Merge remote-tracking branch 'upstream/master' into arrow-string-array-dtype

Author: simonjayhawkins

doc/source/ecosystem.rst

@@ -75,12 +75,12 @@ Statsmodels leverages pandas objects as the underlying data container for comput
 Use pandas DataFrames in your `scikit-learn <https://scikit-learn.org/>`__
 ML pipeline.
 
-`Featuretools <https://github.com/featuretools/featuretools/>`__
+`Featuretools <https://github.com/alteryx/featuretools/>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Featuretools is a Python library for automated feature engineering built on top of pandas. It excels at transforming temporal and relational datasets into feature matrices for machine learning using reusable feature engineering "primitives". Users can contribute their own primitives in Python and share them with the rest of the community.
 
-`Compose <https://github.com/FeatureLabs/compose>`__
+`Compose <https://github.com/alteryx/compose>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Compose is a machine learning tool for labeling data and prediction engineering. It allows you to structure the labeling process by parameterizing prediction problems and transforming time-driven relational data into target values with cutoff times that can be used for supervised learning.
@@ -551,11 +551,12 @@ Library            Accessor     Classes                              Description
 ================== ============ ==================================== ===============================================================================
 `cyberpandas`_     ``ip``       ``Series``                           Provides common operations for working with IP addresses.
 `pdvega`_          ``vgplot``   ``Series``, ``DataFrame``            Provides plotting functions from the Altair_ library.
-`pandas-genomics`_ ``genomics`` ``Series``, ``DataFrame``            Provides common operations for quality control and analysis of genomics data
+`pandas-genomics`_ ``genomics`` ``Series``, ``DataFrame``            Provides common operations for quality control and analysis of genomics data.
 `pandas_path`_     ``path``     ``Index``, ``Series``                Provides `pathlib.Path`_ functions for Series.
 `pint-pandas`_     ``pint``     ``Series``, ``DataFrame``            Provides units support for numeric Series and DataFrames.
 `composeml`_       ``slice``    ``DataFrame``                        Provides a generator for enhanced data slicing.
 `datatest`_        ``validate`` ``Series``, ``DataFrame``, ``Index`` Provides validation, differences, and acceptance managers.
+`woodwork`_        ``ww``       ``Series``, ``DataFrame``            Provides physical, logical, and semantic data typing information for Series and DataFrames.
 ================== ============ ==================================== ===============================================================================
 
 .. _cyberpandas: https://cyberpandas.readthedocs.io/en/latest
@@ -565,5 +566,6 @@ Library            Accessor     Classes                              Description
 .. _pandas_path: https://github.com/drivendataorg/pandas-path/
 .. _pathlib.Path: https://docs.python.org/3/library/pathlib.html
 .. _pint-pandas: https://github.com/hgrecco/pint-pandas
-.. _composeml: https://github.com/FeatureLabs/compose
+.. _composeml: https://github.com/alteryx/compose
 .. _datatest: https://datatest.readthedocs.io/
+.. _woodwork: https://github.com/alteryx/woodwork

doc/source/user_guide/style.ipynb

@@ -1462,7 +1462,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df4.style.format(escape=True)"
+    "df4.style.format(escape=\"html\")"
    ]
   },
   {
@@ -1471,7 +1471,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df4.style.format('<a href=\"https://pandas.pydata.org\" target=\"_blank\">{}</a>', escape=True)"
+    "df4.style.format('<a href=\"https://pandas.pydata.org\" target=\"_blank\">{}</a>', escape=\"html\")"
    ]
   },
   {

doc/source/whatsnew/v1.3.0.rst

@@ -729,9 +729,14 @@ Deprecations
 - Deprecated the ``convert_float`` optional argument in :func:`read_excel` and :meth:`ExcelFile.parse` (:issue:`41127`)
 - Deprecated behavior of :meth:`DatetimeIndex.union` with mixed timezones; in a future version both will be cast to UTC instead of object dtype (:issue:`39328`)
 - Deprecated using ``usecols`` with out of bounds indices for ``read_csv`` with ``engine="c"`` (:issue:`25623`)
+- Deprecated passing arguments as positional (except for ``"codes"``) in :meth:`MultiIndex.codes` (:issue:`41485`)
+- Deprecated passing arguments as positional in :meth:`Index.set_names` and :meth:`MultiIndex.set_names` (except for ``names``) (:issue:`41485`)
+- Deprecated passing arguments (apart from ``cond`` and ``other``) as positional in :meth:`DataFrame.mask` and :meth:`Series.mask` (:issue:`41485`)
 - Deprecated passing arguments as positional in :meth:`DataFrame.clip` and :meth:`Series.clip` (other than ``"upper"`` and ``"lower"``) (:issue:`41485`)
 - Deprecated special treatment of lists with first element a Categorical in the :class:`DataFrame` constructor; pass as ``pd.DataFrame({col: categorical, ...})`` instead (:issue:`38845`)
 - Deprecated passing arguments as positional (except for ``"method"``) in :meth:`DataFrame.interpolate` and :meth:`Series.interpolate` (:issue:`41485`)
+- Deprecated passing arguments as positional in :meth:`DataFrame.ffill`, :meth:`Series.ffill`, :meth:`DataFrame.bfill`, and :meth:`Series.bfill` (:issue:`41485`)
+- Deprecated passing arguments as positional in :meth:`DataFrame.sort_values` (other than ``"by"``) and :meth:`Series.sort_values` (:issue:`41485`)
 - Deprecated passing arguments as positional in :meth:`DataFrame.dropna` and :meth:`Series.dropna` (:issue:`41485`)
 - Deprecated passing arguments as positional in :meth:`DataFrame.set_index` (other than ``"keys"``) (:issue:`41485`)
 - Deprecated passing arguments as positional (except for ``"levels"``) in :meth:`MultiIndex.set_levels` (:issue:`41485`)
@@ -740,7 +745,11 @@ Deprecations
 - Deprecated passing arguments (apart from ``value``) as positional in :meth:`DataFrame.fillna` and :meth:`Series.fillna` (:issue:`41485`)
 - Deprecated passing arguments as positional in :meth:`DataFrame.reset_index` (other than ``"level"``) and :meth:`Series.reset_index` (:issue:`41485`)
 - Deprecated construction of :class:`Series` or :class:`DataFrame` with ``DatetimeTZDtype`` data and ``datetime64[ns]`` dtype.  Use ``Series(data).dt.tz_localize(None)`` instead (:issue:`41555`,:issue:`33401`)
+- Deprecated passing arguments as positional in :meth:`DataFrame.set_axis` and :meth:`Series.set_axis` (other than ``"labels"``) (:issue:`41485`)
 - Deprecated passing arguments as positional in :meth:`DataFrame.where` and :meth:`Series.where` (other than ``"cond"`` and ``"other"``) (:issue:`41485`)
+- Deprecated passing arguments as positional in :meth:`DataFrame.drop` (other than ``"labels"``) and :meth:`Series.drop` (:issue:`41485`)
+-
+
 
 .. _whatsnew_130.deprecations.nuisance_columns:
 

pandas/core/arrays/categorical.py

@@ -2453,7 +2453,9 @@ def replace(self, to_replace, value, inplace: bool = False):
 
     # ------------------------------------------------------------------------
     # String methods interface
-    def _str_map(self, f, na_value=np.nan, dtype=np.dtype("object")):
+    def _str_map(
+        self, f, na_value=np.nan, dtype=np.dtype("object"), convert: bool = True
+    ):
         # Optimization to apply the callable `f` to the categories once
         # and rebuild the result by `take`ing from the result with the codes.
         # Returns the same type as the object-dtype implementation though.

pandas/core/arrays/string_.py

@@ -495,7 +495,9 @@ def _cmp_method(self, other, op):
     # String methods interface
     _str_na_value = StringDtype.na_value
 
-    def _str_map(self, f, na_value=None, dtype: Dtype | None = None):
+    def _str_map(
+        self, f, na_value=None, dtype: Dtype | None = None, convert: bool = True
+    ):
         from pandas.arrays import BooleanArray
 
         if dtype is None:

pandas/core/arrays/string_arrow.py

@@ -653,7 +653,9 @@ def value_counts(self, dropna: bool = True) -> Series:
 
     _str_na_value = StringDtype.na_value
 
-    def _str_map(self, f, na_value=None, dtype: Dtype | None = None):
+    def _str_map(
+        self, f, na_value=None, dtype: Dtype | None = None, convert: bool = True
+    ):
         # TODO: de-duplicate with StringArray method. This method is moreless copy and
         # paste.
 

pandas/core/frame.py

@@ -4703,6 +4703,7 @@ def set_axis(
     ) -> DataFrame | None:
         ...
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "labels"])
     @Appender(
         """
         Examples
@@ -4766,6 +4767,7 @@ def reindex(self, *args, **kwargs) -> DataFrame:
         kwargs.pop("labels", None)
         return super().reindex(**kwargs)
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "labels"])
     def drop(
         self,
         labels=None,
@@ -6221,6 +6223,7 @@ def f(vals) -> tuple[np.ndarray, int]:
     # ----------------------------------------------------------------------
     # Sorting
     # TODO: Just move the sort_values doc here.
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "by"])
     @Substitution(**_shared_doc_kwargs)
     @Appender(NDFrame.sort_values.__doc__)
     # error: Signature of "sort_values" incompatible with supertype "NDFrame"
@@ -10645,6 +10648,26 @@ def values(self) -> np.ndarray:
         self._consolidate_inplace()
         return self._mgr.as_array(transpose=True)
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
+    def ffill(
+        self: DataFrame,
+        axis: None | Axis = None,
+        inplace: bool = False,
+        limit: None | int = None,
+        downcast=None,
+    ) -> DataFrame | None:
+        return super().ffill(axis, inplace, limit, downcast)
+
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
+    def bfill(
+        self: DataFrame,
+        axis: None | Axis = None,
+        inplace: bool = False,
+        limit: None | int = None,
+        downcast=None,
+    ) -> DataFrame | None:
+        return super().bfill(axis, inplace, limit, downcast)
+
     @deprecate_nonkeyword_arguments(
         version=None, allowed_args=["self", "lower", "upper"]
     )
@@ -10697,6 +10720,21 @@ def where(
     ):
         return super().where(cond, other, inplace, axis, level, errors, try_cast)
 
+    @deprecate_nonkeyword_arguments(
+        version=None, allowed_args=["self", "cond", "other"]
+    )
+    def mask(
+        self,
+        cond,
+        other=np.nan,
+        inplace=False,
+        axis=None,
+        level=None,
+        errors="raise",
+        try_cast=lib.no_default,
+    ):
+        return super().mask(cond, other, inplace, axis, level, errors, try_cast)
+
 
 DataFrame._add_numeric_operations()
 

pandas/core/generic.py

@@ -6392,47 +6392,6 @@ def fillna(
         else:
             return result.__finalize__(self, method="fillna")
 
-    @overload
-    def ffill(
-        self: FrameOrSeries,
-        axis: None | Axis = ...,
-        inplace: Literal[False] = ...,
-        limit: None | int = ...,
-        downcast=...,
-    ) -> FrameOrSeries:
-        ...
-
-    @overload
-    def ffill(
-        self: FrameOrSeries,
-        axis: None | Axis,
-        inplace: Literal[True],
-        limit: None | int = ...,
-        downcast=...,
-    ) -> None:
-        ...
-
-    @overload
-    def ffill(
-        self: FrameOrSeries,
-        *,
-        inplace: Literal[True],
-        limit: None | int = ...,
-        downcast=...,
-    ) -> None:
-        ...
-
-    @overload
-    def ffill(
-        self: FrameOrSeries,
-        axis: None | Axis = ...,
-        inplace: bool_t = ...,
-        limit: None | int = ...,
-        downcast=...,
-    ) -> FrameOrSeries | None:
-        ...
-
-    @final
     @doc(klass=_shared_doc_kwargs["klass"])
     def ffill(
         self: FrameOrSeries,
@@ -6455,47 +6414,6 @@ def ffill(
 
     pad = ffill
 
-    @overload
-    def bfill(
-        self: FrameOrSeries,
-        axis: None | Axis = ...,
-        inplace: Literal[False] = ...,
-        limit: None | int = ...,
-        downcast=...,
-    ) -> FrameOrSeries:
-        ...
-
-    @overload
-    def bfill(
-        self: FrameOrSeries,
-        axis: None | Axis,
-        inplace: Literal[True],
-        limit: None | int = ...,
-        downcast=...,
-    ) -> None:
-        ...
-
-    @overload
-    def bfill(
-        self: FrameOrSeries,
-        *,
-        inplace: Literal[True],
-        limit: None | int = ...,
-        downcast=...,
-    ) -> None:
-        ...
-
-    @overload
-    def bfill(
-        self: FrameOrSeries,
-        axis: None | Axis = ...,
-        inplace: bool_t = ...,
-        limit: None | int = ...,
-        downcast=...,
-    ) -> FrameOrSeries | None:
-        ...
-
-    @final
     @doc(klass=_shared_doc_kwargs["klass"])
     def bfill(
         self: FrameOrSeries,
@@ -9144,7 +9062,7 @@ def mask(
                 "try_cast keyword is deprecated and will be removed in a "
                 "future version",
                 FutureWarning,
-                stacklevel=2,
+                stacklevel=4,
             )
 
         # see gh-21891
@@ -9303,7 +9221,7 @@ def shift(
         else:
             new_ax = index.shift(periods, freq)
 
-        result = self.set_axis(new_ax, axis)
+        result = self.set_axis(new_ax, axis=axis)
         return result.__finalize__(self, method="shift")
 
     @final

pandas/core/indexes/base.py

@@ -1538,7 +1538,7 @@ def _set_names(self, values, level=None) -> None:
 
     names = property(fset=_set_names, fget=_get_names)
 
-    @final
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "names"])
     def set_names(self, names, level=None, inplace: bool = False):
         """
         Set Index or MultiIndex name.

pandas/core/indexes/multi.py

@@ -292,7 +292,6 @@ class MultiIndex(Index):
     _levels = FrozenList()
     _codes = FrozenList()
     _comparables = ["names"]
-    rename = Index.set_names
 
     sortorder: int | None
 
@@ -992,6 +991,7 @@ def _set_codes(
 
         self._reset_cache()
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "codes"])
     def set_codes(self, codes, level=None, inplace=None, verify_integrity: bool = True):
         """
         Set new codes on MultiIndex. Defaults to returning new index.
@@ -1059,7 +1059,7 @@ def set_codes(self, codes, level=None, inplace=None, verify_integrity: bool = Tr
             warnings.warn(
                 "inplace is deprecated and will be removed in a future version.",
                 FutureWarning,
-                stacklevel=2,
+                stacklevel=3,
             )
         else:
             inplace = False
@@ -3585,7 +3585,9 @@ def _get_reconciled_name_object(self, other) -> MultiIndex:
         """
         names = self._maybe_match_names(other)
         if self.names != names:
-            return self.rename(names)
+            # Incompatible return value type (got "Optional[MultiIndex]", expected
+            # "MultiIndex")
+            return self.rename(names)  # type: ignore[return-value]
         return self
 
     def _maybe_match_names(self, other):
@@ -3784,6 +3786,12 @@ def isin(self, values, level=None) -> np.ndarray:
                 return np.zeros(len(levs), dtype=np.bool_)
             return levs.isin(values)
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "names"])
+    def set_names(self, names, level=None, inplace: bool = False) -> MultiIndex | None:
+        return super().set_names(names=names, level=level, inplace=inplace)
+
+    rename = set_names
+
     @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
     def drop_duplicates(self, keep: str | bool = "first") -> MultiIndex:
         return super().drop_duplicates(keep=keep)