Merge branch 'master' into ind-sort-values

Author: AlexKirko

pandas/_testing.py

@@ -939,7 +939,7 @@ def assert_categorical_equal(
     if check_category_order:
         assert_index_equal(left.categories, right.categories, obj=f"{obj}.categories")
         assert_numpy_array_equal(
-            left.codes, right.codes, check_dtype=check_dtype, obj=f"{obj}.codes",
+            left.codes, right.codes, check_dtype=check_dtype, obj=f"{obj}.codes"
         )
     else:
         try:
@@ -948,9 +948,7 @@ def assert_categorical_equal(
         except TypeError:
             # e.g. '<' not supported between instances of 'int' and 'str'
             lc, rc = left.categories, right.categories
-        assert_index_equal(
-            lc, rc, obj=f"{obj}.categories",
-        )
+        assert_index_equal(lc, rc, obj=f"{obj}.categories")
         assert_index_equal(
             left.categories.take(left.codes),
             right.categories.take(right.codes),
@@ -1092,7 +1090,7 @@ def _raise(left, right, err_msg):
         if err_msg is None:
             if left.shape != right.shape:
                 raise_assert_detail(
-                    obj, f"{obj} shapes are different", left.shape, right.shape,
+                    obj, f"{obj} shapes are different", left.shape, right.shape
                 )
 
             diff = 0
@@ -1559,7 +1557,7 @@ def assert_frame_equal(
     # shape comparison
     if left.shape != right.shape:
         raise_assert_detail(
-            obj, f"{obj} shape mismatch", f"{repr(left.shape)}", f"{repr(right.shape)}",
+            obj, f"{obj} shape mismatch", f"{repr(left.shape)}", f"{repr(right.shape)}"
         )
 
     if check_like:
@@ -2884,7 +2882,7 @@ def convert_rows_list_to_csv_str(rows_list: List[str]):
     return expected
 
 
-def external_error_raised(expected_exception: Type[Exception],) -> ContextManager:
+def external_error_raised(expected_exception: Type[Exception]) -> ContextManager:
     """
     Helper function to mark pytest.raises that have an external error message.
 

pandas/core/aggregation.py

@@ -10,28 +10,27 @@
     Callable,
     DefaultDict,
     Dict,
+    Iterable,
     List,
     Optional,
     Sequence,
     Tuple,
     Union,
 )
 
-from pandas._typing import AggFuncType, Label
+from pandas._typing import AggFuncType, FrameOrSeries, Label
 
 from pandas.core.dtypes.common import is_dict_like, is_list_like
 
 from pandas.core.base import SpecificationError
 import pandas.core.common as com
 from pandas.core.indexes.api import Index
-from pandas.core.series import FrameOrSeriesUnion, Series
+from pandas.core.series import Series
 
 
 def reconstruct_func(
-    func: Optional[AggFuncType], **kwargs,
-) -> Tuple[
-    bool, Optional[AggFuncType], Optional[List[str]], Optional[List[int]],
-]:
+    func: Optional[AggFuncType], **kwargs
+) -> Tuple[bool, Optional[AggFuncType], Optional[List[str]], Optional[List[int]]]:
     """
     This is the internal function to reconstruct func given if there is relabeling
     or not and also normalize the keyword to get new order of columns.
@@ -278,12 +277,13 @@ def maybe_mangle_lambdas(agg_spec: Any) -> Any:
 
 
 def relabel_result(
-    result: FrameOrSeriesUnion,
+    result: FrameOrSeries,
     func: Dict[str, List[Union[Callable, str]]],
-    columns: Tuple,
-    order: List[int],
+    columns: Iterable[Label],
+    order: Iterable[int],
 ) -> Dict[Label, Series]:
-    """Internal function to reorder result if relabelling is True for
+    """
+    Internal function to reorder result if relabelling is True for
     dataframe.agg, and return the reordered result in dict.
 
     Parameters:

pandas/core/algorithms.py

@@ -10,7 +10,7 @@
 import numpy as np
 
 from pandas._libs import Timestamp, algos, hashtable as htable, iNaT, lib
-from pandas._typing import AnyArrayLike, ArrayLike, DtypeObj
+from pandas._typing import AnyArrayLike, ArrayLike, DtypeObj, FrameOrSeriesUnion
 from pandas.util._decorators import doc
 
 from pandas.core.dtypes.cast import (
@@ -58,7 +58,7 @@
 from pandas.core.indexers import validate_indices
 
 if TYPE_CHECKING:
-    from pandas import Series
+    from pandas import DataFrame, Series
 
 _shared_docs: Dict[str, str] = {}
 
@@ -462,7 +462,7 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
 
 
 def _factorize_array(
-    values, na_sentinel: int = -1, size_hint=None, na_value=None, mask=None,
+    values, na_sentinel: int = -1, size_hint=None, na_value=None, mask=None
 ) -> Tuple[np.ndarray, np.ndarray]:
     """
     Factorize an array-like to codes and uniques.
@@ -1101,6 +1101,9 @@ def __init__(self, obj, n: int, keep: str):
         if self.keep not in ("first", "last", "all"):
             raise ValueError('keep must be either "first", "last" or "all"')
 
+    def compute(self, method: str) -> FrameOrSeriesUnion:
+        raise NotImplementedError
+
     def nlargest(self):
         return self.compute("nlargest")
 
@@ -1133,7 +1136,7 @@ class SelectNSeries(SelectN):
     nordered : Series
     """
 
-    def compute(self, method):
+    def compute(self, method: str) -> "Series":
 
         n = self.n
         dtype = self.obj.dtype
@@ -1207,7 +1210,7 @@ def __init__(self, obj, n: int, keep: str, columns):
         columns = list(columns)
         self.columns = columns
 
