Fix dump_bin.py && check_dump_bin.py

microsoft · Mar 18, 2021 · d245242 · d245242
1 parent 42be8ac
commit d245242
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/scripts/check_dump_bin.py b/scripts/check_dump_bin.py
@@ -66,7 +66,7 @@ def __init__(
         self.csv_files = sorted(csv_path.glob(f"*{file_suffix}") if csv_path.is_dir() else [csv_path])
 
         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:
             check_fields = check_fields.split(",") if isinstance(check_fields, str) else check_fields
         self.check_fields = list(map(lambda x: x.strip(), check_fields))
@@ -91,6 +91,7 @@ def _compare(self, file_path: Path):
             origin_df[self.symbol_field_name] = symbol
         origin_df.set_index([self.symbol_field_name, self.date_field_name], inplace=True)
         origin_df.index.names = qlib_df.index.names
+        origin_df = origin_df.reindex(qlib_df.index)
         try:
             compare = datacompy.Compare(
                 origin_df,

diff --git a/scripts/dump_bin.py b/scripts/dump_bin.py
@@ -219,7 +219,7 @@ def _data_to_bin(self, df: pd.DataFrame, calendar_list: List[pd.Timestamp], feat
         # used when creating a bin file
         date_index = self.get_datetime_index(_df, calendar_list)
         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:
                 continue
             if bin_path.exists() and self._mode == self.UPDATE_MODE: