forked from kedro-org/kedro
-
Notifications
You must be signed in to change notification settings - Fork 0
/
setup.py
186 lines (168 loc) · 6.54 KB
/
setup.py
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
import re
from codecs import open
from glob import glob
from itertools import chain
from os import path
from setuptools import find_packages, setup
name = "kedro"
here = path.abspath(path.dirname(__file__))
# at least 1.3 to be able to use XMLDataSet and pandas integration with fsspec
PANDAS = "pandas~=1.3"
SPARK = "pyspark>=2.2, <4.0"
HDFS = "hdfs>=2.5.8, <3.0"
S3FS = "s3fs>=0.3.0, <0.5"
# get package version
with open(path.join(here, name, "__init__.py"), encoding="utf-8") as f:
result = re.search(r'__version__ = ["\']([^"\']+)', f.read())
if not result:
raise ValueError("Can't find the version in kedro/__init__.py")
version = result.group(1)
# get the dependencies and installs
with open("dependency/requirements.txt", encoding="utf-8") as f:
requires = [x.strip() for x in f if x.strip()]
# get test dependencies and installs
with open("test_requirements.txt", encoding="utf-8") as f:
test_requires = [x.strip() for x in f if x.strip() and not x.startswith("-r")]
# Get the long description from the README file
with open(path.join(here, "README.md"), encoding="utf-8") as f:
readme = f.read()
template_files = []
for pattern in ["**/*", "**/.*", "**/.*/**", "**/.*/.**"]:
template_files.extend(
[
name.replace("kedro/", "", 1)
for name in glob("kedro/templates/" + pattern, recursive=True)
]
)
def _collect_requirements(requires):
return sorted(set(chain.from_iterable(requires.values())))
api_require = {"api.APIDataSet": ["requests~=2.20"]}
biosequence_require = {"biosequence.BioSequenceDataSet": ["biopython~=1.73"]}
dask_require = {"dask.ParquetDataSet": ["dask[complete]~=2021.10", "triad>=0.6.7, <1.0"]}
geopandas_require = {
"geopandas.GeoJSONDataSet": ["geopandas>=0.6.0, <1.0", "pyproj~=3.0"]
}
matplotlib_require = {"matplotlib.MatplotlibWriter": ["matplotlib>=3.0.3, <4.0"]}
holoviews_require = {"holoviews.HoloviewsWriter": ["holoviews~=1.13.0"]}
networkx_require = {"networkx.NetworkXDataSet": ["networkx~=2.4"]}
pandas_require = {
"pandas.CSVDataSet": [PANDAS],
"pandas.ExcelDataSet": [PANDAS, "openpyxl>=3.0.6, <4.0"],
"pandas.FeatherDataSet": [PANDAS],
"pandas.GBQTableDataSet": [PANDAS, "pandas-gbq>=0.12.0, <0.18.0"],
"pandas.GBQQueryDataSet": [PANDAS, "pandas-gbq>=0.12.0, <0.18.0"],
"pandas.HDFDataSet": [
PANDAS,
"tables~=3.6.0; platform_system == 'Windows'",
"tables~=3.6; platform_system != 'Windows'",
],
"pandas.JSONDataSet": [PANDAS],
"pandas.ParquetDataSet": [PANDAS, "pyarrow>=1.0, <7.0"],
"pandas.SQLTableDataSet": [PANDAS, "SQLAlchemy~=1.2"],
"pandas.SQLQueryDataSet": [PANDAS, "SQLAlchemy~=1.2"],
"pandas.XMLDataSet": [PANDAS, "lxml~=4.6"],
"pandas.GenericDataSet": [PANDAS],
}
pickle_require = {"pickle.PickleDataSet": ["compress-pickle[lz4]~=2.1.0"]}
pillow_require = {"pillow.ImageDataSet": ["Pillow~=9.0"]}
video_require = {
"video.VideoDataSet": ["opencv-python~=4.5.5.64"]
}
plotly_require = {
"plotly.PlotlyDataSet": [PANDAS, "plotly>=4.8.0, <6.0"],
"plotly.JSONDataSet": ["plotly>=4.8.0, <6.0"],
}
redis_require = {"redis.PickleDataSet": ["redis~=4.1"]}
spark_require = {
"spark.SparkDataSet": [SPARK, HDFS, S3FS],
"spark.SparkHiveDataSet": [SPARK, HDFS, S3FS],
"spark.SparkJDBCDataSet": [SPARK, HDFS, S3FS],
"spark.DeltaTableDataSet": [SPARK, HDFS, S3FS, "delta-spark>=1.0, <3.0"],
}
svmlight_require = {"svmlight.SVMLightDataSet": ["scikit-learn~=1.0.2", "scipy~=1.7.3"]}
tensorflow_required = {
"tensorflow.TensorflowModelDataset": [
# currently only TensorFlow V2 supported for saving and loading.
# V1 requires HDF5 and serialises differently
"tensorflow~=2.0"
]
}
yaml_require = {"yaml.YAMLDataSet": [PANDAS, "PyYAML>=4.2, <7.0"]}
extras_require = {
"api": _collect_requirements(api_require),
"biosequence": _collect_requirements(biosequence_require),
"dask": _collect_requirements(dask_require),
"docs": [
"docutils==0.16",
"sphinx~=3.4.3",
"sphinx_rtd_theme==1.1.1",
"nbsphinx==0.8.1",
"nbstripout~=0.4",
"sphinx-autodoc-typehints==1.11.1",
"sphinx_copybutton==0.3.1",
"ipykernel>=5.3, <7.0",
"sphinxcontrib-mermaid~=0.7.1",
"myst-parser~=0.17.2",
"Jinja2<3.1.0",
],
"geopandas": _collect_requirements(geopandas_require),
"matplotlib": _collect_requirements(matplotlib_require),
"holoviews": _collect_requirements(holoviews_require),
"networkx": _collect_requirements(networkx_require),
"pandas": _collect_requirements(pandas_require),
"pickle": _collect_requirements(pickle_require),
"pillow": _collect_requirements(pillow_require),
"video": _collect_requirements(video_require),
"plotly": _collect_requirements(plotly_require),
"redis": _collect_requirements(redis_require),
"spark": _collect_requirements(spark_require),
"svmlight": _collect_requirements(svmlight_require),
"tensorflow": _collect_requirements(tensorflow_required),
"yaml": _collect_requirements(yaml_require),
**api_require,
**biosequence_require,
**dask_require,
**geopandas_require,
**matplotlib_require,
**holoviews_require,
**networkx_require,
**pandas_require,
**pickle_require,
**pillow_require,
**video_require,
**plotly_require,
**spark_require,
**svmlight_require,
**tensorflow_required,
**yaml_require,
}
extras_require["all"] = _collect_requirements(extras_require)
setup(
name=name,
version=version,
description="Kedro helps you build production-ready data and analytics pipelines",
license="Apache Software License (Apache 2.0)",
long_description=readme,
long_description_content_type="text/markdown",
url="https://github.com/kedro-org/kedro",
python_requires=">=3.7, <3.11",
packages=find_packages(exclude=["docs*", "tests*", "tools*", "features*"]),
include_package_data=True,
tests_require=test_requires,
install_requires=requires,
author="Kedro",
entry_points={"console_scripts": ["kedro = kedro.framework.cli:main"]},
package_data={
name: ["py.typed", "test_requirements.txt"] + template_files
},
zip_safe=False,
keywords="pipelines, machine learning, data pipelines, data science, data engineering",
classifiers=[
"Development Status :: 4 - Beta",
"Programming Language :: Python :: 3.7",
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
],
extras_require=extras_require,
)