proeval/pyproject.toml at main · google-deepmind/proeval · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
[build-system]
requires = ["setuptools>=64", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "proeval"
version = "0.1.1"
description = "ProEval — Proactive failure discovery and efficient performance estimation for Generative AI evaluation."
readme = "README.md"
requires-python = ">=3.9"
license = { file = "LICENSE" }
authors = [
    { name = "Yizheng Huang" },
    { name = "Wenjun Zeng" },
    { name = "Aditi Kumaresan" },
    { name = "Zi Wang" },
]
maintainers = [
    { name = "ProEval Authors", email = "proeval@google.com" },
]
keywords = [
    "llm",
    "evaluation",
    "active-learning",
    "bayesian-quadrature",
    "gaussian-process",
    "generative-ai",
    "benchmarking",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries :: Python Modules",
]

dependencies = [
    "numpy>=1.24.0",
    "pandas>=2.0.0",
    "scikit-learn>=1.3.0",
    "requests>=2.31.0",
    "tqdm>=4.65.0",
]

[project.optional-dependencies]
# Neural-encoder training + BQ-TPF sampler.
encoder = [
    "torch>=2.0.0",
]
# Topic-aware test-case generation (BERTopic + HDBSCAN).
topics = [
    "bertopic>=0.16.0",
    "hdbscan>=0.8.33",
]
# HuggingFace dataset loading helpers (for evaluator.load_dataset_data).
datasets = [
    "datasets>=2.14.0",
]
# Plotting utilities (utils/plotting.py).
plotting = [
    "matplotlib>=3.7.0",
    "seaborn>=0.12.0",
]
# Everything required to run the full experiment suite.
all = [
    "torch>=2.0.0",
    "bertopic>=0.16.0",
    "hdbscan>=0.8.33",
    "datasets>=2.14.0",
    "matplotlib>=3.7.0",
    "seaborn>=0.12.0",
]
# Developer tooling.
dev = [
    "pytest>=7.0",
    "pytest-cov>=4.0",
    "ruff>=0.1.0",
    "build>=1.0",
    "twine>=4.0",
]

[project.urls]
Homepage = "https://github.com/google-deepmind/proeval"
Documentation = "https://github.com/google-deepmind/proeval#readme"
Repository = "https://github.com/google-deepmind/proeval"
Issues = "https://github.com/google-deepmind/proeval/issues"
Paper = "https://arxiv.org/abs/2604.23099"

[tool.setuptools]
include-package-data = true

[tool.setuptools.packages.find]
where = ["."]
include = ["proeval*"]
exclude = ["data*", "experiment*", "utils*", "tests*"]

[tool.ruff]
line-length = 100
target-version = "py39"

[tool.ruff.lint]
select = ["E", "F", "W", "I", "B", "UP"]
ignore = ["E501"]

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
addopts = "-ra --strict-markers"