groupby

Author: cmp0xff

pandas-stubs/core/frame.pyi

@@ -1394,7 +1394,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     @overload
     def groupby(  # type: ignore[overload-overlap] # pyright: ignore reportOverlappingOverload
         self,
-        by: MultiIndex | GroupByObjectNonScalar | None = ...,
+        by: MultiIndex | GroupByObjectNonScalar[Any] | None = ...,
         level: IndexLabel | None = ...,
         as_index: Literal[True] = True,
         sort: _bool = ...,
@@ -1405,7 +1405,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     @overload
     def groupby(  # type: ignore[overload-overlap]
         self,
-        by: MultiIndex | GroupByObjectNonScalar | None = ...,
+        by: MultiIndex | GroupByObjectNonScalar[Any] | None = ...,
         level: IndexLabel | None = ...,
         as_index: Literal[False] = False,
         sort: _bool = ...,

tests/test_frame.py

@@ -3626,17 +3626,13 @@ def test_groupby_result() -> None:
     check(assert_type(value3, pd.DataFrame), pd.DataFrame)
 
     # Want to make sure these cases are differentiated
-    for (_k1, _k2), _g in df.groupby(  # pyright: ignore[reportUnknownVariableType]
-        ["a", "b"]
-    ):
+    for (_k1, _k2), _g in df.groupby(["a", "b"]):
         pass
 
     for _kk, _g in df.groupby("a"):
         pass
 
-    for (_k1, _k2), _g in df.groupby(  # pyright: ignore[reportUnknownVariableType]
-        multi_index
-    ):
+    for (_k1, _k2), _g in df.groupby(multi_index):
         pass
 
 

tests/test_io.py

@@ -19,16 +19,26 @@
     HDFStore,
     Series,
     errors,
+    read_clipboard,
+    read_csv,
     read_feather,
     read_fwf,
     read_hdf,
+    read_html,
     read_json,
+    read_parquet,
     read_pickle,
     read_sas,
     read_spss,
+    read_sql,
+    read_sql_query,
     read_sql_table,
     read_stata,
+    read_table,
+    read_xml,
 )
+from pandas import read_excel  # pyright: ignore[reportUnknownVariableType]
+from pandas import read_orc  # pyright: ignore[reportUnknownVariableType]
 from pandas.api.typing import JsonReader
 import pytest
 import sqlalchemy
@@ -44,30 +54,14 @@
 )
 from tests import NUMPY20  # See https://github.com/PyTables/PyTables/issues/1172
 
-from pandas.io.clipboards import read_clipboard
-from pandas.io.excel._base import (
-    read_excel,  # pyright: ignore[reportUnknownVariableType]
-)
-from pandas.io.html import read_html
-from pandas.io.orc import read_orc  # pyright: ignore[reportUnknownVariableType]
-from pandas.io.parquet import read_parquet
 from pandas.io.parsers import TextFileReader
-from pandas.io.parsers.readers import (
-    read_csv,
-    read_table,
-)
 from pandas.io.pytables import (
     TableIterator,
     Term,
 )
 from pandas.io.sas.sas7bdat import SAS7BDATReader
 from pandas.io.sas.sas_xport import XportReader
-from pandas.io.sql import (
-    read_sql,
-    read_sql_query,
-)
 from pandas.io.stata import StataReader
-from pandas.io.xml import read_xml
 
 DF = DataFrame({"a": [1, 2, 3], "b": [0.0, 0.0, 0.0]})
 CWD = Path(__file__).parent.resolve()

tests/test_plotting.py

@@ -707,7 +707,7 @@ def test_grouped_dataframe_boxplot(close_figures: None) -> None:
     df = pd.DataFrame(
         data=np.random.randn(len(index), 2), columns=["A", "B"], index=index
     )
-    grouped = df.groupby(level="lvl1")  # pyright: ignore[reportUnknownVariableType]
+    grouped = df.groupby(level="lvl1")
 
     # subplots (default is subplots=True)
     check(assert_type(grouped.boxplot(), Series), Series)
@@ -743,7 +743,7 @@ def test_grouped_dataframe_boxplot_single(close_figures: None) -> None:
     df = pd.DataFrame(
         data=np.random.randn(len(index), 2), columns=["A", "B"], index=index
     )
-    grouped = df.groupby(level="lvl1")  # pyright: ignore[reportUnknownVariableType]
+    grouped = df.groupby(level="lvl1")
 
     # a single plot
     check(