Merge branch 'main' into float_format

Yuvraj Pradhan · web-flow · commit 0d6d3558b890 · 2024-11-27T21:57:48.000+05:30
diff --git a/.github/workflows/comment-commands.yml b/.github/workflows/comment-commands.yml
@@ -11,7 +11,7 @@ permissions:
 jobs:
   issue_assign:
     runs-on: ubuntu-22.04
-    if: (!github.event.issue.pull_request) && trim(github.event.comment.body) == 'take'
+    if: (!github.event.issue.pull_request) && github.event.comment.body == 'take'
     concurrency:
       group: ${{ github.actor }}-issue-assign
     steps:
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -152,7 +152,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.21.3
+        uses: pypa/cibuildwheel@v2.22.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -82,7 +82,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
-        -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
@@ -109,17 +108,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.std SA01" \
         -i "pandas.core.resample.Resampler.transform PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.var SA01" \
-        -i "pandas.errors.DuplicateLabelError SA01" \
         -i "pandas.errors.IntCastingNaNError SA01" \
-        -i "pandas.errors.InvalidIndexError SA01" \
         -i "pandas.errors.NullFrequencyError SA01" \
-        -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
-        -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
-        -i "pandas.errors.PossibleDataLossError SA01" \
         -i "pandas.errors.UndefinedVariableError PR01,SA01" \
-        -i "pandas.errors.UnsortedIndexError SA01" \
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
         -i "pandas.infer_freq SA01" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
diff --git a/doc/source/conf.py b/doc/source/conf.py
@@ -242,7 +242,6 @@
     "external_links": [],
     "footer_start": ["pandas_footer", "sphinx-version"],
     "github_url": "https://github.com/pandas-dev/pandas",
-    "twitter_url": "https://twitter.com/pandas_dev",
     "analytics": {
         "plausible_analytics_domain": "pandas.pydata.org",
         "plausible_analytics_url": "https://views.scientific-python.org/js/script.js",
@@ -258,6 +257,11 @@
     # patch version doesn't compare as equal (e.g. 2.2.1 != 2.2.0 but it should be)
     "show_version_warning_banner": False,
     "icon_links": [
+        {
+            "name": "X",
+            "url": "https://x.com/pandas_dev",
+            "icon": "fa-brands fa-square-x-twitter",
+        },
         {
             "name": "Mastodon",
             "url": "https://fosstodon.org/@pandas_dev",
diff --git a/doc/source/user_guide/reshaping.rst b/doc/source/user_guide/reshaping.rst
@@ -321,7 +321,7 @@ The missing value can be filled with a specific value with the ``fill_value`` ar
 .. image:: ../_static/reshaping_melt.png
 
 The top-level :func:`~pandas.melt` function and the corresponding :meth:`DataFrame.melt`
-are useful to massage a :class:`DataFrame` into a format where one or more columns
+are useful to reshape a :class:`DataFrame` into a format where one or more columns
 are *identifier variables*, while all other columns, considered *measured
 variables*, are "unpivoted" to the row axis, leaving just two non-identifier
 columns, "variable" and "value". The names of those columns can be customized
diff --git a/doc/source/user_guide/window.rst b/doc/source/user_guide/window.rst
@@ -567,9 +567,9 @@ One must have :math:`0 < \alpha \leq 1`, and while it is possible to pass
 
    \alpha =
     \begin{cases}
-        \frac{2}{s + 1},               & \text{for span}\ s \geq 1\\
-        \frac{1}{1 + c},               & \text{for center of mass}\ c \geq 0\\
-        1 - \exp^{\frac{\log 0.5}{h}}, & \text{for half-life}\ h > 0
+        \frac{2}{s + 1},            & \text{for span}\ s \geq 1\\
+        \frac{1}{1 + c},            & \text{for center of mass}\ c \geq 0\\
+        1 - e^{\frac{\log 0.5}{h}}, & \text{for half-life}\ h > 0
     \end{cases}
 
 One must specify precisely one of **span**, **center of mass**, **half-life**
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -690,6 +690,7 @@ I/O
 - Bug in :meth:`DataFrame.from_records` where ``columns`` parameter with numpy structured array was not reordering and filtering out the columns (:issue:`59717`)
 - Bug in :meth:`DataFrame.to_dict` raises unnecessary ``UserWarning`` when columns are not unique and ``orient='tight'``. (:issue:`58281`)
 - Bug in :meth:`DataFrame.to_excel` when writing empty :class:`DataFrame` with :class:`MultiIndex` on both axes (:issue:`57696`)
+- Bug in :meth:`DataFrame.to_excel` where the :class:`MultiIndex` index with a period level was not a date (:issue:`60099`)
 - Bug in :meth:`DataFrame.to_stata` when writing :class:`DataFrame` and ``byteorder=`big```. (:issue:`58969`)
 - Bug in :meth:`DataFrame.to_stata` when writing more than 32,000 value labels. (:issue:`60107`)
 - Bug in :meth:`DataFrame.to_string` that raised ``StopIteration`` with nested DataFrames. (:issue:`16098`)
@@ -788,6 +789,7 @@ Other
 - Bug in :meth:`Series.dt` methods in :class:`ArrowDtype` that were returning incorrect values. (:issue:`57355`)
 - Bug in :meth:`Series.rank` that doesn't preserve missing values for nullable integers when ``na_option='keep'``. (:issue:`56976`)
 - Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` inconsistently replacing matching instances when ``regex=True`` and missing values are present. (:issue:`56599`)
+- Bug in :meth:`Series.to_string` when series contains complex floats with exponents (:issue:`60405`)
 - Bug in :meth:`read_csv` where chained fsspec TAR file and ``compression="infer"`` fails with ``tarfile.ReadError`` (:issue:`60028`)
 - Bug in Dataframe Interchange Protocol implementation was returning incorrect results for data buffers' associated dtype, for string and datetime columns (:issue:`54781`)
 - Bug in ``Series.list`` methods not preserving the original :class:`Index`. (:issue:`58425`)
diff --git a/pandas/_libs/index.pyi b/pandas/_libs/index.pyi
@@ -72,6 +72,9 @@ class MaskedUInt16Engine(MaskedIndexEngine): ...
 class MaskedUInt8Engine(MaskedIndexEngine): ...
 class MaskedBoolEngine(MaskedUInt8Engine): ...
 
+class StringObjectEngine(ObjectEngine):
+    def __init__(self, values: object, na_value) -> None: ...
+
 class BaseMultiIndexCodesEngine:
     levels: list[np.ndarray]
     offsets: np.ndarray  # np.ndarray[..., ndim=1]
diff --git a/pandas/_libs/index.pyx b/pandas/_libs/index.pyx
@@ -557,6 +557,31 @@ cdef class StringEngine(IndexEngine):
             raise KeyError(val)
         return str(val)
 
+cdef class StringObjectEngine(ObjectEngine):
+
+    cdef:
+        object na_value
+        bint uses_na
+
+    def __init__(self, ndarray values, na_value):
+        super().__init__(values)
+        self.na_value = na_value
+        self.uses_na = na_value is C_NA
+
+    cdef bint _checknull(self, object val):
+        if self.uses_na:
+            return val is C_NA
+        else:
+            return util.is_nan(val)
+
+    cdef _check_type(self, object val):
+        if isinstance(val, str):
+            return val
+        elif self._checknull(val):
+            return self.na_value
+        else:
+            raise KeyError(val)
+
 
 cdef class DatetimeEngine(Int64Engine):
 
diff --git a/pandas/_libs/tslibs/np_datetime.pyx b/pandas/_libs/tslibs/np_datetime.pyx
@@ -201,6 +201,10 @@ class OutOfBoundsTimedelta(ValueError):
 
     Representation should be within a timedelta64[ns].
 
+    See Also
+    --------
+    date_range : Return a fixed frequency DatetimeIndex.
+
     Examples
     --------
     >>> pd.date_range(start="1/1/1700", freq="B", periods=100000)
diff --git a/pandas/core/arrays/interval.py b/pandas/core/arrays/interval.py
@@ -1055,7 +1055,9 @@ def shift(self, periods: int = 1, fill_value: object = None) -> IntervalArray:
             from pandas import Index
 
             fill_value = Index(self._left, copy=False)._na_value
-            empty = IntervalArray.from_breaks([fill_value] * (empty_len + 1))
+            empty = IntervalArray.from_breaks(
+                [fill_value] * (empty_len + 1), closed=self.closed
+            )
         else:
             empty = self._from_sequence([fill_value] * empty_len, dtype=self.dtype)
 
diff --git a/pandas/core/dtypes/inference.py b/pandas/core/dtypes/inference.py
@@ -190,12 +190,17 @@ def is_re_compilable(obj: object) -> bool:
     Parameters
     ----------
     obj : The object to check
+        The object to check if the object can be compiled into a regex pattern instance.
 
