tabred 0.1.0__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.
- tabred-0.1.0/LICENSE +201 -0
- tabred-0.1.0/PKG-INFO +311 -0
- tabred-0.1.0/README.md +91 -0
- tabred-0.1.0/pyproject.toml +67 -0
- tabred-0.1.0/src/tabred/__init__.py +10 -0
- tabred-0.1.0/src/tabred/cli.py +28 -0
- tabred-0.1.0/src/tabred/kaggle_utils.py +369 -0
- tabred-0.1.0/src/tabred/registry.py +118 -0
tabred-0.1.0/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
tabred-0.1.0/PKG-INFO
ADDED
|
@@ -0,0 +1,311 @@
|
|
|
1
|
+
Metadata-Version: 2.3
|
|
2
|
+
Name: tabred
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: TabReD: Benchmark of industry-grade tabular datasets
|
|
5
|
+
Author: Ivan Rubachev
|
|
6
|
+
License: Apache License
|
|
7
|
+
Version 2.0, January 2004
|
|
8
|
+
http://www.apache.org/licenses/
|
|
9
|
+
|
|
10
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
11
|
+
|
|
12
|
+
1. Definitions.
|
|
13
|
+
|
|
14
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
15
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
16
|
+
|
|
17
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
18
|
+
the copyright owner that is granting the License.
|
|
19
|
+
|
|
20
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
21
|
+
other entities that control, are controlled by, or are under common
|
|
22
|
+
control with that entity. For the purposes of this definition,
|
|
23
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
24
|
+
direction or management of such entity, whether by contract or
|
|
25
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
26
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
27
|
+
|
|
28
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
29
|
+
exercising permissions granted by this License.
|
|
30
|
+
|
|
31
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
32
|
+
including but not limited to software source code, documentation
|
|
33
|
+
source, and configuration files.
|
|
34
|
+
|
|
35
|
+
"Object" form shall mean any form resulting from mechanical
|
|
36
|
+
transformation or translation of a Source form, including but
|
|
37
|
+
not limited to compiled object code, generated documentation,
|
|
38
|
+
and conversions to other media types.
|
|
39
|
+
|
|
40
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
41
|
+
Object form, made available under the License, as indicated by a
|
|
42
|
+
copyright notice that is included in or attached to the work
|
|
43
|
+
(an example is provided in the Appendix below).
|
|
44
|
+
|
|
45
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
46
|
+
form, that is based on (or derived from) the Work and for which the
|
|
47
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
48
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
49
|
+
of this License, Derivative Works shall not include works that remain
|
|
50
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
51
|
+
the Work and Derivative Works thereof.
|
|
52
|
+
|
|
53
|
+
"Contribution" shall mean any work of authorship, including
|
|
54
|
+
the original version of the Work and any modifications or additions
|
|
55
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
56
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
57
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
58
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
59
|
+
means any form of electronic, verbal, or written communication sent
|
|
60
|
+
to the Licensor or its representatives, including but not limited to
|
|
61
|
+
communication on electronic mailing lists, source code control systems,
|
|
62
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
63
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
64
|
+
excluding communication that is conspicuously marked or otherwise
|
|
65
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
66
|
+
|
|
67
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
68
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
69
|
+
subsequently incorporated within the Work.
|
|
70
|
+
|
|
71
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
72
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
73
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
74
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
75
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
76
|
+
Work and such Derivative Works in Source or Object form.
|
|
77
|
+
|
|
78
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
79
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
80
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
81
|
+
(except as stated in this section) patent license to make, have made,
|
|
82
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
83
|
+
where such license applies only to those patent claims licensable
|
|
84
|
+
by such Contributor that are necessarily infringed by their
|
|
85
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
86
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
87
|
+
institute patent litigation against any entity (including a
|
|
88
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
89
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
90
|
+
or contributory patent infringement, then any patent licenses
|
|
91
|
+
granted to You under this License for that Work shall terminate
|
|
92
|
+
as of the date such litigation is filed.
|
|
93
|
+
|
|
94
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
95
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
96
|
+
modifications, and in Source or Object form, provided that You
|
|
97
|
+
meet the following conditions:
|
|
98
|
+
|
|
99
|
+
(a) You must give any other recipients of the Work or
|
|
100
|
+
Derivative Works a copy of this License; and
|
|
101
|
+
|
|
102
|
+
(b) You must cause any modified files to carry prominent notices
|
|
103
|
+
stating that You changed the files; and
|
|
104
|
+
|
|
105
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
106
|
+
that You distribute, all copyright, patent, trademark, and
|
|
107
|
+
attribution notices from the Source form of the Work,
|
|
108
|
+
excluding those notices that do not pertain to any part of
|
|
109
|
+
the Derivative Works; and
|
|
110
|
+
|
|
111
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
112
|
+
distribution, then any Derivative Works that You distribute must
|
|
113
|
+
include a readable copy of the attribution notices contained
|
|
114
|
+
within such NOTICE file, excluding those notices that do not
|
|
115
|
+
pertain to any part of the Derivative Works, in at least one
|
|
116
|
+
of the following places: within a NOTICE text file distributed
|
|
117
|
+
as part of the Derivative Works; within the Source form or
|
|
118
|
+
documentation, if provided along with the Derivative Works; or,
|
|
119
|
+
within a display generated by the Derivative Works, if and
|
|
120
|
+
wherever such third-party notices normally appear. The contents
|
|
121
|
+
of the NOTICE file are for informational purposes only and
|
|
122
|
+
do not modify the License. You may add Your own attribution
|
|
123
|
+
notices within Derivative Works that You distribute, alongside
|
|
124
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
125
|
+
that such additional attribution notices cannot be construed
|
|
126
|
+
as modifying the License.
|
|
127
|
+
|
|
128
|
+
You may add Your own copyright statement to Your modifications and
|
|
129
|
+
may provide additional or different license terms and conditions
|
|
130
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
131
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
132
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
133
|
+
the conditions stated in this License.
|
|
134
|
+
|
|
135
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
136
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
137
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
138
|
+
this License, without any additional terms or conditions.
|
|
139
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
140
|
+
the terms of any separate license agreement you may have executed
|
|
141
|
+
with Licensor regarding such Contributions.
|
|
142
|
+
|
|
143
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
144
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
145
|
+
except as required for reasonable and customary use in describing the
|
|
146
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
147
|
+
|
|
148
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
149
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
150
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
151
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
152
|
+
implied, including, without limitation, any warranties or conditions
|
|
153
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
154
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
155
|
+
appropriateness of using or redistributing the Work and assume any
|
|
156
|
+
risks associated with Your exercise of permissions under this License.
|
|
157
|
+
|
|
158
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
159
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
160
|
+
unless required by applicable law (such as deliberate and grossly
|
|
161
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
162
|
+
liable to You for damages, including any direct, indirect, special,
|
|
163
|
+
incidental, or consequential damages of any character arising as a
|
|
164
|
+
result of this License or out of the use or inability to use the
|
|
165
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
166
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
167
|
+
other commercial damages or losses), even if such Contributor
|
|
168
|
+
has been advised of the possibility of such damages.
|
|
169
|
+
|
|
170
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
171
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
172
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
173
|
+
or other liability obligations and/or rights consistent with this
|
|
174
|
+
License. However, in accepting such obligations, You may act only
|
|
175
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
176
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
177
|
+
defend, and hold each Contributor harmless for any liability
|
|
178
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
179
|
+
of your accepting any such warranty or additional liability.
|
|
180
|
+
|
|
181
|
+
END OF TERMS AND CONDITIONS
|
|
182
|
+
|
|
183
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
184
|
+
|
|
185
|
+
To apply the Apache License to your work, attach the following
|
|
186
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
187
|
+
replaced with your own identifying information. (Don't include
|
|
188
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
189
|
+
comment syntax for the file format. We also recommend that a
|
|
190
|
+
file or class name and description of purpose be included on the
|
|
191
|
+
same "printed page" as the copyright notice for easier
|
|
192
|
+
identification within third-party archives.
|
|
193
|
+
|
|
194
|
+
Copyright [yyyy] [name of copyright owner]
|
|
195
|
+
|
|
196
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
197
|
+
you may not use this file except in compliance with the License.
|
|
198
|
+
You may obtain a copy of the License at
|
|
199
|
+
|
|
200
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
201
|
+
|
|
202
|
+
Unless required by applicable law or agreed to in writing, software
|
|
203
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
204
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
205
|
+
See the License for the specific language governing permissions and
|
|
206
|
+
limitations under the License.
|
|
207
|
+
Classifier: Intended Audience :: Science/Research
|
|
208
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
209
|
+
Classifier: Programming Language :: Python :: 3
|
|
210
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
211
|
+
Requires-Dist: cyclopts>=4.18.0,<5
|
|
212
|
+
Requires-Dist: kaggle>=2.2,<3
|
|
213
|
+
Requires-Dist: kagglesdk>=0.1.30,<0.2
|
|
214
|
+
Requires-Dist: requests>=2.34.2,<3
|
|
215
|
+
Requires-Dist: rich>=15.0.0,<16
|
|
216
|
+
Requires-Python: >=3.12, <4
|
|
217
|
+
Project-URL: Code, https://github.com/yandex-research/tabred
|
|
218
|
+
Project-URL: Documentation, https://github.com/yandex-research/tabred/tree/main/README.md
|
|
219
|
+
Description-Content-Type: text/markdown
|
|
220
|
+
|
|
221
|
+
# TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks
|
|
222
|
+
|
|
223
|
+
:scroll: [arXiv](https://arxiv.org/abs/2406.19380)
|
|
224
|
+
:books: [Other tabular DL projects](https://github.com/yandex-research/rtdl)
|
|
225
|
+
|
|
226
|
+
> [!NOTE]
|
|
227
|
+
> **Download preprocessed TabReD datasets with one command**
|
|
228
|
+
>
|
|
229
|
+
> ```bash
|
|
230
|
+
> uvx tabred download all
|
|
231
|
+
> # or individual datasets with
|
|
232
|
+
> uvx tabred download cooking-time weather
|
|
233
|
+
> ```
|
|
234
|
+
>
|
|
235
|
+
> *You need a Kaggle account and an API token at `~/.kaggle/kaggle.json` for this to work.*
|
|
236
|
+
|
|
237
|
+
TabReD is a collection of eight industry-grade tabular datasets designed to evaluate machine learning methods under more realistic conditions: temporal distribution shift, rich feature sets from feature engineering pipelines, closer aligned with some real world applications of tabular machine learning.
|
|
238
|
+
|
|
239
|
+
<p align="center">
|
|
240
|
+
<img src="assets/about_tabred.png" alt="TabReD overview" width="75%">
|
|
241
|
+
</p>
|
|
242
|
+
|
|
243
|
+
## Datasets
|
|
244
|
+
|
|
245
|
+
| Dataset | Features | Task | Instances Used | Instances Available | Source |
|
|
246
|
+
| ------------------ | -------- | -------------- | -------------- | ------------------- | ------------------------------------------------------------------------------------------ |
|
|
247
|
+
| Homesite Insurance | 299 | Classification | 260,753 | - | [Competition](https://www.kaggle.com/competitions/homesite-quote-conversion) |
|
|
248
|
+
| Ecom Offers | 119 | Classification | 160,057 | - | [Competition](https://www.kaggle.com/c/acquire-valued-shoppers-challenge) |
|
|
249
|
+
| Homecredit Default | 696 | Classification | 381,664 | 1,526,659 | [Competition](https://www.kaggle.com/competitions/home-credit-credit-risk-model-stability) |
|
|
250
|
+
| Sberbank Housing | 392 | Regression | 28,321 | - | [Competition](https://www.kaggle.com/competitions/sberbank-russian-housing-market) |
|
|
251
|
+
| Cooking Time | 192 | Regression | 319,986 | 12,799,642 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
252
|
+
| Delivery ETA | 223 | Regression | 416,451 | 17,044,043 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
253
|
+
| Maps Routing | 986 | Regression | 340,981 | 13,639,272 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
254
|
+
| Weather | 103 | Regression | 423,795 | 16,951,828 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
255
|
+
## Preprocessed data format
|
|
256
|
+
|
|
257
|
+
The downloader unpacks each dataset into its own directory:
|
|
258
|
+
|
|
259
|
+
```
|
|
260
|
+
data/<dataset>/
|
|
261
|
+
├── info.json
|
|
262
|
+
├── x_num.npy
|
|
263
|
+
├── x_cat.npy # when present
|
|
264
|
+
├── x_bin.npy # when present
|
|
265
|
+
├── x_meta.npy
|
|
266
|
+
├── y.npy
|
|
267
|
+
└── splits/
|
|
268
|
+
├── default/
|
|
269
|
+
│ ├── train.npy
|
|
270
|
+
│ ├── val.npy
|
|
271
|
+
│ └── test.npy
|
|
272
|
+
├── random-{0,1,2}/
|
|
273
|
+
│ ├── train.npy
|
|
274
|
+
│ ├── val.npy
|
|
275
|
+
│ └── test.npy
|
|
276
|
+
└── sliding-window-{0,1,2}/
|
|
277
|
+
├── train.npy
|
|
278
|
+
├── val.npy
|
|
279
|
+
└── test.npy
|
|
280
|
+
```
|
|
281
|
+
|
|
282
|
+
The `x_*.npy` files contain feature matrices, `y.npy` contains targets, and
|
|
283
|
+
`info.json` contains task metadata. Split files contain row indices into these
|
|
284
|
+
arrays. The `default` split is the main split from the TabReD paper; the random
|
|
285
|
+
and sliding-window splits are provided for split-strategy studies.
|
|
286
|
+
|
|
287
|
+
## Repository structure
|
|
288
|
+
|
|
289
|
+
- `src/tabred`: downloader package and CLI.
|
|
290
|
+
- `paper`: code for reproducing the paper
|
|
291
|
+
|
|
292
|
+
## Rebuilding datasets from raw sources
|
|
293
|
+
|
|
294
|
+
Most users should use the preprocessed downloader above. The preprocessing pipeline is kept in this repository for reproducibility and maintenance, but it is not the recommended way to obtain the benchmark data.
|
|
295
|
+
|
|
296
|
+
> The cleaned-up dataset preparation scripts will be published in a few days (@puhsu 10.07.26). For now consult the previous commits and the preprocessing folder there.
|
|
297
|
+
|
|
298
|
+
## Citation
|
|
299
|
+
|
|
300
|
+
If you use TabReD, please cite:
|
|
301
|
+
|
|
302
|
+
```bibtex
|
|
303
|
+
@inproceedings{
|
|
304
|
+
rubachev2025tabred,
|
|
305
|
+
title={TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks},
|
|
306
|
+
author={Ivan Rubachev and Nikolay Kartashev and Yury Gorishniy and Artem Babenko},
|
|
307
|
+
booktitle={The Thirteenth International Conference on Learning Representations},
|
|
308
|
+
year={2025},
|
|
309
|
+
url={https://openreview.net/forum?id=L14sqcrUC3}
|
|
310
|
+
}
|
|
311
|
+
```
|
tabred-0.1.0/README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
# TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks
|
|
2
|
+
|
|
3
|
+
:scroll: [arXiv](https://arxiv.org/abs/2406.19380)
|
|
4
|
+
:books: [Other tabular DL projects](https://github.com/yandex-research/rtdl)
|
|
5
|
+
|
|
6
|
+
> [!NOTE]
|
|
7
|
+
> **Download preprocessed TabReD datasets with one command**
|
|
8
|
+
>
|
|
9
|
+
> ```bash
|
|
10
|
+
> uvx tabred download all
|
|
11
|
+
> # or individual datasets with
|
|
12
|
+
> uvx tabred download cooking-time weather
|
|
13
|
+
> ```
|
|
14
|
+
>
|
|
15
|
+
> *You need a Kaggle account and an API token at `~/.kaggle/kaggle.json` for this to work.*
|
|
16
|
+
|
|
17
|
+
TabReD is a collection of eight industry-grade tabular datasets designed to evaluate machine learning methods under more realistic conditions: temporal distribution shift, rich feature sets from feature engineering pipelines, closer aligned with some real world applications of tabular machine learning.
|
|
18
|
+
|
|
19
|
+
<p align="center">
|
|
20
|
+
<img src="assets/about_tabred.png" alt="TabReD overview" width="75%">
|
|
21
|
+
</p>
|
|
22
|
+
|
|
23
|
+
## Datasets
|
|
24
|
+
|
|
25
|
+
| Dataset | Features | Task | Instances Used | Instances Available | Source |
|
|
26
|
+
| ------------------ | -------- | -------------- | -------------- | ------------------- | ------------------------------------------------------------------------------------------ |
|
|
27
|
+
| Homesite Insurance | 299 | Classification | 260,753 | - | [Competition](https://www.kaggle.com/competitions/homesite-quote-conversion) |
|
|
28
|
+
| Ecom Offers | 119 | Classification | 160,057 | - | [Competition](https://www.kaggle.com/c/acquire-valued-shoppers-challenge) |
|
|
29
|
+
| Homecredit Default | 696 | Classification | 381,664 | 1,526,659 | [Competition](https://www.kaggle.com/competitions/home-credit-credit-risk-model-stability) |
|
|
30
|
+
| Sberbank Housing | 392 | Regression | 28,321 | - | [Competition](https://www.kaggle.com/competitions/sberbank-russian-housing-market) |
|
|
31
|
+
| Cooking Time | 192 | Regression | 319,986 | 12,799,642 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
32
|
+
| Delivery ETA | 223 | Regression | 416,451 | 17,044,043 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
33
|
+
| Maps Routing | 986 | Regression | 340,981 | 13,639,272 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
34
|
+
| Weather | 103 | Regression | 423,795 | 16,951,828 | [Dataset](https://www.kaggle.com/datasets/irubachev/tabred) |
|
|
35
|
+
## Preprocessed data format
|
|
36
|
+
|
|
37
|
+
The downloader unpacks each dataset into its own directory:
|
|
38
|
+
|
|
39
|
+
```
|
|
40
|
+
data/<dataset>/
|
|
41
|
+
├── info.json
|
|
42
|
+
├── x_num.npy
|
|
43
|
+
├── x_cat.npy # when present
|
|
44
|
+
├── x_bin.npy # when present
|
|
45
|
+
├── x_meta.npy
|
|
46
|
+
├── y.npy
|
|
47
|
+
└── splits/
|
|
48
|
+
├── default/
|
|
49
|
+
│ ├── train.npy
|
|
50
|
+
│ ├── val.npy
|
|
51
|
+
│ └── test.npy
|
|
52
|
+
├── random-{0,1,2}/
|
|
53
|
+
│ ├── train.npy
|
|
54
|
+
│ ├── val.npy
|
|
55
|
+
│ └── test.npy
|
|
56
|
+
└── sliding-window-{0,1,2}/
|
|
57
|
+
├── train.npy
|
|
58
|
+
├── val.npy
|
|
59
|
+
└── test.npy
|
|
60
|
+
```
|
|
61
|
+
|
|
62
|
+
The `x_*.npy` files contain feature matrices, `y.npy` contains targets, and
|
|
63
|
+
`info.json` contains task metadata. Split files contain row indices into these
|
|
64
|
+
arrays. The `default` split is the main split from the TabReD paper; the random
|
|
65
|
+
and sliding-window splits are provided for split-strategy studies.
|
|
66
|
+
|
|
67
|
+
## Repository structure
|
|
68
|
+
|
|
69
|
+
- `src/tabred`: downloader package and CLI.
|
|
70
|
+
- `paper`: code for reproducing the paper
|
|
71
|
+
|
|
72
|
+
## Rebuilding datasets from raw sources
|
|
73
|
+
|
|
74
|
+
Most users should use the preprocessed downloader above. The preprocessing pipeline is kept in this repository for reproducibility and maintenance, but it is not the recommended way to obtain the benchmark data.
|
|
75
|
+
|
|
76
|
+
> The cleaned-up dataset preparation scripts will be published in a few days (@puhsu 10.07.26). For now consult the previous commits and the preprocessing folder there.
|
|
77
|
+
|
|
78
|
+
## Citation
|
|
79
|
+
|
|
80
|
+
If you use TabReD, please cite:
|
|
81
|
+
|
|
82
|
+
```bibtex
|
|
83
|
+
@inproceedings{
|
|
84
|
+
rubachev2025tabred,
|
|
85
|
+
title={TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks},
|
|
86
|
+
author={Ivan Rubachev and Nikolay Kartashev and Yury Gorishniy and Artem Babenko},
|
|
87
|
+
booktitle={The Thirteenth International Conference on Learning Representations},
|
|
88
|
+
year={2025},
|
|
89
|
+
url={https://openreview.net/forum?id=L14sqcrUC3}
|
|
90
|
+
}
|
|
91
|
+
```
|
|
@@ -0,0 +1,67 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["uv_build>=0.11.16,<0.12.0"]
|
|
3
|
+
build-backend = "uv_build"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "tabred"
|
|
7
|
+
version = "0.1.0"
|
|
8
|
+
description = "TabReD: Benchmark of industry-grade tabular datasets"
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
requires-python = ">=3.12,<4"
|
|
11
|
+
license = { file = "LICENSE" }
|
|
12
|
+
authors = [{ name = "Ivan Rubachev" }]
|
|
13
|
+
classifiers = [
|
|
14
|
+
"Intended Audience :: Science/Research",
|
|
15
|
+
"License :: OSI Approved :: Apache Software License",
|
|
16
|
+
"Programming Language :: Python :: 3",
|
|
17
|
+
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
18
|
+
]
|
|
19
|
+
dependencies = [
|
|
20
|
+
"cyclopts>=4.18.0,<5",
|
|
21
|
+
"kaggle>=2.2,<3",
|
|
22
|
+
"kagglesdk>=0.1.30,<0.2",
|
|
23
|
+
"requests>=2.34.2,<3",
|
|
24
|
+
"rich>=15.0.0,<16",
|
|
25
|
+
]
|
|
26
|
+
|
|
27
|
+
[project.urls]
|
|
28
|
+
Code = "https://github.com/yandex-research/tabred"
|
|
29
|
+
Documentation = "https://github.com/yandex-research/tabred/tree/main/README.md"
|
|
30
|
+
|
|
31
|
+
[project.scripts]
|
|
32
|
+
tabred = "tabred.cli:main"
|
|
33
|
+
|
|
34
|
+
[dependency-groups]
|
|
35
|
+
data = [
|
|
36
|
+
# dependencies in this group are intentionally
|
|
37
|
+
# strict for reproducible dataset artifacts.
|
|
38
|
+
"numpy==2.4.6",
|
|
39
|
+
"polars>=1.41,<2",
|
|
40
|
+
"pyarrow==24.0.0",
|
|
41
|
+
"scikit-learn==1.8.0",
|
|
42
|
+
]
|
|
43
|
+
dev = [
|
|
44
|
+
"ipython>=9.13.0,<10",
|
|
45
|
+
"pytest>=8.0.0,<9",
|
|
46
|
+
"ruff>=0.15.0,<0.16",
|
|
47
|
+
]
|
|
48
|
+
|
|
49
|
+
[tool.pyright]
|
|
50
|
+
exclude = [
|
|
51
|
+
"**/node_modules",
|
|
52
|
+
"**/__pycache__",
|
|
53
|
+
"**/.*",
|
|
54
|
+
"local",
|
|
55
|
+
]
|
|
56
|
+
venv = ".venv"
|
|
57
|
+
venvPath = "."
|
|
58
|
+
|
|
59
|
+
[tool.ruff]
|
|
60
|
+
line-length = 120
|
|
61
|
+
|
|
62
|
+
[tool.ruff.lint]
|
|
63
|
+
extend-select = ["ARG", "RUF", "UP", "E501", "E731", "I"]
|
|
64
|
+
|
|
65
|
+
|
|
66
|
+
[tool.ruff.format]
|
|
67
|
+
quote-style = "single"
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
from tabred.kaggle_utils import download_kaggle_data, download_preprocessed_data, require_competition_access
|
|
2
|
+
from tabred.registry import get_preprocessed_files, get_raw_files
|
|
3
|
+
|
|
4
|
+
__all__ = [
|
|
5
|
+
'download_kaggle_data',
|
|
6
|
+
'download_preprocessed_data',
|
|
7
|
+
'get_preprocessed_files',
|
|
8
|
+
'get_raw_files',
|
|
9
|
+
'require_competition_access',
|
|
10
|
+
]
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
from pathlib import Path
|
|
2
|
+
|
|
3
|
+
import cyclopts
|
|
4
|
+
|
|
5
|
+
import tabred
|
|
6
|
+
|
|
7
|
+
app = cyclopts.App(name='tabred')
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
@app.command
|
|
11
|
+
def download(
|
|
12
|
+
names: list[str] = ['all'],
|
|
13
|
+
*,
|
|
14
|
+
output_path: Path = Path('data'),
|
|
15
|
+
force: bool = False,
|
|
16
|
+
max_workers: int = 4,
|
|
17
|
+
) -> None:
|
|
18
|
+
tabred.require_competition_access(names)
|
|
19
|
+
tabred.download_preprocessed_data(
|
|
20
|
+
names,
|
|
21
|
+
output_path,
|
|
22
|
+
force=force,
|
|
23
|
+
max_workers=max_workers,
|
|
24
|
+
)
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
def main() -> None:
|
|
28
|
+
app()
|
|
@@ -0,0 +1,369 @@
|
|
|
1
|
+
import hashlib
|
|
2
|
+
import random
|
|
3
|
+
import shutil
|
|
4
|
+
import tarfile
|
|
5
|
+
import tempfile
|
|
6
|
+
from collections.abc import Iterable
|
|
7
|
+
from concurrent.futures import FIRST_EXCEPTION, ThreadPoolExecutor, wait
|
|
8
|
+
from pathlib import Path
|
|
9
|
+
from threading import Event
|
|
10
|
+
|
|
11
|
+
import kagglesdk
|
|
12
|
+
import requests
|
|
13
|
+
from kagglesdk.competitions.types.competition_api_service import (
|
|
14
|
+
ApiDownloadDataFilesRequest,
|
|
15
|
+
ApiListCompetitionsRequest,
|
|
16
|
+
)
|
|
17
|
+
from kagglesdk.competitions.types.competition_enums import CompetitionListTab
|
|
18
|
+
from kagglesdk.datasets.types.dataset_api_service import ApiDownloadDatasetRequest
|
|
19
|
+
from requests import exceptions as requests_exceptions
|
|
20
|
+
from rich.console import Console
|
|
21
|
+
from rich.panel import Panel
|
|
22
|
+
from rich.progress import (
|
|
23
|
+
BarColumn,
|
|
24
|
+
DownloadColumn,
|
|
25
|
+
Progress,
|
|
26
|
+
TextColumn,
|
|
27
|
+
TransferSpeedColumn,
|
|
28
|
+
)
|
|
29
|
+
from rich.theme import Theme
|
|
30
|
+
from urllib3 import exceptions as urllib3_exceptions
|
|
31
|
+
|
|
32
|
+
from tabred.registry import KaggleRef, competition_slugs, dataset_names, get_preprocessed_files
|
|
33
|
+
|
|
34
|
+
_CHUNK_SIZE = 1024 * 1024
|
|
35
|
+
_DOWNLOAD_RETRIES = 5
|
|
36
|
+
_DOWNLOAD_TIMEOUT = (5, 5)
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
class DownloadFailed(Exception):
|
|
40
|
+
pass
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
_DOWNLOAD_ERRORS = (
|
|
44
|
+
requests_exceptions.RequestException,
|
|
45
|
+
urllib3_exceptions.HTTPError,
|
|
46
|
+
)
|
|
47
|
+
|
|
48
|
+
console = Console(
|
|
49
|
+
highlight=False,
|
|
50
|
+
theme=Theme(
|
|
51
|
+
{
|
|
52
|
+
'bar.complete': 'dim green',
|
|
53
|
+
'bar.pulse': 'dim green',
|
|
54
|
+
'bar.back': 'white',
|
|
55
|
+
}
|
|
56
|
+
),
|
|
57
|
+
)
|
|
58
|
+
|
|
59
|
+
|
|
60
|
+
def download_preprocessed_data(
|
|
61
|
+
names: Iterable[str],
|
|
62
|
+
dst: Path,
|
|
63
|
+
*,
|
|
64
|
+
force: bool = False,
|
|
65
|
+
max_workers: int = 4,
|
|
66
|
+
) -> dict[str, Path]:
|
|
67
|
+
names = dataset_names(names)
|
|
68
|
+
dst.mkdir(parents=True, exist_ok=True)
|
|
69
|
+
|
|
70
|
+
todo = []
|
|
71
|
+
for name in names:
|
|
72
|
+
dataset_dir = dst / name
|
|
73
|
+
if dataset_dir.exists():
|
|
74
|
+
if force:
|
|
75
|
+
shutil.rmtree(dataset_dir)
|
|
76
|
+
else:
|
|
77
|
+
console.print(f'[bold]{name}[/] [yellow]already exists[/]')
|
|
78
|
+
continue
|
|
79
|
+
todo.append(name)
|
|
80
|
+
|
|
81
|
+
if not todo:
|
|
82
|
+
return {name: dst / name for name in names}
|
|
83
|
+
|
|
84
|
+
with tempfile.TemporaryDirectory(dir=dst) as tmp_dir_str:
|
|
85
|
+
tmp_dir = Path(tmp_dir_str)
|
|
86
|
+
archives = download_kaggle_data(
|
|
87
|
+
get_preprocessed_files(todo),
|
|
88
|
+
tmp_dir,
|
|
89
|
+
force=True,
|
|
90
|
+
max_workers=max_workers,
|
|
91
|
+
)
|
|
92
|
+
for name, archive in archives.items():
|
|
93
|
+
with tarfile.open(archive, 'r:gz') as tar:
|
|
94
|
+
tar.extractall(dst, filter='data')
|
|
95
|
+
if not (dst / name).is_dir():
|
|
96
|
+
raise DownloadFailed(f'{archive.name} did not extract to expected directory {name}')
|
|
97
|
+
|
|
98
|
+
console.print(f'[bold green]✓[/] unpacked requested data into `{dst.as_posix()}`')
|
|
99
|
+
return {name: dst / name for name in names}
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
# This could have been a for loop with kaggle cli download,
|
|
103
|
+
# but I wanted the download to be faster and have a nice ui, so...
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
def download_kaggle_data(
|
|
107
|
+
data: dict[str, KaggleRef],
|
|
108
|
+
dst: Path,
|
|
109
|
+
*,
|
|
110
|
+
force: bool = False,
|
|
111
|
+
max_workers: int = 4,
|
|
112
|
+
) -> dict[str, Path]:
|
|
113
|
+
if not data:
|
|
114
|
+
return {}
|
|
115
|
+
|
|
116
|
+
stop = Event()
|
|
117
|
+
workers = max(1, min(max_workers, len(data)))
|
|
118
|
+
|
|
119
|
+
with Progress(
|
|
120
|
+
TextColumn('{task.description}', style='dim'),
|
|
121
|
+
BarColumn(bar_width=30),
|
|
122
|
+
DownloadColumn(),
|
|
123
|
+
TransferSpeedColumn(),
|
|
124
|
+
console=console,
|
|
125
|
+
transient=True,
|
|
126
|
+
refresh_per_second=10,
|
|
127
|
+
expand=False,
|
|
128
|
+
) as progress:
|
|
129
|
+
task_ids = {name: progress.add_task(ref.name, total=None) for name, ref in data.items()}
|
|
130
|
+
|
|
131
|
+
def run(name: str) -> Path:
|
|
132
|
+
return _download(data[name], dst / name, force, progress, task_ids[name], stop)
|
|
133
|
+
|
|
134
|
+
with ThreadPoolExecutor(max_workers=workers) as pool:
|
|
135
|
+
futures = {pool.submit(run, name): name for name in data}
|
|
136
|
+
|
|
137
|
+
try:
|
|
138
|
+
done, _pending = wait(futures, return_when=FIRST_EXCEPTION)
|
|
139
|
+
except KeyboardInterrupt:
|
|
140
|
+
# fast Ctrl-C cancelation niceties
|
|
141
|
+
stop.set()
|
|
142
|
+
console.print('[bold yellow]⊘[/] download interrupted')
|
|
143
|
+
raise SystemExit(130)
|
|
144
|
+
|
|
145
|
+
failed = next((f for f in done if f.exception() is not None), None)
|
|
146
|
+
|
|
147
|
+
if failed is not None:
|
|
148
|
+
# cancel other ongoing downloads and reraise the error
|
|
149
|
+
stop.set()
|
|
150
|
+
name = futures[failed]
|
|
151
|
+
progress.update(task_ids[name], description=f'{name} failed')
|
|
152
|
+
raise failed.exception() # ty: ignore
|
|
153
|
+
|
|
154
|
+
return {futures[f]: f.result() for f in done}
|
|
155
|
+
|
|
156
|
+
|
|
157
|
+
def require_competition_access(names: Iterable[str]) -> None:
|
|
158
|
+
slugs = competition_slugs(names)
|
|
159
|
+
if not slugs:
|
|
160
|
+
return
|
|
161
|
+
|
|
162
|
+
with console.status('Checking Kaggle competition access'):
|
|
163
|
+
with ThreadPoolExecutor(max_workers=min(8, len(slugs))) as pool:
|
|
164
|
+
access = dict(zip(slugs, pool.map(_entered_competition, slugs), strict=True))
|
|
165
|
+
|
|
166
|
+
missing = [slug for slug, ok in access.items() if not ok]
|
|
167
|
+
if not missing:
|
|
168
|
+
console.print('[bold green]✓[/] competition access verified')
|
|
169
|
+
return
|
|
170
|
+
|
|
171
|
+
links = '\n'.join(f' • [steel_blue3]https://www.kaggle.com/competitions/{slug}[/]' for slug in missing)
|
|
172
|
+
console.print(
|
|
173
|
+
Panel(
|
|
174
|
+
'\nPlease accept the rules for the following Kaggle competitions '
|
|
175
|
+
'and then rerun the command\n'
|
|
176
|
+
'[dim] Use the account corresponding to the ~/.kaggle/kaggle.json API key[/]'
|
|
177
|
+
'\n\n'
|
|
178
|
+
f'{links}',
|
|
179
|
+
title='[bold]Kaggle competition access required[/]',
|
|
180
|
+
border_style='black',
|
|
181
|
+
)
|
|
182
|
+
)
|
|
183
|
+
raise SystemExit(0)
|
|
184
|
+
|
|
185
|
+
|
|
186
|
+
def _entered_competition(slug: str) -> bool:
|
|
187
|
+
request = ApiListCompetitionsRequest()
|
|
188
|
+
request.group = CompetitionListTab.COMPETITION_LIST_TAB_ENTERED
|
|
189
|
+
request.search = slug
|
|
190
|
+
request.page = 1
|
|
191
|
+
request.page_size = 5
|
|
192
|
+
|
|
193
|
+
with kagglesdk.KaggleClient() as client:
|
|
194
|
+
response = client.competitions.competition_api_client.list_competitions(request)
|
|
195
|
+
|
|
196
|
+
for competition in response.competitions or []:
|
|
197
|
+
for value in (competition.ref, competition.url):
|
|
198
|
+
if value and value.rstrip('/').split('/')[-1] == slug:
|
|
199
|
+
return True
|
|
200
|
+
return False
|
|
201
|
+
|
|
202
|
+
|
|
203
|
+
# This is a "vendored" KaggleApi.download_file
|
|
204
|
+
# it supports restarts, but also does write intermediate files into .part (no correptud)
|
|
205
|
+
# plus it is integrated nicer with the Rich progress bar
|
|
206
|
+
# original: https://github.com/Kaggle/kaggle-cli/blob/c97b6268ff1c6008207049144037cd556f957db3/src/kaggle/api/kaggle_api_extended.py#L4231
|
|
207
|
+
|
|
208
|
+
|
|
209
|
+
def _download(
|
|
210
|
+
file: KaggleRef,
|
|
211
|
+
dst: Path,
|
|
212
|
+
force: bool,
|
|
213
|
+
progress: Progress,
|
|
214
|
+
task_id,
|
|
215
|
+
stop: Event,
|
|
216
|
+
) -> Path:
|
|
217
|
+
dst.mkdir(parents=True, exist_ok=True)
|
|
218
|
+
|
|
219
|
+
out = dst / (file.local_name or Path(file.name).name)
|
|
220
|
+
part = out.with_name(out.name + '.part')
|
|
221
|
+
|
|
222
|
+
if force:
|
|
223
|
+
out.unlink(missing_ok=True)
|
|
224
|
+
part.unlink(missing_ok=True)
|
|
225
|
+
|
|
226
|
+
if out.exists():
|
|
227
|
+
_check_existing_file(out, file)
|
|
228
|
+
size = out.stat().st_size
|
|
229
|
+
progress.update(task_id, total=size, completed=size)
|
|
230
|
+
progress.remove_task(task_id)
|
|
231
|
+
return out
|
|
232
|
+
|
|
233
|
+
with kagglesdk.KaggleClient() as client:
|
|
234
|
+
if file.kind == 'dataset':
|
|
235
|
+
owner, slug = file.ref.split('/', 1)
|
|
236
|
+
request = ApiDownloadDatasetRequest()
|
|
237
|
+
request.owner_slug = owner
|
|
238
|
+
request.dataset_slug = slug
|
|
239
|
+
request.file_name = file.name
|
|
240
|
+
response = client.datasets.dataset_api_client.download_dataset(request)
|
|
241
|
+
elif file.kind == 'competition':
|
|
242
|
+
request = ApiDownloadDataFilesRequest()
|
|
243
|
+
request.competition_name = file.ref
|
|
244
|
+
response = client.competitions.competition_api_client.download_data_files(request)
|
|
245
|
+
else:
|
|
246
|
+
raise DownloadFailed(f'Unknown Kaggle file kind: {file.kind}')
|
|
247
|
+
|
|
248
|
+
_stream_download(
|
|
249
|
+
response,
|
|
250
|
+
out=out,
|
|
251
|
+
part=part,
|
|
252
|
+
file=file,
|
|
253
|
+
progress=progress,
|
|
254
|
+
task_id=task_id,
|
|
255
|
+
stop=stop,
|
|
256
|
+
)
|
|
257
|
+
|
|
258
|
+
progress.remove_task(task_id)
|
|
259
|
+
return out
|
|
260
|
+
|
|
261
|
+
|
|
262
|
+
def _stream_download(
|
|
263
|
+
response,
|
|
264
|
+
*,
|
|
265
|
+
out: Path,
|
|
266
|
+
part: Path,
|
|
267
|
+
file: KaggleRef,
|
|
268
|
+
stop: Event,
|
|
269
|
+
progress: Progress,
|
|
270
|
+
task_id,
|
|
271
|
+
) -> None:
|
|
272
|
+
content_length = response.headers.get('Content-Length')
|
|
273
|
+
total = int(content_length) if content_length else None
|
|
274
|
+
resumable = response.headers.get('Accept-Ranges') == 'bytes'
|
|
275
|
+
|
|
276
|
+
url = response.url
|
|
277
|
+
request = response.request
|
|
278
|
+
method = request.method if request is not None else 'GET'
|
|
279
|
+
headers = dict(request.headers) if request is not None else {}
|
|
280
|
+
|
|
281
|
+
response.close()
|
|
282
|
+
|
|
283
|
+
for attempt in range(1, _DOWNLOAD_RETRIES + 2):
|
|
284
|
+
if stop.is_set():
|
|
285
|
+
raise DownloadFailed('Interrupted')
|
|
286
|
+
start = part.stat().st_size if resumable and part.exists() else 0
|
|
287
|
+
|
|
288
|
+
if total is not None and start >= total:
|
|
289
|
+
break
|
|
290
|
+
|
|
291
|
+
request_headers = headers.copy()
|
|
292
|
+
|
|
293
|
+
if start:
|
|
294
|
+
request_headers['Range'] = f'bytes={start}-'
|
|
295
|
+
|
|
296
|
+
try:
|
|
297
|
+
with requests.request(
|
|
298
|
+
method,
|
|
299
|
+
url,
|
|
300
|
+
headers=request_headers,
|
|
301
|
+
stream=True,
|
|
302
|
+
timeout=_DOWNLOAD_TIMEOUT,
|
|
303
|
+
) as response:
|
|
304
|
+
response.raise_for_status()
|
|
305
|
+
progress.update(task_id, total=total, completed=start)
|
|
306
|
+
|
|
307
|
+
mode = 'ab' if start else 'wb'
|
|
308
|
+
with part.open(mode) as f:
|
|
309
|
+
for chunk in response.iter_content(_CHUNK_SIZE):
|
|
310
|
+
if stop.is_set():
|
|
311
|
+
raise DownloadFailed('Interrupted')
|
|
312
|
+
|
|
313
|
+
if not chunk:
|
|
314
|
+
continue
|
|
315
|
+
|
|
316
|
+
f.write(chunk)
|
|
317
|
+
progress.update(task_id, advance=len(chunk))
|
|
318
|
+
break
|
|
319
|
+
|
|
320
|
+
except _DOWNLOAD_ERRORS as error:
|
|
321
|
+
if attempt > _DOWNLOAD_RETRIES:
|
|
322
|
+
raise DownloadFailed(f'Could not download {out.name}. Try running the command again.') from error
|
|
323
|
+
|
|
324
|
+
if not resumable:
|
|
325
|
+
part.unlink(missing_ok=True)
|
|
326
|
+
|
|
327
|
+
if stop.wait(min(2**attempt + random.random(), 60)):
|
|
328
|
+
raise DownloadFailed('Download cancelled') from error
|
|
329
|
+
|
|
330
|
+
if total is not None and part.stat().st_size != total:
|
|
331
|
+
part.unlink(missing_ok=True)
|
|
332
|
+
raise DownloadFailed(
|
|
333
|
+
f'Downloaded size for {out.name} does not match Kaggle metadata. Try running the command again.'
|
|
334
|
+
)
|
|
335
|
+
|
|
336
|
+
if file.sha256 is not None:
|
|
337
|
+
actual = _sha256(part)
|
|
338
|
+
expected = file.sha256.lower()
|
|
339
|
+
|
|
340
|
+
if actual != expected:
|
|
341
|
+
part.unlink(missing_ok=True)
|
|
342
|
+
raise DownloadFailed(f'Checksum mismatch for {out.name}. Try running the command again.')
|
|
343
|
+
|
|
344
|
+
part.replace(out)
|
|
345
|
+
size = out.stat().st_size
|
|
346
|
+
progress.update(task_id, total=size, completed=size)
|
|
347
|
+
|
|
348
|
+
|
|
349
|
+
def _check_existing_file(path: Path, file: KaggleRef) -> None:
|
|
350
|
+
if file.sha256 is None:
|
|
351
|
+
return
|
|
352
|
+
|
|
353
|
+
actual = _sha256(path)
|
|
354
|
+
expected = file.sha256.lower()
|
|
355
|
+
|
|
356
|
+
if actual != expected:
|
|
357
|
+
raise DownloadFailed(
|
|
358
|
+
f'{path.name} already exists, but its checksum does not match. Run again with --force to replace it.'
|
|
359
|
+
)
|
|
360
|
+
|
|
361
|
+
|
|
362
|
+
def _sha256(path: Path) -> str:
|
|
363
|
+
sha = hashlib.sha256()
|
|
364
|
+
|
|
365
|
+
with path.open('rb') as f:
|
|
366
|
+
for chunk in iter(lambda: f.read(_CHUNK_SIZE), b''):
|
|
367
|
+
sha.update(chunk)
|
|
368
|
+
|
|
369
|
+
return sha.hexdigest().lower()
|
|
@@ -0,0 +1,118 @@
|
|
|
1
|
+
from collections.abc import Iterable
|
|
2
|
+
from dataclasses import dataclass
|
|
3
|
+
from typing import Literal
|
|
4
|
+
|
|
5
|
+
_TABRED_KAGGLE_DATASET = 'irubachev/tabred'
|
|
6
|
+
|
|
7
|
+
KaggleKind = Literal['dataset', 'competition']
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
@dataclass(frozen=True)
|
|
11
|
+
class KaggleRef:
|
|
12
|
+
kind: KaggleKind
|
|
13
|
+
ref: str
|
|
14
|
+
name: str
|
|
15
|
+
sha256: str | None
|
|
16
|
+
local_name: str | None = None
|
|
17
|
+
|
|
18
|
+
@property
|
|
19
|
+
def slug(self):
|
|
20
|
+
return self.ref if self.kind == 'competition' else None
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
@dataclass(frozen=True)
|
|
24
|
+
class Dataset:
|
|
25
|
+
name: str
|
|
26
|
+
|
|
27
|
+
raw: KaggleRef
|
|
28
|
+
preprocessed: KaggleRef
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
def dataset_names(names: Iterable[str]) -> list[str]:
|
|
32
|
+
names = list(names)
|
|
33
|
+
result = list(DATASETS) if names == ['all'] else names
|
|
34
|
+
unknown = sorted(set(result) - set(DATASETS))
|
|
35
|
+
if unknown:
|
|
36
|
+
raise SystemExit('Unknown dataset(s): ' + ', '.join(unknown) + '. Available datasets: ' + ', '.join(DATASETS))
|
|
37
|
+
return result
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
def competition_slugs(names: Iterable[str]) -> list[str]:
|
|
41
|
+
return [ds.raw.slug for name in dataset_names(names) if (ds := DATASETS[name]).raw.kind == 'competition']
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
def get_raw_files(names: Iterable[str]) -> dict[str, KaggleRef]:
|
|
45
|
+
return {name: DATASETS[name].raw for name in dataset_names(names)}
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
def get_preprocessed_files(names: Iterable[str]) -> dict[str, KaggleRef]:
|
|
49
|
+
return {name: DATASETS[name].preprocessed for name in dataset_names(names)}
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
def _preprocessed_ref(name: str) -> KaggleRef:
|
|
53
|
+
return KaggleRef(
|
|
54
|
+
'dataset',
|
|
55
|
+
_TABRED_KAGGLE_DATASET,
|
|
56
|
+
f'preprocessed/{name}.tabred',
|
|
57
|
+
_PREPROCESSED_SHA256[name],
|
|
58
|
+
)
|
|
59
|
+
|
|
60
|
+
|
|
61
|
+
def _competition_dataset(name, slug):
|
|
62
|
+
return Dataset(
|
|
63
|
+
name=name,
|
|
64
|
+
raw=KaggleRef('competition', slug, f'{slug}.zip', None),
|
|
65
|
+
preprocessed=_preprocessed_ref(name),
|
|
66
|
+
)
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
def _yandex_dataset(name, filename):
|
|
70
|
+
return Dataset(
|
|
71
|
+
name=name,
|
|
72
|
+
raw=KaggleRef(
|
|
73
|
+
'dataset',
|
|
74
|
+
_TABRED_KAGGLE_DATASET,
|
|
75
|
+
f'raw/{name}/{filename}',
|
|
76
|
+
_RAW_SHA256[name],
|
|
77
|
+
local_name=filename,
|
|
78
|
+
),
|
|
79
|
+
preprocessed=_preprocessed_ref(name),
|
|
80
|
+
)
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
_PREPROCESSED_SHA256 = {
|
|
84
|
+
'cooking-time': 'ff7fb7f5be7101019164ec190831766997c28b00aefb4b902050099948435d95',
|
|
85
|
+
'delivery-eta': '097b1272e45de3a723f66d7b0d5c0a397b53a773cd5a781b8f094bfb753d5362',
|
|
86
|
+
'ecom-offers': 'de7f96400b9006eab4bfa4318993506aa667c0508da32a5e00b912b2bc702bc9',
|
|
87
|
+
'homecredit-default': 'fdcdcfe9b67e9ac8fae0291ee0aa8b492e41c123f99c9d3cecae2b78602c7f30',
|
|
88
|
+
'homesite-insurance': '9c94a9ba8a2dc68221c97d45273076714ad308b5e556ac59fd52117e1ea17d75',
|
|
89
|
+
'maps-routing': 'bdf503d49f10af2594594feb8c2ad8f4d90725bf21f1fe3de238acf0cb9f2abf',
|
|
90
|
+
'sberbank-housing': 'a6a11bc09204a5d6d0015dfae504cd630186c813a87e384eaf8caf5b960eb334',
|
|
91
|
+
'weather': 'b5dfc96c4e33d3567b748f0cc2b12baa5ea28fac400147953a3cd1cb735697e5',
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
_RAW_SHA256 = {
|
|
95
|
+
'cooking-time': '330b0b811195e7a6b75a43a7bd0ab65b52c83967c8f24d4765ccd2584c3228b9',
|
|
96
|
+
'delivery-eta': '37dc8c9479821da3539d1c42f6d97afbc4bf8b1466604839edac834ceb9e1ef5',
|
|
97
|
+
'maps-routing': '225712c539cf18503347c2d88bf4e4e9f624f180e7156a0fc4fedb19c43775b2',
|
|
98
|
+
'weather': '1984681822f14d24fbb491a8935446f9a263f48a469564c038a856b8194195e8',
|
|
99
|
+
}
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
DATASETS = {
|
|
103
|
+
name: _yandex_dataset(name, filename)
|
|
104
|
+
for name, filename in [
|
|
105
|
+
('cooking-time', 'cooking_time.parquet'),
|
|
106
|
+
('delivery-eta', 'delivery_eta.parquet'),
|
|
107
|
+
('maps-routing', 'maps_routing.parquet'),
|
|
108
|
+
('weather', 'weather.parquet'),
|
|
109
|
+
]
|
|
110
|
+
} | {
|
|
111
|
+
name: _competition_dataset(name, slug)
|
|
112
|
+
for name, slug in [
|
|
113
|
+
('sberbank-housing', 'sberbank-russian-housing-market'),
|
|
114
|
+
('ecom-offers', 'acquire-valued-shoppers-challenge'),
|
|
115
|
+
('homesite-insurance', 'homesite-quote-conversion'),
|
|
116
|
+
('homecredit-default', 'home-credit-credit-risk-model-stability'),
|
|
117
|
+
]
|
|
118
|
+
}
|