Merge branch 'pandas-dev:main' into CLN/separate_logic_from_init

Author: PedroVerardo

.github/workflows/unit-tests.yml

@@ -314,7 +314,7 @@ jobs:
     timeout-minutes: 90
 
     concurrency:
-      #https://i.8713187.xyzmunity/t/concurrecy-not-work-for-push/183068/7
+      # https://i.8713187.xyzmunity/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-${{ matrix.pytest_target }}-dev
       cancel-in-progress: true
 
@@ -346,3 +346,62 @@ jobs:
 
       - name: Run Tests
         uses: ./.github/actions/run-tests
+
+  emscripten:
+    # Note: the Python version, Emscripten toolchain version are determined
+    # by the Pyodide version. The appropriate versions can be found in the
+    # Pyodide repodata.json "info" field, or in the Makefile.envs file:
+    # https://github.com/pyodide/pyodide/blob/stable/Makefile.envs#L2
+    # The Node.js version can be determined via Pyodide:
+    # https://pyodide.org/en/stable/usage/index.html#node-js
+    name: Pyodide build
+    runs-on: ubuntu-22.04
+    concurrency:
+      # https://i.8713187.xyzmunity/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-wasm
+      cancel-in-progress: true
+    steps:
+      - name: Checkout pandas Repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python for Pyodide
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11.3'
+
+      - name: Set up Emscripten toolchain
+        uses: mymindstorm/setup-emsdk@v14
+        with:
+          version: '3.1.46'
+          actions-cache-folder: emsdk-cache
+
+      - name: Install pyodide-build
+        run: pip install "pyodide-build==0.25.1"
+
+      - name: Build pandas for Pyodide
+        run: |
+          pyodide build
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+
+      - name: Set up Pyodide virtual environment
+        run: |
+          pyodide venv .venv-pyodide
+          source .venv-pyodide/bin/activate
+          pip install dist/*.whl
+
+      - name: Test pandas for Pyodide
+        env:
+          PANDAS_CI: 1
+        run: |
+          source .venv-pyodide/bin/activate
+          pip install pytest hypothesis
+          # do not import pandas from the checked out repo
+          cd ..
+          python -c 'import pandas as pd; pd.test(extra_args=["-m not clipboard and not single_cpu and not slow and not network and not db"])'

ci/code_checks.sh

@@ -223,6 +223,7 @@ Removal of prior version deprecations/changes
 - All arguments except ``name`` in :meth:`Index.rename` are now keyword only (:issue:`56493`)
 - All arguments except the first ``path``-like argument in IO writers are now keyword only (:issue:`54229`)
 - Changed behavior of :meth:`Series.__getitem__` and :meth:`Series.__setitem__` to always treat integer keys as labels, never as positional, consistent with :class:`DataFrame` behavior (:issue:`50617`)
+- Disallow a callable argument to :meth:`Series.iloc` to return a ``tuple`` (:issue:`53769`)
 - Disallow allowing logical operations (``||``, ``&``, ``^``) between pandas objects and dtype-less sequences (e.g. ``list``, ``tuple``); wrap the objects in :class:`Series`, :class:`Index`, or ``np.array`` first instead (:issue:`52264`)
 - Disallow automatic casting to object in :class:`Series` logical operations (``&``, ``^``, ``||``) between series with mismatched indexes and dtypes other than ``object`` or ``bool`` (:issue:`52538`)
 - Disallow calling :meth:`Series.replace` or :meth:`DataFrame.replace` without a ``value`` and with non-dict-like ``to_replace`` (:issue:`33302`)
@@ -234,6 +235,7 @@ Removal of prior version deprecations/changes
 - Removed "freq" keyword from :class:`PeriodArray` constructor, use "dtype" instead (:issue:`52462`)
 - Removed 'fastpath' keyword in :class:`Categorical` constructor (:issue:`20110`)
 - Removed 'kind' keyword in :meth:`Series.resample` and :meth:`DataFrame.resample` (:issue:`58125`)
+- Removed ``Block``, ``DatetimeTZBlock``, ``ExtensionBlock``, ``create_block_manager_from_blocks`` from ``pandas.core.internals`` and ``pandas.core.internals.api`` (:issue:`55139`)
 - Removed alias :class:`arrays.PandasArray` for :class:`arrays.NumpyExtensionArray` (:issue:`53694`)
 - Removed deprecated "method" and "limit" keywords from :meth:`Series.replace` and :meth:`DataFrame.replace` (:issue:`53492`)
 - Removed extension test classes ``BaseNoReduceTests``, ``BaseNumericReduceTests``, ``BaseBooleanReduceTests`` (:issue:`54663`)

doc/source/whatsnew/v3.0.0.rst

@@ -769,6 +769,18 @@ class NaTType(_NaT):
 
         Return a new Timestamp representing UTC day and time.
 
