ai4ruby 1.11
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +47 -0
- data/examples/classifiers/id3_data.csv +121 -0
- data/examples/classifiers/id3_example.rb +29 -0
- data/examples/classifiers/naive_bayes_data.csv +11 -0
- data/examples/classifiers/naive_bayes_example.rb +16 -0
- data/examples/classifiers/results.txt +31 -0
- data/examples/genetic_algorithm/genetic_algorithm_example.rb +37 -0
- data/examples/genetic_algorithm/travel_cost.csv +16 -0
- data/examples/neural_network/backpropagation_example.rb +67 -0
- data/examples/neural_network/patterns_with_base_noise.rb +68 -0
- data/examples/neural_network/patterns_with_noise.rb +66 -0
- data/examples/neural_network/training_patterns.rb +68 -0
- data/examples/neural_network/xor_example.rb +35 -0
- data/examples/som/som_data.rb +156 -0
- data/examples/som/som_multi_node_example.rb +22 -0
- data/examples/som/som_single_example.rb +24 -0
- data/lib/ai4r.rb +33 -0
- data/lib/ai4r/classifiers/classifier.rb +62 -0
- data/lib/ai4r/classifiers/hyperpipes.rb +118 -0
- data/lib/ai4r/classifiers/ib1.rb +121 -0
- data/lib/ai4r/classifiers/id3.rb +326 -0
- data/lib/ai4r/classifiers/multilayer_perceptron.rb +135 -0
- data/lib/ai4r/classifiers/naive_bayes.rb +259 -0
- data/lib/ai4r/classifiers/one_r.rb +110 -0
- data/lib/ai4r/classifiers/prism.rb +197 -0
- data/lib/ai4r/classifiers/zero_r.rb +73 -0
- data/lib/ai4r/clusterers/average_linkage.rb +59 -0
- data/lib/ai4r/clusterers/bisecting_k_means.rb +93 -0
- data/lib/ai4r/clusterers/centroid_linkage.rb +66 -0
- data/lib/ai4r/clusterers/clusterer.rb +61 -0
- data/lib/ai4r/clusterers/complete_linkage.rb +67 -0
- data/lib/ai4r/clusterers/diana.rb +139 -0
- data/lib/ai4r/clusterers/k_means.rb +126 -0
- data/lib/ai4r/clusterers/median_linkage.rb +61 -0
- data/lib/ai4r/clusterers/single_linkage.rb +194 -0
- data/lib/ai4r/clusterers/ward_linkage.rb +64 -0
- data/lib/ai4r/clusterers/ward_linkage_hierarchical.rb +31 -0
- data/lib/ai4r/clusterers/weighted_average_linkage.rb +61 -0
- data/lib/ai4r/data/data_set.rb +266 -0
- data/lib/ai4r/data/parameterizable.rb +64 -0
- data/lib/ai4r/data/proximity.rb +100 -0
- data/lib/ai4r/data/statistics.rb +77 -0
- data/lib/ai4r/experiment/classifier_evaluator.rb +95 -0
- data/lib/ai4r/genetic_algorithm/genetic_algorithm.rb +270 -0
- data/lib/ai4r/neural_network/backpropagation.rb +326 -0
- data/lib/ai4r/neural_network/hopfield.rb +149 -0
- data/lib/ai4r/som/layer.rb +68 -0
- data/lib/ai4r/som/node.rb +96 -0
- data/lib/ai4r/som/som.rb +155 -0
- data/lib/ai4r/som/two_phase_layer.rb +90 -0
- data/test/classifiers/hyperpipes_test.rb +84 -0
- data/test/classifiers/ib1_test.rb +78 -0
- data/test/classifiers/id3_test.rb +208 -0
- data/test/classifiers/multilayer_perceptron_test.rb +79 -0
- data/test/classifiers/naive_bayes_test.rb +43 -0
- data/test/classifiers/one_r_test.rb +62 -0
- data/test/classifiers/prism_test.rb +85 -0
- data/test/classifiers/zero_r_test.rb +49 -0
- data/test/clusterers/average_linkage_test.rb +51 -0
- data/test/clusterers/bisecting_k_means_test.rb +66 -0
- data/test/clusterers/centroid_linkage_test.rb +53 -0
- data/test/clusterers/complete_linkage_test.rb +57 -0
- data/test/clusterers/diana_test.rb +69 -0
- data/test/clusterers/k_means_test.rb +100 -0
- data/test/clusterers/median_linkage_test.rb +53 -0
- data/test/clusterers/single_linkage_test.rb +122 -0
- data/test/clusterers/ward_linkage_hierarchical_test.rb +61 -0
- data/test/clusterers/ward_linkage_test.rb +53 -0
- data/test/clusterers/weighted_average_linkage_test.rb +53 -0
- data/test/data/data_set_test.rb +96 -0
- data/test/data/proximity_test.rb +81 -0
