TYP: replace Label alias from pandas._typing with Hashable (pandas-dev#39107)

Author: simonjayhawkins

pandas/_typing.py

@@ -84,9 +84,8 @@
 FrameOrSeries = TypeVar("FrameOrSeries", bound="NDFrame")
 
 Axis = Union[str, int]
-Label = Optional[Hashable]
-IndexLabel = Union[Label, Sequence[Label]]
-Level = Union[Label, int]
+IndexLabel = Union[Hashable, Sequence[Hashable]]
+Level = Union[Hashable, int]
 Shape = Tuple[int, ...]
 Suffixes = Tuple[str, str]
 Ordered = Optional[bool]
@@ -99,11 +98,11 @@
     "ExtensionDtype", NpDtype, Type[Union[str, float, int, complex, bool, object]]
 ]
 # DtypeArg specifies all allowable dtypes in a functions its dtype argument
-DtypeArg = Union[Dtype, Dict[Label, Dtype]]
+DtypeArg = Union[Dtype, Dict[Hashable, Dtype]]
 DtypeObj = Union[np.dtype, "ExtensionDtype"]
 
 # For functions like rename that convert one label to another
-Renamer = Union[Mapping[Label, Any], Callable[[Label], Label]]
+Renamer = Union[Mapping[Hashable, Any], Callable[[Hashable], Hashable]]
 
 # to maintain type information across generic functions and parametrization
 T = TypeVar("T")
@@ -120,7 +119,7 @@
 
 # types of `func` kwarg for DataFrame.aggregate and Series.aggregate
 AggFuncTypeBase = Union[Callable, str]
-AggFuncTypeDict = Dict[Label, Union[AggFuncTypeBase, List[AggFuncTypeBase]]]
+AggFuncTypeDict = Dict[Hashable, Union[AggFuncTypeBase, List[AggFuncTypeBase]]]
 AggFuncType = Union[
     AggFuncTypeBase,
     List[AggFuncTypeBase],
@@ -155,8 +154,8 @@
 FormattersType = Union[
     List[Callable], Tuple[Callable, ...], Mapping[Union[str, int], Callable]
 ]
-ColspaceType = Mapping[Label, Union[str, int]]
+ColspaceType = Mapping[Hashable, Union[str, int]]
 FloatFormatType = Union[str, Callable, "EngFormatter"]
 ColspaceArgType = Union[
-    str, int, Sequence[Union[str, int]], Mapping[Label, Union[str, int]]
+    str, int, Sequence[Union[str, int]], Mapping[Hashable, Union[str, int]]
 ]

pandas/core/aggregation.py

@@ -11,6 +11,7 @@
     Callable,
     DefaultDict,
     Dict,
+    Hashable,
     Iterable,
     List,
     Optional,
@@ -28,7 +29,6 @@
     Axis,
     FrameOrSeries,
     FrameOrSeriesUnion,
-    Label,
 )
 
 from pandas.core.dtypes.cast import is_nested_object
@@ -294,9 +294,9 @@ def maybe_mangle_lambdas(agg_spec: Any) -> Any:
 def relabel_result(
     result: FrameOrSeries,
     func: Dict[str, List[Union[Callable, str]]],
-    columns: Iterable[Label],
+    columns: Iterable[Hashable],
     order: Iterable[int],
-) -> Dict[Label, "Series"]:
+) -> Dict[Hashable, "Series"]:
     """
     Internal function to reorder result if relabelling is True for
     dataframe.agg, and return the reordered result in dict.
@@ -323,7 +323,7 @@ def relabel_result(
     reordered_indexes = [
         pair[0] for pair in sorted(zip(columns, order), key=lambda t: t[1])
     ]
-    reordered_result_in_dict: Dict[Label, "Series"] = {}
+    reordered_result_in_dict: Dict[Hashable, "Series"] = {}
     idx = 0
 
     reorder_mask = not isinstance(result, ABCSeries) and len(result.columns) > 1
@@ -493,7 +493,7 @@ def transform_dict_like(
         # GH 15931 - deprecation of renaming keys
         raise SpecificationError("nested renamer is not supported")
 
