Merge remote-tracking branch 'upstream/main' into fix-doc-data-structures

fbourgey · fbourgey · commit e1c909a51fa3 · 2024-09-24T09:22:53.000-04:00
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -92,7 +92,13 @@ jobs:
           no_output_timeout: 30m # Sometimes the tests won't generate any output, make sure the job doesn't get killed by that
           command: |
             pip3 install cibuildwheel==2.20.0
-            cibuildwheel --output-dir wheelhouse
+            if [[ $CIBW_BUILD == cp313t* ]]; then
+              # TODO: temporarily run 3.13 free threaded builds without build isolation
+              # since we need pre-release cython
+              CIBW_BUILD_FRONTEND="pip; args: --no-build-isolation" cibuildwheel --output-dir wheelhouse
+            else
+              cibuildwheel --output-dir wheelhouse
+            fi
 
           environment:
             CIBW_BUILD: << parameters.cibw-build >>
@@ -141,6 +147,10 @@ workflows:
               cibw-build: ["cp310-manylinux_aarch64",
                            "cp311-manylinux_aarch64",
                            "cp312-manylinux_aarch64",
+                           "cp313-manylinux_aarch64",
+                           "cp313t-manylinux_aarch64",
                            "cp310-musllinux_aarch64",
                            "cp311-musllinux_aarch64",
-                           "cp312-musllinux_aarch64",]
+                           "cp312-musllinux_aarch64",
+                           "cp313-musllinux_aarch64",
+                           "cp313t-musllinux_aarch64"]
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -102,9 +102,7 @@ jobs:
         python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"]]
         include:
         # TODO: Remove this plus installing build deps in cibw_before_build.sh
-        # and test deps in cibw_before_test.sh after pandas can be built with a released NumPy/Cython
-        - python: ["cp313", "3.13"]
-          cibw_build_frontend: 'pip; args: --no-build-isolation'
+        # after pandas can be built with a released NumPy/Cython
         - python: ["cp313t", "3.13"]
           cibw_build_frontend: 'pip; args: --no-build-isolation'
         # Build Pyodide wheels and upload them to Anaconda.org
@@ -187,11 +185,9 @@ jobs:
       - name: Test Windows Wheels
         if: ${{ matrix.buildplat[1] == 'win_amd64' }}
         shell: pwsh
-        # TODO: Remove NumPy nightly install when there's a 3.13 wheel on PyPI
         run: |
           $TST_CMD = @"
           python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
-          ${{ matrix.python[1] == '3.13' && 'python -m pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy;' }}
           python -m pip install `$(Get-Item pandas\wheelhouse\*.whl);
           python -c `'import pandas as pd; pd.test(extra_args=[`\"--no-strict-data-files`\", `\"-m not clipboard and not single_cpu and not slow and not network and not db`\"])`';
           "@
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -65,4 +65,3 @@ graft pandas/_libs/include
 
 # Include cibw script in sdist since it's needed for building wheels
 include scripts/cibw_before_build.sh
-include scripts/cibw_before_test.sh
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -144,7 +144,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -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" \
-        -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
@@ -383,7 +382,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Week.n GL08" \
         -i "pandas.tseries.offsets.Week.normalize GL08" \
         -i "pandas.tseries.offsets.Week.weekday GL08" \
-        -i "pandas.tseries.offsets.WeekOfMonth SA01" \
         -i "pandas.tseries.offsets.WeekOfMonth.is_on_offset GL08" \
         -i "pandas.tseries.offsets.WeekOfMonth.n GL08" \
         -i "pandas.tseries.offsets.WeekOfMonth.normalize GL08" \
diff --git a/doc/source/conf.py b/doc/source/conf.py
@@ -254,7 +254,9 @@
         "json_url": "https://pandas.pydata.org/versions.json",
         "version_match": switcher_version,
     },
-    "show_version_warning_banner": True,
+    # This shows a warning for patch releases since the
+    # 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": "Mastodon",
diff --git a/doc/source/whatsnew/v2.2.2.rst b/doc/source/whatsnew/v2.2.2.rst
@@ -56,4 +56,4 @@ Other
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v2.2.1..v2.2.2|HEAD
+.. contributors:: v2.2.1..v2.2.2
diff --git a/doc/source/whatsnew/v2.2.3.rst b/doc/source/whatsnew/v2.2.3.rst
@@ -1,6 +1,6 @@
 .. _whatsnew_223:
 
-What's new in 2.2.3 (September XX, 2024)
+What's new in 2.2.3 (September 20, 2024)
 ----------------------------------------
 
 These are the changes in pandas 2.2.3. See :ref:`release` for a full changelog
@@ -9,28 +9,37 @@ including other versions of pandas.
 {{ header }}
 
 .. ---------------------------------------------------------------------------
-.. _whatsnew_223.regressions:
 
-Fixed regressions
-~~~~~~~~~~~~~~~~~
--
+.. _whatsnew_220.py13_compat:
+
+Pandas 2.2.3 is now compatible with Python 3.13
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Pandas 2.2.3 is the first version of pandas that is generally compatible with the upcoming
+Python 3.13, and both wheels for free-threaded and normal Python 3.13 will be uploaded for
+this release.
+
+As usual please report any bugs discovered to our `issue tracker <https://github.com/pandas-dev/pandas/issues/new/choose>`_
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_223.bug_fixes:
 
 Bug fixes
 ~~~~~~~~~
--
+- Bug in :func:`eval` on :class:`complex` including division ``/`` discards imaginary part. (:issue:`21374`)
+- Minor fixes for numpy 2.1 compatibility. (:issue:`59444`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_223.other:
 
 Other
 ~~~~~
--
+- Missing licenses for 3rd party dependencies were added back into the wheels. (:issue:`58632`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_223.contributors:
 
 Contributors
 ~~~~~~~~~~~~
+
+.. contributors:: v2.2.2..v2.2.3|HEAD
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -630,6 +630,7 @@ I/O
 - Bug in :meth:`read_csv` where the order of the ``na_values`` makes an inconsistency when ``na_values`` is a list non-string values. (:issue:`59303`)
 - Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
 - Bug in :meth:`read_json` not validating the ``typ`` argument to not be exactly ``"frame"`` or ``"series"`` (:issue:`59124`)
+- Bug in :meth:`read_json` where extreme value integers in string format were incorrectly parsed as a different integer number (:issue:`20608`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
 - Bug in :meth:`read_stata` where extreme value integers were incorrectly interpreted as missing for format versions 111 and prior (:issue:`58130`)
 - Bug in :meth:`read_stata` where the missing code for double was not recognised for format versions 105 and prior (:issue:`58149`)
@@ -693,7 +694,6 @@ Other
 ^^^^^
 - Bug in :class:`DataFrame` when passing a ``dict`` with a NA scalar and ``columns`` that would always return ``np.nan`` (:issue:`57205`)
 - Bug in :func:`eval` on :class:`ExtensionArray` on including division ``/`` failed with a ``TypeError``. (:issue:`58748`)
-- Bug in :func:`eval` on :class:`complex` including division ``/`` discards imaginary part. (:issue:`21374`)
 - Bug in :func:`eval` where the names of the :class:`Series` were not preserved when using ``engine="numexpr"``. (:issue:`10239`)
 - Bug in :func:`unique` on :class:`Index` not always returning :class:`Index` (:issue:`57043`)
 - Bug in :meth:`DataFrame.apply` where passing ``engine="numba"`` ignored ``args`` passed to the applied function (:issue:`58712`)
diff --git a/pandas/_libs/tslibs/np_datetime.pxd b/pandas/_libs/tslibs/np_datetime.pxd
@@ -89,7 +89,7 @@ cdef int string_to_dts(
     int* out_local,
     int* out_tzoffset,
     bint want_exc,
-    format: str | None = *,
+    str format = *,
     bint exact = *
 ) except? -1
 
diff --git a/pandas/_libs/tslibs/np_datetime.pyx b/pandas/_libs/tslibs/np_datetime.pyx
@@ -331,7 +331,7 @@ cdef int string_to_dts(
     int* out_local,
     int* out_tzoffset,
     bint want_exc,
-    format: str | None=None,
+    str format=None,
     bint exact=True,
 ) except? -1:
     cdef:
diff --git a/pandas/_libs/tslibs/offsets.pyx b/pandas/_libs/tslibs/offsets.pyx
@@ -3582,6 +3582,11 @@ cdef class WeekOfMonth(WeekOfMonthMixin):
     """
     Describes monthly dates like "the Tuesday of the 2nd week of each month".
 
+    This offset allows for generating or adjusting dates by specifying
+    a particular week and weekday within a month. The week is zero-indexed,
+    where 0 corresponds to the first week of the month, and weekday follows
+    a Monday=0 convention.
+
     Attributes
     ----------
     n : int, default 1
@@ -3602,6 +3607,12 @@ cdef class WeekOfMonth(WeekOfMonthMixin):
         - 5 is Saturday
         - 6 is Sunday.
 
+    See Also
+    --------
+    offsets.Week : Describes weekly frequency adjustments.
+    offsets.MonthEnd : Describes month-end frequency adjustments.
+    date_range : Generates a range of dates based on a specific frequency.
+
     Examples
     --------
     >>> ts = pd.Timestamp(2022, 1, 1)
diff --git a/pandas/core/groupby/generic.py b/pandas/core/groupby/generic.py
@@ -2694,7 +2694,9 @@ def hist(
 
         Returns
         -------
-        matplotlib.Axes or numpy.ndarray of them
+        matplotlib.Axes or numpy.ndarray
+            A ``matplotlib.Axes`` object or an array of ``Axes`` objects, depending on
+            the layout and grouping.
 
         See Also
         --------
diff --git a/pandas/io/json/_json.py b/pandas/io/json/_json.py
@@ -1168,6 +1168,7 @@ def _try_convert_data(
         """
         Try to parse a Series into a column by inferring dtype.
         """
+        org_data = data
         # don't try to coerce, unless a force conversion
         if use_dtypes:
             if not self.dtype:
@@ -1222,7 +1223,7 @@ def _try_convert_data(
         if len(data) and data.dtype in ("float", "object"):
             # coerce ints if we can
             try:
-                new_data = data.astype("int64")
+                new_data = org_data.astype("int64")
                 if (new_data == data).all():
                     data = new_data
                     converted = True
diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py
@@ -2286,3 +2286,15 @@ def test_read_json_lines_rangeindex():
     result = read_json(StringIO(data), lines=True).index
     expected = RangeIndex(2)
     tm.assert_index_equal(result, expected, exact=True)
+
+
+def test_large_number():
+    # GH#20608
+    result = read_json(
+        StringIO('["9999999999999999"]'),
+        orient="values",
+        typ="series",
+        convert_dates=False,
+    )
+    expected = Series([9999999999999999])
+    tm.assert_series_equal(result, expected)
diff --git a/pyproject.toml b/pyproject.toml
@@ -156,8 +156,7 @@ test-command = """
   pd.test(extra_args=["-m not clipboard and single_cpu and not slow and not network and not db", "--no-strict-data-files"]);' \
   """
 free-threaded-support = true
-before-build = "bash {package}/scripts/cibw_before_build.sh"
-before-test = "bash {package}/scripts/cibw_before_test.sh"
+before-build = "PACKAGE_DIR={package} bash {package}/scripts/cibw_before_build.sh"
 
 [tool.cibuildwheel.windows]
 before-build = "pip install delvewheel && bash {package}/scripts/cibw_before_build.sh"
@@ -173,7 +172,7 @@ test-command = """
 
 [[tool.cibuildwheel.overrides]]
