Merge pull request #830 from fsschneider/pyproject.toml

Switch to `pyproject.toml`

.github/workflows/linting.yml

@@ -50,7 +50,7 @@ jobs:
     - name: Install yapf
       run: |
         python -m pip install --upgrade pip
-        pip install yapf==0.32
+        pip install yapf==0.32 toml
     - name: Run yapf
       run: |
         yapf . --diff --recursive

pyproject.toml

@@ -0,0 +1,329 @@
+###############################################################################
+#                      MLCommons Algorithmic Efficiency.                      #
+###############################################################################
+
+[project]
+name = "algorithmic_efficiency"
+dynamic = ["version"]
+description = "Codebase for the AlgoPerf: Training Algorithms benchmark"
+authors = [
+  { name = "MLCommons Algorithms Working Group", email = "[email protected]" },
+]
+license = { text = "Apache 2.0" }
+readme = "README.md"
+requires-python = ">=3.8"
+keywords = [
+  "algoperf",
+  "algorithmic-efficiency",
+  "machine-learning",
+  "deep-learning",
+  "optimization",
+  "benchmarking",
+  "training-methods",
+]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+  "absl-py==1.4.0",
+  "networkx==3.1",
+  "docker==7.0.0",
+  "numpy>=1.23",
+  "pandas>=2.0.1",
+  "tensorflow==2.12.0",
+  "tensorflow-datasets==4.9.2",
+  "tensorflow-probability==0.20.0",
+  "tensorflow-addons==0.20.0",
+  "gputil==1.4.0",
+  "psutil==5.9.5",
+  "clu==0.0.7",
+  "matplotlib>=3.7.2",
+  "tabulate==0.9.0",
+]
+
+[build-system]
+requires = ["setuptools>=45", "setuptools_scm[toml]>=6.2"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+py-modules = ["submission_runner"]
+include-package-data = true
+zip-safe = false
+
+[tool.setuptools.packages]
+find = {} # Scanning implicit namespaces is active by default
+
+[tool.setuptools.dynamic]
+version = { attr = "algorithmic_efficiency.__version__" }
+
+###############################################################################
+#                          (Optional) Dependencies                            #
+###############################################################################
+[project.optional-dependencies]
+# All workloads
+full = [
+  "algorithmic_efficiency[criteo1tb,fastmri,ogbg,librispeech_conformer,wmt]",
+]
+# All workloads plus development dependencies
+full_dev = ["algorithmic_efficiency[full,dev]"]
+# Dependencies for developing the package
+dev = [
+  "isort==5.12.0",
+  "pylint==2.17.4",
+  "pytest==7.3.1",
+  "yapf==0.33.0",
+  "pre-commit==3.3.1",
+]
+
+# Workloads
+criteo1tb = ["scikit-learn==1.2.2"]
+fastmri = ["h5py==3.8.0", "scikit-image==0.20.0"]
+ogbg = ["jraph==0.0.6.dev0", "scikit-learn==1.2.2"]
+librispeech_conformer = [
+  "sentencepiece==0.1.99",
+  "tensorflow-text==2.12.1",
+  "pydub==0.25.1",
+]
+wmt = ["sentencepiece==0.1.99", "tensorflow-text==2.12.1", "sacrebleu==1.3.1"]
+
+# Frameworks
+jax_core_deps = [
+  "flax==0.6.10",
+  "optax==0.1.5",
+  # Todo(kasimbeg): verify if this is necessary after we upgrade jax.
+  "chex==0.1.7",
+  "ml_dtypes==0.2.0",
+  "protobuf==4.25.3",
+]
+jax_cpu = [
+  "jax==0.4.10",
+  "jaxlib==0.4.10",
+  "algorithmic_efficiency[jax_core_deps]",
+]
+jax_gpu = [
+  "jax==0.4.10",
+  "jaxlib==0.4.10+cuda12.cudnn88",
+  "algorithmic_efficiency[jax_core_deps]",
+]
+pytorch_cpu = ["torch==2.1.0", "torchvision==0.16.0"]
+pytorch_gpu = [
+  "torch==2.1.0",
+  "torchvision==0.16.0",
+] # Note: omit the cuda suffix and installing from the appropriate wheel will result in using locally installed CUDA.
+wandb = ["wandb==0.16.5"]
+
+###############################################################################
+#                           Linting Configurations                            #
+###############################################################################
+
+# yapf configuration
+[tool.yapf]
+based_on_style = "yapf"
+each_dict_entry_on_separate_line = false
+split_all_top_level_comma_separated_values = true
+
+# isort configuration
+[tool.isort]
+profile = "google"
+
+# pylint configuration
+[tool.pylint.MASTER]
+persistent = false
+ignore = "get_references_web.py,get_references_web_single_group.py"
+
+[tool.pylint.REPORTS]
+reports = false
+msg-template = "{msg_id}:{line:3} {obj}: {msg} [{symbol}]"
+
+[tool.pylint.MESSAGES_CONTROL]
+enable = "indexing-exception,old-raise-syntax"
+
+[tool.pylint.BASIC]
+# Required attributes for module, separated by a comma
+#required-attributes=
+# Regular expression which should only match the name
+# of functions or classes which do not require a docstring.
+no-docstring-rgx = "(__.*__|main)"
+# Min length in lines of a function that requires a docstring.
+docstring-min-length = 10
+# Regular expression which should only match correct module names. The
+# leading underscore is sanctioned for private modules by Google's style
+# guide.
+#
+# There are exceptions to the basic rule (_?[a-z][a-z0-9_]*) to cover
+# requirements of Python's module system.
+module-rgx = "^(_?[a-z][a-z0-9_]*)|__init__$"
+# Regular expression which should only match correct module level names
+const-rgx = "^(_?[A-Z][A-Z0-9_]*|__[a-z0-9_]+__|_?[a-z][a-z0-9_]*)$"
+# Regular expression which should only match correct class attribute
+class-attribute-rgx = "^(_?[A-Z][A-Z0-9_]*|__[a-z0-9_]+__|_?[a-z][a-z0-9_]*)$"
+# Regular expression which should only match correct class names
+class-rgx = "^_?[A-Z][a-zA-Z0-9]*$"
+# Regular expression which should only match correct function names.
+# 'camel_case' and 'snake_case' group names are used for consistency of naming
+# styles across functions and methods.
+function-rgx = "^(?:(?P<exempt>setUp|tearDown|setUpModule|tearDownModule)|(?P<camel_case>_?[A-Z][a-zA-Z0-9]*)|(?P<snake_case>_?[a-z][a-z0-9_]*))$"
+# Regular expression which should only match correct method names.
+# 'camel_case' and 'snake_case' group names are used for consistency of naming
+# styles across functions and methods. 'exempt' indicates a name which is
+# consistent with all naming styles.
+method-rgx = "(?x)^(?:(?P<exempt>_[a-z0-9_]+__|runTest|setUp|tearDown|setUpTestCase|tearDownTestCase|setupSelf|tearDownClass|_testDatasetSize|setUpClass|test|assert)_*[A-Z0-9][a-zA-Z0-9_]*|(?:test|assert)_*[A-Z0-9][a-zA-Z0-9_]*|next|(?P<camel_case>_{0,2}[A-Z][a-zA-Z0-9_]*)|(?P<snake_case>_{0,2}[a-z][a-z0-9_]*))$"
+# Regular expression which should only match correct instance attribute names
+attr-rgx = "^_{0,2}[a-z][a-z0-9_]*$"
+# Regular expression which should only match correct argument names
+argument-rgx = "^[a-z][a-z0-9_]*$"
+# Regular expression which should only match correct variable names
+variable-rgx = "^[a-z][a-z0-9_]*$"
+# Regular expression which should only match correct list comprehension /
+# generator expression variable names
+inlinevar-rgx = "^[a-z][a-z0-9_]*$"
+# Good variable names which should always be accepted, separated by a comma
+good-names = "main,_"
+# Bad variable names which should always be refused, separated by a comma
+bad-names = ""
+# List of builtins function names that should not be used, separated by a comma
+#bad-functions=input,apply,reduce
+# List of decorators that define properties, such as abc.abstractproperty.
+property-classes = "abc.abstractproperty"
+
+[tool.pylint.typecheck]
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members = true
+
+# List of decorators that create context managers from functions, such as
+# contextlib.contextmanager.
+contextmanager-decorators = [
+  "contextlib.contextmanager",
+  "contextlib2.contextmanager",
+]
+
+[tool.pylint.VARIABLES]
+# Tells whether we should check for unused import in __init__ files.
+init-import = false
+
+# A regular expression matching names used for dummy variables (i.e. not used).
+dummy-variables-rgx = "^\\*{0,2}(_$|unused_|dummy_)"
+
+# List of additional names supposed to be defined in builtins.