+        See Also
+        --------
+        Timestamp : Constructs an arbitrary datetime.
+        Timestamp.now : Return the current local date and time, which
+            can be timezone-aware.
+        Timestamp.today : Return the current local date and time with
+            timezone information set to None.
+        to_datetime : Convert argument to datetime.
+        date_range : Return a fixed frequency DatetimeIndex.
+        Timestamp.utctimetuple : Return UTC time tuple, compatible with
+            time.localtime().
+
         Examples
         --------
         >>> pd.Timestamp.utcnow()   # doctest: +SKIP
@@ -1383,6 +1395,14 @@ default 'raise'
         -------
         Timestamp
 
+        See Also
+        --------
+        Timestamp.asm8 : Return numpy datetime64 format in nanoseconds.
+        Timestamp.to_pydatetime : Convert Timestamp object to a native
+            Python datetime object.
+        to_timedelta : Convert argument into timedelta object,
+            which can represent differences in times.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 00:00:00.01')

pandas/_libs/tslibs/nattype.pyx

@@ -429,6 +429,12 @@ cdef class BaseOffset:
         """
         Return a dict of extra parameters for the offset.
 
+        See Also
+        --------
+        tseries.offsets.DateOffset : The base class for all pandas date offsets.
+        tseries.offsets.WeekOfMonth : Represents the week of the month.
+        tseries.offsets.LastWeekOfMonth : Represents the last week of the month.
+
         Examples
         --------
         >>> pd.DateOffset(5).kwds
@@ -558,6 +564,14 @@ cdef class BaseOffset:
         """
         Return a string representing the base frequency.
 
+        See Also
+        --------
+        tseries.offsets.Week : Represents a weekly offset.
+        DateOffset : Base class for all other offset classes.
+        tseries.offsets.Day : Represents a single day offset.
+        tseries.offsets.MonthEnd : Represents a monthly offset that
+            snaps to the end of the month.
+
         Examples
         --------
         >>> pd.offsets.Hour().name

pandas/_libs/tslibs/offsets.pyx

@@ -1115,6 +1115,14 @@ cdef class _Timestamp(ABCTimestamp):
         -------
         Timestamp
 
+        See Also
+        --------
+        Timestamp.asm8 : Return numpy datetime64 format in nanoseconds.
+        Timestamp.to_pydatetime : Convert Timestamp object to a native
+            Python datetime object.
+        to_timedelta : Convert argument into timedelta object,
+            which can represent differences in times.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 00:00:00.01')
@@ -1452,6 +1460,18 @@ class Timestamp(_Timestamp):
 
         Return a new Timestamp representing UTC day and time.
 
+        See Also
+        --------
+        Timestamp : Constructs an arbitrary datetime.
+        Timestamp.now : Return the current local date and time, which
+            can be timezone-aware.
+        Timestamp.today : Return the current local date and time with
+            timezone information set to None.
+        to_datetime : Convert argument to datetime.
+        date_range : Return a fixed frequency DatetimeIndex.
+        Timestamp.utctimetuple : Return UTC time tuple, compatible with
+            time.localtime().
+
         Examples
         --------
         >>> pd.Timestamp.utcnow()   # doctest: +SKIP

pandas/_libs/tslibs/timestamps.pyx

@@ -22,6 +22,7 @@
     PY311,
     PY312,
     PYPY,
+    WASM,
 )
 import pandas.compat.compressors
 from pandas.compat.numpy import is_numpy_dev
@@ -122,6 +123,18 @@ def is_platform_power() -> bool:
     return platform.machine() in ("ppc64", "ppc64le")
 
 
+def is_platform_riscv64() -> bool:
+    """
+    Checking if the running platform use riscv64 architecture.
+
+    Returns
+    -------
+    bool
+        True if the running platform uses riscv64 architecture.
+    """
+    return platform.machine() == "riscv64"
+
+
 def is_ci_environment() -> bool:
     """
     Checking if running in a continuous integration environment by checking
@@ -195,4 +208,5 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
     "PY311",
     "PY312",
     "PYPY",
+    "WASM",
 ]

pandas/compat/__init__.py

@@ -17,6 +17,7 @@
 PY311 = sys.version_info >= (3, 11)
 PY312 = sys.version_info >= (3, 12)
 PYPY = platform.python_implementation() == "PyPy"
+WASM = (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"])
 ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
 REF_COUNT = 2 if PY311 else 3
 
@@ -27,4 +28,5 @@
     "PY311",
     "PY312",
     "PYPY",
+    "WASM",
 ]

pandas/compat/_constants.py

@@ -1913,6 +1913,15 @@ def isocalendar(self) -> DataFrame:
         """
         The number of days in the month.
 
+        See Also
+        --------
+        Series.dt.day : Return the day of the month.
+        Series.dt.is_month_end : Return a boolean indicating if the
+            date is the last day of the month.
+        Series.dt.is_month_start : Return a boolean indicating if the
+            date is the first day of the month.
+        Series.dt.month : Return the month as January=1 through December=12.
+
         Examples
         --------
         >>> s = pd.Series(["1/1/2020 10:00:00+00:00", "2/1/2020 11:00:00+00:00"])

pandas/core/arrays/datetimes.py

@@ -703,6 +703,11 @@ def empty(self) -> bool:
         """
         Indicator whether Index is empty.
 
