Merge remote-tracking branch 'upstream/main' into 59717-from-records-columns-reorder

Author: VibavariG

.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`\"])`';
           "@

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

ci/code_checks.sh

@@ -383,7 +383,6 @@ 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" \

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
 

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:

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)

pyproject.toml

@@ -157,7 +157,6 @@ test-command = """
   """
 free-threaded-support = true
 before-build = "bash {package}/scripts/cibw_before_build.sh"
-before-test = "bash {package}/scripts/cibw_before_test.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*"

scripts/cibw_before_build.sh

@@ -1,8 +1,6 @@
-# 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 [[ $PYTHON_VERSION == "313" ]]; then
+# TODO: Delete when there's a PyPI Cython release that supports free-threaded Python 3.13.
+FREE_THREADED_BUILD="$(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]

scripts/cibw_before_test.sh

@@ -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/)