Merge remote-tracking branch 'upstream/main' into better-msg-delta-series_timestamp

KevsterAmp · KevsterAmp · commit b9f41fbef185 · 2024-10-03T18:38:54.000+08:00
diff --git a/.github/actions/setup-conda/action.yml b/.github/actions/setup-conda/action.yml
@@ -9,6 +9,8 @@ runs:
     - name: Install ${{ inputs.environment-file }}
       uses: mamba-org/setup-micromamba@v1
       with:
+        # Pinning to avoid 2.0 failures
+        micromamba-version: '1.5.10-0'
         environment-file: ${{ inputs.environment-file }}
         environment-name: test
         condarc-file: ci/.condarc
diff --git a/.github/workflows/code-checks.yml b/.github/workflows/code-checks.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
 
 env:
   ENV_FILE: environment.yml
diff --git a/.github/workflows/docbuild-and-upload.yml b/.github/workflows/docbuild-and-upload.yml
@@ -4,13 +4,13 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
 
 env:
   ENV_FILE: environment.yml
diff --git a/.github/workflows/package-checks.yml b/.github/workflows/package-checks.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     types: [ labeled, opened, synchronize, reopened ]
 
 permissions:
diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     paths-ignore:
       - "doc/**"
       - "web/**"
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -97,25 +97,18 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt.unit GL08" \
         -i "pandas.Series.pad PR01,SA01" \
         -i "pandas.Series.sparse.from_coo PR07,SA01" \
-        -i "pandas.Series.sparse.npoints SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
-        -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.types.is_dict_like PR07,SA01" \
-        -i "pandas.api.types.is_file_like PR07,SA01" \
         -i "pandas.api.types.is_float PR01,SA01" \
-        -i "pandas.api.types.is_hashable PR01,RT03,SA01" \
         -i "pandas.api.types.is_integer PR01,SA01" \
         -i "pandas.api.types.is_iterator PR07,SA01" \
-        -i "pandas.api.types.is_named_tuple PR07,SA01" \
-        -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
@@ -128,8 +121,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.__iter__ RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.agg RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.aggregate RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
@@ -140,8 +131,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.agg RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.aggregate RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
@@ -170,7 +159,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.CSSWarning SA01" \
         -i "pandas.errors.CategoricalConversionWarning SA01" \
         -i "pandas.errors.ChainedAssignmentError SA01" \
-        -i "pandas.errors.ClosedFileError SA01" \
         -i "pandas.errors.DataError SA01" \
         -i "pandas.errors.DuplicateLabelError SA01" \
         -i "pandas.errors.IntCastingNaNError SA01" \
@@ -180,7 +168,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
         -i "pandas.errors.OptionError SA01" \
-        -i "pandas.errors.OutOfBoundsDatetime SA01" \
         -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
         -i "pandas.errors.PossibleDataLossError SA01" \
diff --git a/doc/source/development/contributing.rst b/doc/source/development/contributing.rst
@@ -305,15 +305,15 @@ It is important to periodically update your local ``main`` branch with updates f
 branch and update your development environment to reflect any changes to the various packages that
 are used during development.
 
-If using :ref:`mamba <contributing.mamba>`, run:
+If using :ref:`conda <contributing.conda>`, run:
 
 .. code-block:: shell
 
     git checkout main
     git fetch upstream
     git merge upstream/main
-    mamba activate pandas-dev
-    mamba env update -f environment.yml --prune
+    conda activate pandas-dev
+    conda env update -f environment.yml --prune
 
 If using :ref:`pip <contributing.pip>` , do:
 
diff --git a/doc/source/development/contributing_codebase.rst b/doc/source/development/contributing_codebase.rst
@@ -244,7 +244,7 @@ in your python environment.
 
 .. warning::
 
-    * Please be aware that the above commands will use the current python environment. If your python packages are older/newer than those installed by the pandas CI, the above commands might fail. This is often the case when the ``mypy`` or ``numpy`` versions do not match. Please see :ref:`how to setup the python environment <contributing.mamba>` or select a `recently succeeded workflow <https://github.com/pandas-dev/pandas/actions/workflows/code-checks.yml?query=branch%3Amain+is%3Asuccess>`_, select the "Docstring validation, typing, and other manual pre-commit hooks" job, then click on "Set up Conda" and "Environment info" to see which versions the pandas CI installs.
+    * Please be aware that the above commands will use the current python environment. If your python packages are older/newer than those installed by the pandas CI, the above commands might fail. This is often the case when the ``mypy`` or ``numpy`` versions do not match. Please see :ref:`how to setup the python environment <contributing.conda>` or select a `recently succeeded workflow <https://github.com/pandas-dev/pandas/actions/workflows/code-checks.yml?query=branch%3Amain+is%3Asuccess>`_, select the "Docstring validation, typing, and other manual pre-commit hooks" job, then click on "Set up Conda" and "Environment info" to see which versions the pandas CI installs.
 
 .. _contributing.ci:
 
diff --git a/doc/source/development/contributing_environment.rst b/doc/source/development/contributing_environment.rst
@@ -43,17 +43,17 @@ and consult the ``Linux`` instructions below.
 
 **macOS**
 
-To use the :ref:`mamba <contributing.mamba>`-based compilers, you will need to install the
+To use the :ref:`conda <contributing.conda>`-based compilers, you will need to install the
 Developer Tools using ``xcode-select --install``.
 
 If you prefer to use a different compiler, general information can be found here:
 https://devguide.python.org/setup/#macos
 
 **Linux**
 
-For Linux-based :ref:`mamba <contributing.mamba>` installations, you won't have to install any
-additional components outside of the mamba environment. The instructions
-below are only needed if your setup isn't based on mamba environments.
+For Linux-based :ref:`conda <contributing.conda>` installations, you won't have to install any
+additional components outside of the conda environment. The instructions
+below are only needed if your setup isn't based on conda environments.
 
 Some Linux distributions will come with a pre-installed C compiler. To find out
 which compilers (and versions) are installed on your system::
@@ -82,19 +82,18 @@ Before we begin, please:
 * Make sure that you have :any:`cloned the repository <contributing.forking>`
 * ``cd`` to the pandas source directory you just created with the clone command
 
-.. _contributing.mamba:
+.. _contributing.conda:
 
-Option 1: using mamba (recommended)
+Option 1: using conda (recommended)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-* Install miniforge to get `mamba <https://mamba.readthedocs.io/en/latest/installation/mamba-installation.html>`_
-* Make sure your mamba is up to date (``mamba update mamba``)
-* Create and activate the ``pandas-dev`` mamba environment using the following commands:
+* Install miniforge to get `conda <https://github.com/conda-forge/miniforge?tab=readme-ov-file#download>`_
+* Create and activate the ``pandas-dev`` conda environment using the following commands:
 
-.. code-block:: none
+.. code-block:: bash
 
-   mamba env create --file environment.yml
-   mamba activate pandas-dev
+   conda env create --file environment.yml
+   conda activate pandas-dev
 
 .. _contributing.pip:
 
diff --git a/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst b/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
@@ -271,7 +271,7 @@ Add the parameters' full description and name, provided by the parameters metada
 
