numo-liblinear 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +20 -0
- data/.rspec +3 -0
- data/.travis.yml +14 -0
- data/CHANGELOG.md +2 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +27 -0
- data/README.md +168 -0
- data/Rakefile +15 -0
- data/ext/numo/liblinear/converter.c +102 -0
- data/ext/numo/liblinear/converter.h +16 -0
- data/ext/numo/liblinear/extconf.rb +39 -0
- data/ext/numo/liblinear/liblinearext.c +421 -0
- data/ext/numo/liblinear/liblinearext.h +17 -0
- data/ext/numo/liblinear/model.c +45 -0
- data/ext/numo/liblinear/model.h +15 -0
- data/ext/numo/liblinear/parameter.c +98 -0
- data/ext/numo/liblinear/parameter.h +15 -0
- data/ext/numo/liblinear/problem.c +61 -0
- data/ext/numo/liblinear/problem.h +12 -0
- data/ext/numo/liblinear/solver_type.c +34 -0
- data/ext/numo/liblinear/solver_type.h +9 -0
- data/lib/numo/liblinear.rb +5 -0
- data/lib/numo/liblinear/version.rb +8 -0
- data/numo-liblinear.gemspec +40 -0
- metadata +144 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7db70ba7431ce52aa9530d3d340a6dce5a616daa
|
4
|
+
data.tar.gz: ce1a99b9082477922ed35768de8467b514d36541
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 79e9cbacea54a665ddb971da7b08fd3a43d159a0314715d0aecbf5c19b3b3c95adca6f8b29217c354348d9d8417b9c14742a8d1a5f2debd2db51dd92c32007d5
|
7
|
+
data.tar.gz: 96a37fde1a15d9a79d7c2bbf374691e8358b42afadf1df58ac1097a6af1bc52ebcd5e6b43601e5ec15582fc79e9b430c20bc39b42503083c0991066b34d9bbbc
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CHANGELOG.md
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at yoshoku@outlook.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
Copyright (c) 2019 Atsushi Tatsuma
|
2
|
+
All rights reserved.
|
3
|
+
|
4
|
+
Redistribution and use in source and binary forms, with or without
|
5
|
+
modification, are permitted provided that the following conditions are met:
|
6
|
+
|
7
|
+
* Redistributions of source code must retain the above copyright notice, this
|
8
|
+
list of conditions and the following disclaimer.
|
9
|
+
|
10
|
+
* Redistributions in binary form must reproduce the above copyright notice,
|
11
|
+
this list of conditions and the following disclaimer in the documentation
|
12
|
+
and/or other materials provided with the distribution.
|
13
|
+
|
14
|
+
* Neither the name of the copyright holder nor the names of its
|
15
|
+
contributors may be used to endorse or promote products derived from
|
16
|
+
this software without specific prior written permission.
|
17
|
+
|
18
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
19
|
+
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
20
|
+
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
21
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
22
|
+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
23
|
+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
24
|
+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
25
|
+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
26
|
+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
27
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
data/README.md
ADDED
@@ -0,0 +1,168 @@
|
|
1
|
+
# Numo::Liblinear
|
2
|
+
|
3
|
+
[![Build Status](https://travis-ci.org/yoshoku/numo-liblinear.svg?branch=master)](https://travis-ci.org/yoshoku/numo-liblinear)
|
4
|
+
[![BSD 3-Clause License](https://img.shields.io/badge/License-BSD%203--Clause-orange.svg)](https://github.com/yoshoku/numo-liblinear/blob/master/LICENSE.txt)
|
5
|
+
|
6
|
+
Numo::Liblinear is a Ruby gem binding to the [LIBLINEAR](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library.
|
7
|
+
LIBLINEAR is one of the famous libraries for large-scale regularized linear classification and regression.
|
8
|
+
Numo::Liblinear makes to use the LIBLINEAR functions with
|
9
|
+
dataset represented by [Numo::NArray](https://github.com/ruby-numo/numo-narray).
|
10
|
+
|
11
|
+
Note: There are other useful Ruby gems binding to LIBLINEAR:
|
12
|
+
[liblinear-ruby](https://github.com/kei500/liblinear-ruby) by Kei Tsuchiya and
|
13
|
+
[liblinear-ruby-swig](https://github.com/tomz/liblinear-ruby-swig) by Tom Zeng.
|
14
|
+
|
15
|
+
## Installation
|
16
|
+
Numo::Liblinear does not bundle LIBLINEAR. You need to install LIBLINEAR in advance along your environment.
|
17
|
+
|
18
|
+
macOS:
|
19
|
+
|
20
|
+
$ brew install liblinear
|
21
|
+
|
22
|
+
Ubuntu:
|
23
|
+
|
24
|
+
$ sudo apt-get install liblinear-dev
|
25
|
+
|
26
|
+
Add this line to your application's Gemfile:
|
27
|
+
|
28
|
+
```ruby
|
29
|
+
gem 'numo-liblinear'
|
30
|
+
```
|
31
|
+
|
32
|
+
And then execute:
|
33
|
+
|
34
|
+
$ bundle
|
35
|
+
|
36
|
+
Or install it yourself as:
|
37
|
+
|
38
|
+
$ gem install numo-liblinear
|
39
|
+
|
40
|
+
## Usage
|
41
|
+
|
42
|
+
### Preparation
|
43
|
+
|
44
|
+
In the following examples, we use [red-datasets](https://github.com/red-data-tools/red-datasets) to download dataset.
|
45
|
+
|
46
|
+
$ gem install red-datasets-numo-narray
|
47
|
+
|
48
|
+
### Example 1. Cross-validation
|
49
|
+
|
50
|
+
We conduct cross validation of the Support Vector Classifier on [Iris dataset](https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass.html#iris).
|
51
|
+
|
52
|
+
```ruby
|
53
|
+
require 'numo/narray'
|
54
|
+
require 'numo/liblinear'
|
55
|
+
require 'datasets-numo-narray'
|
56
|
+
|
57
|
+
# Download Iris dataset.
|
58
|
+
puts 'Download dataset.'
|
59
|
+
iris = Datasets::LIBSVM.new('iris').to_narray
|
60
|
+
x = iris[true, 1..-1]
|
61
|
+
y = iris[true, 0]
|
62
|
+
|
63
|
+
# Define parameters of L2-regularized L2-loss support vector classification.
|
64
|
+
param = {
|
65
|
+
solver_type: Numo::Liblinear::SolverType::L2R_L2LOSS_SVC_DUAL,
|
66
|
+
C: 1
|
67
|
+
}
|
68
|
+
|
69
|
+
# Perform 5-cross validation.
|
70
|
+
puts 'Perform cross validation.'
|
71
|
+
n_folds = 5
|
72
|
+
predicted = Numo::Liblinear::cv(x, y, param, n_folds)
|
73
|
+
|
74
|
+
# Print mean accuracy.
|
75
|
+
mean_accuracy = y.eq(predicted).count.fdiv(y.size)
|
76
|
+
puts "Accuracy: %.1f %%" % (100 * mean_accuracy)
|
77
|
+
```
|
78
|
+
|
79
|
+
Execution result in the following:
|
80
|
+
|
81
|
+
```sh
|
82
|
+
Download dataset.
|
83
|
+
Perform cross validation.
|
84
|
+
Accuracy: 87.3 %
|
85
|
+
```
|
86
|
+
|
87
|
+
### Example 2. Pendigits dataset classification
|
88
|
+
|
89
|
+
We first train the Logistic Regression using training [pendigits dataset](https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass.html#pendigits).
|
90
|
+
|
91
|
+
```ruby
|
92
|
+
require 'numo/liblinear'
|
93
|
+
require 'datasets-numo-narray'
|
94
|
+
|
95
|
+
# Download pendigits training dataset.
|
96
|
+
puts 'Download dataset.'
|
97
|
+
pendigits = Datasets::LIBSVM.new('pendigits').to_narray
|
98
|
+
x = pendigits[true, 1..-1]
|
99
|
+
y = pendigits[true, 0]
|
100
|
+
|
101
|
+
# Define parameters of L2-regularized logistic regression.
|
102
|
+
param = {
|
103
|
+
solver_type: Numo::Liblinear::SolverType::L2R_LR_DUAL,
|
104
|
+
C: 1
|
105
|
+
}
|
106
|
+
|
107
|
+
# Perform training procedure.
|
108
|
+
puts 'Train logistic regression.'
|
109
|
+
model = Numo::Liblinear.train(x, y, param)
|
110
|
+
|
111
|
+
# Save parameters and trained model.
|
112
|
+
puts 'Save parameters and model with Marshal'
|
113
|
+
File.open('pendigits.dat', 'wb') { |f| f.write(Marshal.dump([param, model])) }
|
114
|
+
```
|
115
|
+
|
116
|
+
```sh
|
117
|
+
Download dataset.
|
118
|
+
Train logistic regression.
|
119
|
+
Save parameters and model with Marshal
|
120
|
+
```
|
121
|
+
|
122
|
+
We then predict labels of testing dataset, and evaluate the classifier.
|
123
|
+
|
124
|
+
```ruby
|
125
|
+
require 'numo/liblinear'
|
126
|
+
require 'datasets-numo-narray'
|
127
|
+
|
128
|
+
# Download pendigits testing dataset.
|
129
|
+
puts 'Download dataset.'
|
130
|
+
pendigits_test = Datasets::LIBSVM.new('pendigits', note: 'testing').to_narray
|
131
|
+
x = pendigits_test[true, 1..-1]
|
132
|
+
y = pendigits_test[true, 0]
|
133
|
+
|
134
|
+
# Load parameter and model.
|
135
|
+
puts 'Load parameter and model.'
|
136
|
+
param, model = Marshal.load(File.binread('pendigits.dat'))
|
137
|
+
|
138
|
+
# Predict labels.
|
139
|
+
puts 'Predict labels.'
|
140
|
+
predicted = Numo::Liblinear.predict(x, param, model)
|
141
|
+
|
142
|
+
# Evaluate classification results.
|
143
|
+
mean_accuracy = y.eq(predicted).count.fdiv(y.size)
|
144
|
+
puts "Accuracy: %.1f %%" % (100 * mean_accuracy)
|
145
|
+
```
|
146
|
+
|
147
|
+
```sh
|
148
|
+
Download dataset.
|
149
|
+
Load parameter and model.
|
150
|
+
Predict labels.
|
151
|
+
Accuracy: 87.9 %
|
152
|
+
```
|
153
|
+
|
154
|
+
## Development
|
155
|
+
|
156
|
+
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.
|
157
|
+
|
158
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
159
|
+
|
160
|
+
## Contributing
|
161
|
+
|
162
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/numo-liblinear.
|
163
|
+
This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
164
|
+
|
165
|
+
## Code of Conduct
|
166
|
+
|
167
|
+
Everyone interacting in the Numo::Liblinear project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow
|
168
|
+
the [code of conduct](https://github.com/yoshoku/numo-liblinear/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'bundler/gem_tasks'
|
2
|
+
require 'rspec/core/rake_task'
|
3
|
+
|
4
|
+
RSpec::Core::RakeTask.new(:spec)
|
5
|
+
|
6
|
+
require 'rake/extensiontask'
|
7
|
+
|
8
|
+
task :build => :compile
|
9
|
+
|
10
|
+
Rake::ExtensionTask.new('liblinearext') do |ext|
|
11
|
+
ext.ext_dir = 'ext/numo/liblinear'
|
12
|
+
ext.lib_dir = 'lib/numo/liblinear'
|
13
|
+
end
|
14
|
+
|
15
|
+
task :default => [:clobber, :compile, :spec]
|
@@ -0,0 +1,102 @@
|
|
1
|
+
#include "converter.h"
|
2
|
+
|
3
|
+
VALUE int_vec_to_nary(int* const arr, int const size)
|
4
|
+
{
|
5
|
+
int i;
|
6
|
+
size_t shape[1] = { size };
|
7
|
+
VALUE v = rb_narray_new(numo_cInt32, 1, shape);
