red-datasets 0.1.0 → 0.1.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +6 -0
- data/doc/text/news.md +48 -0
- data/lib/datasets.rb +7 -0
- data/lib/datasets/cifar.rb +4 -12
- data/lib/datasets/cldr-plurals.rb +385 -0
- data/lib/datasets/communities.rb +198 -0
- data/lib/datasets/dataset.rb +8 -1
- data/lib/datasets/downloader.rb +53 -27
- data/lib/datasets/e-stat-japan.rb +320 -0
- data/lib/datasets/error.rb +4 -0
- data/lib/datasets/mnist.rb +6 -4
- data/lib/datasets/penguins.rb +146 -0
- data/lib/datasets/rdatasets.rb +95 -0
- data/lib/datasets/seaborn-data.rb +49 -0
- data/lib/datasets/sudachi-synonym-dictionary.rb +171 -0
- data/lib/datasets/tar-gz-readable.rb +14 -0
- data/lib/datasets/version.rb +1 -1
- data/red-datasets.gemspec +1 -0
- data/test/run-test.rb +2 -0
- data/test/test-cldr-plurals.rb +180 -0
- data/test/test-communities.rb +290 -0
- data/test/test-dataset.rb +27 -0
- data/test/test-downloader.rb +29 -0
- data/test/test-e-stat-japan.rb +383 -0
- data/test/test-penguins.rb +251 -0
- data/test/test-rdatasets.rb +136 -0
- data/test/test-seaborn-data.rb +97 -0
- data/test/test-sudachi-synonym-dictionary.rb +48 -0
- metadata +55 -15
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
class RdatasetsTest < Test::Unit::TestCase
|
|
2
|
+
sub_test_case("RdatasetsList") do
|
|
3
|
+
def setup
|
|
4
|
+
@dataset = Datasets::RdatasetsList.new
|
|
5
|
+
end
|
|
6
|
+
|
|
7
|
+
sub_test_case("#each") do
|
|
8
|
+
test("with package_name") do
|
|
9
|
+
records = @dataset.filter(package: "datasets").to_a
|
|
10
|
+
assert_equal([
|
|
11
|
+
84,
|
|
12
|
+
{
|
|
13
|
+
package: "datasets",
|
|
14
|
+
dataset: "ability.cov",
|
|
15
|
+
title: "Ability and Intelligence Tests",
|
|
16
|
+
rows: 6,
|
|
17
|
+
cols: 8,
|
|
18
|
+
n_binary: 0,
|
|
19
|
+
n_character: 0,
|
|
20
|
+
n_factor: 0,
|
|
21
|
+
n_logical: 0,
|
|
22
|
+
n_numeric: 8,
|
|
23
|
+
csv: "https://vincentarelbundock.github.io/Rdatasets/csv/datasets/ability.cov.csv",
|
|
24
|
+
doc: "https://vincentarelbundock.github.io/Rdatasets/doc/datasets/ability.cov.html"
|
|
25
|
+
},
|
|
26
|
+
{
|
|
27
|
+
package: "datasets",
|
|
28
|
+
dataset: "WWWusage",
|
|
29
|
+
title: "Internet Usage per Minute",
|
|
30
|
+
rows: 100,
|
|
31
|
+
cols: 2,
|
|
32
|
+
n_binary: 0,
|
|
33
|
+
n_character: 0,
|
|
34
|
+
n_factor: 0,
|
|
35
|
+
n_logical: 0,
|
|
36
|
+
n_numeric: 2,
|
|
37
|
+
csv: "https://vincentarelbundock.github.io/Rdatasets/csv/datasets/WWWusage.csv",
|
|
38
|
+
doc: "https://vincentarelbundock.github.io/Rdatasets/doc/datasets/WWWusage.html"
|
|
39
|
+
}
|
|
40
|
+
],
|
|
41
|
+
[
|
|
42
|
+
records.size,
|
|
43
|
+
records[0].to_h,
|
|
44
|
+
records[-1].to_h
|
|
45
|
+
])
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
test("without package_name") do
|
|
49
|
+
records = @dataset.each.to_a
|
|
50
|
+
assert_equal([
|
|
51
|
+
1714,
|
|
52
|
+
{
|
|
53
|
+
package: "AER",
|
|
54
|
+
dataset: "Affairs",
|
|
55
|
+
title: "Fair's Extramarital Affairs Data",
|
|
56
|
+
rows: 601,
|
|
57
|
+
cols: 9,
|
|
58
|
+
n_binary: 2,
|
|
59
|
+
n_character: 0,
|
|
60
|
+
n_factor: 2,
|
|
61
|
+
n_logical: 0,
|
|
62
|
+
n_numeric: 7,
|
|
63
|
+
csv: "https://vincentarelbundock.github.io/Rdatasets/csv/AER/Affairs.csv",
|
|
64
|
+
doc: "https://vincentarelbundock.github.io/Rdatasets/doc/AER/Affairs.html"
|
|
65
|
+
},
|
|
66
|
+
{
|
|
67
|
+
package: "vcd",
|
|
68
|
+
dataset: "WomenQueue",
|
|
69
|
+
title: "Women in Queues",
|
|
70
|
+
rows: 11,
|
|
71
|
+
cols: 2,
|
|
72
|
+
n_binary: 0,
|
|
73
|
+
n_character: 0,
|
|
74
|
+
n_factor: 1,
|
|
75
|
+
n_logical: 0,
|
|
76
|
+
n_numeric: 1,
|
|
77
|
+
csv: "https://vincentarelbundock.github.io/Rdatasets/csv/vcd/WomenQueue.csv",
|
|
78
|
+
doc: "https://vincentarelbundock.github.io/Rdatasets/doc/vcd/WomenQueue.html"
|
|
79
|
+
},
|
|
80
|
+
],
|
|
81
|
+
[
|
|
82
|
+
records.size,
|
|
83
|
+
records[0].to_h,
|
|
84
|
+
records[-1].to_h
|
|
85
|
+
])
|
|
86
|
+
end
|
|
87
|
+
end
|
|
88
|
+
end
|
|
89
|
+
|
|
90
|
+
sub_test_case("Rdatasets") do
|
|
91
|
+
sub_test_case("datasets") do
|
|
92
|
+
sub_test_case("AirPassengers") do
|
|
93
|
+
def setup
|
|
94
|
+
@dataset = Datasets::Rdatasets.new("datasets", "AirPassengers")
|
|
95
|
+
end
|
|
96
|
+
|
|
97
|
+
test("#each") do
|
|
98
|
+
records = @dataset.each.to_a
|
|
99
|
+
assert_equal([
|
|
100
|
+
144,
|
|
101
|
+
{ time: 1949, value: 112 },
|
|
102
|
+
{ time: 1960.91666666667, value: 432 },
|
|
103
|
+
],
|
|
104
|
+
[
|
|
105
|
+
records.size,
|
|
106
|
+
records[0],
|
|
107
|
+
records[-1]
|
|
108
|
+
])
|
|
109
|
+
end
|
|
110
|
+
|
|
111
|
+
test("#metadata.id") do
|
|
112
|
+
assert_equal("rdatasets-datasets-AirPassengers", @dataset.metadata.id)
|
|
113
|
+
end
|
|
114
|
+
|
|
115
|
+
test("#metadata.description") do
|
|
116
|
+
description = @dataset.metadata.description
|
|
117
|
+
assert do
|
|
118
|
+
description.include?("Monthly Airline Passenger Numbers 1949-1960")
|
|
119
|
+
end
|
|
120
|
+
end
|
|
121
|
+
end
|
|
122
|
+
|
|
123
|
+
test("invalid dataset name") do
|
|
124
|
+
assert_raise(ArgumentError) do
|
|
125
|
+
Datasets::Rdatasets.new("datasets", "invalid datasets name")
|
|
126
|
+
end
|
|
127
|
+
end
|
|
128
|
+
end
|
|
129
|
+
|
|
130
|
+
test("invalid package name") do
|
|
131
|
+
assert_raise(ArgumentError) do
|
|
132
|
+
Datasets::Rdatasets.new("invalid package name", "AirPassengers")
|
|
133
|
+
end
|
|
134
|
+
end
|
|
135
|
+
end
|
|
136
|
+
end
|
|
@@ -0,0 +1,97 @@
|
|
|
1
|
+
class SeabornDataTest < Test::Unit::TestCase
|
|
2
|
+
sub_test_case("fmri") do
|
|
3
|
+
def setup
|
|
4
|
+
@dataset = Datasets::SeabornData.new("fmri")
|
|
5
|
+
end
|
|
6
|
+
|
|
7
|
+
def test_each
|
|
8
|
+
records = @dataset.each.to_a
|
|
9
|
+
assert_equal([
|
|
10
|
+
1064,
|
|
11
|
+
{
|
|
12
|
+
subject: "s5",
|
|
13
|
+
timepoint: 14,
|
|
14
|
+
event: "stim",
|
|
15
|
+
region: "parietal",
|
|
16
|
+
signal: -0.0808829319505
|
|
17
|
+
},
|
|
18
|
+
{
|
|
19
|
+
subject: "s0",
|
|
20
|
+
timepoint: 0,
|
|
21
|
+
event: "cue",
|
|
22
|
+
region: "parietal",
|
|
23
|
+
signal: -0.00689923478092
|
|
24
|
+
}
|
|
25
|
+
],
|
|
26
|
+
[
|
|
27
|
+
records.size,
|
|
28
|
+
records[1].to_h,
|
|
29
|
+
records[-1].to_h
|
|
30
|
+
])
|
|
31
|
+
end
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
sub_test_case("flights") do
|
|
35
|
+
def setup
|
|
36
|
+
@dataset = Datasets::SeabornData.new("flights")
|
|
37
|
+
end
|
|
38
|
+
|
|
39
|
+
def test_each
|
|
40
|
+
records = @dataset.each.to_a
|
|
41
|
+
assert_equal([
|
|
42
|
+
144,
|
|
43
|
+
{
|
|
44
|
+
year: 1949,
|
|
45
|
+
month: "Feb",
|
|
46
|
+
passengers: 118
|
|
47
|
+
},
|
|
48
|
+
{
|
|
49
|
+
year: 1960,
|
|
50
|
+
month: "Dec",
|
|
51
|
+
passengers: 432
|
|
52
|
+
}
|
|
53
|
+
],
|
|
54
|
+
[
|
|
55
|
+
records.size,
|
|
56
|
+
records[1].to_h,
|
|
57
|
+
records[-1].to_h
|
|
58
|
+
])
|
|
59
|
+
end
|
|
60
|
+
end
|
|
61
|
+
|
|
62
|
+
sub_test_case("penguins") do
|
|
63
|
+
def setup
|
|
64
|
+
@dataset = Datasets::SeabornData.new("penguins")
|
|
65
|
+
end
|
|
66
|
+
|
|
67
|
+
def test_each
|
|
68
|
+
records = @dataset.each.to_a
|
|
69
|
+
assert_equal([
|
|
70
|
+
344,
|
|
71
|
+
{
|
|
72
|
+
species: "Adelie",
|
|
73
|
+
island: "Torgersen",
|
|
74
|
+
bill_length_mm: 39.5,
|
|
75
|
+
bill_depth_mm: 17.4,
|
|
76
|
+
flipper_length_mm: 186,
|
|
77
|
+
body_mass_g: 3800,
|
|
78
|
+
sex: "Female"
|
|
79
|
+
},
|
|
80
|
+
{
|
|
81
|
+
species: "Gentoo",
|
|
82
|
+
island: "Biscoe",
|
|
83
|
+
bill_length_mm: 49.9,
|
|
84
|
+
bill_depth_mm: 16.1,
|
|
85
|
+
flipper_length_mm: 213,
|
|
86
|
+
body_mass_g: 5400,
|
|
87
|
+
sex: "Male"
|
|
88
|
+
}
|
|
89
|
+
],
|
|
90
|
+
[
|
|
91
|
+
records.size,
|
|
92
|
+
records[1].to_h,
|
|
93
|
+
records[-1].to_h
|
|
94
|
+
])
|
|
95
|
+
end
|
|
96
|
+
end
|
|
97
|
+
end
|
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
class SudachiSynonymDictionaryTest < Test::Unit::TestCase
|
|
2
|
+
def setup
|
|
3
|
+
@dataset = Datasets::SudachiSynonymDictionary.new
|
|
4
|
+
end
|
|
5
|
+
|
|
6
|
+
test('#each') do
|
|
7
|
+
records = @dataset.each.to_a
|
|
8
|
+
assert_equal([
|
|
9
|
+
61335,
|
|
10
|
+
{
|
|
11
|
+
group_id: "000001",
|
|
12
|
+
is_noun: true,
|
|
13
|
+
expansion_type: :always,
|
|
14
|
+
lexeme_id: 1,
|
|
15
|
+
form_type: :typical,
|
|
16
|
+
acronym_type: :typical,
|
|
17
|
+
variant_type: :typical,
|
|
18
|
+
categories: [],
|
|
19
|
+
notation: "曖昧",
|
|
20
|
+
},
|
|
21
|
+
{
|
|
22
|
+
group_id: "023705",
|
|
23
|
+
is_noun: true,
|
|
24
|
+
expansion_type: :always,
|
|
25
|
+
lexeme_id: 1,
|
|
26
|
+
form_type: :typical,
|
|
27
|
+
acronym_type: :alphabet,
|
|
28
|
+
variant_type: :typical,
|
|
29
|
+
categories: ["単位"],
|
|
30
|
+
notation: "GB",
|
|
31
|
+
},
|
|
32
|
+
],
|
|
33
|
+
[
|
|
34
|
+
records.size,
|
|
35
|
+
records[0].to_h,
|
|
36
|
+
records[-1].to_h,
|
|
37
|
+
])
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
sub_test_case('#metadata') do
|
|
41
|
+
test('#description') do
|
|
42
|
+
description = @dataset.metadata.description
|
|
43
|
+
assert do
|
|
44
|
+
description.start_with?('# Sudachi 同義語辞書')
|
|
45
|
+
end
|
|
46
|
+
end
|
|
47
|
+
end
|
|
48
|
+
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: 0.1.
|
|
4
|
+
version: 0.1.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- tomisuker
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date:
|
|
12
|
+
date: 2021-07-13 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: csv
|
|
@@ -25,6 +25,20 @@ dependencies:
|
|
|
25
25
|
- - ">="
|
|
26
26
|
- !ruby/object:Gem::Version
|
|
27
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'
|
|
28
42
|
- !ruby/object:Gem::Dependency
|
|
29
43
|
name: rubyzip
|
|
30
44
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -129,9 +143,13 @@ files:
|
|
|
129
143
|
- lib/datasets.rb
|
|
130
144
|
- lib/datasets/adult.rb
|
|
131
145
|
- lib/datasets/cifar.rb
|
|
146
|
+
- lib/datasets/cldr-plurals.rb
|
|
147
|
+
- lib/datasets/communities.rb
|
|
132
148
|
- lib/datasets/dataset.rb
|
|
133
149
|
- lib/datasets/dictionary.rb
|
|
134
150
|
- lib/datasets/downloader.rb
|
|
151
|
+
- lib/datasets/e-stat-japan.rb
|
|
152
|
+
- lib/datasets/error.rb
|
|
135
153
|
- lib/datasets/fashion-mnist.rb
|
|
136
154
|
- lib/datasets/hepatitis.rb
|
|
137
155
|
- lib/datasets/iris.rb
|
|
@@ -140,9 +158,14 @@ files:
|
|
|
140
158
|
- lib/datasets/metadata.rb
|
|
141
159
|
- lib/datasets/mnist.rb
|
|
142
160
|
- lib/datasets/mushroom.rb
|
|
161
|
+
- lib/datasets/penguins.rb
|
|
143
162
|
- lib/datasets/penn-treebank.rb
|
|
144
163
|
- lib/datasets/postal-code-japan.rb
|
|
164
|
+
- lib/datasets/rdatasets.rb
|
|
165
|
+
- lib/datasets/seaborn-data.rb
|
|
166
|
+
- lib/datasets/sudachi-synonym-dictionary.rb
|
|
145
167
|
- lib/datasets/table.rb
|
|
168
|
+
- lib/datasets/tar-gz-readable.rb
|
|
146
169
|
- lib/datasets/version.rb
|
|
147
170
|
- lib/datasets/wikipedia.rb
|
|
148
171
|
- lib/datasets/wine.rb
|
|
@@ -151,7 +174,12 @@ files:
|
|
|
151
174
|
- test/run-test.rb
|
|
152
175
|
- test/test-adult.rb
|
|
153
176
|
- test/test-cifar.rb
|
|
177
|
+
- test/test-cldr-plurals.rb
|
|
178
|
+
- test/test-communities.rb
|
|
179
|
+
- test/test-dataset.rb
|
|
154
180
|
- test/test-dictionary.rb
|
|
181
|
+
- test/test-downloader.rb
|
|
182
|
+
- test/test-e-stat-japan.rb
|
|
155
183
|
- test/test-fashion-mnist.rb
|
|
156
184
|
- test/test-hepatitis.rb
|
|
157
185
|
- test/test-iris.rb
|
|
@@ -159,8 +187,12 @@ files:
|
|
|
159
187
|
- test/test-libsvm.rb
|
|
160
188
|
- test/test-mnist.rb
|
|
161
189
|
- test/test-mushroom.rb
|
|
190
|
+
- test/test-penguins.rb
|
|
162
191
|
- test/test-penn-treebank.rb
|
|
163
192
|
- test/test-postal-code-japan.rb
|
|
193
|
+
- test/test-rdatasets.rb
|
|
194
|
+
- test/test-seaborn-data.rb
|
|
195
|
+
- test/test-sudachi-synonym-dictionary.rb
|
|
164
196
|
- test/test-table.rb
|
|
165
197
|
- test/test-wikipedia.rb
|
|
166
198
|
- test/test-wine.rb
|
|
@@ -183,26 +215,34 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
183
215
|
- !ruby/object:Gem::Version
|
|
184
216
|
version: '0'
|
|
185
217
|
requirements: []
|
|
186
|
-
|
|
187
|
-
rubygems_version: 2.7.6.2
|
|
218
|
+
rubygems_version: 3.3.0.dev
|
|
188
219
|
signing_key:
|
|
189
220
|
specification_version: 4
|
|
190
221
|
summary: Red Datasets provides classes that provide common datasets such as iris dataset.
|
|
191
222
|
test_files:
|
|
192
|
-
- test/test-wine.rb
|
|
193
|
-
- test/test-iris.rb
|
|
194
|
-
- test/test-wikipedia.rb
|
|
195
|
-
- test/test-mnist.rb
|
|
196
223
|
- test/helper.rb
|
|
197
|
-
- test/test-penn-treebank.rb
|
|
198
224
|
- test/run-test.rb
|
|
199
|
-
- test/test-
|
|
200
|
-
- test/test-fashion-mnist.rb
|
|
225
|
+
- test/test-adult.rb
|
|
201
226
|
- test/test-cifar.rb
|
|
227
|
+
- test/test-cldr-plurals.rb
|
|
228
|
+
- test/test-communities.rb
|
|
229
|
+
- test/test-dataset.rb
|
|
202
230
|
- test/test-dictionary.rb
|
|
203
|
-
- test/test-
|
|
204
|
-
- test/test-
|
|
231
|
+
- test/test-downloader.rb
|
|
232
|
+
- test/test-e-stat-japan.rb
|
|
233
|
+
- test/test-fashion-mnist.rb
|
|
205
234
|
- test/test-hepatitis.rb
|
|
206
|
-
- test/test-
|
|
207
|
-
- test/test-
|
|
235
|
+
- test/test-iris.rb
|
|
236
|
+
- test/test-libsvm-dataset-list.rb
|
|
208
237
|
- test/test-libsvm.rb
|
|
238
|
+
- test/test-mnist.rb
|
|
239
|
+
- test/test-mushroom.rb
|
|
240
|
+
- test/test-penguins.rb
|
|
241
|
+
- test/test-penn-treebank.rb
|
|
242
|
+
- test/test-postal-code-japan.rb
|
|
243
|
+
- test/test-rdatasets.rb
|
|
244
|
+
- test/test-seaborn-data.rb
|
|
245
|
+
- test/test-sudachi-synonym-dictionary.rb
|
|
246
|
+
- test/test-table.rb
|
|
247
|
+
- test/test-wikipedia.rb
|
|
248
|
+
- test/test-wine.rb
|