 select = "*-musllinux*"
-before-test = "apk update && apk add musl-locales && bash {package}/scripts/cibw_before_test.sh"
+before-test = "apk update && apk add musl-locales"
 
 [[tool.cibuildwheel.overrides]]
 select = "*-win*"
diff --git a/scripts/cibw_before_build.sh b/scripts/cibw_before_build.sh
@@ -1,8 +1,11 @@
-# TODO: Delete when there's PyPI NumPy/Cython releases the support Python 3.13.
-# If free-threading support is not included in those releases, this script will have
-# to whether this runs for a free-threaded build instead.
-PYTHON_VERSION="$(python -c "import sys; print(f'{sys.version_info.major}{sys.version_info.minor}')")"
-if [[ $PYTHON_VERSION == "313" ]]; then
+# Add 3rd party licenses, like numpy does
+for file in $PACKAGE_DIR/LICENSES/*; do
+  cat $file >> $PACKAGE_DIR/LICENSE
+done
+
+# TODO: Delete when there's a PyPI Cython release that supports free-threaded Python 3.13.
+FREE_THREADED_BUILD="$(python -c"import sysconfig; print(bool(sysconfig.get_config_var('Py_GIL_DISABLED')))")"
+if [[ $FREE_THREADED_BUILD == "True"  ]]; then
     python -m pip install -U pip
     python -m pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy cython
     python -m pip install ninja meson-python versioneer[toml]
diff --git a/scripts/cibw_before_test.sh b/scripts/cibw_before_test.sh
diff --git a/web/pandas/community/ecosystem.md b/web/pandas/community/ecosystem.md
@@ -367,6 +367,97 @@ pandas-gbq provides high performance reads and writes to and from
 these methods were exposed as `pandas.read_gbq` and `DataFrame.to_gbq`.
 Use `pandas_gbq.read_gbq` and `pandas_gbq.to_gbq`, instead.
 
+
+### [ArcticDB](https://github.com/man-group/ArcticDB)
+
+ArcticDB is a serverless DataFrame database engine designed for the Python Data Science ecosystem. ArcticDB enables you to store, retrieve, and process pandas DataFrames at scale. It is a storage engine designed for object storage and also supports local-disk storage using LMDB. ArcticDB requires zero additional infrastructure beyond a running Python environment and access to object storage and can be installed in seconds. Please find full documentation [here](https://docs.arcticdb.io/latest/).
+
+#### ArcticDB Terminology
+
+ArcticDB is structured to provide a scalable and efficient way to manage and retrieve DataFrames, organized into several key components:
+
+- `Object Store` Collections of libraries. Used to separate logical environments from each other. Analogous to a database server.
+- `Library` Contains multiple symbols which are grouped in a certain way (different users, markets, etc). Analogous to a database.
+- `Symbol` Atomic unit of data storage. Identified by a string name. Data stored under a symbol strongly resembles a pandas DataFrame. Analogous to tables.
+- `Version` Every modifying action (write, append, update) performed on a symbol creates a new version of that object.
+
+#### Installation
+
+To install, simply run:
+
+```console
+pip install arcticdb
+```
+
+To get started, we can import ArcticDB and instantiate it:
+
+```python
+import arcticdb as adb
+import numpy as np
+import pandas as pd
+# this will set up the storage using the local file system
+arctic = adb.Arctic("lmdb://arcticdb_test")
+```
+
+> **Note:** ArcticDB supports any S3 API compatible storage, including AWS. ArcticDB also supports Azure Blob storage.  
+> ArcticDB also supports LMDB for local/file based storage - to use LMDB, pass an LMDB path as the URI: `adb.Arctic('lmdb://path/to/desired/database')`.
+
+#### Library Setup
+
+ArcticDB is geared towards storing many (potentially millions) of tables. Individual tables (DataFrames) are called symbols and are stored in collections called libraries. A single library can store many symbols. Libraries must first be initialized prior to use:
+
+```python
+lib = arctic.get_library('sample', create_if_missing=True)
+```
+
+#### Writing Data to ArcticDB
+
+Now we have a library set up, we can get to reading and writing data. ArcticDB has a set of simple functions for DataFrame storage. Let's write a DataFrame to storage.
+
+```python
+df = pd.DataFrame(
+    {
+        "a": list("abc"),
+        "b": list(range(1, 4)),
+        "c": np.arange(3, 6).astype("u1"),
+        "d": np.arange(4.0, 7.0, dtype="float64"),
+        "e": [True, False, True],
+        "f": pd.date_range("20130101", periods=3)
+    }
+)
+
+df
+df.dtypes
+```
+
+Write to ArcticDB.
+
+```python
+write_record = lib.write("test", df)
+```
+
+> **Note:** When writing pandas DataFrames, ArcticDB supports the following index types:
+>
+> - `pandas.Index` containing int64 (or the corresponding dedicated types Int64Index, UInt64Index)
+> - `RangeIndex`
+> - `DatetimeIndex`
+> - `MultiIndex` composed of above supported types
+>
+> The "row" concept in `head`/`tail` refers to the row number ('iloc'), not the value in the `pandas.Index` ('loc').
+
+#### Reading Data from ArcticDB
+
+Read the data back from storage:
+
+```python
+read_record = lib.read("test")
+read_record.data
+df.dtypes
+```
+
+ArcticDB also supports appending, updating, and querying data from storage to a pandas DataFrame. Please find more information [here](https://docs.arcticdb.io/latest/api/query_builder/).
+
+
 ## Out-of-core
 
 ### [Bodo](https://bodo.ai/)

Original file line number	Diff line number	Diff line change
`@@ -65,4 +65,3 @@ graft pandas/_libs/include`
`65`	`65`
`66`	`66`	`# Include cibw script in sdist since it's needed for building wheels`
`67`	`67`	`include scripts/cibw_before_build.sh`
`68`		`-include scripts/cibw_before_test.sh`