Merge branch 'main' into 50040-add-math-mode-formatter-escape=latex-part2

Author: natmokval

.github/actions/build_pandas/action.yml

@@ -16,5 +16,7 @@ runs:
         python -m pip install -e . --no-build-isolation --no-use-pep517 --no-index
       shell: bash -el {0}
       env:
-        # https://docs.github.com/en/actions/using-github-hosted-runners/about-github-hosted-runners#supported-runners-and-hardware-resources
-        N_JOBS: ${{ runner.os == 'macOS' && 3 || 2 }}
+        # Cannot use parallel compilation on Windows, see https://github.com/pandas-dev/pandas/issues/30873
+        # GH 47305: Parallel build causes flaky ImportError: /home/runner/work/pandas/pandas/pandas/_libs/tslibs/timestamps.cpython-38-x86_64-linux-gnu.so: undefined symbol: pandas_datetime_to_datetimestruct
+        N_JOBS: 1
+        #N_JOBS: ${{ runner.os == 'Windows' && 1 || 2 }}

.github/actions/setup-conda/action.yml

@@ -30,7 +30,7 @@ runs:
         environment-name: ${{ inputs.environment-name }}
         extra-specs: ${{ inputs.extra-specs }}
         channels: conda-forge
-        channel-priority: 'strict'
+        channel-priority: ${{ runner.os == 'macOS' && 'flexible' || 'strict' }}
         condarc-file: ci/condarc.yml
         cache-env: true
         cache-downloads: true

.github/workflows/package-checks.yml

@@ -20,7 +20,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        extra: ["test", "performance", "timezone", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output_formatting", "clipboard", "compression", "all"]
+        extra: ["test", "performance", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output_formatting", "clipboard", "compression", "all"]
       fail-fast: false
     name: Install Extras - ${{ matrix.extra }}
     concurrency:

ci/deps/actions-310-numpydev.yaml

@@ -18,9 +18,11 @@ dependencies:
   - python-dateutil
   - pytz
   - pip
+
   - pip:
     - "cython"
     - "--extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple"
     - "--pre"
     - "numpy"
     - "scipy"
+    - "tzdata>=2022.1"

ci/deps/actions-310.yaml

@@ -49,8 +49,10 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-311.yaml

@@ -49,8 +49,10 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-38-downstream_compat.yaml

@@ -68,3 +68,6 @@ dependencies:
   - pandas-gbq>=0.15.0
   - pyyaml
   - py
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-38-minimum_versions.yaml

@@ -52,11 +52,11 @@ dependencies:
   - scipy=1.7.1
   - sqlalchemy=1.4.16
   - tabulate=0.8.9
-  - tzdata=2022a
   - xarray=0.21.0
   - xlrd=2.0.1
   - xlsxwriter=1.4.3
   - zstandard=0.15.2
 
   - pip:
     - pyqt5==5.15.1
+    - tzdata==2022.1

ci/deps/actions-38.yaml

@@ -53,3 +53,6 @@ dependencies:
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-39.yaml

@@ -49,8 +49,10 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - tzdata>=2022.1

ci/deps/actions-pypy-38.yaml

@@ -22,3 +22,6 @@ dependencies:
   - numpy
   - python-dateutil
   - pytz
+
+  - pip:
+    - tzdata>=2022.1

ci/test_wheels_windows.bat

@@ -3,7 +3,7 @@ pd.test(extra_args=['-m not clipboard and not single_cpu and not slow and not ne
 pd.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db'])
 
 python --version
-pip install pytz six numpy python-dateutil
+pip install pytz six numpy python-dateutil tzdata>=2022.1
 pip install hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17
 pip install --find-links=pandas/dist --no-index pandas
 python -c "%test_command%"

doc/source/getting_started/install.rst

@@ -308,25 +308,6 @@ Dependency                                            Minimum Version    pip ext
 `numba <https://github.com/numba/numba>`__            0.53.1             performance        Alternative execution engine for operations that accept ``engine="numba"`` using a JIT compiler that translates Python functions to optimized machine code using the LLVM compiler.
 ===================================================== ================== ================== ===================================================================================================================================================================================
 
-Timezones
-^^^^^^^^^
-
-Installable with ``pip install "pandas[timezone]"``
-
-========================= ========================= =============== =============================================================
-Dependency                Minimum Version           pip extra       Notes
-========================= ========================= =============== =============================================================
-tzdata                    2022.1(pypi)/             timezone        Allows the use of ``zoneinfo`` timezones with pandas.
-                          2022a(for system tzdata)                  **Note**: You only need to install the pypi package if your
-                                                                    system does not already provide the IANA tz database.
-                                                                    However, the minimum tzdata version still applies, even if it
-                                                                    is not enforced through an error.
-
-                                                                    If you would like to keep your system tzdata version updated,
-                                                                    it is recommended to use the ``tzdata`` package from
-                                                                    conda-forge.
-========================= ========================= =============== =============================================================
-
 Visualization
 ^^^^^^^^^^^^^
 

doc/source/user_guide/copy_on_write.rst

@@ -114,10 +114,11 @@ two subsequent indexing operations, e.g.
 The column ``foo`` is updated where the column ``bar`` is greater than 5.
 This violates the CoW principles though, because it would have to modify the
 view ``df["foo"]`` and ``df`` in one step. Hence, chained assignment will
-consistently never work and raise a ``ChainedAssignmentError`` with CoW enabled:
+consistently never work and raise a ``ChainedAssignmentError`` warning
+with CoW enabled:
 