 Compared to the previous example, there is no common column name.
 However, the ``parameter`` column in the ``air_quality`` table and the
-``id`` column in the ``air_quality_parameters_name`` both provide the
+``id`` column in the ``air_quality_parameters`` table both provide the
 measured variable in a common format. The ``left_on`` and ``right_on``
 arguments are used here (instead of just ``on``) to make the link
 between the two tables.
diff --git a/doc/source/user_guide/10min.rst b/doc/source/user_guide/10min.rst
@@ -177,7 +177,7 @@ See the indexing documentation :ref:`Indexing and Selecting Data <indexing>` and
 Getitem (``[]``)
 ~~~~~~~~~~~~~~~~
 
-For a :class:`DataFrame`, passing a single label selects a columns and
+For a :class:`DataFrame`, passing a single label selects a column and
 yields a :class:`Series` equivalent to ``df.A``:
 
 .. ipython:: python
diff --git a/doc/source/user_guide/dsintro.rst b/doc/source/user_guide/dsintro.rst
@@ -87,8 +87,9 @@ index will be pulled out.
 
 **From scalar value**
 
-If ``data`` is a scalar value, an index must be
-provided. The value will be repeated to match the length of **index**.
+If ``data`` is a scalar value, the value will be repeated to match
+the length of **index**.  If the **index** is not provided, it defaults
+to ``RangeIndex(1)``.
 
 .. ipython:: python
 
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -652,6 +652,7 @@ Plotting
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
 - Bug in :meth:`.DataFrameGroupBy.__len__` and :meth:`.SeriesGroupBy.__len__` would raise when the grouping contained NA values and ``dropna=False`` (:issue:`58644`)
+- Bug in :meth:`.DataFrameGroupBy.any` that returned True for groups where all Timedelta values are NaT. (:issue:`59712`)
 - Bug in :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupby.groups` that would not respect groupby argument ``dropna`` (:issue:`55919`)
 - Bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
diff --git a/pandas/_libs/include/pandas/datetime/date_conversions.h b/pandas/_libs/include/pandas/datetime/date_conversions.h
@@ -9,6 +9,7 @@ The full license is in the LICENSE file, distributed with this software.
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
+
 #include <numpy/ndarraytypes.h>
 
 // Scales value inplace from nanosecond resolution to unit resolution
diff --git a/pandas/_libs/include/pandas/parser/io.h b/pandas/_libs/include/pandas/parser/io.h
@@ -10,9 +10,10 @@ The full license is in the LICENSE file, distributed with this software.
 #pragma once
 
 #define PY_SSIZE_T_CLEAN
-#include "tokenizer.h"
 #include <Python.h>
 
+#include "tokenizer.h"
+
 #define FS(source) ((file_source *)source)
 
 typedef struct _rd_source {
diff --git a/pandas/_libs/include/pandas/parser/pd_parser.h b/pandas/_libs/include/pandas/parser/pd_parser.h
@@ -13,9 +13,10 @@ extern "C" {
 #endif
 
 #define PY_SSIZE_T_CLEAN
-#include "pandas/parser/tokenizer.h"
 #include <Python.h>
 
+#include "pandas/parser/tokenizer.h"
+
 typedef struct {
   int (*to_double)(char *, double *, char, char, int *);
   int (*floatify)(PyObject *, double *, int *);
diff --git a/pandas/_libs/include/pandas/vendored/klib/khash_python.h b/pandas/_libs/include/pandas/vendored/klib/khash_python.h
@@ -3,6 +3,7 @@
 #pragma once
 
 #include <Python.h>
+
 #include <pymem.h>
 #include <string.h>
 
diff --git a/pandas/_libs/src/vendored/ujson/python/JSONtoObj.c b/pandas/_libs/src/vendored/ujson/python/JSONtoObj.c
@@ -38,10 +38,11 @@ Numeric decoder derived from TCL library
 
 // Licence at LICENSES/ULTRAJSON_LICENSE
 
-#include "pandas/vendored/ujson/lib/ultrajson.h"
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
 
+#include "pandas/vendored/ujson/lib/ultrajson.h"
+
 static int Object_objectAddKey(void *Py_UNUSED(prv), JSOBJ obj, JSOBJ name,
                                JSOBJ value) {
   int ret = PyDict_SetItem(obj, name, value);
diff --git a/pandas/_libs/src/vendored/ujson/python/ujson.c b/pandas/_libs/src/vendored/ujson/python/ujson.c
@@ -40,6 +40,7 @@ Numeric decoder derived from TCL library
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
+
 #define PY_ARRAY_UNIQUE_SYMBOL UJSON_NUMPY
 #include "numpy/arrayobject.h"
 
diff --git a/pandas/_libs/tslibs/nattype.pyx b/pandas/_libs/tslibs/nattype.pyx
@@ -500,6 +500,8 @@ class NaTType(_NaT):
         --------
         to_timedelta : Convert argument to timedelta.
         Timedelta : Represents a duration, the difference between two dates or times.
+        Timedelta.seconds : Returns the seconds component of the timedelta.
+        Timedelta.microseconds : Returns the microseconds component of the timedelta.
 
         Examples
