liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-14 16:26:55 +08:00
Code Activity

sort index after loader (#538)

Browse Source 
make sure the fetch method is based on a index-sorted pd.DataFrame
This commit is contained in:
you-n-g
2021-07-29 12:06:59 +08:00
committed by GitHub
parent dc6859bdd9
commit 05d28469ad
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -18,6 +18,7 @@ from ...config import C
from ...utils import parse_config, transform_end_date, init_instance_by_config from ...utils import parse_config, transform_end_date, init_instance_by_config
from ...utils.serial import Serializable from ...utils.serial import Serializable
from .utils import fetch_df_by_index from .utils import fetch_df_by_index
from ...utils import lazy_sort_index
from pathlib import Path from pathlib import Path
from .loader import DataLoader from .loader import DataLoader
@@ -146,7 +147,8 @@ class DataHandler(Serializable):
# Setup data. # Setup data.
# _data may be with multiple column index level. The outer level indicates the feature set name # _data may be with multiple column index level. The outer level indicates the feature set name
with TimeInspector.logt("Loading data"): with TimeInspector.logt("Loading data"):
self._data = self.data_loader.load(self.instruments, self.start_time, self.end_time) # make sure the fetch method is based on a index-sorted pd.DataFrame
self._data = lazy_sort_index(self.data_loader.load(self.instruments, self.start_time, self.end_time))
# TODO: cache # TODO: cache
CS_ALL = "__all" # return all columns with single-level index column CS_ALL = "__all" # return all columns with single-level index column