-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathpyproject.toml
168 lines (148 loc) · 3.73 KB
/
pyproject.toml
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
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
[build-system]
requires = ["setuptools >= 61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llm-datasets"
version = "0.0.3"
authors = [{ name = "Malte Ostendorff", email = "[email protected]" }]
description = "A collection of datasets for language model training including scripts for downloading, preprocesssing, and sampling."
readme = "README.md"
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"License :: OSI Approved :: Apache Software License",
"Programming Language :: Python :: 3 :: Only",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
]
requires-python = ">=3.9"
dependencies = [
"requests",
"pandas",
"datasets",
"smart-open",
"wget",
"zstandard",
"polars",
"pyarrow>=14.0.1",
"dill",
]
license = { text = "Apache 2.0" }
[project.scripts]
llm-datasets = "llm_datasets.__main__:main"
[project.optional-dependencies]
datasets = [
"wget==3.2",
"mwparserfromhell>=0.6.4",
"gensim>=4.3.0",
"zstandard>=0.20.0",
"treelib>=1.6.4",
"conllu>=4.5.3",
"prevert>=1.0.2",
"translate-toolkit>=3.9.1",
"folia>=2.5.8",
"estnltk>=1.7.1",
"Jinja2",
]
dev = [
"pre-commit",
"black",
"flake8",
"flake8-pyproject",
"pytest",
"pytest-cov",
"pytest-runner",
"pytest-xdist",
"coverage",
"pylint",
"twine",
"jupyter",
"ruff>=0.0.254",
]
docs = [
"mkdocs",
"mkdocs-material",
"mkdocs-exclude",
"mkdocstrings",
"mkdocstrings[python]",
]
viewer = ["streamlit", "ngrok"]
datatrove = ["datatrove[all]>=0.2.0"]
all = [
"llm-datasets[datasets]",
"llm-datasets[dev]",
"llm-datasets[docs]",
"llm-datasets[viewer]",
"llm-datasets[datatrove]",
]
[project.urls]
Documentation = "https://github.com/malteos/llm-datasets/tree/main#readme"
Source = "https://github.com/malteos/llm-datasets"
Tracker = "https://github.com/malteos/llm-datasets/issues"
[tool.coverage.run]
branch = true
[tool.coverage.report]
fail_under = 100
[tool.flake8]
max-line-length = 120
select = "F,E,W,B,B901,B902,B903"
exclude = [
".eggs",
".git",
".tox",
".github",
".vscode",
"nssm",
"obj",
"out",
"packages",
"pywin32",
"tests",
"swagger_client",
"dist",
"images",
"docs",
]
ignore = ["E722", "B001", "W503", "E203"]
reportMissingImports = true
reportMissingTypeStubs = false
pythonVersion = "3.10"
pythonPlatform = "Linux"
executionEnvironments = [{ root = "src" }]
[tool.pytest.ini_options]
pythonpath = ["src"]
testpaths = "tests"
[tool.ruff]
target-version = "py310"
line-length = 120
[tool.ruff.lint]
select = ["F", "I", "E", "D"]
ignore = [
"E501", # line too long
"E741", # ambiguous variable name
"F403", # undefined import
"D100", # Missing docstring in public module
"D101", # Missing docstring in public class
"D102", # Missing docstring in public method
"D103", # Missing docstring in public function
"D105", # Missing docstring in magic method
"D104", # Missing docstring in public package
"D107", # Missing docstring in __init__
"D205", # 1 blank line required between summary line and description
"D415", # First line should end with a period
]
[tool.ruff.lint.pydocstyle]
convention = "google"
[tool.ruff.lint.flake8-annotations]
mypy-init-return = true
suppress-none-returning = true
[tool.semantic_release]
branch = "main"
version_toml = ["pyproject.toml:project.version"]
build_command = "python -m pip install build; python -m build"
tag_format = "{version}"
[tool.semantic_release.commit_parser_options]
major_types = ["breaking"]
minor_types = ["feat"]
patch_types = ["fix", "perf"]