forked from techwolf-ai/workrb
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpyproject.toml
More file actions
210 lines (182 loc) · 5 KB
/
pyproject.toml
File metadata and controls
210 lines (182 loc) · 5 KB
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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
[build-system] # https://docs.astral.sh/uv/concepts/projects/config/#build-systems
requires = ["hatchling>=1.27.0"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["src/workrb"]
[project]
name = "workrb"
version = "0.3.0"
description = "WorkRB: Work Research Benchmark. Easy benchmarking of AI progress in the work domain."
readme = "README.md"
requires-python = ">=3.10,<4.0"
license = { text = "Apache 2.0" }
authors = [
{ name = "TechWolf Research Team" },
{ name = "Matthias De Lange", email = "matthias.delange@techwolf.ai" },
]
keywords = [
"nlp",
"benchmarking",
"skills",
"jobs",
"evaluation",
"machine-learning",
]
classifiers = [
"Intended Audience :: Science/Research",
"Intended Audience :: Developers",
"License :: OSI Approved :: Apache Software License",
"Programming Language :: Python :: 3",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Text Processing :: Linguistic",
"Operating System :: OS Independent",
]
dependencies = [
"torch>=2.6.0",
"pandas>=2.0.0",
"numpy>=1.24.0",
"scikit-learn>=1.6.1",
"tqdm>=4.65.0",
"datasets>=2.18.0",
"requests>=2.31.0",
"appdirs>=1.4.4",
"PyYAML>=6.0",
"sentence-transformers>=5.1.0",
"pydantic>=2.11.9",
"rank-bm25>=0.2.2",
"rapidfuzz>=3.9.4",
]
[dependency-groups] # https://docs.astral.sh/uv/concepts/projects/dependencies/#development-dependencies
example = []
dev = [
"commitizen (>=4.3.0)",
"coverage[toml] (>=7.6.10)",
"ipykernel (>=6.29.4)",
"ipython (>=8.18.0)",
"ipywidgets (>=8.1.2)",
"pdoc (>=15.0.1)",
"poethepoet (>=0.32.1)",
"pre-commit (>=4.0.1)",
"pytest (>=8.3.4)",
"pytest-mock (>=3.14.0)",
"pytest-xdist (>=3.6.1)",
"ruff (>=0.9.2)",
"jupyter>=1.0.0",
]
[project.urls]
Homepage = "https://github.com/techwolf-ai/workrb"
Documentation = "https://github.com/techwolf-ai/workrb#readme"
Repository = "https://github.com/techwolf-ai/workrb.git"
Issues = "https://github.com/techwolf-ai/workrb/issues"
[tool.commitizen] # https://commitizen-tools.github.io/commitizen/config/
bump_message = "bump: v$current_version → v$new_version"
tag_format = "v$version"
update_changelog_on_bump = true
version_provider = "uv"
[tool.coverage.report] # https://coverage.readthedocs.io/en/latest/config.html#report
precision = 1
show_missing = true
skip_covered = true
[tool.coverage.run] # https://coverage.readthedocs.io/en/latest/config.html#run
branch = true
command_line = "--module pytest -m 'not model_performance'"
data_file = "reports/.coverage"
source = ["src"]
[tool.coverage.xml] # https://coverage.readthedocs.io/en/latest/config.html#xml
output = "reports/coverage.xml"
[tool.pytest.ini_options] # https://docs.pytest.org/en/latest/reference/reference.html#ini-options-ref
addopts = "--color=yes --doctest-modules --exitfirst --failed-first --verbosity=2 --junitxml=reports/pytest.xml"
testpaths = ["src", "tests"]
xfail_strict = true
markers = [
"model_performance: marks tests that run heavy model benchmark evaluation (excluded by default, use poe test-benchmark)",
]
[tool.ruff] # https://docs.astral.sh/ruff/settings/
fix = true
line-length = 100
src = ["src", "tests"]
target-version = "py310"
[tool.ruff.format]
docstring-code-format = true
[tool.ruff.lint]
select = [
"A",
"ASYNC",
"B",
"C4",
"C90",
"D",
"DTZ",
"E",
"F",
"FLY",
"FURB",
"I",
"ISC",
"LOG",
"N",
"NPY",
"PERF",
"PGH",
"PIE",
"PL",
"PT",
"Q",
"RET",
"RUF",
"RSE",
"SIM",
"TID",
"UP",
"W",
"YTT",
]
ignore = ["D203", "D213", "E501", "PGH002", "PGH003", "RET504", "S101", "S307"]
unfixable = ["F401", "F841"]
[tool.ruff.lint.flake8-tidy-imports]
ban-relative-imports = "all"
[tool.ruff.lint.pycodestyle]
max-doc-length = 100
[tool.ruff.lint.pydocstyle]
convention = "numpy"
[tool.ruff.lint.isort]
known-first-party = ["src"]
[tool.poe.executor] # https://github.com/nat-n/poethepoet
type = "simple"
[tool.poe.tasks]
[tool.poe.tasks.docs]
help = "Generate this package's docs"
cmd = """
pdoc
--docformat $docformat
--output-directory $outputdirectory
workrb
"""
[[tool.poe.tasks.docs.args]]
help = "The docstring style (default: numpy)"
name = "docformat"
options = ["--docformat"]
default = "numpy"
[[tool.poe.tasks.docs.args]]
help = "The output directory (default: docs)"
name = "outputdirectory"
options = ["--output-directory"]
default = "docs"
[tool.poe.tasks.lint]
help = "Lint this package"
cmd = """
pre-commit run
--all-files
--color always
"""
[tool.poe.tasks.test]
help = "Test this package (excludes model_performance benchmarks by default)"
[[tool.poe.tasks.test.sequence]]
cmd = "coverage run"
[[tool.poe.tasks.test.sequence]]
cmd = "coverage report"
[[tool.poe.tasks.test.sequence]]
cmd = "coverage xml"
[tool.poe.tasks.test-benchmark]
help = "Run model benchmark tests only (model_performance marked tests)"
cmd = "pytest -m 'model_performance' -v"