-    def compute(self, method):
+    def compute(self, method: str) -> "DataFrame":
 
         from pandas import Int64Index
 

pandas/core/arrays/_mixins.py

@@ -40,7 +40,7 @@ def take(
             fill_value = self._validate_fill_value(fill_value)
 
         new_data = take(
-            self._ndarray, indices, allow_fill=allow_fill, fill_value=fill_value,
+            self._ndarray, indices, allow_fill=allow_fill, fill_value=fill_value
         )
         return self._from_backing_data(new_data)
 

pandas/core/arrays/base.py

@@ -1167,6 +1167,10 @@ class ExtensionOpsMixin:
        with NumPy arrays.
     """
 
+    @classmethod
+    def _create_arithmetic_method(cls, op):
+        raise AbstractMethodError(cls)
+
     @classmethod
     def _add_arithmetic_ops(cls):
         cls.__add__ = cls._create_arithmetic_method(operator.add)
@@ -1186,6 +1190,10 @@ def _add_arithmetic_ops(cls):
         cls.__divmod__ = cls._create_arithmetic_method(divmod)
         cls.__rdivmod__ = cls._create_arithmetic_method(ops.rdivmod)
 
+    @classmethod
+    def _create_comparison_method(cls, op):
+        raise AbstractMethodError(cls)
+
     @classmethod
     def _add_comparison_ops(cls):
         cls.__eq__ = cls._create_comparison_method(operator.eq)
@@ -1195,6 +1203,10 @@ def _add_comparison_ops(cls):
         cls.__le__ = cls._create_comparison_method(operator.le)
         cls.__ge__ = cls._create_comparison_method(operator.ge)
 
+    @classmethod
+    def _create_logical_method(cls, op):
+        raise AbstractMethodError(cls)
+
     @classmethod
     def _add_logical_ops(cls):
         cls.__and__ = cls._create_logical_method(operator.and_)

pandas/core/arrays/categorical.py

@@ -1505,7 +1505,7 @@ def argsort(self, ascending=True, kind="quicksort", **kwargs):
         return super().argsort(ascending=ascending, kind=kind, **kwargs)
 
     def sort_values(
-        self, inplace: bool = False, ascending: bool = True, na_position: str = "last",
+        self, inplace: bool = False, ascending: bool = True, na_position: str = "last"
     ):
         """
         Sort the Categorical by category value returning a new

pandas/core/arrays/integer.py

@@ -138,7 +138,7 @@ def __from_arrow__(
         return IntegerArray._concat_same_type(results)
 
 
-def integer_array(values, dtype=None, copy: bool = False,) -> "IntegerArray":
+def integer_array(values, dtype=None, copy: bool = False) -> "IntegerArray":
     """
     Infer and return an integer array of the values.
 
@@ -182,7 +182,7 @@ def safe_cast(values, dtype, copy: bool):
 
 
 def coerce_to_array(
-    values, dtype, mask=None, copy: bool = False,
+    values, dtype, mask=None, copy: bool = False
 ) -> Tuple[np.ndarray, np.ndarray]:
     """
     Coerce the input values array to numpy arrays with a mask

pandas/core/arrays/masked.py

@@ -126,7 +126,7 @@ def __invert__(self: BaseMaskedArrayT) -> BaseMaskedArrayT:
         return type(self)(~self._data, self._mask)
 
     def to_numpy(
-        self, dtype=None, copy: bool = False, na_value: Scalar = lib.no_default,
+        self, dtype=None, copy: bool = False, na_value: Scalar = lib.no_default
     ) -> np.ndarray:
         """
         Convert to a NumPy Array.

pandas/core/arrays/numpy_.py

@@ -280,7 +280,7 @@ def isna(self) -> np.ndarray:
         return isna(self._ndarray)
 
     def fillna(
-        self, value=None, method: Optional[str] = None, limit: Optional[int] = None,
+        self, value=None, method: Optional[str] = None, limit: Optional[int] = None
     ) -> "PandasArray":
         # TODO(_values_for_fillna): remove this
         value, method = validate_fillna_kwargs(value, method)

pandas/core/arrays/period.py

@@ -634,7 +634,7 @@ def _sub_period_array(self, other):
         return new_values
 
     def _addsub_int_array(
-        self, other: np.ndarray, op: Callable[[Any, Any], Any],
+        self, other: np.ndarray, op: Callable[[Any, Any], Any]
     ) -> "PeriodArray":
         """
         Add or subtract array of integers; equivalent to applying

pandas/core/construction.py

@@ -514,9 +514,7 @@ def sanitize_array(
     return subarr
 
 
-def _try_cast(
-    arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bool,
-):
+def _try_cast(arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bool):
     """
     Convert input to numpy ndarray and optionally cast to a given dtype.
 

pandas/core/frame.py

@@ -7415,6 +7415,12 @@ def aggregate(self, func=None, axis=0, *args, **kwargs):
         if relabeling:
             # This is to keep the order to columns occurrence unchanged, and also
             # keep the order of new columns occurrence unchanged
+
+            # For the return values of reconstruct_func, if relabeling is
+            # False, columns and order will be None.
+            assert columns is not None
+            assert order is not None
+
             result_in_dict = relabel_result(result, func, columns, order)
             result = DataFrame(result_in_dict, index=columns)
 
@@ -9306,7 +9312,6 @@ def _AXIS_NAMES(self) -> Dict[int, str]:
 
 
 DataFrame._add_numeric_operations()
-DataFrame._add_series_or_dataframe_operations()
 
 ops.add_flex_arithmetic_methods(DataFrame)
 ops.add_special_arithmetic_methods(DataFrame)