-    results: Dict[Label, FrameOrSeriesUnion] = {}
+    results: Dict[Hashable, FrameOrSeriesUnion] = {}
     for name, how in func.items():
         colg = obj._gotitem(name, ndim=1)
         try:

pandas/core/computation/parsing.py

@@ -6,9 +6,7 @@
 from keyword import iskeyword
 import token
 import tokenize
-from typing import Iterator, Tuple
-
-from pandas._typing import Label
+from typing import Hashable, Iterator, Tuple
 
 # A token value Python's tokenizer probably will never use.
 BACKTICK_QUOTED_STRING = 100
@@ -90,7 +88,7 @@ def clean_backtick_quoted_toks(tok: Tuple[int, str]) -> Tuple[int, str]:
     return toknum, tokval
 
 
-def clean_column_name(name: "Label") -> "Label":
+def clean_column_name(name: Hashable) -> Hashable:
     """
     Function to emulate the cleaning of a backtick quoted name.
 

pandas/core/frame.py

@@ -61,7 +61,6 @@
     FrameOrSeriesUnion,
     IndexKeyFunc,
     IndexLabel,
-    Label,
     Level,
     PythonFuncType,
     Renamer,
@@ -992,7 +991,7 @@ def style(self) -> Styler:
         """
 
     @Appender(_shared_docs["items"])
-    def items(self) -> Iterable[Tuple[Label, Series]]:
+    def items(self) -> Iterable[Tuple[Hashable, Series]]:
         if self.columns.is_unique and hasattr(self, "_item_cache"):
             for k in self.columns:
                 yield k, self._get_item_cache(k)
@@ -1001,10 +1000,10 @@ def items(self) -> Iterable[Tuple[Label, Series]]:
                 yield k, self._ixs(i, axis=1)
 
     @Appender(_shared_docs["items"])
-    def iteritems(self) -> Iterable[Tuple[Label, Series]]:
+    def iteritems(self) -> Iterable[Tuple[Hashable, Series]]:
         yield from self.items()
 
-    def iterrows(self) -> Iterable[Tuple[Label, Series]]:
+    def iterrows(self) -> Iterable[Tuple[Hashable, Series]]:
         """
         Iterate over DataFrame rows as (index, Series) pairs.
 
@@ -2121,14 +2120,14 @@ def _from_arrays(
     def to_stata(
         self,
         path: FilePathOrBuffer,
-        convert_dates: Optional[Dict[Label, str]] = None,
+        convert_dates: Optional[Dict[Hashable, str]] = None,
         write_index: bool = True,
         byteorder: Optional[str] = None,
         time_stamp: Optional[datetime.datetime] = None,
         data_label: Optional[str] = None,
-        variable_labels: Optional[Dict[Label, str]] = None,
+        variable_labels: Optional[Dict[Hashable, str]] = None,
         version: Optional[int] = 114,
-        convert_strl: Optional[Sequence[Label]] = None,
+        convert_strl: Optional[Sequence[Hashable]] = None,
         compression: CompressionOptions = "infer",
         storage_options: StorageOptions = None,
     ) -> None:
@@ -4483,7 +4482,7 @@ def fillna(
             downcast=downcast,
         )
 
-    def pop(self, item: Label) -> Series:
+    def pop(self, item: Hashable) -> Series:
         """
         Return item and drop from frame. Raise KeyError if not found.
 
