Transition from using setup.py to pyproject.toml to specify project metadata

.github/workflows/readme.yml

@@ -22,5 +22,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         python -m pip install invoke rundoc .
+        python -m pip install tomli
+        python -m pip install packaging
     - name: Run the README.md
       run: invoke readme

Makefile

@@ -130,9 +130,7 @@ coverage: ## check code coverage quickly with the default Python
 
 .PHONY: dist
 dist: clean ## builds source and wheel package
-	python setup.py sdist
-	python setup.py bdist_wheel
-	python rdt/transformers/addons/addons_setup.py
+	python -m build --wheel --sdist
 	ls -l dist
 
 .PHONY: publish-confirm

pyproject.toml

@@ -0,0 +1,138 @@
+[build-system]
+requires = ['setuptools', 'wheel']
+build-backend = 'setuptools.build_meta'
+
+[project]
+name = 'rdt'
+description = 'Reversible Data Transforms'
+authors = [{ name = 'DataCebo, Inc.', email = '[email protected]' }]
+classifiers = [
+    'Development Status :: 5 - Production/Stable',
+    'Intended Audience :: Developers',
+    'License :: Free for non-commercial use',
+    'Natural Language :: English',
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Topic :: Scientific/Engineering :: Artificial Intelligence',
+]
+keywords = ['machine learning', 'synthetic data generation', 'benchmark', 'generative models']
+version = '1.9.3.dev0'
+license = { text = 'BSL-1.1' }
+requires-python = '>=3.8,<3.12'
+readme = 'README.md'
+dependencies = [
+    "numpy>=1.20.0,<2;python_version<'3.10'",
+    "numpy>=1.23.3,<2;python_version>='3.10'",
+    "pandas>=1.1.3;python_version<'3.10'",
+    "pandas>=1.3.4;python_version>='3.10' and python_version<'3.11'",
+    "pandas>=1.5.0;python_version>='3.11'",
+    "scipy>=1.5.4,<2;python_version<'3.10'",
+    "scipy>=1.9.2,<2;python_version>='3.10'",
+    "scikit-learn>=0.24,<2;python_version<'3.10'",
+    "scikit-learn>=1.1.0;python_version>='3.10' and python_version<'3.11'",
+    "scikit-learn>=1.1.3,<2;python_version>='3.11'",
+    'Faker>=17,<20',
+]
+
+[project.urls]
+"Source Code"= "https://github.com/sdv-dev/RDT/"
+"Issue Tracker" = "https://github.com/sdv-dev/RDT/issues"
+"Changes" = "https://github.com/sdv-dev/RDT/blob/main/HISTORY.md"
+"Twitter" = "https://twitter.com/sdv_dev"
+"Chat" = "https://bit.ly/sdv-slack-invite"
+
+[project.entry-points]
+rdt = { main = 'rdt.cli.__main__:main' }
+
+[project.optional-dependencies]
+copulas = ['copulas>=0.10.0,<0.11',]
+test = [
+    'rdt[copulas]',
+
+    'pytest>=3.4.2',
+    'pytest-cov>=2.6.0',
+    'jupyter>=1.0.0,<2',
+    'rundoc>=0.4.3,<0.5',
+    'pytest-subtests>=0.5,<1.0',
+    'pytest-runner >= 2.11.1',
+    'tomli>=2.0.0,<3',
+]
+dev = [
+    'rdt[test]',
+
+    # general
+    'bumpversion>=0.5.3,<0.6',
+    'pip>=9.0.1',
+    'watchdog>=0.8.3,<0.11',
+
+    # style check
+    'pycodestyle<2.8.0,>=2.7.0',
+    'pyflakes<2.4.0,>=2.3.0',
+    'flake8>=3.7.7,<4',
+    'flake8-absolute-import>=1.0,<2',
+    'flake8-builtins>=1.5.3,<1.6',
+    'flake8-comprehensions>=3.6.1,<3.7',
+    'flake8-debugger>=4.0.0,<4.1',
+    'flake8-docstrings>=1.5.0,<2',
+    'flake8-mock>=0.3,<0.4',
+    'flake8-variables-names>=0.0.4,<0.1',
+    'dlint>=0.11.0,<0.12',  # code security addon for flake8
+    'flake8-fixme>=1.1.1,<1.2',
+    'flake8-eradicate>=1.1.0,<1.2',
+    'flake8-mutable>=1.2.0,<1.3',
+    'flake8-print>=4.0.0,<4.1',
+    'isort>=4.3.4,<5',
+    'pylint>=2.5.3,<3',
+    'pandas-vet>=0.2.3,<0.3',
+    'flake8-multiline-containers>=0.0.18,<0.1',
+    'flake8-pytest-style>=1.5.0,<2',
+    'flake8-quotes>=3.3.0,<4',
+    'flake8-expression-complexity>=0.0.9,<0.1',
+    'pep8-naming>=0.12.1,<0.13',
+    'pydocstyle>=6.1.1,<6.2',
+    'flake8-sfs>=0.0.3,<0.1',
+
+    # fix style issues
+    'autoflake>=1.1,<2',
+    'autopep8>=1.4.3,<1.6',
+
+    # distribute on PyPI
+    'twine>=1.10.0,<4',
+    'wheel>=0.30.0',
+
+    # Advanced testing
+    'coverage>=4.5.1,<6',
+    'tox>=2.9.1,<4',
+    'tabulate>=0.8.9,<1',
+
+    # Invoking test commands
+    'invoke'
+]
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+include = ['rdt', 'rdt.*']
+namespaces = false
+
+[tool.isort]
+line_length = 99
+lines_between_types = 0
+multi_line_output = 4
+not_skip = ['__init__.py']
+use_parentheses = true
+
+[tool.pydocstyle]
+convention = 'google'
+add-ignore = ['D107', 'D407', 'D417']
+
+[tool.pytest.ini_options]
+collect_ignore = ['pyproject.toml']
+
+[tool.coverage.report]
+exclude_lines = ['NotImplementedError()']
+

rdt/__init__.py

@@ -7,15 +7,8 @@
 __email__ = '[email protected]'
 __version__ = '1.9.3.dev0'
 
-
-import sys
-import warnings
-from operator import attrgetter
-from types import ModuleType
-
 import numpy as np
 import pandas as pd
-from pkg_resources import iter_entry_points
 
 from rdt import transformers
 from rdt.hyper_transformer import HyperTransformer
@@ -94,82 +87,3 @@ def get_demo(num_rows=5):
             'dollars_spent': dollars_spent
         })
     ], ignore_index=True)
-
-
-def _get_addon_target(addon_path_name):
-    """Find the target object for the add-on.
-
-    Args:
-        addon_path_name (str):
-            The add-on's name. The add-on's name should be the full path of valid Python
-            identifiers (i.e. importable.module:object.attr).
-
-    Returns:
-        tuple:
-            * object:
-                The base module or object the add-on should be added to.
-            * str:
-                The name the add-on should be added to under the module or object.
-    """
-    module_path, _, object_path = addon_path_name.partition(':')
-    module_path = module_path.split('.')
-
-    if module_path[0] != __name__:
-        msg = f"expected base module to be '{__name__}', found '{module_path[0]}'"
-        raise AttributeError(msg)
-
-    target_base = sys.modules[__name__]
-    for submodule in module_path[1:-1]:
-        target_base = getattr(target_base, submodule)
-
-    addon_name = module_path[-1]
-    if object_path:
-        if len(module_path) > 1 and not hasattr(target_base, module_path[-1]):
-            msg = f"cannot add '{object_path}' to unknown submodule '{'.'.join(module_path)}'"
-            raise AttributeError(msg)
-
-        if len(module_path) > 1:
-            target_base = getattr(target_base, module_path[-1])
-
-        split_object = object_path.split('.')
-        addon_name = split_object[-1]
-
-        if len(split_object) > 1:
-            target_base = attrgetter('.'.join(split_object[:-1]))(target_base)
-
-    return target_base, addon_name
-
-
-def _find_addons():
-    """Find and load all RDT add-ons.
-
-    If the add-on is a module, we add it both to the target module and to
-    ``system.modules`` so that they can be imported from the top of a file as follows:
-
-    from top_module.addon_module import x
-    """
-    group = 'rdt_modules'
-    for entry_point in iter_entry_points(group=group):
-        try:
-            addon = entry_point.load()
-        except Exception:  # pylint: disable=broad-exception-caught
-            msg = f'Failed to load "{entry_point.name}" from "{entry_point.module_name}".'
-            warnings.warn(msg)
-            continue
-
-        try:
-            addon_target, addon_name = _get_addon_target(entry_point.name)
-        except AttributeError as error:
-            msg = f"Failed to set '{entry_point.name}': {error}."
-            warnings.warn(msg)
-            continue
-
-        if isinstance(addon, ModuleType):
-            addon_module_name = f'{addon_target.__name__}.{addon_name}'
-            if addon_module_name not in sys.modules:
-                sys.modules[addon_module_name] = addon
-
-        setattr(addon_target, addon_name, addon)
-
-
-_find_addons()

rdt/transformers/__init__.py

@@ -2,12 +2,9 @@
 
 import importlib
 import inspect
-import json
-import sys
 from collections import defaultdict
 from copy import deepcopy
 from functools import lru_cache
-from pathlib import Path
 
 from rdt.transformers.base import BaseMultiColumnTransformer, BaseTransformer
 from rdt.transformers.boolean import BinaryEncoder
@@ -49,21 +46,6 @@
 ]
 
 
-def _import_addons():
-    """Import all the addon modules."""
-    addons_path = Path(__file__).parent / 'addons'
-    for addon_json_path in addons_path.glob('*/*.json'):
-        with open(addon_json_path, 'r', encoding='utf-8') as addon_json_file:
-            transformers = json.load(addon_json_file).get('transformers', [])
-            for transformer in transformers:
-                module = transformer.rsplit('.', 1)[0]
-                if module not in sys.modules:
-                    importlib.import_module(module)
-
-
-_import_addons()
-
-
 def get_transformer_name(transformer):
     """Return the fully qualified path of the transformer.