Repository navigation
Expand file tree
/
Copy pathpyproject.toml
More file actions
279 lines (251 loc) · 6.86 KB
/
Copy pathpyproject.toml
File metadata and controls
279 lines (251 loc) · 6.86 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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
[tool.ruff]
exclude = [
"*/target/*",
"**/*.ipynb",
"docs/.local_ruby_bundle/",
"*python/pyspark/cloudpickle/*.py",
"*python/pyspark/ml/deepspeed/tests/*.py",
"*python/docs/build/*",
"*python/docs/source/conf.py",
"*python/.eggs/*",
"dist/*",
".git/*",
"*python/pyspark/sql/pandas/functions.pyi",
"*python/pyspark/sql/column.pyi",
"*python/pyspark/worker.pyi",
"*python/pyspark/java_gateway.pyi",
"*python/pyspark/sql/connect/proto/*",
"*python/pyspark/sql/streaming/proto/*",
"*venv*/*",
]
line-length = 100
[tool.ruff.lint]
extend-select = [
"G010", # logging-warn
# ambiguous unicode character
"RUF001", # string
"RUF002", # docstring
"RUF003", # comment
# ambiguous unicode character end
"RUF100", # unused-noqa
]
ignore = [
"E402", # Module top level import is disabled for optional import check, etc.
"E741", # Ambiguous variables like l, I or O.
]
[tool.ruff.lint.per-file-ignores]
# E501 is ignored as shared.py is auto-generated.
"python/pyspark/ml/param/shared.py" = ["E501"]
# E501 is ignored as we should keep the json string format in error_classes.py.
"python/pyspark/errors/error_classes.py" = ["E501"]
# Examples contain some unused variables.
"examples/src/main/python/sql/datasource.py" = ["F841"]
# DataFrame golden test scripts are executed by the framework with ``spark``
# injected into their namespace, so it is undefined at lint time.
"python/pyspark/sql/tests/df_golden/scripts/**/*.py" = ["F821"]
[dependency-groups]
_py4j = ["py4j>=0.10.9.9"]
_numpy = ["numpy>=1.23.2"]
_pandas = ["pandas>=2.2.0,<3.0.0"]
_protobuf = ["protobuf==6.33.5"]
_pyarrow = ["pyarrow>=18.0.0"]
_pyspark_devtool = [
# Optional tools that are used by pyspark directly.
"memory-profiler>=0.61.0",
"flameprof==0.4",
"psutil",
"pystack>=1.6.0; sys_platform=='linux'",
]
connect = [
{include-group = "_py4j"},
{include-group = "_pandas"},
{include-group = "_protobuf"},
{include-group = "_pyarrow"},
"grpcio>=1.76.0",
"grpcio-status>=1.76.0",
"googleapis-common-protos>=1.71.0",
"zstandard>=0.25.0",
"graphviz>=0.20",
]
sql = [
{include-group = "_py4j"},
{include-group = "_pandas"},
{include-group = "_pyarrow"},
]
pandas_on_spark = [
{include-group = "_py4j"},
{include-group = "_pandas"},
{include-group = "_pyarrow"},
]
pandas_on_spark_extra = [
"plotly<6.0.0",
"matplotlib",
"mlflow>=2.3.1",
"jinja2",
]
ml = [
{include-group = "_py4j"},
{include-group = "_numpy"},
]
mllib = [
{include-group = "_py4j"},
{include-group = "_numpy"},
]
ml_extra_base = [
"scipy>=1.8.0",
"scikit-learn",
"torcheval",
"deepspeed; sys_platform != 'darwin'",
]
ml_torch = [
# We often need to install torch related packages from index-url like
# https://download.pytorch.org/whl/cpu. This group is designed for that and
# it should only have packages that are available from that index-url.
"torch",
"torchvision",
]
ml_extra = [
{include-group = "ml_extra_base"},
{include-group = "ml_torch"},
]
pipelines = [
{include-group = "connect"},
"pyyaml>=3.11",
]
_lint = [
"ruff==0.14.8",
"mypy==1.19.1",
"pytest",
"pytest-mypy-plugins==3.2.0",
"mypy-protobuf==3.3.0",
"googleapis-common-protos-stubs==2.2.0",
"grpc-stubs==1.24.11",
"pandas-stubs>=2.2.0",
"scipy-stubs",
"types-protobuf==6.32.1.20260221",
"types-PyYAML"
]
_test = [
# Dependency for running tests
"unittest-xml-reporting",
# Coverage tool
"coverage",
# 3rd party libraries that unittests use.
"openpyxl",
"tabulate",
"lxml",
"testcontainers[kafka]>=3.7.0",
"kafka-python-ng>=2.0.2",
]
_docs = [
"sphinx==8.2.3",
"sphinx-plotly-directive",
"sphinx-copybutton",
"docutils",
"markupsafe",
"pydata_sphinx_theme>=0.13",
"ipython",
"nbsphinx",
"numpydoc",
"mkdocs",
]
_devtools = [
# Devtools that are used by pyspark developers.
"debugpy",
"viztracer",
"jira>=3.5.2",
"PyGithub",
"asv",
]
dev = [
{include-group = "_pyspark_devtool"},
{include-group = "_lint"},
{include-group = "_test"},
{include-group = "_docs"},
{include-group = "_devtools"},
{include-group = "sql"},
{include-group = "connect"},
{include-group = "ml"},
{include-group = "ml_extra"},
{include-group = "mllib"},
{include-group = "pandas_on_spark"},
{include-group = "pandas_on_spark_extra"},
{include-group = "pipelines"},
]
_ci_connect = [
{include-group = "connect"},
"grpcio==1.76.0",
"grpcio-status==1.76.0",
"googleapis-common-protos==1.71.0",
"zstandard==0.25.0",
"protobuf==6.33.5",
]
ci_connect_standard = [
{include-group = "_ci_connect"},
"graphviz==0.20.3",
]
ci_connect_minimum = [
{include-group = "_ci_connect"},
"graphviz==0.20",
]
ci_classic_standard = [
{include-group = "_pyspark_devtool"},
{include-group = "sql"},
{include-group = "pandas_on_spark"},
{include-group = "pandas_on_spark_extra"},
{include-group = "ml"},
# torch should be installed with ml_torch group
{include-group = "ml_extra_base"},
{include-group = "_test"},
"pyarrow>=23.0.0",
"pandas==2.3.3",
]
ci_classic_minimum = [
{include-group = "sql"},
{include-group = "pandas_on_spark"},
{include-group = "ml"},
"numpy==1.23.2",
"pyarrow==18.0.0",
"pandas==2.2.0",
"scipy",
"scikit-learn",
"unittest-xml-reporting",
# Debug tools
"psutil",
]
ci_lint = [
{include-group = "_lint"},
{include-group = "ml_extra_base"},
{include-group = "pandas_on_spark_extra"},
{include-group = "_ci_connect"},
"pyarrow>=23.0.0",
"pandas==2.3.3",
"pandas-stubs==2.3.3.260113",
"ipython"
]
ci_docs = [
{include-group = "_docs"},
{include-group = "_ci_connect"},
{include-group = "_numpy"},
# These are required for sphinx to introspect the code
"pyarrow>=23.0.0",
"pandas==2.3.3",
# plotly is used for sphinx_plotly_directive examples
"plotly>=4.8"
]