+additional-builtins = []
+
+[tool.pylint.CLASSES]
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods = ["__init__", "__new__", "setUp"]
+
+# Valid names for the first argument to a class method.
+valid-classmethod-first-arg = ["cls", "class_"]
+
+[tool.pylint.EXCEPTIONS]
+overgeneral-exceptions = [
+  "builtins.StandardError",
+  "builtins.Exception",
+  "builtins.BaseException",
+]
+
+[tool.pylint.IMPORTS]
+# Deprecated modules which should not be used, separated by a comma
+deprecated-modules = ["regsub", "TERMIOS", "Bastion", "rexec", "sets"]
+
+[tool.pylint.FORMAT]
+# List of checkers and warnings to disable.
+disable = [
+  "abstract-method",
+  "access-member-before-definition",
+  "arguments-differ",
+  "assignment-from-no-return",
+  "attribute-defined-outside-init",
+  "bad-mcs-classmethod-argument",
+  "bad-option-value",
+  "c-extension-no-member",
+  "consider-merging-isinstance",
+  "consider-using-dict-comprehension",
+  "consider-using-enumerate",
+  "consider-using-in",
+  "consider-using-set-comprehension",
+  "consider-using-ternary",
+  "deprecated-method",
+  "design",
+  "file-ignored",
+  "fixme",
+  "global-statement",
+  "import-error",
+  "inconsistent-return-statements",
+  "invalid-unary-operand-type",
+  "len-as-condition",
+  "locally-disabled",
+  "locally-enabled",
+  "misplaced-comparison-constant",
+  "missing-docstring",
+  "multiple-imports",
+  "no-else-return",
+  "no-member",
+  "no-name-in-module",
+  "no-self-use",
+  "no-value-for-parameter",
+  "not-an-iterable",
+  "not-context-manager",
+  "pointless-except",
+  "protected-access",
+  "redefined-argument-from-local",
+  "signature-differs",
+  "similarities",
+  "simplifiable-if-expression",
+  "star-args",
+  "super-init-not-called",
+  "suppressed-message",
+  "too-many-function-args",
+  "trailing-comma-tuple",
+  "trailing-newlines",
+  "ungrouped-imports",
+  "unnecessary-pass",
+  "unsubscriptable-object",
+  "unused-argument",
+  "useless-object-inheritance",
+  "useless-return",
+  "useless-suppression",
+  "wrong-import-order",
+  "wrong-import-position",
+  "unneeded-not",
+  "unexpected-keyword-arg",
+  "redundant-keyword-arg",
+  "unspecified-encoding",
+  "logging-fstring-interpolation",
+  "consider-using-f-string",
+  "use-dict-literal",
+]
+# Maximum number of characters on a single line.
+max-line-length = 80
+ignore-long-lines = "(?x)(^\\s*(import|from)\\s|^\\s*(\\#\\ )?<?(https?|ftp):\\/\\/[^\\s\\/$.?#].[^\\s]*>?$|^[a-zA-Z_][a-zA-Z0-9_]*\\s*=\\s*('[^']\\S+'|\"[^\"]\\S+\"))"
+# Maximum number of lines in a module
+max-module-lines = 99999
+# String used as indentation unit. We differ from PEP8's normal 4 spaces.
+indent-string = '  '
+single-line-if-stmt = true
+# Do not warn about multiple statements on a single line for constructs like
+#   if test: stmt
+[tool.pylint.LOGGING]
+logging-modules = "logging,absl.logging"
+# Add logging modules.
+[tool.pylint.MISCELLANEOUS]
+# Maximum line length for lambdas
+#short-func-length=1
+# List of module members that should be marked as deprecated.
+# All of the string functions are listed in 4.1.4 Deprecated string functions
+# in the Python 2.4 docs.
+#deprecated-members=string.atof,string.atoi,string.atol,string.capitalize,string.expandtabs,string.find,string.rfind,string.index,string.rindex,string.count,string.lower,string.split,string.rsplit,string.splitfields,string.join,string.joinfields,string.lstrip,string.rstrip,string.strip,string.swapcase,string.translate,string.upper,string.ljust,string.rjust,string.center,string.zfill,string.replace,sys.exitfunc,sys.maxint
+# List of exceptions that do not need to be mentioned in the Raises section of
+# a docstring.
+#ignore-exceptions=AssertionError,NotImplementedError,StopIteration,TypeError
+# Number of spaces of indent required when the last token on the preceding line
+# is an open (, [, or {.
+indent-after-paren = 4