1
0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-14 00:06:58 +08:00

fixed a problem with multi index caused by the default value of groupkey (#1917)

* fixed a problem with multi index caused by the default value of groupkey

* modify group_key default value

* limit pandas verion

* format with black

* fix docs error

* fix docs error

* fixed bugs caused by pandas upgrade

* remove needless code

* reformat with black

* limit version & add docs
This commit is contained in:
Linlang
2025-05-13 16:02:49 +08:00
committed by GitHub
parent df557d29d5
commit fbba768006
43 changed files with 153 additions and 98 deletions

View File

@@ -78,13 +78,15 @@ DATASET_SETTING = {
def get_shifted_label(data_df, shifts=5, col_shift="LABEL0"):
return data_df[[col_shift]].groupby("instrument").apply(lambda df: df.shift(shifts))
return data_df[[col_shift]].groupby("instrument", group_keys=False).apply(lambda df: df.shift(shifts))
def fill_test_na(test_df):
test_df_res = test_df.copy()
feature_cols = ~test_df_res.columns.str.contains("label", case=False)
test_feature_fna = test_df_res.loc[:, feature_cols].groupby("datetime").apply(lambda df: df.fillna(df.mean()))
test_feature_fna = (
test_df_res.loc[:, feature_cols].groupby("datetime", group_keys=False).apply(lambda df: df.fillna(df.mean()))
)
test_df_res.loc[:, feature_cols] = test_feature_fna
return test_df_res