libsvmloader 0.1.3 → 0.2.0

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 (11) hide show
  1. checksums.yaml +5 -5
  2. data/.coveralls.yml +1 -0
  3. data/.gitignore +9 -0
  4. data/.rubocop.yml +6 -0
  5. data/.travis.yml +6 -1
  6. data/HISTORY.md +6 -0
  7. data/README.md +30 -1
  8. data/lib/libsvmloader.rb +71 -51
  9. data/lib/libsvmloader/version.rb +3 -1
  10. data/libsvmloader.gemspec +2 -3
  11. metadata +12 -11
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
- SHA1:
3
- metadata.gz: a02d403d7d0960462edd290a33ac4b41c3aea2db
4
- data.tar.gz: fd5fa99a1dd15d76c60c2dcf5ef2361f92fc5e65
2
+ SHA256:
3
+ metadata.gz: e887dc00c4c665e3bf78221650a6740440cf9d07549c01bc47ccfb6940825ddd
4
+ data.tar.gz: bff658751c419564ccbac3896307a2a1799d46ef7370fd5528e641f35073089b
5
5
  SHA512:
6
- metadata.gz: 44400787b97fd5933c36c23b83458ff9628d38829f7e12479aec87425adf6a88312bebc769ad7f89dd1f1fcade3fe785772e97dbb39d54ba075c6a7410dd4404
7
- data.tar.gz: d1d336f24796652fdf203dc773853403cc980ccfc4f3c02e7e7da476e669be2cdbeb5c4bf076c72ad7ce1160dff4fb74a3dbff966e399efd4d2fd32767eb6738
6
+ metadata.gz: ab4062fbd21fdddb5b139e6fef498234e04588e858f172042265f2f2ef33f9f06e60f147e52f56a022a12a2e10d527f3d0c6c64d815651a32cd6741ef488dadd
7
+ data.tar.gz: 8ca0ffb36321df79bb6fd018d2e45d7a6c600371d852ef70ffad644eebcb7273dfb011f34596c3492cd9a1c42b13516ff8b8341df6d2d996e0d660613d3c809a
data/.coveralls.yml ADDED
@@ -0,0 +1 @@
1
+ service_name: travis-ci
data/.gitignore CHANGED
@@ -8,5 +8,14 @@
8
8
  /spec/reports/
9
9
  /tmp/
10
10
 
11
+
11
12
  # rspec failure tracking
12
13
  .rspec_status
14
+
15
+ *.swp
16
+ .DS_Store
17
+ .ruby-version
18
+ /spec/dump_cmp.t
19
+ /spec/dump_dbl.t
20
+ /spec/dump_int.t
21
+ /spec/dump_zb.t
data/.rubocop.yml CHANGED
@@ -6,3 +6,9 @@ Metrics/ModuleLength:
6
6
 
7
7
  Metrics/ClassLength:
8
8
  Max: 200
9
+
10
+ Metrics/MethodLength:
11
+ Max: 40
12
+
13
+ Style/FormatStringToken:
14
+ Enabled: false
data/.travis.yml CHANGED
@@ -1,5 +1,10 @@
1
1
  sudo: false
2
+ os: linux
3
+ dist: trusty
2
4
  language: ruby
3
5
  rvm:
4
- - 2.4.1
6
+ - 2.2
7
+ - 2.3
8
+ - 2.4
9
+ - 2.5
5
10
  before_install: gem install bundler -v 1.15.3
data/HISTORY.md CHANGED
@@ -1,3 +1,9 @@
1
+ # 0.2.0
2
+ ## Breaking changes
3
+
4
+ LibSVMLoader has been modified to return the samples and labels of dataset as Ruby Array.
5
+ Thus, LibSVMLoader does not require NMatrix.
6
+
1
7
  # 0.1.3
2
8
  - Changed the visibility of protected methods to the private.
3
9
  - Fixed the description in the gemspec file.
data/README.md CHANGED
@@ -1,6 +1,7 @@
1
1
  # LibSVMLoader
2
2
 
3
3
  [![Build Status](https://travis-ci.org/yoshoku/LibSVMLoader.svg?branch=master)](https://travis-ci.org/yoshoku/LibSVMLoader)
4
+ [![Coverage Status](https://coveralls.io/repos/github/yoshoku/LibSVMLoader/badge.svg?branch=master)](https://coveralls.io/github/yoshoku/LibSVMLoader?branch=master)
4
5
  [![Gem Version](https://badge.fury.io/rb/libsvmloader.svg)](https://badge.fury.io/rb/libsvmloader)
5
6
  [![MIT License](https://img.shields.io/badge/License-MIT-blue.svg)](https://github.com/yoshoku/LibSVMLoader/blob/master/LICENSE.txt)
6
7
 
@@ -32,10 +33,38 @@ samples, labels = LibSVMLoader.load_libsvm_file('foo.t')
32
33
  LibSVMLoader.dump_libsvm_file(samples, labels, 'bar.t')
33
34
 
34
35
  # for regression task
35
- samples, target_variables = LibSVMLoader.load_libsvm_file('foo.t', label_dtype: :float64)
36
+ samples, target_variables = LibSVMLoader.load_libsvm_file('foo.t', label_dtype: 'float')
36
37
  LibSVMLoader.dump_libsvm_file(samples, target_variables, 'bar.t')
37
38
  ```
38
39
 
40
+ When using with Numo::NArray:
41
+
42
+ ```ruby
43
+ require 'libsvmloader'
44
+ require 'numo/narray'
45
+
46
+ samples, labels = LibSVMLoader.load_libsvm_file('foo.t')
47
+
48
+ samples_na = Numo::NArray[*samples]
49
+ labels_na = Numo::NArray[*labels]
50
+
51
+ LibSVMLoader.dump_libsvm_file(samples_na.to_a, labels_na.to_a, 'bar.t')
52
+ ```
53
+
54
+ When using with NMatrix:
55
+
56
+ ```ruby
57
+ require 'libsvmloader'
58
+ require 'nmatrix/nmatrix'
59
+
60
+ samples, labels = LibSVMLoader.load_libsvm_file('foo.t')
61
+
62
+ samples_nm = N[*samples]
63
+ labels_nm = N[*labels]
64
+
65
+ LibSVMLoader.dump_libsvm_file(samples_nm.to_a, labels_nm.to_a, 'bar.t')
66
+ ```
67
+
39
68
  ## Development
40
69
 
41
70
  After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
data/lib/libsvmloader.rb CHANGED
@@ -1,92 +1,112 @@
1
+ # frozen_string_literal: true
1
2
 
2
3
  require 'libsvmloader/version'
3
- require 'nmatrix/nmatrix'
4
+ require 'csv'
4
5
 
5
6
  # LibSVMLoader loads (and dumps) dataset file with the libsvm file format.
6
7
  class LibSVMLoader
7
8
  class << self
8
- # Load a dataset with the libsvm file format into NMatrix.
9
+ # Load a dataset with the libsvm file format.
9
10
  #
10
- # @param filename [String] A path to a dataset file.
11
+ # @param filename [String] Path to a dataset file.
11
12
  # @param zero_based [Boolean] Whether the column index starts from 0 (true) or 1 (false).
12
- # @param stype [Symbol] The strorage type of the nmatrix consisting of feature vectors.
13
- # @param label_dtype [Symbol] The data type of the NMatrix consisting of labels or target values.
14
- # @param value_dtype [Symbol] The data type of the NMatrix consisting of feature vectors.
13
+ # @param label_dtype [String] Data type of labels or target values ('int', 'float', 'complex').
14
+ # @param value_dtype [String] Data type of feature vectors ('int', 'float', 'complex').
15
15
  #
16
- # @return [Array<NMatrix>]
16
+ # @return [Array<Array>]
17
17
  # Returns array containing the (n_samples x n_features) matrix for feature vectors
18
- # and (n_samples x 1) matrix for labels or target values.
19
- def load_libsvm_file(filename, zero_based: false, stype: :yale, label_dtype: :int32, value_dtype: :float64)
20
- ftvecs = []
18
+ # and (n_samples) vector for labels or target values.
19
+ def load_libsvm_file(filename, zero_based: false, label_dtype: 'int', value_dtype: 'float')
21
20
  labels = []
22
- n_features = 0
23
- File.read(filename).split("\n").each do |line|
24
- label, ftvec, max_idx = parse_libsvm_line(line, zero_based)
21
+ ftvecs = []
22
+ maxids = []
23
+ label_class = parse_dtype(label_dtype)
24
+ value_class = parse_dtype(value_dtype)
25
+ CSV.foreach(filename, col_sep: "\s", headers: false) do |row|
26
+ label, ftvec, maxid = parse_libsvm_row(row, zero_based, label_class, value_class)
25
27
  labels.push(label)
26
28
  ftvecs.push(ftvec)
27
- n_features = [n_features, max_idx].max
29
+ maxids.push(maxid)
28
30
  end
29
- [convert_to_nmatrix(ftvecs, n_features, value_dtype, stype),
30
- NMatrix.new([labels.size, 1], labels, dtype: label_dtype)]
31
+ [convert_to_matrix(ftvecs, maxids.max + 1, value_class), labels]
31
32
  end
32
33
 
33
34
  # Dump the dataset with the libsvm file format.
34
35
  #
35
- # @param data [NMatrix] (n_samples x n_features) matrix consisting of feature vectors.
36
- # @param labels [NMatrix] (n_samples x 1) matrix consisting of labels or target values.
37
- # @param filename [String] A path to the output libsvm file.
36
+ # @param data [Array] (n_samples x n_features) matrix consisting of feature vectors.
37
+ # @param labels [Array] (n_samples) vector consisting of labels or target values.
38
+ # @param filename [String] Path to the output libsvm file.
38
39
  # @param zero_based [Boolean] Whether the column index starts from 0 (true) or 1 (false).
39
40
  def dump_libsvm_file(data, labels, filename, zero_based: false)
40
- n_samples = [data.rows, labels.rows].min
41
- label_type = detect_dtype(labels)
42
- value_type = detect_dtype(data)
41
+ n_samples = [data.size, labels.size].min
42
+ label_format = detect_format(labels.first)
43
+ value_format = detect_format(data.flatten.first)
43
44
  File.open(filename, 'w') do |file|
44
- n_samples.times do |n|
45
- file.puts(dump_libsvm_line(labels[n], data.row(n),
46
- label_type, value_type, zero_based))
47
- end
45
+ n_samples.times { |n| file.puts(dump_libsvm_line(labels[n], data[n], label_format, value_format, zero_based)) }
48
46
  end
49
47
  end
50
48
 
51
49
  private
52
50
 
53
- def parse_libsvm_line(line, zero_based)
54
- tokens = line.split
55
- label = tokens.shift.to_f
56
- ftvec = tokens.map do |el|
51
+ def parse_libsvm_row(row, zero_based, label_type, value_type)
52
+ label = convert_type(row.shift, label_type)
53
+ ftvec = row.map do |el|
57
54
  idx, val = el.split(':')
58
- idx = idx.to_i - (zero_based == false ? 1 : 0)
59
- [idx, val.to_f]
55
+ [idx.to_i - (zero_based == false ? 1 : 0), convert_type(val, value_type)]
60
56
  end
61
- max_idx = ftvec.map { |el| el[0] }.max
62
- max_idx ||= 0
57
+ max_idx = ftvec.map { |idx, _val| idx }.max || 0
63
58
  [label, ftvec, max_idx]
64
59
  end
65
60
 
66
- def convert_to_nmatrix(data, n_features, value_dtype, stype)
67
- n_samples = data.size
68
- mat = NMatrix.zeros([n_samples, n_features + 1],
69
- dtype: value_dtype, stype: stype)
70
- data.each_with_index do |ftvec, n|
71
- ftvec.each do |el|
72
- mat[n, el[0]] = el[1]
73
- end
61
+ def parse_dtype(dtype)
62
+ case dtype.to_s
63
+ when /^(int)/i
64
+ :int
65
+ when /^(float)/i
66
+ :float
67
+ when /^(complex)/i
68
+ :complex
69
+ else
70
+ :string
74
71
  end
75
- mat
76
72
  end
77
73
 
78
- def detect_dtype(data)
74
+ def convert_type(value, dtype)
75
+ case dtype
76
+ when :int
77
+ value.to_i
78
+ when :float
79
+ value.to_f
80
+ when :complex
81
+ value.to_c
82
+ else
83
+ value
84
+ end
85
+ end
86
+
87
+ def convert_to_matrix(data, n_features, value_type)
88
+ z = convert_type(0, value_type)
89
+ data.map do |ft|
90
+ vec = Array.new(n_features) { z }
91
+ ft.each { |idx, val| vec[idx] = val }
92
+ vec
93
+ end
94
+ end
95
+
96
+ def detect_format(data)
79
97
  type = '%s'
80
- type = '%d' if %i[int8 int16 int32 int64].include?(data.dtype)
81
- type = '%.10g' if %i[float32 float64].include?(data.dtype)
98
+ type = '%d' if data.is_a?(Integer)
99
+ type = '%.10g' if data.is_a?(Float)
82
100
  type
83
101
  end
84
102
 
85
- def dump_libsvm_line(label, ftvec, label_type, value_type, zero_based)
86
- line = format(label_type.to_s, label)
87
- ftvec.to_a.each_with_index do |val, n|
88
- idx = n + (zero_based == false ? 1 : 0)
89
- line += format(" %d:#{value_type}", idx, val) if val != 0.0
103
+ def dump_libsvm_line(label, ftvec, label_format, value_format, zero_based)
104
+ line = format(label_format, label)
105
+ ftvec.each_with_index do |val, n|
106
+ unless val.zero?
