utilsds 0.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- utilsds-0.1/PKG-INFO +181 -0
- utilsds-0.1/README.md +3 -0
- utilsds-0.1/setup.cfg +4 -0
- utilsds-0.1/setup.py +186 -0
- utilsds-0.1/utilsds/__init__.py +0 -0
- utilsds-0.1/utilsds/ds_statistics.py +35 -0
- utilsds-0.1/utilsds/modeling.py +416 -0
- utilsds-0.1/utilsds/train_val_test_split.py +83 -0
- utilsds-0.1/utilsds/transform_data.py +147 -0
- utilsds-0.1/utilsds/visualization.py +374 -0
- utilsds-0.1/utilsds.egg-info/PKG-INFO +181 -0
- utilsds-0.1/utilsds.egg-info/SOURCES.txt +13 -0
- utilsds-0.1/utilsds.egg-info/dependency_links.txt +1 -0
- utilsds-0.1/utilsds.egg-info/requires.txt +166 -0
- utilsds-0.1/utilsds.egg-info/top_level.txt +1 -0
utilsds-0.1/PKG-INFO
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
1
|
+
Metadata-Version: 2.1
|
|
2
|
+
Name: utilsds
|
|
3
|
+
Version: 0.1
|
|
4
|
+
Summary: Solution for DS Team
|
|
5
|
+
Author: DS Team
|
|
6
|
+
Author-email: ds@sts.pl
|
|
7
|
+
Classifier: Programming Language :: Python :: 3
|
|
8
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
9
|
+
Classifier: Operating System :: OS Independent
|
|
10
|
+
Requires-Python: >=3.11
|
|
11
|
+
Description-Content-Type: text/markdown
|
|
12
|
+
Requires-Dist: aiohttp==3.9.5
|
|
13
|
+
Requires-Dist: aiohttp-retry==2.8.3
|
|
14
|
+
Requires-Dist: aiosignal==1.3.1
|
|
15
|
+
Requires-Dist: amqp==5.2.0
|
|
16
|
+
Requires-Dist: annotated-types==0.6.0
|
|
17
|
+
Requires-Dist: antlr4-python3-runtime==4.9.3
|
|
18
|
+
Requires-Dist: appdirs==1.4.4
|
|
19
|
+
Requires-Dist: appnope==0.1.4
|
|
20
|
+
Requires-Dist: asttokens==2.4.1
|
|
21
|
+
Requires-Dist: asyncssh==2.14.2
|
|
22
|
+
Requires-Dist: atpublic==4.1.0
|
|
23
|
+
Requires-Dist: attrs==23.2.0
|
|
24
|
+
Requires-Dist: billiard==4.2.0
|
|
25
|
+
Requires-Dist: boto==2.49.0
|
|
26
|
+
Requires-Dist: cachetools==5.3.3
|
|
27
|
+
Requires-Dist: celery==5.4.0
|
|
28
|
+
Requires-Dist: certifi==2024.2.2
|
|
29
|
+
Requires-Dist: cffi==1.16.0
|
|
30
|
+
Requires-Dist: charset-normalizer==3.3.2
|
|
31
|
+
Requires-Dist: click==8.1.7
|
|
32
|
+
Requires-Dist: click-didyoumean==0.3.1
|
|
33
|
+
Requires-Dist: click-plugins==1.1.1
|
|
34
|
+
Requires-Dist: click-repl==0.3.0
|
|
35
|
+
Requires-Dist: cloudpickle==3.0.0
|
|
36
|
+
Requires-Dist: colorama==0.4.6
|
|
37
|
+
Requires-Dist: comm==0.2.2
|
|
38
|
+
Requires-Dist: configobj==5.0.8
|
|
39
|
+
Requires-Dist: contourpy==1.2.1
|
|
40
|
+
Requires-Dist: cryptography==42.0.7
|
|
41
|
+
Requires-Dist: cycler==0.12.1
|
|
42
|
+
Requires-Dist: db-dtypes==1.2.0
|
|
43
|
+
Requires-Dist: debugpy==1.8.1
|
|
44
|
+
Requires-Dist: decorator==5.1.1
|
|
45
|
+
Requires-Dist: dictdiffer==0.9.0
|
|
46
|
+
Requires-Dist: diskcache==5.6.3
|
|
47
|
+
Requires-Dist: distro==1.9.0
|
|
48
|
+
Requires-Dist: docstring_parser==0.16
|
|
49
|
+
Requires-Dist: dpath==2.1.6
|
|
50
|
+
Requires-Dist: ds_utils==0.4.1
|
|
51
|
+
Requires-Dist: dulwich==0.22.1
|
|
52
|
+
Requires-Dist: dvc==3.50.2
|
|
53
|
+
Requires-Dist: dvc-data==3.15.1
|
|
54
|
+
Requires-Dist: dvc-gs==3.0.1
|
|
55
|
+
Requires-Dist: dvc-http==2.32.0
|
|
56
|
+
Requires-Dist: dvc-objects==5.1.0
|
|
57
|
+
Requires-Dist: dvc-render==1.0.2
|
|
58
|
+
Requires-Dist: dvc-studio-client==0.20.0
|
|
59
|
+
Requires-Dist: dvc-task==0.4.0
|
|
60
|
+
Requires-Dist: entrypoints==0.4
|
|
61
|
+
Requires-Dist: executing==2.0.1
|
|
62
|
+
Requires-Dist: filelock==3.14.0
|
|
63
|
+
Requires-Dist: flatten-dict==0.4.2
|
|
64
|
+
Requires-Dist: flufl.lock==7.1.1
|
|
65
|
+
Requires-Dist: fonttools==4.51.0
|
|
66
|
+
Requires-Dist: frozenlist==1.4.1
|
|
67
|
+
Requires-Dist: fsspec==2024.5.0
|
|
68
|
+
Requires-Dist: funcy==2.0
|
|
69
|
+
Requires-Dist: future==1.0.0
|
|
70
|
+
Requires-Dist: gcsfs==2024.5.0
|
|
71
|
+
Requires-Dist: gitdb==4.0.11
|
|
72
|
+
Requires-Dist: GitPython==3.1.43
|
|
73
|
+
Requires-Dist: google-api-core==2.19.0
|
|
74
|
+
Requires-Dist: google-auth==2.29.0
|
|
75
|
+
Requires-Dist: google-auth-oauthlib==1.2.0
|
|
76
|
+
Requires-Dist: google-cloud-aiplatform==1.51.0
|
|
77
|
+
Requires-Dist: google-cloud-bigquery==3.22.0
|
|
78
|
+
Requires-Dist: google-cloud-core==2.4.1
|
|
79
|
+
Requires-Dist: google-cloud-resource-manager==1.12.3
|
|
80
|
+
Requires-Dist: google-cloud-storage==2.16.0
|
|
81
|
+
Requires-Dist: google-crc32c==1.5.0
|
|
82
|
+
Requires-Dist: google-resumable-media==2.7.0
|
|
83
|
+
Requires-Dist: googleapis-common-protos==1.63.0
|
|
84
|
+
Requires-Dist: grandalf==0.8
|
|
85
|
+
Requires-Dist: grpc-google-iam-v1==0.13.0
|
|
86
|
+
Requires-Dist: grpcio==1.63.0
|
|
87
|
+
Requires-Dist: grpcio-status==1.62.2
|
|
88
|
+
Requires-Dist: gto==1.7.1
|
|
89
|
+
Requires-Dist: hydra-core==1.3.2
|
|
90
|
+
Requires-Dist: hyperopt==0.2.7
|
|
91
|
+
Requires-Dist: idna==3.7
|
|
92
|
+
Requires-Dist: imbalanced-learn==0.12.2
|
|
93
|
+
Requires-Dist: ipykernel==6.29.4
|
|
94
|
+
Requires-Dist: ipython==8.24.0
|
|
95
|
+
Requires-Dist: iterative-telemetry==0.0.8
|
|
96
|
+
Requires-Dist: jedi==0.19.1
|
|
97
|
+
Requires-Dist: joblib==1.4.2
|
|
98
|
+
Requires-Dist: jupyter_client==8.6.1
|
|
99
|
+
Requires-Dist: jupyter_core==5.7.2
|
|
100
|
+
Requires-Dist: kiwisolver==1.4.5
|
|
101
|
+
Requires-Dist: kombu==5.3.7
|
|
102
|
+
Requires-Dist: markdown-it-py==3.0.0
|
|
103
|
+
Requires-Dist: matplotlib==3.9.0
|
|
104
|
+
Requires-Dist: matplotlib-inline==0.1.7
|
|
105
|
+
Requires-Dist: mdurl==0.1.2
|
|
106
|
+
Requires-Dist: multidict==6.0.5
|
|
107
|
+
Requires-Dist: nest-asyncio==1.6.0
|
|
108
|
+
Requires-Dist: networkx==3.3
|
|
109
|
+
Requires-Dist: numpy==1.26.4
|
|
110
|
+
Requires-Dist: oauthlib==3.2.2
|
|
111
|
+
Requires-Dist: omegaconf==2.3.0
|
|
112
|
+
Requires-Dist: orjson==3.10.3
|
|
113
|
+
Requires-Dist: packaging==24.0
|
|
114
|
+
Requires-Dist: pandas==2.2.2
|
|
115
|
+
Requires-Dist: parso==0.8.4
|
|
116
|
+
Requires-Dist: pathspec==0.12.1
|
|
117
|
+
Requires-Dist: pexpect==4.9.0
|
|
118
|
+
Requires-Dist: phik==0.12.4
|
|
119
|
+
Requires-Dist: pillow==10.3.0
|
|
120
|
+
Requires-Dist: platformdirs==3.11.0
|
|
121
|
+
Requires-Dist: prompt-toolkit==3.0.43
|
|
122
|
+
Requires-Dist: proto-plus==1.23.0
|
|
123
|
+
Requires-Dist: protobuf==4.25.3
|
|
124
|
+
Requires-Dist: psutil==5.9.8
|
|
125
|
+
Requires-Dist: ptyprocess==0.7.0
|
|
126
|
+
Requires-Dist: pure-eval==0.2.2
|
|
127
|
+
Requires-Dist: py4j==0.10.9.7
|
|
128
|
+
Requires-Dist: pyarrow==16.1.0
|
|
129
|
+
Requires-Dist: pyasn1==0.6.0
|
|
130
|
+
Requires-Dist: pyasn1_modules==0.4.0
|
|
131
|
+
Requires-Dist: pycparser==2.22
|
|
132
|
+
Requires-Dist: pydantic==2.7.1
|
|
133
|
+
Requires-Dist: pydantic_core==2.18.2
|
|
134
|
+
Requires-Dist: pydot==2.0.0
|
|
135
|
+
Requires-Dist: pygit2==1.14.1
|
|
136
|
+
Requires-Dist: Pygments==2.18.0
|
|
137
|
+
Requires-Dist: pygtrie==2.5.0
|
|
138
|
+
Requires-Dist: pyparsing==3.1.2
|
|
139
|
+
Requires-Dist: python-dateutil==2.9.0.post0
|
|
140
|
+
Requires-Dist: pytz==2024.1
|
|
141
|
+
Requires-Dist: PyYAML==6.0.1