@@ -4546,7 +4545,7 @@ def replace(
         )
 
     def _replace_columnwise(
-        self, mapping: Dict[Label, Tuple[Any, Any]], inplace: bool, regex
+        self, mapping: Dict[Hashable, Tuple[Any, Any]], inplace: bool, regex
     ):
         """
         Dispatch to Series.replace column-wise.
@@ -4724,7 +4723,7 @@ def set_index(
             "one-dimensional arrays."
         )
 
-        missing: List[Label] = []
+        missing: List[Hashable] = []
         for col in keys:
             if isinstance(col, (Index, Series, np.ndarray, list, abc.Iterator)):
                 # arrays are fine as long as they are one-dimensional
@@ -4752,7 +4751,7 @@ def set_index(
             frame = self.copy()
 
         arrays = []
-        names: List[Label] = []
+        names: List[Hashable] = []
         if append:
             names = list(self.index.names)
             if isinstance(self.index, MultiIndex):
@@ -4761,7 +4760,7 @@ def set_index(
             else:
                 arrays.append(self.index)
 
-        to_remove: List[Label] = []
+        to_remove: List[Hashable] = []
         for col in keys:
             if isinstance(col, MultiIndex):
                 for n in range(col.nlevels):
@@ -4819,7 +4818,7 @@ def reset_index(  # type: ignore[misc]
         drop: bool = ...,
         inplace: Literal[False] = ...,
         col_level: Hashable = ...,
-        col_fill: Label = ...,
+        col_fill: Hashable = ...,
     ) -> DataFrame:
         ...
 
@@ -4830,7 +4829,7 @@ def reset_index(
         drop: bool = ...,
         inplace: Literal[True] = ...,
         col_level: Hashable = ...,
-        col_fill: Label = ...,
+        col_fill: Hashable = ...,
     ) -> None:
         ...
 
@@ -4840,7 +4839,7 @@ def reset_index(
         drop: bool = False,
         inplace: bool = False,
         col_level: Hashable = 0,
-        col_fill: Label = "",
+        col_fill: Hashable = "",
     ) -> Optional[DataFrame]:
         """
         Reset the index, or a level of it.
@@ -5630,7 +5629,7 @@ def sort_index(
 
     def value_counts(
         self,
-        subset: Optional[Sequence[Label]] = None,
+        subset: Optional[Sequence[Hashable]] = None,
         normalize: bool = False,
         sort: bool = True,
         ascending: bool = False,
@@ -7511,7 +7510,7 @@ def diff(self, periods: int = 1, axis: Axis = 0) -> DataFrame:
 
     def _gotitem(
         self,
-        key: Union[Label, List[Label]],
+        key: IndexLabel,
         ndim: int,
         subset: Optional[FrameOrSeriesUnion] = None,
     ) -> FrameOrSeriesUnion:

pandas/core/generic.py

@@ -44,7 +44,6 @@
     IndexKeyFunc,
     IndexLabel,
     JSONSerializable,
-    Label,
     Level,
     NpDtype,
     Renamer,
@@ -526,7 +525,7 @@ def _get_axis_resolvers(self, axis: str) -> Dict[str, Union[Series, MultiIndex]]
         return d
 
     @final
-    def _get_index_resolvers(self) -> Dict[Label, Union[Series, MultiIndex]]:
+    def _get_index_resolvers(self) -> Dict[Hashable, Union[Series, MultiIndex]]:
         from pandas.core.computation.parsing import clean_column_name
 
         d: Dict[str, Union[Series, MultiIndex]] = {}
@@ -536,7 +535,7 @@ def _get_index_resolvers(self) -> Dict[Label, Union[Series, MultiIndex]]:
         return {clean_column_name(k): v for k, v in d.items() if not isinstance(k, int)}
 
     @final
-    def _get_cleaned_column_resolvers(self) -> Dict[Label, Series]:
+    def _get_cleaned_column_resolvers(self) -> Dict[Hashable, Series]:
         """
         Return the special character free column resolvers of a dataframe.
 
