Merge branch 'main' into 57884-add-kwargs-to-pivot_table

Author: ruimamaral

.circleci/config.yml

@@ -1,46 +1,64 @@
 version: 2.1
 
 jobs:
-  test-arm:
+  test-linux-arm:
     machine:
       image: default
     resource_class: arm.large
     environment:
-      ENV_FILE: ci/deps/circle-310-arm64.yaml
+      ENV_FILE: ci/deps/circle-311-arm64.yaml
       PYTEST_WORKERS: auto
       PATTERN: "not single_cpu and not slow and not network and not clipboard and not arm_slow and not db"
       PYTEST_TARGET: "pandas"
       PANDAS_CI: "1"
     steps:
       - checkout
-      - run: .circleci/setup_env.sh
-      - run: >
-          PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
-          LD_PRELOAD=$HOME/miniconda3/envs/pandas-dev/lib/libgomp.so.1:$LD_PRELOAD
-          ci/run_tests.sh
-  linux-musl:
+      - run:
+          name: Install Environment and Run Tests
+          shell: /bin/bash -exuo pipefail
+          command: |
+            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MAMBA_URL -O minimamba.sh
+            chmod +x minimamba.sh
+            MAMBA_DIR="$HOME/miniconda3"
+            rm -rf $MAMBA_DIR
+            ./minimamba.sh -b -p $MAMBA_DIR
+            export PATH=$MAMBA_DIR/bin:$PATH
+            conda info -a
+            conda env create -q -n pandas-dev -f $ENV_FILE
+            conda list -n pandas-dev
+            source activate pandas-dev
+            if pip show pandas 1>/dev/null; then
+                pip uninstall -y pandas
+            fi
+            python -m pip install --no-build-isolation -ve . --config-settings=setup-args="--werror"
+            PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
+            ci/run_tests.sh
+  test-linux-musl:
     docker:
       - image: quay.io/pypa/musllinux_1_1_aarch64
     resource_class: arm.large
     steps:
       # Install pkgs first to have git in the image
       # (needed for checkout)
-      - run: |
-          apk update
-          apk add git
-          apk add musl-locales
+      - run:
+          name: Install System Packages
+          command: |
+            apk update
+            apk add git
+            apk add musl-locales
       - checkout
-      - run: |
-          /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
-          . ~/virtualenvs/pandas-dev/bin/activate
-          python -m pip install --no-cache-dir -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.2.1
-          python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
-          python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
-          python -m pip list --no-cache-dir
-      - run: |
-          . ~/virtualenvs/pandas-dev/bin/activate
-          export PANDAS_CI=1
-          python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
+      - run:
+          name: Install Environment and Run Tests
+          command: |
+            /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
+            . ~/virtualenvs/pandas-dev/bin/activate
+            python -m pip install --no-cache-dir -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.2.1
+            python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+            python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
+            python -m pip list --no-cache-dir
+            export PANDAS_CI=1
+            python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
   build-aarch64:
     parameters:
       cibw-build:
@@ -71,7 +89,7 @@ jobs:
           name: Build aarch64 wheels
           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==2.15.0
+            pip3 install cibuildwheel==2.18.1
             cibuildwheel --prerelease-pythons --output-dir wheelhouse
 
           environment:
@@ -81,7 +99,7 @@ jobs:
           name: Install Anaconda Client & Upload Wheels
           command: |
             echo "Install Mambaforge"
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/23.1.0-0/Mambaforge-23.1.0-0-Linux-aarch64.sh"
+            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
             echo "Downloading $MAMBA_URL"
             wget -q $MAMBA_URL -O minimamba.sh
             chmod +x minimamba.sh
@@ -107,14 +125,14 @@ workflows:
       not:
         equal: [ scheduled_pipeline, << pipeline.trigger_source >> ]
     jobs:
-      - test-arm
+      - test-linux-arm
   test-musl:
     # Don't run trigger this one when scheduled pipeline runs
     when:
       not:
         equal: [ scheduled_pipeline, << pipeline.trigger_source >> ]
     jobs:
-      - linux-musl
+      - test-linux-musl
   build-wheels:
     jobs:
       - build-aarch64:

.circleci/setup_env.sh

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.3
+    rev: v0.4.7
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -40,7 +40,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.3.0
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
@@ -92,7 +92,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v18.1.4
+    rev: v18.1.5
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

.pre-commit-config.yaml

@@ -343,7 +343,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
-        -i "pandas.bdate_range RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.agg RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.aggregate RT03" \
@@ -404,7 +403,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.window.rolling.Window.std PR01" \
         -i "pandas.core.window.rolling.Window.var PR01" \
         -i "pandas.date_range RT03" \
-        -i "pandas.describe_option SA01" \
         -i "pandas.errors.AbstractMethodError PR01,SA01" \
         -i "pandas.errors.AttributeConflictWarning SA01" \
         -i "pandas.errors.CSSWarning SA01" \
@@ -470,24 +468,15 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.merge PR07" \
         -i "pandas.merge_asof PR07,RT03" \
         -i "pandas.merge_ordered PR07" \
-        -i "pandas.option_context SA01" \
         -i "pandas.period_range RT03,SA01" \
         -i "pandas.pivot PR07" \
-        -i "pandas.pivot_table PR07" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
-        -i "pandas.plotting.autocorrelation_plot RT03,SA01" \
         -i "pandas.plotting.lag_plot RT03,SA01" \
-        -i "pandas.plotting.parallel_coordinates PR07,RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
-        -i "pandas.plotting.table PR07,RT03,SA01" \
         -i "pandas.qcut PR07,SA01" \
-        -i "pandas.read_orc SA01" \
         -i "pandas.read_spss SA01" \
-        -i "pandas.reset_option SA01" \
         -i "pandas.set_eng_float_format RT03,SA01" \
-        -i "pandas.show_versions SA01" \
         -i "pandas.testing.assert_extension_array_equal SA01" \
-        -i "pandas.testing.assert_series_equal PR07,SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BQuarterBegin PR02" \
         -i "pandas.tseries.offsets.BQuarterBegin.freqstr SA01" \
@@ -779,7 +768,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.YearEnd.nanos GL08" \
         -i "pandas.tseries.offsets.YearEnd.normalize GL08" \
         -i "pandas.tseries.offsets.YearEnd.rule_code GL08" \
-        -i "pandas.unique PR07" \
         -i "pandas.util.hash_pandas_object PR07,SA01" # There should be no backslash in the final line, please keep this comment in the last ignored function
 
     RET=$(($RET + $?)) ; echo $MSG "DONE"

ci/code_checks.sh

@@ -2,7 +2,7 @@ name: pandas-dev
 channels:
   - conda-forge
 dependencies:
-  - python=3.10
+  - python=3.11
 
   # build dependencies
   - versioneer[toml]

ci/deps/circle-310-arm64.yaml renamed to ci/deps/circle-311-arm64.yaml

@@ -134,8 +134,8 @@ to explore, clean, and process your data. In pandas, a data table is called a :c
             <div id="collapseTwo" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-pandas supports the integration with many file formats or data sources out of the box (csv, excel, sql, json, parquet,…). Importing data from each of these
-data sources is provided by function with the prefix ``read_*``. Similarly, the ``to_*`` methods are used to store data.
+pandas supports the integration with many file formats or data sources out of the box (csv, excel, sql, json, parquet,…). The ability to import data from each of these
+data sources is provided by functions with the prefix, ``read_*``. Similarly, the ``to_*`` methods are used to store data.
 
 .. image:: ../_static/schemas/02_io_readwrite.svg
    :align: center
@@ -181,7 +181,7 @@ data sources is provided by function with the prefix ``read_*``. Similarly, the
             <div id="collapseThree" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-Selecting or filtering specific rows and/or columns? Filtering the data on a condition? Methods for slicing, selecting, and extracting the
+Selecting or filtering specific rows and/or columns? Filtering the data on a particular condition? Methods for slicing, selecting, and extracting the
 data you need are available in pandas.
 
 .. image:: ../_static/schemas/03_subset_columns_rows.svg
@@ -228,7 +228,7 @@ data you need are available in pandas.
             <div id="collapseFour" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-pandas provides plotting your data out of the box, using the power of Matplotlib. You can pick the plot type (scatter, bar, boxplot,...)
+pandas provides plotting for your data right out of the box with the power of Matplotlib. Simply pick the plot type (scatter, bar, boxplot,...)
 corresponding to your data.
 
 .. image:: ../_static/schemas/04_plot_overview.svg
@@ -275,7 +275,7 @@ corresponding to your data.
             <div id="collapseFive" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-There is no need to loop over all rows of your data table to do calculations. Data manipulations on a column work elementwise.
+There's no need to loop over all rows of your data table to do calculations. Column data manipulations work elementwise in pandas.
 Adding a column to a :class:`DataFrame` based on existing data in other columns is straightforward.
 
 .. image:: ../_static/schemas/05_newcolumn_2.svg
@@ -322,7 +322,7 @@ Adding a column to a :class:`DataFrame` based on existing data in other columns
             <div id="collapseSix" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-Basic statistics (mean, median, min, max, counts...) are easily calculable. These or custom aggregations can be applied on the entire
+Basic statistics (mean, median, min, max, counts...) are easily calculable across data frames. These, or even custom aggregations, can be applied on the entire
 data set, a sliding window of the data, or grouped by categories. The latter is also known as the split-apply-combine approach.
 
 .. image:: ../_static/schemas/06_groupby.svg
@@ -369,8 +369,8 @@ data set, a sliding window of the data, or grouped by categories. The latter is
             <div id="collapseSeven" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-Change the structure of your data table in multiple ways. You can :func:`~pandas.melt` your data table from wide to long/tidy form or :func:`~pandas.pivot`
-from long to wide format. With aggregations built-in, a pivot table is created with a single command.
+Change the structure of your data table in a variety of ways. You can use :func:`~pandas.melt` to reshape your data from a wide format to a long and tidy one. Use :func:`~pandas.pivot`
+ to go from long to wide format. With aggregations built-in, a pivot table can be created with a single command.
 
 .. image:: ../_static/schemas/07_melt.svg
    :align: center
@@ -416,7 +416,7 @@ from long to wide format. With aggregations built-in, a pivot table is created w
             <div id="collapseEight" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-Multiple tables can be concatenated both column wise and row wise as database-like join/merge operations are provided to combine multiple tables of data.
+Multiple tables can be concatenated column wise or row wise with pandas' database-like join and merge operations.
 
 .. image:: ../_static/schemas/08_concat_row.svg
    :align: center
@@ -505,7 +505,7 @@ pandas has great support for time series and has an extensive set of tools for w
             <div id="collapseTen" class="collapse" data-parent="#accordion">
                 <div class="card-body">
 
-Data sets do not only contain numerical data. pandas provides a wide range of functions to clean textual data and extract useful information from it.
+Data sets often contain more than just numerical data. pandas provides a wide range of functions to clean textual data and extract useful information from it.
 
 .. raw:: html
 
@@ -551,9 +551,9 @@ the pandas-equivalent operations compared to software you already know:
         :class-card: comparison-card
         :shadow: md
 
-        The `R programming language <https://www.r-project.org/>`__ provides the
-        ``data.frame`` data structure and multiple packages, such as
-        `tidyverse <https://www.tidyverse.org>`__ use and extend ``data.frame``
+        The `R programming language <https://www.r-project.org/>`__ provides a
+        ``data.frame`` data structure as well as packages like
+        `tidyverse <https://www.tidyverse.org>`__ which use and extend ``data.frame``
         for convenient data handling functionalities similar to pandas.
 
         +++
@@ -572,8 +572,8 @@ the pandas-equivalent operations compared to software you already know:
         :class-card: comparison-card
         :shadow: md
 
-        Already familiar to ``SELECT``, ``GROUP BY``, ``JOIN``, etc.?
-        Most of these SQL manipulations do have equivalents in pandas.
+        Already familiar with ``SELECT``, ``GROUP BY``, ``JOIN``, etc.?
+        Many SQL manipulations have equivalents in pandas.
 
         +++
 
@@ -631,10 +631,10 @@ the pandas-equivalent operations compared to software you already know:
         :class-card: comparison-card
         :shadow: md
 
-        The `SAS <https://en.wikipedia.org/wiki/SAS_(software)>`__ statistical software suite
-        also provides the ``data set`` corresponding to the pandas ``DataFrame``.
-        Also SAS vectorized operations, filtering, string processing operations,
-        and more have similar functions in pandas.
+        `SAS <https://en.wikipedia.org/wiki/SAS_(software)>`__, the statistical software suite,
+        uses the ``data set`` structure, which closely corresponds pandas' ``DataFrame``.
+        Also SAS vectorized operations such as filtering or string processing operations
+        have similar functions in pandas.
 
         +++
 

doc/source/getting_started/index.rst

@@ -337,10 +337,8 @@ When taking the product, NA values or empty data will be treated as 1.
    pd.Series([], dtype="float64").prod()
 
 Cumulative methods like :meth:`~DataFrame.cumsum` and :meth:`~DataFrame.cumprod`
-ignore NA values by default preserve them in the result. This behavior can be changed
-with ``skipna``
-
-* Cumulative methods like :meth:`~DataFrame.cumsum` and :meth:`~DataFrame.cumprod` ignore NA values by default, but preserve them in the resulting arrays. To override this behaviour and include NA values, use ``skipna=False``.
+ignore NA values by default, but preserve them in the resulting array. To override
+this behaviour and include NA values in the calculation, use ``skipna=False``.
 
 
 .. ipython:: python