supported method is not implemented!") raise NotImplementedError("is_proc_func_supported method is not implemented!")
class HasingStockStorage(BaseHandlerStorage): class HashingStockStorage(BaseHandlerStorage):
"""Hasing data storage for datahanlder """Hashing data storage for datahanlder
- The default data storage pandas.DataFrame is too slow when randomly accessing one stock's data - 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`. - HashingStockStorage hashes the multiple stocks' data(pandas.DataFrame) by the key `stock_id`.
- 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: - HashingStockStorage 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, stock1_id: stock1_data,
stock2_id: stock2_data, stock2_id: stock2_data,
@@ -82,7 +82,7 @@ class HasingStockStorage(BaseHandlerStorage):
@staticmethod @staticmethod
def from_df(df): def from_df(df):
return HasingStockStorage(df) return HashingStockStorage(df)
def _fetch_hash_df_by_stock(self, selector, level): def _fetch_hash_df_by_stock(self, selector, level):
"""fetch the data with stock selector """fetch the data with stock selector
@@ -153,5 +153,5 @@ class HasingStockStorage(BaseHandlerStorage):
return pd.concat(fetch_stock_df_list, sort=False, copy=~fetch_orig) return pd.concat(fetch_stock_df_list, sort=False, copy=~fetch_orig)
def is_proc_func_supported(self): def is_proc_func_supported(self):
"""the arg `proc_func` in `fetch` method is not supported in HasingStockStorage""" """the arg `proc_func` in `fetch` method is not supported in HashingStockStorage"""
return False return False

2
tests/test_handler_storage.py
View File

@@ -95,7 +95,7 @@ class TestHandlerStorage(TestAutoData):
fetch_stocks = [instruments[_index] for _index in random_indexs] fetch_stocks = [instruments[_index] for _index in random_indexs]
data_handler.fetch(selector=(fetch_stocks, slice(fetch_start_time, fetch_end_time)), level=None) data_handler.fetch(selector=(fetch_stocks, slice(fetch_start_time, fetch_end_time)), level=None)
with TimeInspector.logt("random fetch with HasingStock Storage"): with TimeInspector.logt("random fetch with HashingStock Storage"):
# single stock # single stock
for i in range(100): for i in range(100):