|
|
142
|
+
Requires-Dist: pyzmq==26.0.3
|
|
143
|
+
Requires-Dist: requests==2.31.0
|
|
144
|
+
Requires-Dist: requests-oauthlib==2.0.0
|
|
145
|
+
Requires-Dist: rich==13.7.1
|
|
146
|
+
Requires-Dist: rsa==4.9
|
|
147
|
+
Requires-Dist: ruamel.yaml==0.18.6
|
|
148
|
+
Requires-Dist: ruamel.yaml.clib==0.2.8
|
|
149
|
+
Requires-Dist: scikit-learn==1.4.2
|
|
150
|
+
Requires-Dist: scipy==1.13.0
|
|
151
|
+
Requires-Dist: scmrepo==3.3.3
|
|
152
|
+
Requires-Dist: seaborn==0.13.2
|
|
153
|
+
Requires-Dist: semver==3.0.2
|
|
154
|
+
Requires-Dist: shapely==2.0.4
|
|
155
|
+
Requires-Dist: shellingham==1.5.4
|
|
156
|
+
Requires-Dist: shortuuid==1.0.13
|
|
157
|
+
Requires-Dist: shtab==1.7.1
|
|
158
|
+
Requires-Dist: six==1.16.0
|
|
159
|
+
Requires-Dist: smmap==5.0.1
|
|
160
|
+
Requires-Dist: sqltrie==0.11.0
|
|
161
|
+
Requires-Dist: stack-data==0.6.3
|
|
162
|
+
Requires-Dist: tabulate==0.9.0
|
|
163
|
+
Requires-Dist: threadpoolctl==3.5.0
|
|
164
|
+
Requires-Dist: tomlkit==0.12.5
|
|
165
|
+
Requires-Dist: tornado==6.4
|
|
166
|
+
Requires-Dist: tqdm==4.66.4
|
|
167
|
+
Requires-Dist: traitlets==5.14.3
|
|
168
|
+
Requires-Dist: typer==0.12.3
|
|
169
|
+
Requires-Dist: typing_extensions==4.11.0
|
|
170
|
+
Requires-Dist: tzdata==2024.1
|
|
171
|
+
Requires-Dist: urllib3==2.2.1
|
|
172
|
+
Requires-Dist: vine==5.1.0
|
|
173
|
+
Requires-Dist: voluptuous==0.14.2
|
|
174
|
+
Requires-Dist: wcwidth==0.2.13
|
|
175
|
+
Requires-Dist: yarl==1.9.4
|
|
176
|
+
Requires-Dist: yellowbrick==1.5
|
|
177
|
+
Requires-Dist: zc.lockfile==3.0.post1
|
|
178
|
+
|
|
179
|
+
# utils
|
|
180
|
+
|
|
181
|
+
Solution includes classes and function used in ds project.
|
utilsds-0.1/README.md
ADDED
utilsds-0.1/setup.cfg
ADDED
utilsds-0.1/setup.py
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
1
|
+
from setuptools import setup, find_packages
|
|
2
|
+
|
|
3
|
+
setup(
|
|
4
|
+
name='utilsds',
|
|
5
|
+
version='0.1',
|
|
6
|
+
packages=find_packages(),
|
|
7
|
+
install_requires=[
|
|
8
|
+
'aiohttp==3.9.5',
|
|
9
|
+
'aiohttp-retry==2.8.3',
|
|
10
|
+
'aiosignal==1.3.1',
|
|
11
|
+
'amqp==5.2.0',
|
|
12
|
+
'annotated-types==0.6.0',
|
|
13
|
+
'antlr4-python3-runtime==4.9.3',
|
|
14
|
+
'appdirs==1.4.4',
|
|
15
|
+
'appnope==0.1.4',
|
|
16
|
+
'asttokens==2.4.1',
|
|
17
|
+
'asyncssh==2.14.2',