+        An Index is considered empty if it has no elements. This property can be
+        useful for quickly checking the state of an Index, especially in data
+        processing and analysis workflows where handling of empty datasets might
+        be required.
+
         Returns
         -------
         bool
@@ -714,10 +719,10 @@ def empty(self) -> bool:
 
         Examples
         --------
-        >>> idx_empty = pd.Index([1, 2, 3])
-        >>> idx_empty
+        >>> idx = pd.Index([1, 2, 3])
+        >>> idx
         Index([1, 2, 3], dtype='int64')
-        >>> idx_empty.empty
+        >>> idx.empty
         False
 
         >>> idx_empty = pd.Index([])
@@ -728,10 +733,10 @@ def empty(self) -> bool:
 
         If we only have NaNs in our DataFrame, it is not considered empty!
 
-        >>> idx_empty = pd.Index([np.nan, np.nan])
-        >>> idx_empty
+        >>> idx = pd.Index([np.nan, np.nan])
+        >>> idx
         Index([nan, nan], dtype='float64')
-        >>> idx_empty.empty
+        >>> idx.empty
         False
         """
         return not self.size

pandas/core/base.py

@@ -1021,7 +1021,13 @@ def ravel(self, order: str_t = "C") -> Self:
 
     def view(self, cls=None):
         """
-        Return a view on self.
+        Return a view of the Index with the specified dtype or a new Index instance.
+
+        This method returns a view of the calling Index object if no arguments are
+        provided. If a dtype is specified through the `cls` argument, it attempts
+        to return a view of the Index with the specified dtype. Note that viewing
+        the Index as a different dtype reinterprets the underlying data, which can
+        lead to unexpected results for non-numeric or incompatible dtype conversions.
 
         Parameters
         ----------
@@ -1034,27 +1040,38 @@ def view(self, cls=None):
 
         Returns
         -------
-        numpy.ndarray
-            A new view of the same data in memory.
+        Index or ndarray
+            A view of the Index. If `cls` is None, the returned object is an Index
+            view with the same dtype as the calling object. If a numeric `cls` is
+            specified an ndarray view with the new dtype is returned.
+
+        Raises
+        ------
+        ValueError
+            If attempting to change to a dtype in a way that is not compatible with
+            the original dtype's memory layout, for example, viewing an 'int64' Index
+            as 'str'.
 
         See Also
         --------
+        Index.copy : Returns a copy of the Index.
         numpy.ndarray.view : Returns a new view of array with the same data.
 
         Examples
         --------
-        >>> s = pd.Series([1, 2, 3], index=["1", "2", "3"])
-        >>> s.index.view("object")
-        array(['1', '2', '3'], dtype=object)
+        >>> idx = pd.Index([-1, 0, 1])
+        >>> idx.view()
+        Index([-1, 0, 1], dtype='int64')
 
-        >>> s = pd.Series([1, 2, 3], index=[-1, 0, 1])
-        >>> s.index.view(np.int64)
-        array([-1,  0,  1])
-        >>> s.index.view(np.float32)
-        array([   nan,    nan, 0.e+00, 0.e+00, 1.e-45, 0.e+00], dtype=float32)
-        >>> s.index.view(np.uint64)
+        >>> idx.view(np.uint64)
         array([18446744073709551615,                    0,                    1],
           dtype=uint64)
+
+        Viewing as 'int32' or 'float32' reinterprets the memory, which may lead to
+        unexpected behavior:
+
+        >>> idx.view("float32")
+        array([   nan,    nan, 0.e+00, 0.e+00, 1.e-45, 0.e+00], dtype=float32)
         """
         # we need to see if we are subclassing an
         # index type here
@@ -1809,19 +1826,34 @@ def _get_names(self) -> FrozenList:
         """
         Get names on index.
 
+        This method returns a FrozenList containing the names of the object.
+        It's primarily intended for internal use.
+
+        Returns
+        -------
+        FrozenList
+            A FrozenList containing the object's names, contains None if the object
+            does not have a name.
+
         See Also
         --------
-        Index.name : Return Index or MultiIndex name.
+        Index.name : Index name as a string, or None for MultiIndex.
 
         Examples
         --------
         >>> idx = pd.Index([1, 2, 3], name="x")
         >>> idx.names
         FrozenList(['x'])
 
-        >>> idx = s = pd.Index([1, 2, 3], name=("x", "y"))
+        >>> idx = pd.Index([1, 2, 3], name=("x", "y"))
         >>> idx.names
         FrozenList([('x', 'y')])
+
+        If the index does not have a name set:
+
+        >>> idx = pd.Index([1, 2, 3])
+        >>> idx.names
+        FrozenList([None])
         """
         return FrozenList((self.name,))