107
+ idx = n + (zero_based == false ? 1 : 0)
108
+ line += format(" %d:#{value_format}", idx, val)
109
+ end
90
110
  end
91
111
  line
92
112
  end
data/lib/libsvmloader/version.rb CHANGED
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  class LibSVMLoader
2
- VERSION = '0.1.3'.freeze
4
+ VERSION = '0.2.0'.freeze
3
5
  end
data/libsvmloader.gemspec CHANGED
@@ -14,7 +14,7 @@ LibSVMLoader loads (and dumps) dataset file with the libsvm file format.
14
14
  MSG
15
15
  spec.description = <<MSG
16
16
  LibSVMLoader is a class that loads (and dumps) dataset file with the libsvm file format.
17
- The sample matrix for feature vectors and target vector for labels are represented by the NMatrix format.
17
+ The feature vectors and labels of dataset are represented by Ruby Array.
18
18
  MSG
19
19
  spec.homepage = 'https://github.com/yoshoku/libsvmloader'
20
20
  spec.license = 'MIT'
@@ -28,9 +28,8 @@ MSG
28
28
 
29
29
  spec.required_ruby_version = '>= 2.1'
30
30
 
31
- spec.add_runtime_dependency 'nmatrix', '~> 0.2.3'
32
-
33
31
  spec.add_development_dependency 'bundler', '~> 1.15'
32
+ spec.add_development_dependency 'coveralls', '~> 0.8'
34
33
  spec.add_development_dependency 'rake', '~> 10.0'
35
34
  spec.add_development_dependency 'rspec', '~> 3.0'
36
35
  end
metadata CHANGED
@@ -1,43 +1,43 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: libsvmloader
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.3
4
+ version: 0.2.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - yoshoku
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2018-01-07 00:00:00.000000000 Z
11
+ date: 2018-08-25 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
- name: nmatrix
14
+ name: bundler
15
15
  requirement: !ruby/object:Gem::Requirement
16
16
  requirements:
17
17
  - - "~>"
18
18
  - !ruby/object:Gem::Version
19
- version: 0.2.3
20
- type: :runtime
19
+ version: '1.15'
20
+ type: :development
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
24
  - - "~>"
25
25
  - !ruby/object:Gem::Version
26
- version: 0.2.3
26
+ version: '1.15'
27
27
  - !ruby/object:Gem::Dependency
28
- name: bundler
28
+ name: coveralls
29
29
  requirement: !ruby/object:Gem::Requirement
30
30
  requirements:
31
31
  - - "~>"
32
32
  - !ruby/object:Gem::Version
33
- version: '1.15'
33
+ version: '0.8'
34
34
  type: :development
35
35
  prerelease: false
36
36
  version_requirements: !ruby/object:Gem::Requirement
37
37
  requirements:
38
38
  - - "~>"
39
39
  - !ruby/object:Gem::Version
40
- version: '1.15'
40
+ version: '0.8'
41
41
  - !ruby/object:Gem::Dependency
42
42
  name: rake
43
43
  requirement: !ruby/object:Gem::Requirement
@@ -68,7 +68,7 @@ dependencies:
68
68
  version: '3.0'
69
69
  description: |
70
70
  LibSVMLoader is a class that loads (and dumps) dataset file with the libsvm file format.
71
- The sample matrix for feature vectors and target vector for labels are represented by the NMatrix format.
71
+ The feature vectors and labels of dataset are represented by Ruby Array.
72
72
  email:
73
73
  - yoshoku@outlook.com
74
74
  executables:
@@ -76,6 +76,7 @@ executables:
76
76
  extensions: []
77
77
  extra_rdoc_files: []
78
78
  files:
79
+ - ".coveralls.yml"
79
80
  - ".gitignore"
80
81
  - ".rspec"
81
82
  - ".rubocop.yml"
@@ -112,7 +113,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
112
113
  version: '0'
113
114
  requirements: []
114
115
  rubyforge_project:
115
- rubygems_version: 2.4.5.4
116
+ rubygems_version: 2.7.6
116
117
  signing_key:
117
118
  specification_version: 4
118
119
  summary: LibSVMLoader loads (and dumps) dataset file with the libsvm file format.