clusto 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +20 -0
- data/README.md +16 -0
- data/clusto.gemspec +9 -0
- data/lib/clusto.rb +81 -0
- data/lib/clusto/cluster.rb +28 -0
- data/lib/clusto/distance.rb +19 -0
- data/lib/clusto/point.rb +15 -0
- metadata +51 -0
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2012 Conor Mulligan, Solas.ca
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
Clusto
|
2
|
+
======
|
3
|
+
|
4
|
+
*Simple Ruby point clustering*
|
5
|
+
|
6
|
+
If you're familiar with the [k-means][1] algorithm then Clusto's clustering process will probably be broadly recognisable, although it does take some liberties in the name of performance.
|
7
|
+
|
8
|
+
Usage
|
9
|
+
-----
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
points = data.map { |p| Clusto::Point.new(p.x, p.y) }
|
13
|
+
clusters = Clusto.cluster(points)
|
14
|
+
```
|
15
|
+
|
16
|
+
[1]: http://en.wikipedia.org/wiki/K-means_clustering
|
data/clusto.gemspec
ADDED
data/lib/clusto.rb
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
require 'clusto/point'
|
2
|
+
require 'clusto/cluster'
|
3
|
+
require 'clusto/distance'
|
4
|
+
|
5
|
+
module Clusto
|
6
|
+
extend self
|
7
|
+
|
8
|
+
INFINITY = +1.0/0
|
9
|
+
RADIANS_PER_DEGREES = Math::PI / 180
|
10
|
+
GREAT_CIRCLE_RADIUS = 6371
|
11
|
+
|
12
|
+
GRID_SIZE = 8
|
13
|
+
|
14
|
+
def minimum_bounding_rectangle(points)
|
15
|
+
xs = points.collect { |p| p.x }.minmax
|
16
|
+
ys = points.collect { |p| p.y }.minmax
|
17
|
+
|
18
|
+
[xs[0], ys[0], xs[1], ys[1]]
|
19
|
+
end
|
20
|
+
|
21
|
+
def cluster(points, options={})
|
22
|
+
bounds = options[:bounds] || Clusto.minimum_bounding_rectangle(points)
|
23
|
+
distance_method = options[:distance_method] || :haversine
|
24
|
+
|
25
|
+
# Create clusters
|
26
|
+
|
27
|
+
clusters = []
|
28
|
+
|
29
|
+
x = bounds[0]
|
30
|
+
y = bounds[3]
|
31
|
+
w = bounds[2] - bounds[0]
|
32
|
+
h = bounds[3] - bounds[1]
|
33
|
+
grid_w = w / GRID_SIZE
|
34
|
+
grid_h = h / GRID_SIZE
|
35
|
+
|
36
|
+
column = 0
|
37
|
+
row = 0
|
38
|
+
|
39
|
+
(GRID_SIZE ** 2).times do |i|
|
40
|
+
offset_x = x + (column * grid_w)
|
41
|
+
offset_y = y - (row * grid_h)
|
42
|
+
|
43
|
+
center = Clusto::Point.new(offset_x + (grid_w / 2), offset_y - (grid_h / 2))
|
44
|
+
clusters.push(Clusto::Cluster.new(center))
|
45
|
+
|
46
|
+
column = column+1
|
47
|
+
if column == GRID_SIZE
|
48
|
+
column = 0
|
49
|
+
row = row+1
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
# Assign points to clusters
|
54
|
+
|
55
|
+
points.each do |point|
|
56
|
+
distance = INFINITY
|
57
|
+
nearest = nil
|
58
|
+
|
59
|
+
clusters.each do |cluster|
|
60
|
+
begin
|
61
|
+
d = Clusto::Distance.send(distance_method, cluster.location, point)
|
62
|
+
rescue NoMethodError
|
63
|
+
raise "Unknown distance method '#{distance_method}."
|
64
|
+
end
|
65
|
+
|
66
|
+
if d < distance
|
67
|
+
distance = d
|
68
|
+
nearest = cluster
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
nearest.points.push(point)
|
73
|
+
end
|
74
|
+
|
75
|
+
# Reposition clusters
|
76
|
+
|
77
|
+
clusters.each do |cluster|
|
78
|
+
cluster.reposition
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
module Clusto
|
2
|
+
class Cluster
|
3
|
+
attr_accessor :location, :points
|
4
|
+
|
5
|
+
def initialize(location)
|
6
|
+
@location = location
|
7
|
+
@points = []
|
8
|
+
end
|
9
|
+
|
10
|
+
def reposition
|
11
|
+
return if @points.empty?
|
12
|
+
|
13
|
+
x = 0
|
14
|
+
y = 0
|
15
|
+
center = @location
|
16
|
+
|
17
|
+
@points.each do |point|
|
18
|
+
x += point.x
|
19
|
+
y += point.y
|
20
|
+
end
|
21
|
+
|
22
|
+
x /= points.length
|
23
|
+
y /= points.length
|
24
|
+
|
25
|
+
@location = Clusto::Point.new(x, y)
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module Clusto
|
2
|
+
class Distance
|
3
|
+
def self.euclidian(pa, pb)
|
4
|
+
Math::sqrt((pa.x - pb.x) ** 2 + (pa.y - pb.y) ** 2)
|
5
|
+
end
|
6
|
+
|
7
|
+
def self.haversine(pa, pb)
|
8
|
+
x = (pb.x - pa.x) * RADIANS_PER_DEGREES
|
9
|
+
y = (pb.y - pa.y) * RADIANS_PER_DEGREES
|
10
|
+
|
11
|
+
ar = pa.x * RADIANS_PER_DEGREES
|
12
|
+
br = pb.x * RADIANS_PER_DEGREES
|
13
|
+
|
14
|
+
a = Math.sin(x / 2) ** 2 + Math.cos(ar) * Math.cos(br) * Math.sin(y / 2) ** 2
|
15
|
+
c = 2 * Math.atan2(Math::sqrt(a), Math::sqrt(1 - a))
|
16
|
+
GREAT_CIRCLE_RADIUS * c;
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
data/lib/clusto/point.rb
ADDED
metadata
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: clusto
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Conor Mulligan
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-10-13 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description:
|
15
|
+
email: conmulligan@gmail.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- ./clusto.gemspec
|
21
|
+
- ./lib/clusto/cluster.rb
|
22
|
+
- ./lib/clusto/distance.rb
|
23
|
+
- ./lib/clusto/point.rb
|
24
|
+
- ./lib/clusto.rb
|
25
|
+
- ./LICENSE
|
26
|
+
- ./README.md
|
27
|
+
homepage:
|
28
|
+
licenses: []
|
29
|
+
post_install_message:
|
30
|
+
rdoc_options: []
|
31
|
+
require_paths:
|
32
|
+
- lib
|
33
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
34
|
+
none: false
|
35
|
+
requirements:
|
36
|
+
- - ! '>='
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '0'
|
39
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
40
|
+
none: false
|
41
|
+
requirements:
|
42
|
+
- - ! '>='
|
43
|
+
- !ruby/object:Gem::Version
|
44
|
+
version: '0'
|
45
|
+
requirements: []
|
46
|
+
rubyforge_project:
|
47
|
+
rubygems_version: 1.8.15
|
48
|
+
signing_key:
|
49
|
+
specification_version: 3
|
50
|
+
summary: Simple Ruby point clustering
|
51
|
+
test_files: []
|