BLD: Move options to pyproject.toml

.github/workflows/package-checks.yml

@@ -42,7 +42,7 @@ jobs:
 
       - name: Install required dependencies
         run: |
-          python -m pip install --upgrade pip setuptools wheel python-dateutil pytz numpy cython
+          python -m pip install --upgrade pip setuptools wheel python-dateutil pytz numpy cython tomli
         shell: bash -el {0}
 
       - name: Pip install with extra

.github/workflows/sdist.yml

@@ -46,7 +46,7 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip setuptools wheel
+        python -m pip install --upgrade pip setuptools wheel tomli
 
         # GH 39416
         pip install numpy

.pre-commit-config.yaml

@@ -269,6 +269,7 @@ repos:
         entry: python scripts/validate_min_versions_in_sync.py
         language: python
         files: ^(ci/deps/actions-.*-minimum_versions\.yaml|pandas/compat/_optional\.py)$
+        additional_dependencies: [tomli]
     -   id: validate-errors-locations
         name: Validate errors locations
         description: Validate errors are in appropriate locations.

pyproject.toml

@@ -5,12 +5,145 @@ requires = [
     "setuptools>=51.0.0",
     "wheel",
     "Cython>=0.29.32,<3",  # Note: sync with setup.py, environment.yml and asv.conf.json
-    "oldest-supported-numpy>=2022.8.16"
+    "oldest-supported-numpy>=2022.8.16",
+    "tomli; python_version < '3.11'" # Versioneer needs this
 ]
 # uncomment to enable pep517 after versioneer problem is fixed.
 # https://github.com/python-versioneer/python-versioneer/issues/193
 # build-backend = "setuptools.build_meta"
 
+[project]
+name = 'pandas'
+dynamic = [
+  'version'
+]
+description = 'Powerful data structures for data analysis, time series, and statistics'
+readme = 'README.md'
+authors = [
+  { name = 'The Pandas Development Team', email='[email protected]' },
+]
+license = {file = 'LICENSE'}
+requires-python = '>=3.8'
+dependencies = [
+  "numpy>=1.20.3; python_version<'3.10'",
+  "numpy>=1.21.0; python_version>='3.10'",
+  "numpy>=1.23.2; python_version>='3.11'",
+  "python-dateutil>=2.8.2",
+  "pytz>=2020.1"
+]
+classifiers = [
+    'Development Status :: 5 - Production/Stable',
+    'Environment :: Console',
+    'Intended Audience :: Science/Research',
+    'License :: OSI Approved :: BSD License',
+    'Operating System :: OS Independent',
+    'Programming Language :: Cython',
+    'Programming Language :: Python',
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3 :: Only',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Topic :: Scientific/Engineering'
+]
+
+[project.urls]
+homepage = 'https://pandas.pydata.org'
+documentation = 'https://pandas.pydata.org/pandas-docs/stable'
+repository = 'https://github.com/pandas-dev/pandas'
+
+[project.entry-points."pandas_plotting_backends"]
+matplotlib = "pandas:plotting._matplotlib"
+
+[project.optional-dependencies]
+test = ['hypothesis>=5.5.3', 'pytest>=6.0', 'pytest-xdist>=1.31', 'pytest-asyncio>=0.17.0']
+performance = ['bottleneck>=1.3.2', 'numba>=0.53.1', 'numexpr>=2.7.1']
+timezone = ['tzdata>=2022.1']
+computation = ['scipy>=1.7.1', 'xarray>=0.19.0']
+fss = ['fsspec>=2021.07.0']
+aws = ['s3fs>=2021.08.0']
+gcp = ['gcsfs>=2021.07.0', 'pandas-gbq>=0.15.0']
+excel = ['odfpy>=1.4.1', 'openpyxl>=3.0.7', 'pyxlsb>=1.0.8', 'xlrd>=2.0.1', 'xlsxwriter>=1.4.3']
+parquet = ['pyarrow>=6.0.0']
+feather = ['pyarrow>=6.0.0']
+hdf5 = [# blosc only available on conda (https://github.com/Blosc/python-blosc/issues/297)
+        #'blosc>=1.20.1',
+        'tables>=3.6.1']
+spss = ['pyreadstat>=1.1.2']
+postgresql = ['SQLAlchemy>=1.4.16', 'psycopg2>=2.8.6']
+mysql = ['SQLAlchemy>=1.4.16', 'pymysql>=1.0.2']
+sql-other = ['SQLAlchemy>=1.4.16']
+html = ['beautifulsoup4>=4.9.3', 'html5lib>=1.1', 'lxml>=4.6.3']
+xml = ['lxml>=4.6.3']
+plot = ['matplotlib>=3.6.1']
+output_formatting = ['jinja2>=3.0.0', 'tabulate>=0.8.9']
+clipboard = ['PyQt5>=5.15.1', 'qtpy>=2.2.0']
+compression = ['brotlipy>=0.7.0', 'python-snappy>=0.6.0', 'zstandard>=0.15.2']
+all = ['beautifulsoup4>=4.9.3',
+       # blosc only available on conda (https://github.com/Blosc/python-blosc/issues/297)
+       #'blosc>=1.21.0',
+       'bottleneck>=1.3.2',
+       'brotlipy>=0.7.0',
+       'fastparquet>=0.6.3',
+       'fsspec>=2021.07.0',
+       'gcsfs>=2021.07.0',
+       'html5lib>=1.1',
+       'hypothesis>=6.13.0',
+       'jinja2>=3.0.0',
+       'lxml>=4.6.3',
+       'matplotlib>=3.6.1',
+       'numba>=0.53.1',
+       'numexpr>=2.7.3',
+       'odfpy>=1.4.1',
+       'openpyxl>=3.0.7',
+       'pandas-gbq>=0.15.0',
+       'psycopg2>=2.8.6',
+       'pyarrow>=6.0.0',
+       'pymysql>=1.0.2',
+       'PyQt5>=5.15.1',
+       'pyreadstat>=1.1.2',
+       'pytest>=6.0',
+       'pytest-xdist>=1.31',
+       'pytest-asyncio>=0.17.0',
+       'python-snappy>=0.6.0',
+       'pyxlsb>=1.0.8',
+       'qtpy>=2.2.0',
+       'scipy>=1.7.1',
+       's3fs>=2021.08.0',
+       'SQLAlchemy>=1.4.16',
+       'tables>=3.6.1',
+       'tabulate>=0.8.9',
+       'tzdata>=2022.1',
+       'xarray>=0.19.0',
+       'xlrd>=2.0.1',
+       'xlsxwriter>=1.4.3',
+       'zstandard>=0.15.2']
+
+# TODO: Remove after setuptools support is dropped.
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+include = ["pandas", "pandas.*"]
+namespaces = false
+
+[tool.setuptools.exclude-package-data]
+"*" = ["*.c", "*.h"]
+
+
+# Consider removing.
+# See the docstring in versioneer.py for instructions. Note that you must
+# re-run 'versioneer.py setup' after changing this section, and commit the
+# resulting files.
+[tool.versioneer]
+VCS = "git"
+style = "pep440"
+versionfile_source = "pandas/_version.py"
+versionfile_build = "pandas/_version.py"
+tag_prefix = "v"
+parentdir_prefix = "pandas-"
+
 [tool.cibuildwheel]
 skip = "cp36-* cp37-* pp37-* *-manylinux_i686 *_ppc64le *_s390x *-musllinux*"
 build-verbosity = "3"

scripts/validate_min_versions_in_sync.py

@@ -14,16 +14,20 @@
 """
 from __future__ import annotations
 
-import configparser
 import pathlib
 import sys
 
+if sys.version_info >= (3, 11):
+    import tomllib
+else:
+    import tomli as tomllib
+
 DOC_PATH = pathlib.Path("doc/source/getting_started/install.rst").resolve()
 CI_PATH = next(
     pathlib.Path("ci/deps").absolute().glob("actions-*-minimum_versions.yaml")
 )
 CODE_PATH = pathlib.Path("pandas/compat/_optional.py").resolve()
-SETUP_PATH = pathlib.Path("setup.cfg").resolve()
+SETUP_PATH = pathlib.Path("pyproject.toml").resolve()
 EXCLUDE_DEPS = {"tzdata", "blosc"}
 # pandas package is not available
 # in pre-commit environment
@@ -80,22 +84,20 @@ def get_versions_from_ci(content: list[str]) -> tuple[dict[str, str], dict[str,
     return required_deps, optional_deps
 
 
-def get_versions_from_setup() -> dict[str, str]:
-    """Min versions in setup.cfg for pip install pandas[extra]."""
+def get_versions_from_toml() -> dict[str, str]:
+    """Min versions in pyproject.toml for pip install pandas[extra]."""
     install_map = _optional.INSTALL_MAPPING
+    dependencies = set()
     optional_dependencies = {}
 
-    parser = configparser.ConfigParser()
-    parser.read(SETUP_PATH)
-    setup_optional = parser["options.extras_require"]["all"]
-    dependencies = setup_optional[1:].split("\n")
+    with open(SETUP_PATH, "rb") as pyproject_f:
+        pyproject_toml = tomllib.load(pyproject_f)
+        opt_deps = pyproject_toml["project"]["optional-dependencies"]
+        dependencies = set(opt_deps["all"])
 
-    # remove test dependencies
-    test = parser["options.extras_require"]["test"]
-    test_dependencies = set(test[1:].split("\n"))
-    dependencies = [
-        package for package in dependencies if package not in test_dependencies
-    ]
+        # remove test dependencies
+        test_deps = set(opt_deps["test"])
+        dependencies = dependencies.difference(test_deps)
 
     for dependency in dependencies:
         package, version = dependency.strip().split(">=")
@@ -111,7 +113,7 @@ def main():
     with open(CI_PATH, encoding="utf-8") as f:
         _, ci_optional = get_versions_from_ci(f.readlines())
     code_optional = get_versions_from_code()
-    setup_optional = get_versions_from_setup()
+    setup_optional = get_versions_from_toml()
 
     diff = (ci_optional.items() | code_optional.items() | setup_optional.items()) - (
         ci_optional.items() & code_optional.items() & setup_optional.items()