red-datasets 0.0.6 → 0.1.1

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.
Files changed (46) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +23 -7
  3. data/doc/text/news.md +124 -0
  4. data/lib/datasets.rb +18 -6
  5. data/lib/datasets/adult.rb +84 -0
  6. data/lib/datasets/cldr-plurals.rb +385 -0
  7. data/lib/datasets/communities.rb +198 -0
  8. data/lib/datasets/dataset.rb +13 -0
  9. data/lib/datasets/dictionary.rb +59 -0
  10. data/lib/datasets/downloader.rb +37 -62
  11. data/lib/datasets/e-stat-japan.rb +320 -0
  12. data/lib/datasets/error.rb +4 -0
  13. data/lib/datasets/fashion-mnist.rb +12 -0
  14. data/lib/datasets/hepatitis.rb +207 -0
  15. data/lib/datasets/iris.rb +1 -1
  16. data/lib/datasets/libsvm-dataset-list.rb +277 -0
  17. data/lib/datasets/libsvm.rb +135 -0
  18. data/lib/datasets/mnist.rb +11 -8
  19. data/lib/datasets/mushroom.rb +256 -0
  20. data/lib/datasets/penguins.rb +125 -0
  21. data/lib/datasets/penn-treebank.rb +2 -9
  22. data/lib/datasets/postal-code-japan.rb +154 -0
  23. data/lib/datasets/table.rb +99 -3
  24. data/lib/datasets/version.rb +1 -1
  25. data/lib/datasets/wikipedia.rb +2 -10
  26. data/lib/datasets/wine.rb +64 -0
  27. data/red-datasets.gemspec +4 -0
  28. data/test/helper.rb +1 -0
  29. data/test/run-test.rb +2 -0
  30. data/test/test-adult.rb +126 -0
  31. data/test/test-cldr-plurals.rb +180 -0
  32. data/test/test-communities.rb +290 -0
  33. data/test/test-dictionary.rb +43 -0
  34. data/test/test-e-stat-japan.rb +383 -0
  35. data/test/test-fashion-mnist.rb +137 -0
  36. data/test/test-hepatitis.rb +74 -0
  37. data/test/test-libsvm-dataset-list.rb +47 -0
  38. data/test/test-libsvm.rb +205 -0
  39. data/test/test-mnist.rb +95 -70
  40. data/test/test-mushroom.rb +80 -0
  41. data/test/test-penguins.rb +239 -0
  42. data/test/test-penn-treebank.rb +6 -6
  43. data/test/test-postal-code-japan.rb +69 -0
  44. data/test/test-table.rb +144 -19
  45. data/test/test-wine.rb +58 -0
  46. metadata +89 -8
data/test/test-wine.rb ADDED
@@ -0,0 +1,58 @@
1
+ class WineTest < Test::Unit::TestCase
2
+ def setup
3
+ @dataset = Datasets::Wine.new
4
+ end
5
+
6
+ test('#each') do
7
+ records = @dataset.each.to_a
8
+ assert_equal([
9
+ 178,
10
+ {
11
+ :alcalinity_of_ash => 15.6,
12
+ :alcohol => 14.23,
13
+ :ash => 2.43,
14
+ :label => 1,
15
+ :color_intensity => 5.64,
16
+ :hue => 1.04,
17
+ :malic_acid => 1.71,
18
+ :total_flavonoids => 3.06,
19
+ :n_magnesiums => 127,
20
+ :total_nonflavanoid_phenols => 0.28,
21
+ :total_proanthocyanins => 2.29,
22
+ :n_prolines => 1065,
23
+ :optical_nucleic_acid_concentration => 3.92,
24
+ :total_phenols => 2.8
25
+ },
26
+ {
27
+ :alcalinity_of_ash => 24.5,
28
+ :alcohol => 14.13,
29
+ :ash => 2.74,
30
+ :label => 3,
31
+ :color_intensity => 9.2,
32
+ :hue => 0.61,
33
+ :malic_acid => 4.1,
34
+ :total_flavonoids => 0.76,
35
+ :n_magnesiums => 96,
36
+ :total_nonflavanoid_phenols => 0.56,
37
+ :total_proanthocyanins => 1.35,
38
+ :n_prolines => 560,
39
+ :optical_nucleic_acid_concentration => 1.6,
40
+ :total_phenols => 2.05,
41
+ },
42
+ ],
43
+ [
44
+ records.size,
45
+ records[0].to_h,
46
+ records[-1].to_h,
47
+ ])
48
+ end
49
+
50
+ sub_test_case('#metadata') do
51
+ test('#description') do
52
+ description = @dataset.metadata.description
53
+ assert do
54
+ description.start_with?('1. Title of Database: Wine recognition data')
55
+ end
56
+ end
57
+ end
58
+ end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: red-datasets
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.6
4
+ version: 0.1.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - tomisuker
@@ -9,8 +9,50 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2018-07-25 00:00:00.000000000 Z
12
+ date: 2021-04-11 00:00:00.000000000 Z
13
13
  dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: csv
16
+ requirement: !ruby/object:Gem::Requirement
17
+ requirements:
18
+ - - ">="
19
+ - !ruby/object:Gem::Version
20
+ version: 3.0.5
21
+ type: :runtime
22
+ prerelease: false
23
+ version_requirements: !ruby/object:Gem::Requirement
24
+ requirements:
25
+ - - ">="
26
+ - !ruby/object:Gem::Version
27
+ version: 3.0.5
28
+ - !ruby/object:Gem::Dependency
29
+ name: rexml
30
+ requirement: !ruby/object:Gem::Requirement
31
+ requirements:
32
+ - - ">="
33
+ - !ruby/object:Gem::Version
34
+ version: '0'
35
+ type: :runtime
36
+ prerelease: false
37
+ version_requirements: !ruby/object:Gem::Requirement
38
+ requirements:
39
+ - - ">="
40
+ - !ruby/object:Gem::Version
41
+ version: '0'
42
+ - !ruby/object:Gem::Dependency
43
+ name: rubyzip
44
+ requirement: !ruby/object:Gem::Requirement
45
+ requirements:
46
+ - - ">="
47
+ - !ruby/object:Gem::Version
48
+ version: '0'
49
+ type: :runtime
50
+ prerelease: false
51
+ version_requirements: !ruby/object:Gem::Requirement
52
+ requirements:
53
+ - - ">="
54
+ - !ruby/object:Gem::Version
55
+ version: '0'
14
56
  - !ruby/object:Gem::Dependency
15
57
  name: bundler
16
58
  requirement: !ruby/object:Gem::Requirement
@@ -84,7 +126,7 @@ dependencies:
84
126
  description: 'You can use datasets easily because you can access each dataset with
85
127
  multiple ways such as `#each` and Apache Arrow Record Batch.
86
128
 
87
- '
129
+ '
88
130
  email:
89
131
  - tomisuker16@gmail.com
90
132
  - kou@clear-code.com
@@ -99,25 +141,52 @@ files:
99
141
  - Rakefile
100
142
  - doc/text/news.md
101
143
  - lib/datasets.rb
144
+ - lib/datasets/adult.rb
102
145
  - lib/datasets/cifar.rb
146
+ - lib/datasets/cldr-plurals.rb
147
+ - lib/datasets/communities.rb
103
148
  - lib/datasets/dataset.rb
149
+ - lib/datasets/dictionary.rb
104
150
  - lib/datasets/downloader.rb
151
+ - lib/datasets/e-stat-japan.rb
152
+ - lib/datasets/error.rb
153
+ - lib/datasets/fashion-mnist.rb
154
+ - lib/datasets/hepatitis.rb
105
155
  - lib/datasets/iris.rb
156
+ - lib/datasets/libsvm-dataset-list.rb
157
+ - lib/datasets/libsvm.rb
106
158
  - lib/datasets/metadata.rb
107
159
  - lib/datasets/mnist.rb
160
+ - lib/datasets/mushroom.rb
161
+ - lib/datasets/penguins.rb
108
162
  - lib/datasets/penn-treebank.rb
163
+ - lib/datasets/postal-code-japan.rb
109
164
  - lib/datasets/table.rb
110
165
  - lib/datasets/version.rb
111
166
  - lib/datasets/wikipedia.rb
167
+ - lib/datasets/wine.rb
112
168
  - red-datasets.gemspec
113
169
  - test/helper.rb
114
170
  - test/run-test.rb
171
+ - test/test-adult.rb
115
172
  - test/test-cifar.rb
173
+ - test/test-cldr-plurals.rb
174
+ - test/test-communities.rb
175
+ - test/test-dictionary.rb
176
+ - test/test-e-stat-japan.rb
177
+ - test/test-fashion-mnist.rb
178
+ - test/test-hepatitis.rb
116
179
  - test/test-iris.rb
180
+ - test/test-libsvm-dataset-list.rb
181
+ - test/test-libsvm.rb
117
182
  - test/test-mnist.rb
183
+ - test/test-mushroom.rb
184
+ - test/test-penguins.rb
118
185
  - test/test-penn-treebank.rb
186
+ - test/test-postal-code-japan.rb
119
187
  - test/test-table.rb
120
188
  - test/test-wikipedia.rb
189
+ - test/test-wine.rb
121
190
  homepage: https://github.com/red-data-tools/red-datasets
122
191
  licenses:
123
192
  - MIT
@@ -137,17 +206,29 @@ required_rubygems_version: !ruby/object:Gem::Requirement
137
206
  - !ruby/object:Gem::Version
138
207
  version: '0'
139
208
  requirements: []
140
- rubyforge_project:
141
- rubygems_version: 3.0.0.beta1
209
+ rubygems_version: 3.3.0.dev
142
210
  signing_key:
143
211
  specification_version: 4
144
212
  summary: Red Datasets provides classes that provide common datasets such as iris dataset.
145
213
  test_files:
214
+ - test/helper.rb
146
215
  - test/run-test.rb
216
+ - test/test-adult.rb
147
217
  - test/test-cifar.rb
148
- - test/test-wikipedia.rb
218
+ - test/test-cldr-plurals.rb
219
+ - test/test-communities.rb
220
+ - test/test-dictionary.rb
221
+ - test/test-e-stat-japan.rb
222
+ - test/test-fashion-mnist.rb
223
+ - test/test-hepatitis.rb
149
224
  - test/test-iris.rb
150
- - test/helper.rb
225
+ - test/test-libsvm-dataset-list.rb
226
+ - test/test-libsvm.rb
151
227
  - test/test-mnist.rb
152
- - test/test-table.rb
228
+ - test/test-mushroom.rb
229
+ - test/test-penguins.rb
153
230
  - test/test-penn-treebank.rb
231
+ - test/test-postal-code-japan.rb
232
+ - test/test-table.rb
233
+ - test/test-wikipedia.rb
234
+ - test/test-wine.rb