     Returns
     -------
     bool
         Whether `obj` can be compiled as a regex pattern.
 
+    See Also
+    --------
+    api.types.is_re : Check if the object is a regex pattern instance.
+
     Examples
     --------
     >>> from pandas.api.types import is_re_compilable
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -838,7 +838,7 @@ def pop(self, item: Hashable) -> Series | Any:
         return result
 
     @final
-    def squeeze(self, axis: Axis | None = None):
+    def squeeze(self, axis: Axis | None = None) -> Scalar | Series | DataFrame:
         """
         Squeeze 1 dimensional axis objects into scalars.
 
diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
@@ -876,7 +876,7 @@ def _engine(
             # ndarray[Any, Any]]" has no attribute "_ndarray"  [union-attr]
             target_values = self._data._ndarray  # type: ignore[union-attr]
         elif is_string_dtype(self.dtype) and not is_object_dtype(self.dtype):
-            return libindex.StringEngine(target_values)
+            return libindex.StringObjectEngine(target_values, self.dtype.na_value)  # type: ignore[union-attr]
 
         # error: Argument 1 to "ExtensionEngine" has incompatible type
         # "ndarray[Any, Any]"; expected "ExtensionArray"
@@ -5974,7 +5974,6 @@ def _should_fallback_to_positional(self) -> bool:
     def get_indexer_non_unique(
         self, target
     ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]:
-        target = ensure_index(target)
         target = self._maybe_cast_listlike_indexer(target)
 
         if not self._should_compare(target) and not self._should_partial_index(target):
diff --git a/pandas/core/reshape/melt.py b/pandas/core/reshape/melt.py
@@ -51,9 +51,9 @@ def melt(
     """
     Unpivot a DataFrame from wide to long format, optionally leaving identifiers set.
 
-    This function is useful to massage a DataFrame into a format where one
+    This function is useful to reshape a DataFrame into a format where one
     or more columns are identifier variables (`id_vars`), while all other
-    columns, considered measured variables (`value_vars`), are "unpivoted" to
+    columns are considered measured variables (`value_vars`), and are "unpivoted" to
     the row axis, leaving just two non-identifier columns, 'variable' and
     'value'.
 
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
@@ -100,6 +100,11 @@ class UnsortedIndexError(KeyError):
 
     Subclass of `KeyError`.
 
+    See Also
+    --------
+    DataFrame.sort_index : Sort a DataFrame by its index.
+    DataFrame.set_index : Set the DataFrame index using existing columns.
+
     Examples
     --------
     >>> df = pd.DataFrame(
@@ -388,6 +393,19 @@ class DuplicateLabelError(ValueError):
     """
     Error raised when an operation would introduce duplicate labels.
 
+    This error is typically encountered when performing operations on objects
+    with `allows_duplicate_labels=False` and the operation would result in
+    duplicate labels in the index. Duplicate labels can lead to ambiguities
+    in indexing and reduce data integrity.
+
+    See Also
+    --------
+    Series.set_flags : Return a new ``Series`` object with updated flags.
+    DataFrame.set_flags : Return a new ``DataFrame`` object with updated flags.
+    Series.reindex : Conform ``Series`` object to new index with optional filling logic.
+    DataFrame.reindex : Conform ``DataFrame`` object to new index with optional filling
+        logic.
+
     Examples
     --------
     >>> s = pd.Series([0, 1, 2], index=["a", "b", "c"]).set_flags(
@@ -407,6 +425,16 @@ class InvalidIndexError(Exception):
     """
     Exception raised when attempting to use an invalid index key.
 
+    This exception is triggered when a user attempts to access or manipulate
+    data in a pandas DataFrame or Series using an index key that is not valid
+    for the given object. This may occur in cases such as using a malformed
+    slice, a mismatched key for a ``MultiIndex``, or attempting to access an index
+    element that does not exist.
+
+    See Also
+    --------
+    MultiIndex : A multi-level, or hierarchical, index object for pandas objects.
+
     Examples
     --------
     >>> idx = pd.MultiIndex.from_product([["x", "y"], [0, 1]])
@@ -510,6 +538,11 @@ class NumExprClobberingError(NameError):
     to 'numexpr'. 'numexpr' is the default engine value for these methods if the
     numexpr package is installed.
 
+    See Also
+    --------
+    eval : Evaluate a Python expression as a string using various backends.
+    DataFrame.query : Query the columns of a DataFrame with a boolean expression.
+
     Examples
     --------
     >>> df = pd.DataFrame({"abs": [1, 1, 1]})
@@ -633,6 +666,15 @@ class PossibleDataLossError(Exception):
     """
     Exception raised when trying to open a HDFStore file when already opened.
 
+    This error is triggered when there is a potential risk of data loss due to
+    conflicting operations on an HDFStore file. It serves to prevent unintended
+    overwrites or data corruption by enforcing exclusive access to the file.
+
+    See Also
+    --------
+    HDFStore : Dict-like IO interface for storing pandas objects in PyTables.
+    HDFStore.open : Open an HDFStore file in the specified mode.
+
     Examples
     --------
     >>> store = pd.HDFStore("my-store", "a")  # doctest: +SKIP
diff --git a/pandas/io/formats/excel.py b/pandas/io/formats/excel.py
@@ -37,6 +37,7 @@
     DataFrame,
     Index,
     MultiIndex,
+    Period,
     PeriodIndex,
 )
 import pandas.core.common as com
@@ -803,6 +804,9 @@ def _format_hierarchical_rows(self) -> Iterable[ExcelCell]:
                         allow_fill=levels._can_hold_na,
                         fill_value=levels._na_value,
                     )
+                    # GH#60099
+                    if isinstance(values[0], Period):
+                        values = values.to_timestamp()
 
                     for i, span_val in spans.items():
                         mergestart, mergeend = None, None
@@ -827,6 +831,10 @@ def _format_hierarchical_rows(self) -> Iterable[ExcelCell]:
                 # Format hierarchical rows with non-merged values.
                 for indexcolvals in zip(*self.df.index):
                     for idx, indexcolval in enumerate(indexcolvals):
+                        # GH#60099
+                        if isinstance(indexcolval, Period):
+                            indexcolval = indexcolval.to_timestamp()
+
                         yield CssExcelCell(
                             row=self.rowcounter + idx,
                             col=gcolidx,
diff --git a/pandas/io/formats/format.py b/pandas/io/formats/format.py
@@ -1749,7 +1749,7 @@ def _trim_zeros_complex(str_complexes: ArrayLike, decimal: str = ".") -> list[st
         # The split will give [{"", "-"}, "xxx", "+/-", "xxx", "j", ""]
         # Therefore, the imaginary part is the 4th and 3rd last elements,
         # and the real part is everything before the imaginary part
-        trimmed = re.split(r"([j+-])", x)
+        trimmed = re.split(r"(?<!e)([j+-])", x)
         real_part.append("".join(trimmed[:-4]))
         imag_part.append("".join(trimmed[-4:-2]))
 
diff --git a/pandas/tests/frame/methods/test_shift.py b/pandas/tests/frame/methods/test_shift.py
@@ -757,3 +757,12 @@ def test_shift_with_offsets_freq_empty(self):
         df_shifted = DataFrame(index=shifted_dates)
         result = df.shift(freq=offset)
         tm.assert_frame_equal(result, df_shifted)
+
+    def test_series_shift_interval_preserves_closed(self):
+        # GH#60389
+        ser = Series(
+            [pd.Interval(1, 2, closed="right"), pd.Interval(2, 3, closed="right")]
+        )
+        result = ser.shift(1)
+        expected = Series([np.nan, pd.Interval(1, 2, closed="right")])
+        tm.assert_series_equal(result, expected)
diff --git a/pandas/tests/indexes/string/test_indexing.py b/pandas/tests/indexes/string/test_indexing.py
diff --git a/pandas/tests/io/excel/test_style.py b/pandas/tests/io/excel/test_style.py
diff --git a/pandas/tests/io/excel/test_writers.py b/pandas/tests/io/excel/test_writers.py
diff --git a/pandas/tests/io/formats/test_to_string.py b/pandas/tests/io/formats/test_to_string.py
diff --git a/pandas/tests/io/parser/common/test_common_basic.py b/pandas/tests/io/parser/common/test_common_basic.py
diff --git a/pandas/tests/test_algos.py b/pandas/tests/test_algos.py