|
8
|
+
int32_t* vp = (int32_t*)na_get_pointer_for_write(v);
|
9
|
+
for (i = 0; i < size; i++) { vp[i] = (int32_t)arr[i]; }
|
10
|
+
return v;
|
11
|
+
}
|
12
|
+
|
13
|
+
int* nary_to_int_vec(VALUE vec_val)
|
14
|
+
{
|
15
|
+
int i;
|
16
|
+
int n_elements;
|
17
|
+
narray_t* vec_nary;
|
18
|
+
int32_t* vec_pt;
|
19
|
+
int* vec;
|
20
|
+
|
21
|
+
if (vec_val == Qnil) return NULL;
|
22
|
+
|
23
|
+
GetNArray(vec_val, vec_nary);
|
24
|
+
n_elements = (int)NA_SHAPE(vec_nary)[0];
|
25
|
+
|
26
|
+
vec = ALLOC_N(int, n_elements);
|
27
|
+
vec_pt = (int32_t*)na_get_pointer_for_read(vec_val);
|
28
|
+
for (i = 0; i < n_elements; i++) { vec[i] = (int)vec_pt[i]; }
|
29
|
+
|
30
|
+
return vec;
|
31
|
+
}
|
32
|
+
|
33
|
+
VALUE dbl_vec_to_nary(double* const arr, int const size)
|
34
|
+
{
|
35
|
+
int i;
|
36
|
+
size_t shape[1] = { size };
|
37
|
+
VALUE v = rb_narray_new(numo_cDFloat, 1, shape);
|
38
|
+
double* vp = (double*)na_get_pointer_for_write(v);
|
39
|
+
for (i = 0; i < size; i++) { vp[i] = arr[i]; }
|
40
|
+
return v;
|
41
|
+
}
|
42
|
+
|
43
|
+
double* nary_to_dbl_vec(VALUE vec_val)
|
44
|
+
{
|
45
|
+
int n_elements;
|
46
|
+
narray_t* vec_nary;
|
47
|
+
double* vec_pt;
|
48
|
+
double* vec;
|
49
|
+
|
50
|
+
if (vec_val == Qnil) return NULL;
|
51
|
+
|
52
|
+
GetNArray(vec_val, vec_nary);
|
53
|
+
n_elements = (int)NA_SHAPE(vec_nary)[0];
|
54
|
+
|
55
|
+
vec = ALLOC_N(double, n_elements);
|
56
|
+
vec_pt = (double*)na_get_pointer_for_read(vec_val);
|
57
|
+
memcpy(vec, vec_pt, n_elements * sizeof(double));
|
58
|
+
|
59
|
+
return vec;
|
60
|
+
}
|
61
|
+
|
62
|
+
VALUE dbl_mat_to_nary(double** const mat, int const n_rows, int const n_cols)
|
63
|
+
{
|
64
|
+
int i, j;
|
65
|
+
size_t shape[2] = { n_rows, n_cols };
|
66
|
+
VALUE v = rb_narray_new(numo_cDFloat, 2, shape);
|
67
|
+
double* vp = (double*)na_get_pointer_for_write(v);
|
68
|
+
|
69
|
+
for (i = 0; i < n_rows; i++) {
|
70
|
+
for (j = 0; j < n_cols; j++) {
|
71
|
+
vp[i * n_cols + j] = mat[i][j];
|
72
|
+
}
|
73
|
+
}
|
74
|
+
|
75
|
+
return v;
|
76
|
+
}
|
77
|
+
|
78
|
+
double** nary_to_dbl_mat(VALUE mat_val)
|
79
|
+
{
|
80
|
+
int i, j;
|
81
|
+
int n_rows, n_cols;
|
82
|
+
narray_t* mat_nary;
|
83
|
+
double* mat_pt;
|
84
|
+
double** mat;
|
85
|
+
|
86
|
+
if (mat_val == Qnil) return NULL;
|
87
|
+
|
88
|
+
GetNArray(mat_val, mat_nary);
|
89
|
+
n_rows = (int)NA_SHAPE(mat_nary)[0];
|
90
|
+
n_cols = (int)NA_SHAPE(mat_nary)[1];
|
91
|
+
|
92
|
+
mat_pt = (double*)na_get_pointer_for_read(mat_val);
|
93
|
+
mat = ALLOC_N(double*, n_rows);
|
94
|
+
for (i = 0; i < n_rows; i++) {
|
95
|
+
mat[i] = ALLOC_N(double, n_cols);
|
96
|
+
for (j = 0; j < n_cols; j++) {
|
97
|
+
mat[i][j] = mat_pt[i * n_cols + j];
|
98
|
+
}
|
99
|
+
}
|
100
|
+
|
101
|
+
return mat;
|
102
|
+
}
|