Merge branch 'pandas-dev:main' into issue-48949

Author: kostyafarber

.github/workflows/scorecards.yml

@@ -29,7 +29,7 @@ jobs:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/[email protected].3
+        uses: ossf/[email protected].6
         with:
           results_file: results.sarif
           results_format: sarif

.github/workflows/wheels.yml

@@ -52,7 +52,7 @@ jobs:
         - [windows-2019, win_amd64]
         - [windows-2019, win32]
         # TODO: support PyPy?
-        python: [["cp38", "3.8"], ["cp39", "3.9"], ["cp310", "3.10"],  ["cp311", "3.11-dev"]]# "pp38", "pp39"]
+        python: [["cp38", "3.8"], ["cp39", "3.9"], ["cp310", "3.10"],  ["cp311", "3.11"]]# "pp38", "pp39"]
     env:
       IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -73,7 +73,7 @@ jobs:
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
 
       # Used to test the built wheels
-      - uses: actions/setup-python@v3
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python[1] }}
 

asv_bench/benchmarks/groupby.py

@@ -683,7 +683,7 @@ class String:
     def setup(self, dtype, method):
         cols = list("abcdefghjkl")
         self.df = DataFrame(
-            np.random.randint(0, 100, size=(1_000_000, len(cols))),
+            np.random.randint(0, 100, size=(10_000, len(cols))),
             columns=cols,
             dtype=dtype,
         )

asv_bench/benchmarks/io/style.py

@@ -83,11 +83,11 @@ def _style_format(self):
     def _style_apply_format_hide(self):
         self.st = self.df.style.applymap(lambda v: "color: red;")
         self.st.format("{:.3f}")
-        self.st.hide_index(self.st.index[1:])
-        self.st.hide_columns(self.st.columns[1:])
+        self.st.hide(self.st.index[1:], axis=0)
+        self.st.hide(self.st.columns[1:], axis=1)
 
     def _style_tooltips(self):
         ttips = DataFrame("abc", index=self.df.index[::2], columns=self.df.columns[::2])
         self.st = self.df.style.set_tooltips(ttips)
-        self.st.hide_index(self.st.index[12:])
-        self.st.hide_columns(self.st.columns[12:])
+        self.st.hide(self.st.index[12:], axis=0)
+        self.st.hide(self.st.columns[12:], axis=1)

doc/source/getting_started/install.rst

@@ -20,7 +20,7 @@ Instructions for installing from source,
 Python version support
 ----------------------
 
-Officially Python 3.8, 3.9 and 3.10.
+Officially Python 3.8, 3.9, 3.10 and 3.11.
 
 Installing pandas
 -----------------

doc/source/whatsnew/v1.5.2.rst

@@ -13,7 +13,7 @@ including other versions of pandas.
 
 Fixed regressions
 ~~~~~~~~~~~~~~~~~
--
+- Fixed regression in :meth:`Series.replace` raising ``RecursionError`` with numeric dtype and when specifying ``value=None`` (:issue:`45725`)
 -
 
 .. ---------------------------------------------------------------------------

doc/source/whatsnew/v2.0.0.rst

@@ -142,6 +142,7 @@ Other API changes
 - The ``other`` argument in :meth:`DataFrame.mask` and :meth:`Series.mask` now defaults to ``no_default`` instead of ``np.nan`` consistent with :meth:`DataFrame.where` and :meth:`Series.where`. Entries will be filled with the corresponding NULL value (``np.nan`` for numpy dtypes, ``pd.NA`` for extension dtypes). (:issue:`49111`)
 - When creating a :class:`Series` with a object-dtype :class:`Index` of datetime objects, pandas no longer silently converts the index to a :class:`DatetimeIndex` (:issue:`39307`, :issue:`23598`)
 - :meth:`Series.unique` with dtype "timedelta64[ns]" or "datetime64[ns]" now returns :class:`TimedeltaArray` or :class:`DatetimeArray` instead of ``numpy.ndarray`` (:issue:`49176`)
+- Passing strings that cannot be parsed as datetimes to :class:`Series` or :class:`DataFrame` with ``dtype="datetime64[ns]"`` will raise instead of silently ignoring the keyword and returning ``object`` dtype (:issue:`24435`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -157,6 +158,7 @@ Deprecations
 
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+- Removed deprecated module ``pandas.core.index`` (:issue:`30193`)
 - Removed deprecated :meth:`Categorical.to_dense`, use ``np.asarray(cat)`` instead (:issue:`32639`)
 - Removed deprecated :meth:`Categorical.take_nd` (:issue:`27745`)
 - Removed deprecated :meth:`Categorical.mode`, use ``Series(cat).mode()`` instead (:issue:`45033`)
@@ -174,8 +176,14 @@ Removal of prior version deprecations/changes
 - Removed deprecated ``weekofyear`` and ``week`` attributes of :class:`DatetimeArray`, :class:`DatetimeIndex` and ``dt`` accessor in favor of ``isocalendar().week`` (:issue:`33595`)
 - Removed deprecated :meth:`RangeIndex._start`, :meth:`RangeIndex._stop`, :meth:`RangeIndex._step`, use ``start``, ``stop``, ``step`` instead (:issue:`30482`)
 - Removed deprecated :meth:`DatetimeIndex.to_perioddelta`, Use ``dtindex - dtindex.to_period(freq).to_timestamp()`` instead (:issue:`34853`)
+- Removed deprecated :meth:`.Styler.hide_index` and :meth:`.Styler.hide_columns` (:issue:`49397`)
+- Removed deprecated :meth:`.Styler.set_na_rep` and :meth:`.Styler.set_precision` (:issue:`49397`)
+- Removed deprecated :meth:`.Styler.where` (:issue:`49397`)
+- Removed deprecated :meth:`.Styler.render` (:issue:`49397`)
+- Removed deprecated argument ``null_color`` in :meth:`.Styler.highlight_null` (:issue:`49397`)
 - Enforced deprecation disallowing passing a timezone-aware :class:`Timestamp` and ``dtype="datetime64[ns]"`` to :class:`Series` or :class:`DataFrame` constructors (:issue:`41555`)
 - Enforced deprecation disallowing passing a sequence of timezone-aware values and ``dtype="datetime64[ns]"`` to to :class:`Series` or :class:`DataFrame` constructors (:issue:`41555`)
+- Enforced deprecation disallowing unit-less "datetime64" dtype in :meth:`Series.astype` and :meth:`DataFrame.astype` (:issue:`47844`)
 - Enforced deprecation disallowing using ``.astype`` to convert a ``datetime64[ns]`` :class:`Series`, :class:`DataFrame`, or :class:`DatetimeIndex` to timezone-aware dtype, use ``obj.tz_localize`` or ``ser.dt.tz_localize`` instead (:issue:`39258`)
 - Enforced deprecation disallowing using ``.astype`` to convert a timezone-aware :class:`Series`, :class:`DataFrame`, or :class:`DatetimeIndex` to timezone-naive ``datetime64[ns]`` dtype, use ``obj.tz_localize(None)`` or ``obj.tz_convert("UTC").tz_localize(None)`` instead (:issue:`39258`)
 - Removed Date parser functions :func:`~pandas.io.date_converters.parse_date_time`,

pandas/core/arrays/_mixins.py

@@ -304,7 +304,6 @@ def _fill_mask_inplace(
         # (for now) when self.ndim == 2, we assume axis=0
         func = missing.get_fill_func(method, ndim=self.ndim)
         func(self._ndarray.T, limit=limit, mask=mask.T)
-        return
 
     @doc(ExtensionArray.fillna)
     def fillna(

pandas/core/arrays/base.py

@@ -1556,7 +1556,6 @@ def _fill_mask_inplace(
         func(npvalues, limit=limit, mask=mask.copy())
         new_values = self._from_sequence(npvalues, dtype=self.dtype)
         self[mask] = new_values[mask]
-        return
 
     def _rank(
         self,

pandas/core/arrays/datetimes.py

@@ -683,15 +683,10 @@ def astype(self, dtype, copy: bool = True):
             and dtype != self.dtype
             and is_unitless(dtype)
         ):
-            # TODO(2.0): just fall through to dtl.DatetimeLikeArrayMixin.astype
-            warnings.warn(
-                "Passing unit-less datetime64 dtype to .astype is deprecated "
-                "and will raise in a future version. Pass 'datetime64[ns]' instead",
-                FutureWarning,
-                stacklevel=find_stack_level(),
+            raise TypeError(
+                "Casting to unit-less dtype 'datetime64' is not supported. "
+                "Pass e.g. 'datetime64[ns]' instead."
             )
-            # unit conversion e.g. datetime64[s]
-            return self._ndarray.astype(dtype)
 
         elif is_period_dtype(dtype):
             return self.to_period(freq=dtype.freq)

pandas/core/dtypes/cast.py

@@ -20,7 +20,6 @@
 )
 import warnings
 
-from dateutil.parser import ParserError
 import numpy as np
 
 from pandas._libs import lib
@@ -1339,28 +1338,21 @@ def maybe_cast_to_datetime(
             if value.size or not is_dtype_equal(value.dtype, dtype):
                 _disallow_mismatched_datetimelike(value, dtype)
 
-                try:
-                    dta = sequence_to_datetimes(value)
-                    # GH 25843: Remove tz information since the dtype
-                    # didn't specify one
-
-                    if dta.tz is not None:
-                        raise ValueError(
-                            "Cannot convert timezone-aware data to "
-                            "timezone-naive dtype. Use "
-                            "pd.Series(values).dt.tz_localize(None) instead."
-                        )
-
-                    # TODO(2.0): Do this astype in sequence_to_datetimes to
-                    #  avoid potential extra copy?
-                    dta = dta.astype(dtype, copy=False)
-                    value = dta
-
-                except OutOfBoundsDatetime:
-                    raise
-                except ParserError:
-                    # Note: this is dateutil's ParserError, not ours.
-                    pass
+                dta = sequence_to_datetimes(value)
+                # GH 25843: Remove tz information since the dtype
+                # didn't specify one
+
+                if dta.tz is not None:
+                    raise ValueError(
+                        "Cannot convert timezone-aware data to "
+                        "timezone-naive dtype. Use "
+                        "pd.Series(values).dt.tz_localize(None) instead."
+                    )
+
+                # TODO(2.0): Do this astype in sequence_to_datetimes to
+                #  avoid potential extra copy?
+                dta = dta.astype(dtype, copy=False)
+                value = dta
 
         elif getattr(vdtype, "kind", None) in ["m", "M"]:
             # we are already datetimelike and want to coerce to non-datetimelike;

pandas/core/index.py

@@ -571,7 +571,6 @@ def replace(
         # Note: the checks we do in NDFrame.replace ensure we never get
         #  here with listlike to_replace or value, as those cases
         #  go through replace_list
-
         values = self.values
 
         if isinstance(values, Categorical):
@@ -610,7 +609,10 @@ def replace(
             return blocks
 
         elif self.ndim == 1 or self.shape[0] == 1:
-            blk = self.coerce_to_target_dtype(value)
+            if value is None:
+                blk = self.astype(np.dtype(object))
+            else:
+                blk = self.coerce_to_target_dtype(value)
             return blk.replace(
                 to_replace=to_replace,
                 value=value,

pandas/core/internals/blocks.py

@@ -258,7 +258,6 @@ def interpolate_array_2d(
             fill_value=fill_value,
             **kwargs,
         )
-    return
 
 
 def _interpolate_2d_with_fill(
@@ -341,7 +340,6 @@ def func(yvalues: np.ndarray) -> None:
     # Sequence[Sequence[Sequence[_SupportsArray[dtype[<nothing>]]]]],
     # Sequence[Sequence[Sequence[Sequence[_SupportsArray[dtype[<nothing>]]]]]]]]"
     np.apply_along_axis(func, axis, data)  # type: ignore[arg-type]
-    return
 
 
 def _index_to_interp_indices(index: Index, method: str) -> np.ndarray:
@@ -762,8 +760,6 @@ def _interpolate_with_limit_area(
 
         values[invalid] = np.nan
 
-    return
-
 
 def interpolate_2d(
     values: np.ndarray,