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

examples/benchmarks/TFT/libs/tft_model.py

@@ -599,7 +599,7 @@ class TemporalFusionTransformer:
         print("Getting valid sampling locations.")
         valid_sampling_locations = []
         split_data_map = {}
-        for identifier, df in data.groupby(id_col):
+        for identifier, df in data.groupby(id_col, group_key=False):
             print("Getting locations for {}".format(identifier))
             num_entries = len(df)
             if num_entries >= self.time_steps:
@@ -678,7 +678,7 @@ class TemporalFusionTransformer:
         input_cols = [tup[0] for tup in self.column_definition if tup[2] not in {InputTypes.ID, InputTypes.TIME}]
 
         data_map = {}
-        for _, sliced in data.groupby(id_col):
+        for _, sliced in data.groupby(id_col, group_keys=False):
             col_mappings = {"identifier": [id_col], "time": [time_col], "outputs": [target_col], "inputs": input_cols}
 
             for k in col_mappings:

examples/benchmarks/TFT/tft.py

@@ -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
 

examples/benchmarks/TRA/src/dataset.py

@@ -29,7 +29,7 @@ def _create_ts_slices(index, seq_len):
     assert index.is_lexsorted(), "index should be sorted"
 
     # number of dates for each code
-    sample_count_by_codes = pd.Series(0, index=index).groupby(level=0).size().values
+    sample_count_by_codes = pd.Series(0, index=index).groupby(level=0, group_keys=False).size().values
 
     # start_index for each code
     start_index_of_codes = np.roll(np.cumsum(sample_count_by_codes), 1)

examples/highfreq/highfreq_ops.py

@@ -25,7 +25,7 @@ class DayLast(ElemOperator):
     def _load_internal(self, instrument, start_index, end_index, freq):
         _calendar = get_calendar_day(freq=freq)
         series = self.feature.load(instrument, start_index, end_index, freq)
-        return series.groupby(_calendar[series.index]).transform("last")
+        return series.groupby(_calendar[series.index], group_keys=False).transform("last")
 
 
 class FFillNan(ElemOperator):
@@ -44,7 +44,7 @@ class FFillNan(ElemOperator):
 
     def _load_internal(self, instrument, start_index, end_index, freq):
         series = self.feature.load(instrument, start_index, end_index, freq)
-        return series.fillna(method="ffill")
+        return series.ffill()
 
 
 class BFillNan(ElemOperator):
@@ -63,7 +63,7 @@ class BFillNan(ElemOperator):
 
     def _load_internal(self, instrument, start_index, end_index, freq):
         series = self.feature.load(instrument, start_index, end_index, freq)
-        return series.fillna(method="bfill")
+        return series.bfill()
 
 
 class Date(ElemOperator):

examples/rl_order_execution/scripts/gen_training_orders.py

@@ -19,9 +19,9 @@ def generate_order(stock: str, start_idx: int, end_idx: int) -> bool:
 
     df["date"] = df["datetime"].dt.date.astype("datetime64")
     df = df.set_index(["instrument", "datetime", "date"])
-    df = df.groupby("date").take(range(start_idx, end_idx)).droplevel(level=0)
+    df = df.groupby("date", group_keys=False).take(range(start_idx, end_idx)).droplevel(level=0)
 
-    order_all = pd.DataFrame(df.groupby(level=(2, 0)).mean().dropna())
+    order_all = pd.DataFrame(df.groupby(level=(2, 0), group_keys=False).mean().dropna())
     order_all["amount"] = np.random.lognormal(-3.28, 1.14) * order_all["$volume0"]
     order_all = order_all[order_all["amount"] > 0.0]
     order_all["order_type"] = 0