 .. ipython:: python
-    :okexcept:
+    :okwarning:
 
     df = pd.DataFrame({"foo": [1, 2, 3], "bar": [4, 5, 6]})
     df["foo"][df["bar"] > 5] = 100

doc/source/whatsnew/v2.0.0.rst

@@ -25,7 +25,7 @@ When installing pandas using pip, sets of optional dependencies can also be inst
   pip install "pandas[performance, aws]>=2.0.0"
 
 The available extras, found in the :ref:`installation guide<install.dependencies>`, are
-``[all, performance, computation, timezone, fss, aws, gcp, excel, parquet, feather, hdf5, spss, postgresql, mysql,
+``[all, performance, computation, fss, aws, gcp, excel, parquet, feather, hdf5, spss, postgresql, mysql,
 sql-other, html, xml, plot, output_formatting, clipboard, compression, test]`` (:issue:`39164`).
 
 .. _whatsnew_200.enhancements.index_can_hold_numpy_numeric_dtypes:
@@ -191,12 +191,12 @@ Copy-on-Write improvements
   of those Series objects for the columns of the DataFrame (:issue:`50777`)
 
 - Trying to set values using chained assignment (for example, ``df["a"][1:3] = 0``)
-  will now always raise an exception when Copy-on-Write is enabled. In this mode,
+  will now always raise an warning when Copy-on-Write is enabled. In this mode,
   chained assignment can never work because we are always setting into a temporary
   object that is the result of an indexing operation (getitem), which under
   Copy-on-Write always behaves as a copy. Thus, assigning through a chain
   can never update the original Series or DataFrame. Therefore, an informative
-  error is raised to the user instead of silently doing nothing (:issue:`49467`)
+  warning is raised to the user to avoid silently doing nothing (:issue:`49467`)
 
 - :meth:`DataFrame.replace` will now respect the Copy-on-Write mechanism
   when ``inplace=True``.
@@ -650,6 +650,8 @@ If installed, we now require:
 +-------------------+-----------------+----------+---------+
 | python-dateutil   | 2.8.2           |    X     |    X    |
 +-------------------+-----------------+----------+---------+
+| tzdata            | 2022.1          |    X     |    X    |
++-------------------+-----------------+----------+---------+
 
 For `optional libraries <https://pandas.pydata.org/docs/getting_started/install.html>`_ the general recommendation is to use the latest version.
 The following table lists the lowest version per library that is currently being tested throughout the development of pandas.

environment.yml

@@ -52,7 +52,6 @@ dependencies:
   - scipy>=1.7.1
   - sqlalchemy>=1.4.16
   - tabulate>=0.8.9
-  - tzdata>=2022a
   - xarray>=0.21.0
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
@@ -119,3 +118,4 @@ dependencies:
   - pip:
       - sphinx-toggleprompt
       - typing_extensions; python_version<"3.11"
+      - tzdata>=2022.1

pandas/_libs/tslibs/offsets.pyx

@@ -2574,11 +2574,28 @@ cdef class MonthBegin(MonthOffset):
     """
     DateOffset of one month at beginning.
 
+    MonthBegin goes to the next date which is a start of the month.
+    To get the start of the current month pass the parameter n equals 0.
+
+    See Also
+    --------
+    :class:`~pandas.tseries.offsets.DateOffset` : Standard kind of date increment.
+
     Examples
     --------
-    >>> ts = pd.Timestamp(2022, 1, 1)
+    >>> ts = pd.Timestamp(2022, 11, 30)
+    >>> ts + pd.offsets.MonthBegin()
+    Timestamp('2022-12-01 00:00:00')
+
+    >>> ts = pd.Timestamp(2022, 12, 1)
     >>> ts + pd.offsets.MonthBegin()
-    Timestamp('2022-02-01 00:00:00')
+    Timestamp('2023-01-01 00:00:00')
+
+    If you want to get the start of the current month pass the parameter n equals 0:
+
+    >>> ts = pd.Timestamp(2022, 12, 1)
+    >>> ts + pd.offsets.MonthBegin(0)
+    Timestamp('2022-12-01 00:00:00')
     """
     _prefix = "MS"
     _day_opt = "start"
@@ -2616,16 +2633,26 @@ cdef class BusinessMonthBegin(MonthOffset):
     """
     DateOffset of one month at the first business day.
 
