buncher 1.0.11 → 1.0.12
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +20 -0
- data/Manifest.txt +1 -0
- data/Rakefile +14 -2
- data/lib/buncher.rb +13 -5
- data/test/test_buncher.rb +4 -2
- metadata +118 -2
data/Gemfile
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- ruby -*-
|
2
|
+
|
3
|
+
# DO NOT EDIT THIS FILE. Instead, edit Rakefile, and run `rake bundler:gemfile`.
|
4
|
+
|
5
|
+
source "https://rubygems.org/"
|
6
|
+
|
7
|
+
|
8
|
+
gem "minitest", "~>5.6", :group => [:development, :test]
|
9
|
+
gem "rdoc", "~>4.0", :group => [:development, :test]
|
10
|
+
gem "rake-compiler", "~>0.7", :group => [:development, :test]
|
11
|
+
gem "hoe-bundler", ">=1.1", :group => [:development, :test]
|
12
|
+
gem "hoe-gemspec", ">=1.0", :group => [:development, :test]
|
13
|
+
gem "hoe-git", ">=1.4", :group => [:development, :test]
|
14
|
+
gem "minitest-focus", ">=0", :group => [:development, :test]
|
15
|
+
gem "rake", ">=0.9", :group => [:development, :test]
|
16
|
+
gem "gnuplot", ">=0", :group => [:development, :test]
|
17
|
+
gem "rubystats", ">=0", :group => [:development, :test]
|
18
|
+
gem "hoe", "~>3.13", :group => [:development, :test]
|
19
|
+
|
20
|
+
# vim: syntax=ruby
|
data/Manifest.txt
CHANGED
data/Rakefile
CHANGED
@@ -1,10 +1,12 @@
|
|
1
1
|
# -*- ruby -*-
|
2
2
|
|
3
3
|
require "rubygems"
|
4
|
+
gem "hoe"
|
4
5
|
require "hoe"
|
5
6
|
|
7
|
+
Hoe.plugin :gemspec
|
8
|
+
Hoe.plugin :bundler
|
6
9
|
Hoe.plugin :git
|
7
|
-
Hoe.plugin :debugging # for gdb
|
8
10
|
Hoe.plugin :compiler
|
9
11
|
# Hoe.plugin :gem_prelude_sucks
|
10
12
|
# Hoe.plugin :inline
|
@@ -15,7 +17,17 @@ Hoe.plugin :minitest
|
|
15
17
|
|
16
18
|
Hoe.spec "buncher" do
|
17
19
|
developer("Robert Mathews", "rob@drync.com")
|
18
|
-
|
20
|
+
self.extra_dev_deps += [
|
21
|
+
["hoe-bundler", ">= 1.1"],
|
22
|
+
["hoe-gemspec", ">= 1.0"],
|
23
|
+
["hoe-git", ">= 1.4"],
|
24
|
+
["minitest", "> 2.2.2"],
|
25
|
+
["minitest-focus"],
|
26
|
+
["rake", ">= 0.9"],
|
27
|
+
["rake-compiler", "> 0.9.2"],
|
28
|
+
['gnuplot'],
|
29
|
+
['rubystats']
|
30
|
+
]
|
19
31
|
|
20
32
|
license "MIT" # this should match the license in the README
|
21
33
|
end
|
data/lib/buncher.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
require 'buncher/buncher'
|
2
2
|
module Buncher
|
3
|
-
VERSION = "1.0.
|
3
|
+
VERSION = "1.0.12"
|
4
4
|
# your cluster needs to look like this. Make a bunch of them and pass them in. It's ok to pass in empty elements to start.
|
5
5
|
class Cluster
|
6
6
|
attr_accessor :elements
|
@@ -60,7 +60,12 @@ module Buncher
|
|
60
60
|
|
61
61
|
# run the clustering algorithm until we have calculated the best number of clusters, taken from this paper:
|
62
62
|
# http://papers.nips.cc/paper/2526-learning-the-k-in-k-means.pdf
|
63
|
+
# min_size: force at least min_size clusters to be created.
|
64
|
+
# plausable: return a hash of #plausable values for k. Sometimes the data has multiple possible answers, so return
|
65
|
+
# the top n of them in a hash of score=>plausable solutions. lowest scores are best, but sometimes there are
|
66
|
+
# "ties".
|
63
67
|
def self.cluster(elements, weights,options={})
|
68
|
+
plausable=options[:plausable] || 1
|
64
69
|
solutions={}
|
65
70
|
min_size=options[:min_size] || 1
|
66
71
|
# try all the sizes of clusters up to #elements. Ok, sure we could probably do something like 50% .. ok, I did
|
@@ -79,11 +84,14 @@ module Buncher
|
|
79
84
|
solutions[last_fK]=centers if number_clusters >= min_size
|
80
85
|
# break if number_clusters == 3 ## debugging
|
81
86
|
end
|
82
|
-
|
83
|
-
|
84
|
-
|
87
|
+
solutions.select! {|min_fK| min_fK <= 0.85}
|
88
|
+
min_fKs =solutions.keys.sort[0...plausable] || [1.0]
|
89
|
+
if options[:plausable]
|
90
|
+
solutions.select {|key| min_fKs.include?(key)}
|
91
|
+
elsif !min_fKs.empty?
|
92
|
+
solutions[min_fKs.first]
|
85
93
|
else
|
86
|
-
|
94
|
+
elements.map {|ele| Cluster.new(ele,[ele])} # ie, not clustered at all
|
87
95
|
end
|
88
96
|
end
|
89
97
|
end
|
data/test/test_buncher.rb
CHANGED
@@ -110,8 +110,9 @@ class TestBuncher < Minitest::Test
|
|
110
110
|
# focus
|
111
111
|
def test_min_size_works
|
112
112
|
elements = init_data(100,1)
|
113
|
-
new_centers = Buncher::cluster(elements,[1]*2,:min_size=>2)
|
114
|
-
assert(new_centers.
|
113
|
+
new_centers = Buncher::cluster(elements,[1]*2,:min_size=>2,:plausable=>3)
|
114
|
+
assert(new_centers.kind_of? Hash)
|
115
|
+
assert(new_centers.first.size >=2,"at least 2 centers")
|
115
116
|
end
|
116
117
|
def test_gaussian_distribution_of_100_points_in_3_clusters
|
117
118
|
1.times do |run|
|
@@ -124,6 +125,7 @@ class TestBuncher < Minitest::Test
|
|
124
125
|
graphfile = "/tmp/#{run}_centers_#{centers.size}.png"
|
125
126
|
plot(graphfile,elements,centers, initial_centers)
|
126
127
|
}
|
128
|
+
new_centers=new_centers.first
|
127
129
|
puts "run #{run}: k is #{new_centers.size}, seed was #{srand}"
|
128
130
|
puts "ERROR "*4 if new_centers.size != 3
|
129
131
|
puts
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: buncher
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.12
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2015-05-
|
12
|
+
date: 2015-05-03 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: minitest
|
@@ -59,6 +59,118 @@ dependencies:
|
|
59
59
|
- - ~>
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: '0.7'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: hoe-bundler
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '1.1'
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '1.1'
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: hoe-gemspec
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '1.0'
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - ! '>='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '1.0'
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: hoe-git
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ! '>='
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '1.4'
|
102
|
+
type: :development
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '1.4'
|
110
|
+
- !ruby/object:Gem::Dependency
|
111
|
+
name: minitest-focus
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
115
|
+
- - ! '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
none: false
|
122
|
+
requirements:
|
123
|
+
- - ! '>='
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
126
|
+
- !ruby/object:Gem::Dependency
|
127
|
+
name: rake
|
128
|
+
requirement: !ruby/object:Gem::Requirement
|
129
|
+
none: false
|
130
|
+
requirements:
|
131
|
+
- - ! '>='
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0.9'
|
134
|
+
type: :development
|
135
|
+
prerelease: false
|
136
|
+
version_requirements: !ruby/object:Gem::Requirement
|
137
|
+
none: false
|
138
|
+
requirements:
|
139
|
+
- - ! '>='
|
140
|
+
- !ruby/object:Gem::Version
|
141
|
+
version: '0.9'
|
142
|
+
- !ruby/object:Gem::Dependency
|
143
|
+
name: gnuplot
|
144
|
+
requirement: !ruby/object:Gem::Requirement
|
145
|
+
none: false
|
146
|
+
requirements:
|
147
|
+
- - ! '>='
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '0'
|
150
|
+
type: :development
|
151
|
+
prerelease: false
|
152
|
+
version_requirements: !ruby/object:Gem::Requirement
|
153
|
+
none: false
|
154
|
+
requirements:
|
155
|
+
- - ! '>='
|
156
|
+
- !ruby/object:Gem::Version
|
157
|
+
version: '0'
|
158
|
+
- !ruby/object:Gem::Dependency
|
159
|
+
name: rubystats
|
160
|
+
requirement: !ruby/object:Gem::Requirement
|
161
|
+
none: false
|
162
|
+
requirements:
|
163
|
+
- - ! '>='
|
164
|
+
- !ruby/object:Gem::Version
|
165
|
+
version: '0'
|
166
|
+
type: :development
|
167
|
+
prerelease: false
|
168
|
+
version_requirements: !ruby/object:Gem::Requirement
|
169
|
+
none: false
|
170
|
+
requirements:
|
171
|
+
- - ! '>='
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '0'
|
62
174
|
- !ruby/object:Gem::Dependency
|
63
175
|
name: hoe
|
64
176
|
requirement: !ruby/object:Gem::Requirement
|
@@ -94,6 +206,7 @@ files:
|
|
94
206
|
- .autotest
|
95
207
|
- History.txt
|
96
208
|
- Manifest.txt
|
209
|
+
- Gemfile
|
97
210
|
- README.txt
|
98
211
|
- Rakefile
|
99
212
|
- ext/buncher/cluster.cpp
|
@@ -118,6 +231,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
118
231
|
- - ! '>='
|
119
232
|
- !ruby/object:Gem::Version
|
120
233
|
version: '0'
|
234
|
+
segments:
|
235
|
+
- 0
|
236
|
+
hash: 630999455354425102
|
121
237
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
122
238
|
none: false
|
123
239
|
requirements:
|