liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-13 07:46:53 +08:00
Code Activity

Merge pull request #350 from zhupr/fix_dump_bin

Browse Source 
Fix dump_bin.py && check_dump_bin.py
This commit is contained in:
you-n-g
2021-03-18 18:39:40 +08:00
committed by GitHub
parent f72771cc81 d245242f2f
commit 06c90d654d
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
scripts/check_dump_bin.py
View File

@@ -66,7 +66,7 @@ class CheckBin:
self.csv_files = sorted(csv_path.glob(f"*{file_suffix}") if csv_path.is_dir() else [csv_path]) self.csv_files = sorted(csv_path.glob(f"*{file_suffix}") if csv_path.is_dir() else [csv_path])
if check_fields is None: if check_fields is None:
check_fields = list(map(lambda x: x.split(".")[0], bin_path_list[0].glob(f"*.bin"))) check_fields = list(map(lambda x: x.name.split(".")[0], bin_path_list[0].glob(f"*.bin")))
else: else:
check_fields = check_fields.split(",") if isinstance(check_fields, str) else check_fields check_fields = check_fields.split(",") if isinstance(check_fields, str) else check_fields
self.check_fields = list(map(lambda x: x.strip(), check_fields)) self.check_fields = list(map(lambda x: x.strip(), check_fields))
@@ -91,6 +91,7 @@ class CheckBin:
origin_df[self.symbol_field_name] = symbol origin_df[self.symbol_field_name] = symbol
origin_df.set_index([self.symbol_field_name, self.date_field_name], inplace=True) origin_df.set_index([self.symbol_field_name, self.date_field_name], inplace=True)
origin_df.index.names = qlib_df.index.names origin_df.index.names = qlib_df.index.names
origin_df = origin_df.reindex(qlib_df.index)
try: try:
compare = datacompy.Compare( compare = datacompy.Compare(
origin_df, origin_df,

2
scripts/dump_bin.py
View File

@@ -219,7 +219,7 @@ class DumpDataBase:
# used when creating a bin file # used when creating a bin file
date_index = self.get_datetime_index(_df, calendar_list) date_index = self.get_datetime_index(_df, calendar_list)
for field in self.get_dump_fields(_df.columns): for field in self.get_dump_fields(_df.columns):
bin_path = features_dir.joinpath(f"{field}.{self.freq}{self.DUMP_FILE_SUFFIX}") bin_path = features_dir.joinpath(f"{field.lower()}.{self.freq}{self.DUMP_FILE_SUFFIX}")
if field not in _df.columns: if field not in _df.columns:
continue continue
if bin_path.exists() and self._mode == self.UPDATE_MODE: if bin_path.exists() and self._mode == self.UPDATE_MODE: