Merge branch 'main' of github.com:pandas-dev/pandas into arrow-to-csv

Author: lithomas1

.circleci/setup_env.sh

@@ -55,6 +55,6 @@ if pip show pandas 1>/dev/null; then
 fi
 
 echo "Install pandas"
-python -m pip install --no-build-isolation -ve .
+python -m pip install --no-build-isolation -ve . --config-settings=setup-args="--werror"
 
 echo "done"

.github/actions/build_pandas/action.yml

@@ -25,8 +25,10 @@ runs:
     - name: Build Pandas
       run: |
         if [[ ${{ inputs.editable }} == "true" ]]; then
-          pip install -e . --no-build-isolation -v --no-deps
+          pip install -e . --no-build-isolation -v --no-deps \
+            --config-settings=setup-args="--werror"
         else
-          pip install . --no-build-isolation -v --no-deps
+          pip install . --no-build-isolation -v --no-deps \
+            --config-settings=setup-args="--werror"
         fi
       shell: bash -el {0}

.github/workflows/unit-tests.yml

@@ -26,7 +26,7 @@ jobs:
     timeout-minutes: 90
     strategy:
       matrix:
-        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml]
+        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
         include:
@@ -69,6 +69,10 @@ jobs:
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "1"
+          - name: "Copy-on-Write 3.12"
+            env_file: actions-312.yaml
+            pattern: "not slow and not network and not single_cpu"
+            pandas_copy_on_write: "1"
           - name: "Copy-on-Write 3.11 (warnings)"
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -190,7 +194,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest, windows-latest]
-        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml]
+        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml, actions-312.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     name: ${{ format('{0} {1}', matrix.os, matrix.env_file) }}
@@ -250,7 +254,7 @@ jobs:
           python -m pip install --no-cache-dir -U pip wheel setuptools meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install numpy --config-settings=setup-args="-Dallow-noblas=true"
           python -m pip install --no-cache-dir versioneer[toml] cython 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 .
+          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
@@ -288,7 +292,7 @@ jobs:
           . ~/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 .
+          python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
           python -m pip list --no-cache-dir
 
       - name: Run Tests
@@ -321,7 +325,7 @@ jobs:
     #    To freeze this file, uncomment out the ``if: false`` condition, and migrate the jobs
     #    to the corresponding posix/windows-macos/sdist etc. workflows.
     # Feel free to modify this comment as necessary.
-    #if: false # Uncomment this to freeze the workflow, comment it to unfreeze
+    if: false # Uncomment this to freeze the workflow, comment it to unfreeze
     defaults:
       run:
         shell: bash -eou pipefail {0}
@@ -361,7 +365,7 @@ jobs:
           python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy
           python -m pip install versioneer[toml]
           python -m pip install python-dateutil pytz tzdata cython hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0 pytest-cov
-          python -m pip install -ve . --no-build-isolation --no-index --no-deps
+          python -m pip install -ve . --no-build-isolation --no-index --no-deps --config-settings=setup-args="--werror"
           python -m pip list
 
       - name: Run Tests

.gitignore

@@ -39,6 +39,7 @@
 .mesonpy-native-file.ini
 MANIFEST
 compile_commands.json
+debug
 .debug
 
 # Python files #
@@ -104,10 +105,11 @@ scikits
 # Generated Sources #
 #####################
 !skts.c
-!np_datetime.c
-!np_datetime_strings.c
 *.c
 *.cpp
+!pandas/_libs/src/**/*.c
+!pandas/_libs/src/**/*.h
+!pandas/_libs/include/**/*.h
 
 # Unit / Performance Testing #
 ##############################

.pre-commit-config.yaml

@@ -20,11 +20,11 @@ ci:
 repos:
 -   repo: https://github.com/hauntsaninja/black-pre-commit-mirror
     # black compiled with mypyc
-    rev: 23.10.1
+    rev: 23.11.0
     hooks:
       - id: black
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.4
+    rev: v0.1.6
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -47,7 +47,7 @@ repos:
         types_or: [python, rst, markdown, cython, c]
         additional_dependencies: [tomli]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.15.0
+    rev: v0.16.0
     hooks:
     -   id: cython-lint
     -   id: double-quote-cython-strings
@@ -111,11 +111,11 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v0.8.1
+    rev: v0.9.0
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v17.0.4
+    rev: v17.0.6
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

asv_bench/benchmarks/arithmetic.py

@@ -6,12 +6,12 @@
 import pandas as pd
 from pandas import (
     DataFrame,
+    Index,
     Series,
     Timestamp,
     date_range,
     to_timedelta,
 )
-import pandas._testing as tm
 from pandas.core.algorithms import checked_add_with_arr
 
 from .pandas_vb_common import numeric_dtypes
@@ -323,8 +323,10 @@ class IndexArithmetic:
 
     def setup(self, dtype):
         N = 10**6
-        indexes = {"int": "makeIntIndex", "float": "makeFloatIndex"}
-        self.index = getattr(tm, indexes[dtype])(N)
+        if dtype == "float":
+            self.index = Index(np.arange(N), dtype=np.float64)
+        elif dtype == "int":
+            self.index = Index(np.arange(N), dtype=np.int64)
 
     def time_add(self, dtype):
         self.index + 2

ci/deps/actions-310.yaml

@@ -46,7 +46,7 @@ dependencies:
   - pyqt>=5.15.9
   - pyreadstat>=1.2.0
   - pytables>=3.8.0
-  - python-calamine>=0.1.6
+  - python-calamine>=0.1.7
   - pyxlsb>=1.0.10
   - s3fs>=2022.11.0
   - scipy>=1.10.0

ci/deps/actions-311-downstream_compat.yaml

@@ -47,7 +47,7 @@ dependencies:
   - pyqt>=5.15.9
   - pyreadstat>=1.2.0
   - pytables>=3.8.0
-  - python-calamine>=0.1.6
+  - python-calamine>=0.1.7
   - pyxlsb>=1.0.10
   - s3fs>=2022.11.0
   - scipy>=1.10.0

ci/deps/actions-311.yaml

@@ -46,7 +46,7 @@ dependencies:
   - pymysql>=1.0.2
   - pyreadstat>=1.2.0
   - pytables>=3.8.0
-  - python-calamine>=0.1.6
+  - python-calamine>=0.1.7
   - pyxlsb>=1.0.10
   - s3fs>=2022.11.0
   - scipy>=1.10.0

ci/deps/actions-312.yaml

@@ -0,0 +1,63 @@
+name: pandas-dev-312
+channels:
+  - conda-forge
+dependencies:
+  - python=3.12
+
+  # build dependencies
+  - versioneer[toml]
+  - cython>=0.29.33
+  - meson[ninja]=1.2.1
+  - meson-python=0.13.1
+
+  # test dependencies
+  - pytest>=7.3.2
+  - pytest-cov
+  - pytest-xdist>=2.2.0
+  - pytest-localserver>=0.7.1
+  - pytest-qt>=4.2.0
+  - boto3
+
+  # required dependencies
+  - python-dateutil
+  - numpy<2
+  - pytz
+
+  # optional dependencies
+  - beautifulsoup4>=4.11.2
+  - blosc>=1.21.3
+  - bottleneck>=1.3.6
+  - fastparquet>=2022.12.0
+  - fsspec>=2022.11.0
+  - html5lib>=1.1
+  - hypothesis>=6.46.1
+  - gcsfs>=2022.11.0
+  - jinja2>=3.1.2
+  - lxml>=4.9.2
+  - matplotlib>=3.6.3
+  # - numba>=0.56.4
+  - numexpr>=2.8.4
+  - odfpy>=1.4.1
+  - qtpy>=2.3.0
+  - pyqt>=5.15.9
+  - openpyxl>=3.1.0
+  - psycopg2>=2.9.6
+  - pyarrow>=10.0.1
+  - pymysql>=1.0.2
+  - pyreadstat>=1.2.0
+  # - pytables>=3.8.0
+  - python-calamine>=0.1.7
+  - pyxlsb>=1.0.10
+  - s3fs>=2022.11.0
+  - scipy>=1.10.0
+  - sqlalchemy>=2.0.0
+  - tabulate>=0.9.0
+  - xarray>=2022.12.0
+  - xlrd>=2.0.1
+  - xlsxwriter>=3.0.5
+  - zstandard>=0.19.0
+
+  - pip:
+    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-sqlite>=0.8.0
+    - tzdata>=2022.7