@@ -776,7 +775,7 @@ def droplevel(self: FrameOrSeries, level, axis=0) -> FrameOrSeries:
         result = self.set_axis(new_labels, axis=axis, inplace=False)
         return result
 
-    def pop(self, item: Label) -> Union[Series, Any]:
+    def pop(self, item: Hashable) -> Union[Series, Any]:
         result = self[item]
         del self[item]
         if self.ndim == 2:
@@ -3225,7 +3224,7 @@ def to_csv(
         sep: str = ",",
         na_rep: str = "",
         float_format: Optional[str] = None,
-        columns: Optional[Sequence[Label]] = None,
+        columns: Optional[Sequence[Hashable]] = None,
         header: Union[bool_t, List[str]] = True,
         index: bool_t = True,
         index_label: Optional[IndexLabel] = None,
@@ -10214,7 +10213,7 @@ def describe_1d(data) -> "Series":
 
         ldesc = [describe_1d(s) for _, s in data.items()]
         # set a convenient order for rows
-        names: List[Label] = []
+        names: List[Hashable] = []
         ldesc_indexes = sorted((x.index for x in ldesc), key=len)
         for idxnames in ldesc_indexes:
             for name in idxnames:

pandas/core/groupby/generic.py

@@ -15,6 +15,7 @@
     Callable,
     Dict,
     FrozenSet,
+    Hashable,
     Iterable,
     List,
     Mapping,
@@ -30,7 +31,7 @@
 import numpy as np
 
 from pandas._libs import lib, reduction as libreduction
-from pandas._typing import ArrayLike, FrameOrSeries, FrameOrSeriesUnion, Label
+from pandas._typing import ArrayLike, FrameOrSeries, FrameOrSeriesUnion
 from pandas.util._decorators import Appender, Substitution, doc
 
 from pandas.core.dtypes.cast import (
@@ -1129,7 +1130,7 @@ def _aggregate_frame(self, func, *args, **kwargs) -> DataFrame:
         axis = self.axis
         obj = self._obj_with_exclusions
 
-        result: Dict[Label, Union[NDFrame, np.ndarray]] = {}
+        result: Dict[Hashable, Union[NDFrame, np.ndarray]] = {}
         if axis != obj._info_axis_number:
             for name, data in self:
                 fres = func(data, *args, **kwargs)

pandas/core/groupby/groupby.py

@@ -43,7 +43,6 @@ class providing the base-class of operations.
     FrameOrSeries,
     FrameOrSeriesUnion,
     IndexLabel,
-    Label,
     Scalar,
     final,
 )
@@ -522,7 +521,7 @@ def __init__(
         axis: int = 0,
         level: Optional[IndexLabel] = None,
         grouper: Optional["ops.BaseGrouper"] = None,
-        exclusions: Optional[Set[Label]] = None,
+        exclusions: Optional[Set[Hashable]] = None,
         selection: Optional[IndexLabel] = None,
         as_index: bool = True,
         sort: bool = True,
@@ -860,7 +859,7 @@ def get_group(self, name, obj=None):
 
         return obj._take_with_is_copy(inds, axis=self.axis)
 
-    def __iter__(self) -> Iterator[Tuple[Label, FrameOrSeries]]:
+    def __iter__(self) -> Iterator[Tuple[Hashable, FrameOrSeries]]:
         """
         Groupby iterator.
 

pandas/core/groupby/grouper.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 
-from pandas._typing import FrameOrSeries, Label, final
+from pandas._typing import FrameOrSeries, final
 from pandas.errors import InvalidIndexError
 from pandas.util._decorators import cache_readonly
 
@@ -616,7 +616,7 @@ def get_grouper(
     mutated: bool = False,
     validate: bool = True,
     dropna: bool = True,
-) -> Tuple["ops.BaseGrouper", Set[Label], FrameOrSeries]:
+) -> Tuple["ops.BaseGrouper", Set[Hashable], FrameOrSeries]:
     """
     Create and return a BaseGrouper, which is an internal
     mapping of how to create the grouper indexers.
@@ -741,7 +741,7 @@ def get_grouper(
         levels = [level] * len(keys)
 
     groupings: List[Grouping] = []
-    exclusions: Set[Label] = set()
+    exclusions: Set[Hashable] = set()
 
     # if the actual grouper should be obj[key]
     def is_in_axis(key) -> bool: