CLN: assorted follow-ups (pandas-dev#49489)

Author: jbrockmendel

doc/source/getting_started/install.rst

@@ -417,7 +417,7 @@ Dependency                Minimum Version    optional_extra   Notes
 PyTables                  3.6.1              hdf5             HDF5-based reading / writing
 blosc                     1.21.0             hdf5             Compression for HDF5
 zlib                                         hdf5             Compression for HDF5
-fastparquet               0.4.0              -                Parquet reading / writing (pyarrow is default)
+fastparquet               0.6.3              -                Parquet reading / writing (pyarrow is default)
 pyarrow                   6.0.0              parquet, feather Parquet, ORC, and feather reading / writing
 pyreadstat                1.1.2              spss             SPSS files (.sav) reading
 odfpy                     1.4.1              excel            Open document format (.odf, .ods, .odt) reading / writing

pandas/core/dtypes/astype.py

@@ -215,6 +215,7 @@ def astype_array(values: ArrayLike, dtype: DtypeObj, copy: bool = False) -> Arra
         # Series.astype behavior pre-2.0 did
         #  values.tz_localize("UTC").tz_convert(dtype.tz)
         #  which did not match the DTA/DTI behavior.
+        # We special-case here to give a Series-specific exception message.
         raise TypeError(
             "Cannot use .astype to convert from timezone-naive dtype to "
             "timezone-aware dtype. Use ser.dt.tz_localize instead."

pandas/core/dtypes/cast.py

@@ -1414,7 +1414,7 @@ def _ensure_nanosecond_dtype(dtype: DtypeObj) -> DtypeObj:
 
 
 # TODO: other value-dependent functions to standardize here include
-#  dtypes.concat.cast_to_common_type and Index._find_common_type_compat
+#  Index._find_common_type_compat
 def find_result_type(left: ArrayLike, right: Any) -> DtypeObj:
     """
     Find the type/dtype for a the result of an operation between these objects.

pandas/core/dtypes/concat.py

@@ -3,30 +3,20 @@
 """
 from __future__ import annotations
 
-from typing import (
-    TYPE_CHECKING,
-    cast,
-)
+from typing import TYPE_CHECKING
 import warnings
 
 import numpy as np
 
-from pandas._typing import (
-    ArrayLike,
-    AxisInt,
-    DtypeObj,
-)
+from pandas._typing import AxisInt
 from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.astype import astype_array
 from pandas.core.dtypes.cast import (
     common_dtype_categorical_compat,
     find_common_type,
 )
-from pandas.core.dtypes.common import (
-    is_dtype_equal,
-    is_sparse,
-)
+from pandas.core.dtypes.common import is_dtype_equal
 from pandas.core.dtypes.dtypes import (
     DatetimeTZDtype,
     ExtensionDtype,
@@ -39,34 +29,6 @@
 
 if TYPE_CHECKING:
     from pandas.core.arrays import Categorical
-    from pandas.core.arrays.sparse import SparseArray
-
-
-def cast_to_common_type(arr: ArrayLike, dtype: DtypeObj) -> ArrayLike:
-    """
-    Helper function for `arr.astype(common_dtype)` but handling all special
-    cases.
-    """
-    if is_dtype_equal(arr.dtype, dtype):
-        return arr
-
-    if is_sparse(arr) and not is_sparse(dtype):
-        # TODO(2.0): remove special case once SparseArray.astype deprecation
-        #  is enforced.
-        # problem case: SparseArray.astype(dtype) doesn't follow the specified
-        # dtype exactly, but converts this to Sparse[dtype] -> first manually
-        # convert to dense array
-
-        # error: Argument 1 to "astype" of "_ArrayOrScalarCommon" has incompatible type
-        # "Union[dtype[Any], ExtensionDtype]"; expected "Union[dtype[Any], None, type, _
-        # SupportsDType[dtype[Any]], str, Union[Tuple[Any, int], Tuple[Any,
-        # Union[SupportsIndex, Sequence[SupportsIndex]]], List[Any], _DTypeDict,
-        # Tuple[Any, Any]]]"  [arg-type]
-        arr = cast("SparseArray", arr)
-        return arr.to_dense().astype(dtype, copy=False)  # type: ignore[arg-type]
-
-    # astype_array includes ensure_wrapped_if_datetimelike
-    return astype_array(arr, dtype=dtype, copy=False)
 
 
 def concat_compat(to_concat, axis: AxisInt = 0, ea_compat_axis: bool = False):
@@ -126,7 +88,9 @@ def is_nonempty(x) -> bool:
         if not single_dtype:
             target_dtype = find_common_type([x.dtype for x in to_concat])
             target_dtype = common_dtype_categorical_compat(to_concat, target_dtype)
-            to_concat = [cast_to_common_type(arr, target_dtype) for arr in to_concat]
+            to_concat = [
+                astype_array(arr, target_dtype, copy=False) for arr in to_concat
+            ]
 
         if isinstance(to_concat[0], ABCExtensionArray):
             # TODO: what about EA-backed Index?

pandas/core/frame.py

@@ -5046,7 +5046,6 @@ def align(
             broadcast_axis=broadcast_axis,
         )
 
-    # error: Signature of "set_axis" incompatible with supertype "NDFrame"
     @Appender(
         """
         Examples

pandas/core/indexes/multi.py

@@ -14,7 +14,6 @@
     Sequence,
     Tuple,
     cast,
-    overload,
 )
 import warnings
 
@@ -3739,28 +3738,9 @@ def isin(self, values, level=None) -> npt.NDArray[np.bool_]:
                 return np.zeros(len(levs), dtype=np.bool_)
             return levs.isin(values)
 
-    @overload
-    def set_names(
-        self, names, *, level=..., inplace: Literal[False] = ...
-    ) -> MultiIndex:
-        ...
-
-    @overload
-    def set_names(self, names, *, level=..., inplace: Literal[True]) -> None:
-        ...
-
-    @overload
-    def set_names(self, names, *, level=..., inplace: bool = ...) -> MultiIndex | None:
-        ...
-
-    def set_names(
-        self, names, *, level=None, inplace: bool = False
-    ) -> MultiIndex | None:
-        return super().set_names(names=names, level=level, inplace=inplace)
-
     # error: Incompatible types in assignment (expression has type overloaded function,
     # base class "Index" defined the type as "Callable[[Index, Any, bool], Any]")
-    rename = set_names  # type: ignore[assignment]
+    rename = Index.set_names  # type: ignore[assignment]
 
     # ---------------------------------------------------------------
     # Arithmetic/Numeric Methods - Disabled

pandas/core/internals/concat.py

@@ -24,6 +24,7 @@
 )
 from pandas.util._decorators import cache_readonly
 
+from pandas.core.dtypes.astype import astype_array
 from pandas.core.dtypes.cast import (
     ensure_dtype_can_hold_na,
     find_common_type,
@@ -34,10 +35,7 @@
     is_scalar,
     needs_i8_conversion,
 )
-from pandas.core.dtypes.concat import (
-    cast_to_common_type,
-    concat_compat,
-)
+from pandas.core.dtypes.concat import concat_compat
 from pandas.core.dtypes.dtypes import (
     DatetimeTZDtype,
     ExtensionDtype,
@@ -153,7 +151,7 @@ def concat_arrays(to_concat: list) -> ArrayLike:
     to_concat = [
         arr.to_array(target_dtype)
         if isinstance(arr, NullArrayProxy)
-        else cast_to_common_type(arr, target_dtype)
+        else astype_array(arr, target_dtype, copy=False)
         for arr in to_concat
     ]
 

pandas/core/series.py

@@ -4925,7 +4925,6 @@ def rename(
         else:
             return self._set_name(index, inplace=inplace)
 
-    # error: Signature of "set_axis" incompatible with supertype "NDFrame"
     @Appender(
         """
         Examples

pandas/core/sorting.py

@@ -11,7 +11,6 @@
     Sequence,
     cast,
 )
-import warnings
 
 import numpy as np
 
@@ -341,14 +340,7 @@ def lexsort_indexer(
     keys = [ensure_key_mapped(k, key) for k in keys]
 
     for k, order in zip(keys, orders):
-        with warnings.catch_warnings():
-            # TODO(2.0): unnecessary once deprecation is enforced
-            # GH#45618 don't issue warning user can't do anything about
-            warnings.filterwarnings(
-                "ignore", ".*(SparseArray|SparseDtype).*", category=FutureWarning
-            )
-
-            cat = Categorical(k, ordered=True)
+        cat = Categorical(k, ordered=True)
 
         if na_position not in ["last", "first"]:
             raise ValueError(f"invalid na_position: {na_position}")

pandas/io/formats/style.py

@@ -3604,15 +3604,11 @@ def _background_gradient(
         rng = smax - smin
         # extend lower / upper bounds, compresses color range
         norm = mpl.colors.Normalize(smin - (rng * low), smax + (rng * high))
-        from pandas.plotting._matplotlib.compat import mpl_ge_3_6_0
 
-        if mpl_ge_3_6_0():
-            if cmap is None:
-                rgbas = mpl.colormaps[mpl.rcParams["image.cmap"]](norm(gmap))
-            else:
-                rgbas = mpl.colormaps.get_cmap(cmap)(norm(gmap))
+        if cmap is None:
+            rgbas = mpl.colormaps[mpl.rcParams["image.cmap"]](norm(gmap))
         else:
-            rgbas = plt.cm.get_cmap(cmap)(norm(gmap))
+            rgbas = mpl.colormaps.get_cmap(cmap)(norm(gmap))
 
         def relative_luminance(rgba) -> float:
             """
@@ -3891,10 +3887,8 @@ def css_calc(x, left: float, right: float, align: str, color: str | list | tuple
     if cmap is not None:
         # use the matplotlib colormap input
         with _mpl(Styler.bar) as (plt, mpl):
-            from pandas.plotting._matplotlib.compat import mpl_ge_3_6_0
-
             cmap = (
-                (mpl.colormaps[cmap] if mpl_ge_3_6_0() else mpl.cm.get_cmap(cmap))
+                mpl.colormaps[cmap]
                 if isinstance(cmap, str)
                 else cmap  # assumed to be a Colormap instance as documented
             )

pandas/plotting/_matplotlib/compat.py

@@ -1,8 +1,6 @@
 # being a bit too dynamic
 from __future__ import annotations
 
-import operator
-
 from pandas.util.version import Version
 
 
@@ -15,8 +13,3 @@ def inner():
         return op(Version(mpl.__version__), Version(version))
 
     return inner
-
-
-mpl_ge_3_4_0 = _mpl_version("3.4.0", operator.ge)
-mpl_ge_3_5_0 = _mpl_version("3.5.0", operator.ge)
-mpl_ge_3_6_0 = _mpl_version("3.6.0", operator.ge)

pandas/plotting/_matplotlib/core.py

@@ -55,7 +55,6 @@
 from pandas.core.frame import DataFrame
 
 from pandas.io.formats.printing import pprint_thing
-from pandas.plotting._matplotlib.compat import mpl_ge_3_6_0
 from pandas.plotting._matplotlib.converter import register_pandas_matplotlib_converters
 from pandas.plotting._matplotlib.groupby import reconstruct_data_with_by
 from pandas.plotting._matplotlib.misc import unpack_single_str_list
@@ -1229,19 +1228,13 @@ def _make_plot(self):
             c_values = c
 
         if self.colormap is not None:
-            if mpl_ge_3_6_0():
-                cmap = mpl.colormaps.get_cmap(self.colormap)
-            else:
-                cmap = self.plt.cm.get_cmap(self.colormap)
+            cmap = mpl.colormaps.get_cmap(self.colormap)
         else:
             # cmap is only used if c_values are integers, otherwise UserWarning
             if is_integer_dtype(c_values):
                 # pandas uses colormap, matplotlib uses cmap.
                 cmap = "Greys"
-                if mpl_ge_3_6_0():
-                    cmap = mpl.colormaps[cmap]
-                else:
-                    cmap = self.plt.cm.get_cmap(cmap)
+                cmap = mpl.colormaps[cmap]
             else:
                 cmap = None
 
@@ -1309,10 +1302,7 @@ def _make_plot(self) -> None:
         ax = self.axes[0]
         # pandas uses colormap, matplotlib uses cmap.
         cmap = self.colormap or "BuGn"
-        if mpl_ge_3_6_0():
-            cmap = mpl.colormaps.get_cmap(cmap)
-        else:
-            cmap = self.plt.cm.get_cmap(cmap)
+        cmap = mpl.colormaps.get_cmap(cmap)
         cb = self.kwds.pop("colorbar", True)
 
         if C is None:

pandas/plotting/_matplotlib/style.py

@@ -10,7 +10,6 @@
 import warnings
 
 import matplotlib as mpl
-from matplotlib import cm
 import matplotlib.colors
 import numpy as np
 
@@ -21,8 +20,6 @@
 
 import pandas.core.common as com
 
-from pandas.plotting._matplotlib.compat import mpl_ge_3_6_0
-
 if TYPE_CHECKING:
     from matplotlib.colors import Colormap
 
@@ -153,10 +150,7 @@ def _get_cmap_instance(colormap: str | Colormap) -> Colormap:
     """Get instance of matplotlib colormap."""
     if isinstance(colormap, str):
         cmap = colormap
-        if mpl_ge_3_6_0():
-            colormap = mpl.colormaps[colormap]
-        else:
-            colormap = cm.get_cmap(colormap)
+        colormap = mpl.colormaps[colormap]
         if colormap is None:
             raise ValueError(f"Colormap {cmap} is not recognized")
     return colormap

pandas/plotting/_matplotlib/tools.py

@@ -22,8 +22,6 @@
     ABCSeries,
 )
 
-from pandas.plotting._matplotlib import compat
-
 if TYPE_CHECKING:
     from matplotlib.axes import Axes
     from matplotlib.axis import Axis
@@ -396,10 +394,7 @@ def handle_shared_axes(
         row_num = lambda x: x.get_subplotspec().rowspan.start
         col_num = lambda x: x.get_subplotspec().colspan.start
 
-        if compat.mpl_ge_3_4_0():
-            is_first_col = lambda x: x.get_subplotspec().is_first_col()
-        else:
-            is_first_col = lambda x: x.is_first_col()
+        is_first_col = lambda x: x.get_subplotspec().is_first_col()
 
         if nrows > 1:
             try:
@@ -421,10 +416,7 @@ def handle_shared_axes(
             except IndexError:
                 # if gridspec is used, ax.rowNum and ax.colNum may different
                 # from layout shape. in this case, use last_row logic
-                if compat.mpl_ge_3_4_0():
-                    is_last_row = lambda x: x.get_subplotspec().is_last_row()
-                else:
-                    is_last_row = lambda x: x.is_last_row()
+                is_last_row = lambda x: x.get_subplotspec().is_last_row()
                 for ax in axarr:
                     if is_last_row(ax):
                         continue