fix #1893

- adapt pandas >= 1.5.0
- add group_keys when the result from apply is a like-indexed Series or DataFrame

Author: csh589

qlib/backtest/position.py

@@ -311,7 +311,7 @@ def fill_stock_value(self, start_time: Union[str, pd.Timestamp], freq: str, last
             freq=freq,
             disk_cache=True,
         ).dropna()
-        price_dict = price_df.groupby(["instrument"]).tail(1).reset_index(level=1, drop=True)["$close"].to_dict()
+        price_dict = price_df.groupby(["instrument"], group_keys=False).tail(1)["$close"].to_dict()
 
         if len(price_dict) < len(stock_list):
             lack_stock = set(stock_list) - set(price_dict)

qlib/contrib/eva/alpha.py

@@ -47,14 +47,14 @@ def calc_long_short_prec(
     if dropna:
         df.dropna(inplace=True)
 
-    group = df.groupby(level=date_col)
+    group = df.groupby(level=date_col, group_keys=False)
 
     def N(x):
         return int(len(x) * quantile)
 
     # find the top/low quantile of prediction and treat them as long and short target
-    long = group.apply(lambda x: x.nlargest(N(x), columns="pred").label).reset_index(level=0, drop=True)
-    short = group.apply(lambda x: x.nsmallest(N(x), columns="pred").label).reset_index(level=0, drop=True)
+    long = group.apply(lambda x: x.nlargest(N(x), columns="pred").label)
+    short = group.apply(lambda x: x.nsmallest(N(x), columns="pred").label)
 
     groupll = long.groupby(date_col)
     l_dom = groupll.apply(lambda x: x > 0)

qlib/contrib/report/analysis_position/parse_position.py

@@ -132,7 +132,7 @@ def _calculate_day_value(g_df: pd.DataFrame):
         g_df["excess_return"] = g_df[_label_name] - g_df[_label_name].mean()
         return g_df
 
-    return df.groupby(level="datetime").apply(_calculate_day_value)
+    return df.groupby(level="datetime", group_keys=False).apply(_calculate_day_value)
 
 
 def get_position_data(

qlib/contrib/report/analysis_position/rank_label.py

@@ -31,7 +31,7 @@ def _get_figure_with_position(
     )
 
     res_dict = dict()
-    _pos_gp = _position_df.groupby(level=1)
+    _pos_gp = _position_df.groupby(level=1, group_keys=False)
     for _item in _pos_gp:
         _date = _item[0]
         _day_df = _item[1]

qlib/utils/paral.py

@@ -51,8 +51,8 @@ def datetime_groupby_apply(
 
     def _naive_group_apply(df):
         if isinstance(apply_func, str):
-            return getattr(df.groupby(axis=axis, level=level), apply_func)()
-        return df.groupby(axis=axis, level=level).apply(apply_func)
+            return getattr(df.groupby(axis=axis, level=level, group_keys=False), apply_func)()
+        return df.groupby(axis=axis, level=level, group_keys=False).apply(apply_func)
 
     if n_jobs != 1:
         dfs = ParallelExt(n_jobs=n_jobs)(