Merge remote-tracking branch 'upstream/main' into pyarrow-nameerror

Author: yuanx749

.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:

ci/code_checks.sh

@@ -109,17 +109,11 @@ 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" \

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**

doc/source/whatsnew/v3.0.0.rst

@@ -791,6 +791,7 @@ 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`)

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)

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)
 

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

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]))
 

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)

pandas/tests/io/formats/test_to_string.py

@@ -422,6 +422,24 @@ def test_to_string_complex_float_formatting(self):
             )
             assert result == expected
 
+    def test_to_string_complex_float_formatting_with_exponents(self):
+        # GH #60393
+        with option_context("display.precision", 6):
+            df = DataFrame(
+                {
+                    "x": [
+                        (1.8816e-09 + 0j),
+                        (1.8816e-09 + 3.39676e-09j),
+                    ]
+                }
+            )
+            result = df.to_string()
+            expected = (
+                "                            x\n0  1.881600e-09+0.000000e+00j\n"
+                "1  1.881600e-09+3.396760e-09j"
+            )
+            assert result == expected
+
     def test_to_string_format_inf(self):
         # GH#24861
         df = DataFrame(