+    BusinessMonthBegin goes to the next date which is the first business day
+    of the month. To get the first business day of the current month pass
+    the parameter n equals 0.
+
     Examples
     --------
-    >>> from pandas.tseries.offsets import BMonthBegin
-    >>> ts=pd.Timestamp('2020-05-24 05:01:15')
-    >>> ts + BMonthBegin()
-    Timestamp('2020-06-01 05:01:15')
-    >>> ts + BMonthBegin(2)
-    Timestamp('2020-07-01 05:01:15')
-    >>> ts + BMonthBegin(-3)
-    Timestamp('2020-03-02 05:01:15')
+    >>> ts = pd.Timestamp(2022, 11, 30)
+    >>> ts + pd.offsets.BMonthBegin()
+    Timestamp('2022-12-01 00:00:00')
+
+    >>> ts = pd.Timestamp(2022, 12, 1)
+    >>> ts + pd.offsets.BMonthBegin()
+    Timestamp('2023-01-02 00:00:00')
+
+    If you want to get the start of the current business month pass
+    the parameter n equals 0:
+
+    >>> ts = pd.Timestamp(2022, 12, 1)
+    >>> ts + pd.offsets.BMonthBegin(0)
+    Timestamp('2022-12-01 00:00:00')
     """
     _prefix = "BMS"
     _day_opt = "business_start"
@@ -3671,7 +3698,9 @@ cdef class Easter(SingleConstructorOffset):
 
 cdef class CustomBusinessDay(BusinessDay):
     """
-    DateOffset subclass representing custom business days excluding holidays.
+    DateOffset subclass representing possibly n custom business days.
+
+    In CustomBusinessDay we can use custom weekmask, holidays, and calendar.
 
     Parameters
     ----------
@@ -3685,13 +3714,50 @@ cdef class CustomBusinessDay(BusinessDay):
         List/array of dates to exclude from the set of valid business days,
         passed to ``numpy.busdaycalendar``.
     calendar : np.busdaycalendar
+        Calendar to integrate.
     offset : timedelta, default timedelta(0)
+        Time offset to apply.
 
     Examples
     --------
-    >>> ts = pd.Timestamp(2022, 8, 5)
-    >>> ts + pd.offsets.CustomBusinessDay(1)
-    Timestamp('2022-08-08 00:00:00')
+    In the example below the default parameters give the next business day.
+
+    >>> ts = pd.Timestamp(2022, 8, 5, 16)
+    >>> ts + pd.offsets.CustomBusinessDay()
+    Timestamp('2022-08-08 16:00:00')
+
+    Business days can be specified by ``weekmask`` parameter. To convert
+    the returned datetime object to its string representation
+    the function strftime() is used in the next example.
+
+    >>> import datetime as dt
+    >>> freq = pd.offsets.CustomBusinessDay(weekmask="Mon Wed Fri")
+    >>> pd.date_range(dt.datetime(2022, 12, 10), dt.datetime(2022, 12, 21),
+    ...               freq=freq).strftime('%a %d %b %Y %H:%M')
+    Index(['Mon 12 Dec 2022 00:00', 'Wed 14 Dec 2022 00:00',
+           'Fri 16 Dec 2022 00:00', 'Mon 19 Dec 2022 00:00',
+           'Wed 21 Dec 2022 00:00'],
+           dtype='object')
+
+    Using NumPy business day calendar you can define custom holidays.
+
+    >>> import datetime as dt
+    >>> bdc = np.busdaycalendar(holidays=['2022-12-12', '2022-12-14'])
+    >>> freq = pd.offsets.CustomBusinessDay(calendar=bdc)
+    >>> pd.date_range(dt.datetime(2022, 12, 10), dt.datetime(2022, 12, 25), freq=freq)
+    DatetimeIndex(['2022-12-13', '2022-12-15', '2022-12-16', '2022-12-19',
+                   '2022-12-20', '2022-12-21', '2022-12-22', '2022-12-23'],
+                   dtype='datetime64[ns]', freq='C')
+
+    If you want to shift the result on n day you can use the parameter ``offset``.
+
+    >>> pd.Timestamp(2022, 8, 5, 16) + pd.offsets.CustomBusinessDay(1)
+    Timestamp('2022-08-08 16:00:00')
+
+    >>> import datetime as dt
+    >>> ts = pd.Timestamp(2022, 8, 5, 16)
+    >>> ts + pd.offsets.CustomBusinessDay(1, offset=dt.timedelta(days=1))
+    Timestamp('2022-08-09 16:00:00')
     """
 
     _prefix = "C"

pandas/_testing/contexts.py

@@ -211,9 +211,9 @@ def raises_chained_assignment_error():
 
         return nullcontext()
     else:
-        import pytest
+        from pandas._testing import assert_produces_warning
 
-        return pytest.raises(
+        return assert_produces_warning(
             ChainedAssignmentError,
             match=(
                 "A value is trying to be set on a copy of a DataFrame or Series "

pandas/_typing.py

@@ -131,9 +131,6 @@
 # Series is passed into a function, a Series is always returned and if a DataFrame is
 # passed in, a DataFrame is always returned.
 NDFrameT = TypeVar("NDFrameT", bound="NDFrame")
-# same as NDFrameT, needed when binding two pairs of parameters to potentially
-# separate NDFrame-subclasses (see NDFrame.align)
-NDFrameTb = TypeVar("NDFrameTb", bound="NDFrame")
 
 NumpyIndexT = TypeVar("NumpyIndexT", np.ndarray, "Index")