caymans 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +2 -0
- data/kmeans.gemspec +17 -0
- data/lib/kmeans.rb +8 -0
- data/lib/kmeans/default_classifier.rb +9 -0
- data/lib/kmeans/errors.rb +4 -0
- data/lib/kmeans/initial.rb +28 -0
- data/lib/kmeans/steps.rb +33 -0
- data/lib/kmeans/util.rb +33 -0
- data/lib/kmeans/version.rb +3 -0
- metadata +58 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Alejandro Ciniglio
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Kmeans
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'kmeans'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install kmeans
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/kmeans.gemspec
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/kmeans/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Alejandro Ciniglio"]
|
6
|
+
gem.email = ["mail@alejandrociniglio.com"]
|
7
|
+
gem.description = %q{A Kmeans classifier written in ruby, good for fast classification}
|
8
|
+
gem.summary = %q{A Kmeans classifier written in ruby}
|
9
|
+
gem.homepage = "http://github.com/ciniglio/kmeans"
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "caymans"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = Kmeans::VERSION
|
17
|
+
end
|
data/lib/kmeans.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
module Kmeans
|
2
|
+
class Classifier
|
3
|
+
def initialize(k, data)
|
4
|
+
@k = k
|
5
|
+
@data = data
|
6
|
+
@clusters = new_clusters(@k)
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
10
|
+
module ForgyInitializer
|
11
|
+
def initialize(*args)
|
12
|
+
super *args
|
13
|
+
@means = random_selection(@k)
|
14
|
+
assignment_step
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
module RandomInitializer
|
19
|
+
def initialize(*args)
|
20
|
+
super *args
|
21
|
+
r = Random.new
|
22
|
+
@data.each do |v|
|
23
|
+
@clusters[r.rand(@k)] << v
|
24
|
+
end
|
25
|
+
update_step
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
data/lib/kmeans/steps.rb
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
module Kmeans
|
2
|
+
class Classifier
|
3
|
+
def assignment_step
|
4
|
+
clusters = new_clusters(@k)
|
5
|
+
@data.each do |d|
|
6
|
+
min_dist = Float::INFINITY
|
7
|
+
nearest = nil
|
8
|
+
@means.each_with_index do |m, i|
|
9
|
+
dist = distance(d, m)
|
10
|
+
if dist < min_dist
|
11
|
+
min_dist = dist
|
12
|
+
nearest = i
|
13
|
+
end
|
14
|
+
end
|
15
|
+
clusters[nearest] << d
|
16
|
+
end
|
17
|
+
@clusters = clusters
|
18
|
+
end
|
19
|
+
|
20
|
+
def update_step
|
21
|
+
means = Array.new(@k)
|
22
|
+
@clusters.each_with_index do |c, i|
|
23
|
+
means[i] = centroid(c)
|
24
|
+
end
|
25
|
+
@means = means
|
26
|
+
assignment_step
|
27
|
+
end
|
28
|
+
|
29
|
+
def run(n = 100)
|
30
|
+
n.times { update_step }
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
data/lib/kmeans/util.rb
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
require 'set'
|
2
|
+
|
3
|
+
module Kmeans
|
4
|
+
class Classifier
|
5
|
+
def random_selection(n = 1)
|
6
|
+
@data.to_a.sample n
|
7
|
+
end
|
8
|
+
|
9
|
+
def distance(u, v)
|
10
|
+
raise LengthMismatch, "||#{u}|| != ||#{v}||" unless (u.length == v.length)
|
11
|
+
sum = 0.to_f
|
12
|
+
u.each_with_index do |p, i|
|
13
|
+
q = v[i]
|
14
|
+
sum += (p - q)**(2.to_f)
|
15
|
+
end
|
16
|
+
Math.sqrt(sum)
|
17
|
+
end
|
18
|
+
|
19
|
+
def new_clusters(n)
|
20
|
+
clusters = []
|
21
|
+
n.times { clusters << Set.new }
|
22
|
+
clusters
|
23
|
+
end
|
24
|
+
|
25
|
+
def centroid(points)
|
26
|
+
x = Array.new(points.first.length, 0)
|
27
|
+
points.each do |p|
|
28
|
+
x = x.zip(p).map { |xi| xi.inject(:+) }
|
29
|
+
end
|
30
|
+
x.map { |xi| xi / points.length.to_f }
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
metadata
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: caymans
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Alejandro Ciniglio
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-01-13 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: A Kmeans classifier written in ruby, good for fast classification
|
15
|
+
email:
|
16
|
+
- mail@alejandrociniglio.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- .gitignore
|
22
|
+
- Gemfile
|
23
|
+
- LICENSE
|
24
|
+
- README.md
|
25
|
+
- Rakefile
|
26
|
+
- kmeans.gemspec
|
27
|
+
- lib/kmeans.rb
|
28
|
+
- lib/kmeans/default_classifier.rb
|
29
|
+
- lib/kmeans/errors.rb
|
30
|
+
- lib/kmeans/initial.rb
|
31
|
+
- lib/kmeans/steps.rb
|
32
|
+
- lib/kmeans/util.rb
|
33
|
+
- lib/kmeans/version.rb
|
34
|
+
homepage: http://github.com/ciniglio/kmeans
|
35
|
+
licenses: []
|
36
|
+
post_install_message:
|
37
|
+
rdoc_options: []
|
38
|
+
require_paths:
|
39
|
+
- lib
|
40
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
47
|
+
none: false
|
48
|
+
requirements:
|
49
|
+
- - ! '>='
|
50
|
+
- !ruby/object:Gem::Version
|
51
|
+
version: '0'
|
52
|
+
requirements: []
|
53
|
+
rubyforge_project:
|
54
|
+
rubygems_version: 1.8.24
|
55
|
+
signing_key:
|
56
|
+
specification_version: 3
|
57
|
+
summary: A Kmeans classifier written in ruby
|
58
|
+
test_files: []
|