DataSciBench/pyproject.toml at main · deeppavlov/DataSciBench · 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
[project]
name = "datascibench"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.12,<3.13"
dependencies = [
    "aiofiles>=25.1.0,<26.0.0",
    "aiohttp>=3.13.5,<4.0.0",
    "beautifulsoup4>=4.14.3,<5.0.0",
    "catboost>=1.2.10,<2.0.0",
    "chardet>=7.4.0.post2,<8.0.0",
    "gitignore-parser>=0.1.13,<0.2.0",
    "gitpython>=3.1.46,<4.0.0",
    "google-genai>=1.70.0,<2.0.0",
    "gymnasium>=1.2.3,<2.0.0",
    "h5py>=3.16.0,<4.0.0",
    "httpx>=0.28.1,<0.29.0",
    "imbalanced-learn>=0.14.1,<0.15.0",
    "ipykernel>=7.2.0,<8.0.0",
    "ipython>=9.12.0,<10.0.0",
    "jellyfish>=1.2.1,<2.0.0",
    "joblib>=1.5.3,<2.0.0",
    "kaleido>=1.2.0,<2.0.0",
    "keras>=3.13.2,<4.0.0",
    "lightgbm>=4.6.0,<5.0.0",
    "loguru>=0.7.3,<0.8.0",
    "lxml>=6.0.2,<7.0.0",
    "matplotlib>=3.10.8,<4.0.0",
    "mcp>=1.26.0,<2.0.0",
    "mlxtend>=0.24.0,<0.25.0",
    "nbclient>=0.10.4,<0.11.0",
    "nbformat>=5.10.4,<6.0.0",
    "networkx>=3.6.1,<4.0.0",
    "nltk>=3.9.4,<4.0.0",
    "numpy>=2.4.4,<3.0.0",
    "openai>=1.109.1,<2.0.0",
    "openpyxl>=3.1.5,<4.0.0",
    "pandas>=3.0.2,<4.0.0",
    "pillow>=12.2.0,<13.0.0",
    "pydantic>=2.12.5,<3.0.0",
    "pydantic-ai>=1.30.1,<2.0.0",
    "pydantic-core>=2.41.5,<3.0.0",
    "pydantic-settings>=2.13.1,<3.0.0",
    "pytest>=9.0.2,<10.0.0",
    "python-dateutil>=2.9.0.post0,<3.0.0",
    "python-levenshtein>=0.27.3,<0.28.0",
    "pytz>=2026.1.post1,<2027.0",
    "pyyaml>=6.0.3,<7.0.0",
    "rank-bm25>=0.2.2,<0.3.0",
    "regex>=2026.3.32,<2027.0.0",
    "reportlab>=4.4.10,<5.0.0",
    "requests>=2.33.1,<3.0.0",
    "rich>=14.3.3,<15.0.0",
    "ruff>=0.15.8,<0.16.0",
    "scikit-learn>=1.8.0,<2.0.0",
    "scipy>=1.17.1,<2.0.0",
    "seaborn>=0.13.2,<0.14.0",
    "semantic-kernel>=1.15.0,<2.0.0",
    "spacy>=3.8.14,<4.0.0",
    "statsmodels>=0.14.6,<0.15.0",
    "tenacity>=9.1.4,<10.0.0",
    "tensorflow>=2.20.0,<3.0.0",
    "tiktoken>=0.12.0,<0.13.0",
    "torch>=2.11.0,<3.0.0",
    "tqdm>=4.67.3,<5.0.0",
    "typing-extensions>=4.15.0,<5.0.0",
    "xgboost>=3.2.0,<4.0.0",
    "xlrd>=2.0.2,<3.0.0",
]

[tool.ruff]
line-length = 120
indent-width = 4
target-version = "py312"
exclude = [
    "metagpt",
]

[tool.ruff.lint]
select = [
    "E",   # pycodestyle errors
    "F",   # Pyflakes
    "UP",  # pyupgrade
    "B",   # flake8-bugbear
    "SIM", # flake8-simplify
    "I",   # isort
]
ignore = [
    "COM812", # missing-trailing-comma (can conflict with formatter)
    "E501",   # line-too-long (too many in generated files)
    "B024",   # abstract class without abstract method
    "B027",   # empty method in abstract class
    "B007",   # unused loop control variable
    "SIM115", # use context handler for opening files
    "SIM117", # multiple with statements
    "SIM113", # enumerate for loop
    "E741",   # ambiguous variable name
]

[tool.ruff.lint.pylint]
max-args = 10

[tool.ruff.lint.pydocstyle]
convention = "google"

[tool.ruff.lint.per-file-ignores]
"tests/*.py" = ["S", "PLR2004", "ERA", "D", "ANN", "SLF"]
"**/*.ipynb" = ["E402", "E722"]
"experiments/*.py" = ["F403", "F405"]
"evaluations/*.py" = ["F403", "F405"]
"src/schemas/__init__.py" = ["F401"]
"src/evaluator/__init__.py" = ["F401"]
"role/__init__.py" = ["F401"]
"data/**/gt/*.py" = ["E402"]