         --------
diff --git a/pandas/_libs/tslibs/np_datetime.pyx b/pandas/_libs/tslibs/np_datetime.pyx
@@ -176,6 +176,15 @@ class OutOfBoundsDatetime(ValueError):
     """
     Raised when the datetime is outside the range that can be represented.
 
+    This error occurs when attempting to convert or parse a datetime value
+    that exceeds the bounds supported by pandas' internal datetime
+    representation.
+
+    See Also
+    --------
+    to_datetime : Convert argument to datetime.
+    Timestamp : Pandas replacement for python ``datetime.datetime`` object.
+
     Examples
     --------
     >>> pd.to_datetime("08335394550")
diff --git a/pandas/_libs/tslibs/timedeltas.pyx b/pandas/_libs/tslibs/timedeltas.pyx
@@ -1196,6 +1196,8 @@ cdef class _Timedelta(timedelta):
         --------
         to_timedelta : Convert argument to timedelta.
         Timedelta : Represents a duration, the difference between two dates or times.
+        Timedelta.seconds : Returns the seconds component of the timedelta.
+        Timedelta.microseconds : Returns the microseconds component of the timedelta.
 
         Examples
         --------
@@ -1493,6 +1495,7 @@ cdef class _Timedelta(timedelta):
 
         See Also
         --------
+        Timedelta.asm8 : Return a numpy timedelta64 array scalar view.
         numpy.ndarray.view : Returns a view of an array with the same data.
         Timedelta.to_numpy : Converts the Timedelta to a NumPy timedelta64.
         Timedelta.total_seconds : Returns the total duration of the Timedelta
diff --git a/pandas/core/arrays/sparse/array.py b/pandas/core/arrays/sparse/array.py
@@ -708,6 +708,18 @@ def npoints(self) -> int:
         """
         The number of non- ``fill_value`` points.
 
+        This property returns the number of elements in the sparse series that are
+        not equal to the ``fill_value``. Sparse data structures store only the
+        non-``fill_value`` elements, reducing memory usage when the majority of
+        values are the same.
+
+        See Also
+        --------
+        Series.sparse.to_dense : Convert a Series from sparse values to dense.
+        Series.sparse.fill_value : Elements in ``data`` that are ``fill_value`` are
+            not stored.
+        Series.sparse.density : The percent of non- ``fill_value`` points, as decimal.
+
         Examples
         --------
         >>> from pandas.arrays import SparseArray
diff --git a/pandas/core/arrays/timedeltas.py b/pandas/core/arrays/timedeltas.py
@@ -790,6 +790,19 @@ def to_pytimedelta(self) -> npt.NDArray[np.object_]:
         Returns
         -------
         numpy.ndarray
+            A NumPy ``timedelta64`` object representing the same duration as the
+            original pandas ``Timedelta`` object. The precision of the resulting
+            object is in nanoseconds, which is the default
+            time resolution used by pandas for ``Timedelta`` objects, ensuring
+            high precision for time-based calculations.
+
+        See Also
+        --------
+        to_timedelta : Convert argument to timedelta format.
+        Timedelta : Represents a duration between two dates or times.
+        DatetimeIndex: Index of datetime64 data.
+        Timedelta.components : Return a components namedtuple-like
+                               of a single timedelta.
 
         Examples
         --------
@@ -800,6 +813,14 @@ def to_pytimedelta(self) -> npt.NDArray[np.object_]:
         >>> tdelta_idx.to_pytimedelta()
         array([datetime.timedelta(days=1), datetime.timedelta(days=2),
                datetime.timedelta(days=3)], dtype=object)
+
+        >>> tidx = pd.TimedeltaIndex(data=["1 days 02:30:45", "3 days 04:15:10"])
+        >>> tidx
+        TimedeltaIndex(['1 days 02:30:45', '3 days 04:15:10'],
+               dtype='timedelta64[ns]', freq=None)
+        >>> tidx.to_pytimedelta()
+        array([datetime.timedelta(days=1, seconds=9045),
+                datetime.timedelta(days=3, seconds=15310)], dtype=object)
         """
         return ints_to_pytimedelta(self._ndarray)
 
diff --git a/pandas/core/dtypes/inference.py b/pandas/core/dtypes/inference.py
diff --git a/pandas/core/groupby/generic.py b/pandas/core/groupby/generic.py
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py
diff --git a/pandas/core/shared_docs.py b/pandas/core/shared_docs.py
diff --git a/pandas/core/strings/accessor.py b/pandas/core/strings/accessor.py
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
diff --git a/pandas/tests/groupby/test_grouping.py b/pandas/tests/groupby/test_grouping.py
diff --git a/scripts/validate_unwanted_patterns.py b/scripts/validate_unwanted_patterns.py