|
|
18
|
+
'atpublic==4.1.0',
|
|
19
|
+
'attrs==23.2.0',
|
|
20
|
+
'billiard==4.2.0',
|
|
21
|
+
'boto==2.49.0',
|
|
22
|
+
'cachetools==5.3.3',
|
|
23
|
+
'celery==5.4.0',
|
|
24
|
+
'certifi==2024.2.2',
|
|
25
|
+
'cffi==1.16.0',
|
|
26
|
+
'charset-normalizer==3.3.2',
|
|
27
|
+
'click==8.1.7',
|
|
28
|
+
'click-didyoumean==0.3.1',
|
|
29
|
+
'click-plugins==1.1.1',
|
|
30
|
+
'click-repl==0.3.0',
|
|
31
|
+
'cloudpickle==3.0.0',
|
|
32
|
+
'colorama==0.4.6',
|
|
33
|
+
'comm==0.2.2',
|
|
34
|
+
'configobj==5.0.8',
|
|
35
|
+
'contourpy==1.2.1',
|
|
36
|
+
'cryptography==42.0.7',
|
|
37
|
+
'cycler==0.12.1',
|
|
38
|
+
'db-dtypes==1.2.0',
|
|
39
|
+
'debugpy==1.8.1',
|
|
40
|
+
'decorator==5.1.1',
|
|
41
|
+
'dictdiffer==0.9.0',
|
|
42
|
+
'diskcache==5.6.3',
|
|
43
|
+
'distro==1.9.0',
|
|
44
|
+
'docstring_parser==0.16',
|
|
45
|
+
'dpath==2.1.6',
|
|
46
|
+
'ds_utils==0.4.1',
|
|
47
|
+
'dulwich==0.22.1',
|
|
48
|
+
'dvc==3.50.2',
|
|
49
|
+
'dvc-data==3.15.1',
|
|
50
|
+
'dvc-gs==3.0.1',
|
|
51
|
+
'dvc-http==2.32.0',
|
|
52
|
+
'dvc-objects==5.1.0',
|
|
53
|
+
'dvc-render==1.0.2',
|
|
54
|
+
'dvc-studio-client==0.20.0',
|
|
55
|
+
'dvc-task==0.4.0',
|
|
56
|
+
'entrypoints==0.4',
|
|
57
|
+
'executing==2.0.1',
|
|
58
|
+
'filelock==3.14.0',
|
|
59
|
+
'flatten-dict==0.4.2',
|
|
60
|
+
'flufl.lock==7.1.1',
|
|
61
|
+
'fonttools==4.51.0',
|
|
62
|
+
'frozenlist==1.4.1',
|
|
63
|
+
'fsspec==2024.5.0',
|
|
64
|
+
'funcy==2.0',
|
|
65
|
+
'future==1.0.0',
|
|
66
|
+
'gcsfs==2024.5.0',
|
|
67
|
+
'gitdb==4.0.11',
|
|
68
|
+
'GitPython==3.1.43',
|
|
69
|
+
'google-api-core==2.19.0',
|
|
70
|
+
'google-auth==2.29.0',
|
|
71
|
+
'google-auth-oauthlib==1.2.0',
|
|
72
|
+
'google-cloud-aiplatform==1.51.0',
|
|
73
|
+
'google-cloud-bigquery==3.22.0',
|
|
74
|
+
'google-cloud-core==2.4.1',
|
|
75
|
+
'google-cloud-resource-manager==1.12.3',
|
|
76
|
+
'google-cloud-storage==2.16.0',
|
|
77
|
+
'google-crc32c==1.5.0',
|
|
78
|
+
'google-resumable-media==2.7.0',
|
|
79
|
+
'googleapis-common-protos==1.63.0',
|
|
80
|
+
'grandalf==0.8',
|
|
81
|
+
'grpc-google-iam-v1==0.13.0',
|
|
82
|
+
'grpcio==1.63.0',
|
|
83
|
+
'grpcio-status==1.62.2',
|
|
84
|
+
'gto==1.7.1',
|
|
85
|
+
'hydra-core==1.3.2',
|
|
86
|
+
'hyperopt==0.2.7',
|
|
87
|
+
'idna==3.7',
|
|
88
|
+
'imbalanced-learn==0.12.2',
|
|
89
|
+
'ipykernel==6.29.4',
|
|
90
|
+
'ipython==8.24.0',
|
|
91
|
+
'iterative-telemetry==0.0.8',
|
|
92
|
+
'jedi==0.19.1',
|
|
93
|
+
'joblib==1.4.2',
|
|
94
|
+
'jupyter_client==8.6.1',
|
|
95
|
+
'jupyter_core==5.7.2',
|
|
96
|
+
'kiwisolver==1.4.5',
|
|
97
|
+
'kombu==5.3.7',
|
|
98
|
+
'markdown-it-py==3.0.0',
|
|
99
|
+
'matplotlib==3.9.0',
|
|
100
|
+
'matplotlib-inline==0.1.7',
|
|
101
|
+
'mdurl==0.1.2',
|
|
102
|
+
'multidict==6.0.5',
|
|
103
|
+
'nest-asyncio==1.6.0',
|
|
104
|
+
'networkx==3.3',
|
|
105
|
+
'numpy==1.26.4',
|
|
106
|
+
'oauthlib==3.2.2',
|
|
107
|
+
'omegaconf==2.3.0',
|
|
108
|
+
'orjson==3.10.3',
|
|
109
|
+
'packaging==24.0',
|
|
110
|
+
'pandas==2.2.2',
|
|
111
|
+
'parso==0.8.4',
|
|
112
|
+
'pathspec==0.12.1',
|
|
113
|
+
'pexpect==4.9.0',
|
|
114
|
+
'phik==0.12.4',
|
|
115
|
+
'pillow==10.3.0',
|
|
116
|
+
'platformdirs==3.11.0',
|
|
117
|
+
'prompt-toolkit==3.0.43',
|
|
118
|
+
'proto-plus==1.23.0',
|
|
119
|
+
'protobuf==4.25.3',
|
|
120
|
+
'psutil==5.9.8',
|
|
121
|
+
'ptyprocess==0.7.0',
|
|
122
|
+
'pure-eval==0.2.2',
|
|
123
|
+
'py4j==0.10.9.7',
|
|
124
|
+
'pyarrow==16.1.0',
|
|
125
|
+
'pyasn1==0.6.0',
|
|
126
|
+
'pyasn1_modules==0.4.0',
|
|
127
|
+
'pycparser==2.22',
|
|
128
|
+
'pydantic==2.7.1',
|
|
129
|
+
'pydantic_core==2.18.2',
|
|
130
|
+
'pydot==2.0.0',
|
|
131
|
+
'pygit2==1.14.1',
|
|
132
|
+
'Pygments==2.18.0',
|
|
133
|
+
'pygtrie==2.5.0',
|
|
134
|
+
'pyparsing==3.1.2',
|
|
135
|
+
'python-dateutil==2.9.0.post0',
|
|
136
|
+
'pytz==2024.1',
|
|
137
|
+
'PyYAML==6.0.1',
|
|
138
|
+
'pyzmq==26.0.3',
|
|
139
|
+
'requests==2.31.0',
|
|
140
|
+
'requests-oauthlib==2.0.0',
|
|
141
|
+
'rich==13.7.1',
|
|
142
|
+
'rsa==4.9',
|
|
143
|
+
'ruamel.yaml==0.18.6',
|
|
144
|
+
'ruamel.yaml.clib==0.2.8',
|
|
145
|
+
'scikit-learn==1.4.2',
|
|
146
|
+
'scipy==1.13.0',
|
|
147
|
+
'scmrepo==3.3.3',
|
|
148
|
+
'seaborn==0.13.2',
|
|
149
|
+
'semver==3.0.2',
|
|
150
|
+
'shapely==2.0.4',
|
|
151
|
+
'shellingham==1.5.4',
|
|
152
|
+
'shortuuid==1.0.13',
|
|
153
|
+
'shtab==1.7.1',
|
|
154
|
+
'six==1.16.0',
|
|
155
|
+
'smmap==5.0.1',
|
|
156
|
+
'sqltrie==0.11.0',
|
|
157
|
+
'stack-data==0.6.3',
|
|
158
|
+
'tabulate==0.9.0',
|
|
159
|
+
'threadpoolctl==3.5.0',
|
|
160
|
+
'tomlkit==0.12.5',
|
|
161
|
+
'tornado==6.4',
|
|
162
|
+
'tqdm==4.66.4',
|
|
163
|
+
'traitlets==5.14.3',
|
|
164
|
+
'typer==0.12.3',
|
|
165
|
+
'typing_extensions==4.11.0',
|
|
166
|
+
'tzdata==2024.1',
|
|
167
|
+
'urllib3==2.2.1',
|
|
168
|
+
'vine==5.1.0',
|
|
169
|
+
'voluptuous==0.14.2',
|
|
170
|
+
'wcwidth==0.2.13',
|
|
171
|
+
'yarl==1.9.4',
|
|
172
|
+
'yellowbrick==1.5',
|
|
173
|
+
'zc.lockfile==3.0.post1',
|
|
174
|
+
],
|
|
175
|
+
author='DS Team',
|
|
176
|
+
author_email='ds@sts.pl',
|
|
177
|
+
description='Solution for DS Team',
|
|
178
|
+
long_description=open('README.md').read(),
|
|
179
|
+
long_description_content_type='text/markdown',
|
|
180
|
+
classifiers=[
|
|
181
|
+
'Programming Language :: Python :: 3',
|
|
182
|
+
'License :: OSI Approved :: MIT License',
|
|
183
|
+
'Operating System :: OS Independent',
|
|
184
|
+
],
|
|
185
|
+
python_requires='>=3.11',
|
|
186
|
+
)
|
|
File without changes
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
'''
|
|
2
|
+
Statistics function
|
|
3
|
+
'''
|
|
4
|
+
|
|
5
|
+
from scipy import stats
|
|
6
|
+
|
|
7
|
+
def test_kruskal_wallis(*groups, variable, dataframe, alpha = 0.02, fill_na=0):
|
|
8
|
+
"""
|
|
9
|
+
Statistical Kruskal-Wallis test.
|
|
10
|
+
|
|
11
|
+
Parameters
|
|
12
|
+
----------
|
|
13
|
+
|
|
14
|
+
groups : packaging argument, pd.Dataframe
|
|
15
|
+
Dataframe with one of the target groups.
|
|
16
|
+
dataframe : pd.Dataframe
|
|
17
|
+
Dataframe with all target groups
|
|
18
|
+
alpha : float, optional
|
|
19
|
+
Statistical significance, by default 0.02
|
|
20
|
+
fill_na : int, optional
|
|
21
|
+
Fill empty rows, by default 0
|
|
22
|
+
"""
|
|
23
|
+
krus_group = []
|
|
24
|
+
for group in groups:
|
|
25
|
+
group = group[variable].fillna(fill_na).to_list()
|
|
26
|
+
krus_group.append(group)
|
|
27
|
+
h_statistic, p_value = stats.kruskal(*krus_group)
|
|
28
|
+
|
|
29
|
+
print("Wartość H-statystyki:", h_statistic)
|
|
30
|
+
print("Wartość p-value:", p_value)
|
|
31
|
+
|
|
32
|
+
if p_value < alpha:
|
|
33
|
+
print("Odrzucamy hipotezę zerową - istnieje istotnie statystycznie różnice między przynajmniej jedną parą grup. Sprawdź poniższe mediany.")
|
|
34
|
+
return dataframe.groupby('category')[variable].median()
|
|
35
|
+
print("Nie ma podstaw do odrzucenia hipotezy zerowej - nie ma istotnych statystycznie różnic między grupami.")
|