- data/test/data/statistics_test.rb +65 -0
- data/test/experiment/classifier_evaluator_test.rb +76 -0
- data/test/genetic_algorithm/chromosome_test.rb +58 -0
- data/test/genetic_algorithm/genetic_algorithm_test.rb +81 -0
- data/test/neural_network/backpropagation_test.rb +82 -0
- data/test/neural_network/hopfield_test.rb +72 -0
- data/test/som/som_test.rb +97 -0
- metadata +168 -0
@@ -0,0 +1,85 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/prism'
|
3
|
+
|
4
|
+
|
5
|
+
class PrismTest < Test::Unit::TestCase
|
6
|
+
|
7
|
+
include Ai4r::Classifiers
|
8
|
+
include Ai4r::Data
|
9
|
+
|
10
|
+
@@data_examples = [ ['New York', '<30', 'M', 'Y'],
|
11
|
+
['Chicago', '<30', 'M', 'Y'],
|
12
|
+
['Chicago', '<30', 'F', 'Y'],
|
13
|
+
['New York', '<30', 'M', 'Y'],
|
14
|
+
['New York', '<30', 'M', 'Y'],
|
15
|
+
['Chicago', '[30-50)', 'M', 'Y'],
|
16
|
+
['New York', '[30-50)', 'F', 'N'],
|
17
|
+
['Chicago', '[30-50)', 'F', 'Y'],
|
18
|
+
['New York', '[30-50)', 'F', 'N'],
|
19
|
+
['Chicago', '[50-80]', 'M', 'N'],
|
20
|
+
['New York', '[50-80]', 'F', 'N'],
|
21
|
+
['New York', '[50-80]', 'M', 'N'],
|
22
|
+
['Chicago', '[50-80]', 'M', 'N'],
|
23
|
+
['New York', '[50-80]', 'F', 'N'],
|
24
|
+
['Chicago', '>80', 'F', 'Y']
|
25
|
+
]
|
26
|
+
|
27
|
+
@@data_labels = [ 'city', 'age_range', 'gender', 'marketing_target' ]
|
28
|
+
|
29
|
+
def test_build
|
30
|
+
assert_raise(ArgumentError) { Prism.new.build(DataSet.new) }
|
31
|
+
classifier = Prism.new.build(DataSet.new(:data_items=>@@data_examples))
|
32
|
+
assert_not_nil(classifier.data_set.data_labels)
|
33
|
+
assert_not_nil(classifier.rules)
|
34
|
+
assert_equal("attribute_1", classifier.data_set.data_labels.first)
|
35
|
+
assert_equal("class_value", classifier.data_set.data_labels.last)
|
36
|
+
classifier = Prism.new.build(DataSet.new(:data_items => @@data_examples,
|
37
|
+
:data_labels => @@data_labels))
|
38
|
+
assert_not_nil(classifier.data_set.data_labels)
|
39
|
+
assert_not_nil(classifier.rules)
|
40
|
+
assert_equal("city", classifier.data_set.data_labels.first)
|
41
|
+
assert_equal("marketing_target", classifier.data_set.data_labels.last)
|
42
|
+
assert !classifier.rules.empty?
|
43
|
+
|
44
|
+
Prism.send(:public, *Prism.protected_instance_methods)
|
45
|
+
Prism.send(:public, *Prism.private_instance_methods)
|
46
|
+
end
|
47
|
+
|
48
|
+
def test_eval
|
49
|
+
classifier = Prism.new.build(DataSet.new(:data_items=>@@data_examples))
|
50
|
+
@@data_examples.each do |data|
|
51
|
+
assert_equal(data.last, classifier.eval(data[0...-1]))
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
def test_get_rules
|
56
|
+
classifier = Prism.new.build(DataSet.new(:data_items => @@data_examples,
|
57
|
+
:data_labels => @@data_labels))
|
58
|
+
marketing_target = nil
|
59
|
+
age_range = nil
|
60
|
+
city = 'Chicago'
|
61
|
+
eval(classifier.get_rules)
|
62
|
+
age_range = '<30'
|
63
|
+
eval(classifier.get_rules)
|
64
|
+
assert_equal("Y", marketing_target)
|
65
|
+
age_range = '[30-50)'
|
66
|
+
eval(classifier.get_rules)
|
67
|
+
assert_equal("Y", marketing_target)
|
68
|
+
age_range = '[30-50)'
|
69
|
+
city = 'New York'
|
70
|
+
eval(classifier.get_rules)
|
71
|
+
assert_equal("N", marketing_target)
|
72
|
+
age_range = '[50-80]'
|
73
|
+
eval(classifier.get_rules)
|
74
|
+
assert_equal("N", marketing_target)
|
75
|
+
end
|
76
|
+
|
77
|
+
def test_matches_conditions
|
78
|
+
classifier = Prism.new.build(DataSet.new(:data_labels => @@data_labels,
|
79
|
+
:data_items => @@data_examples))
|
80
|
+
|
81
|
+
assert classifier.matches_conditions(['New York', '<30', 'M', 'Y'], {"age_range" => "<30"})
|
82
|
+
assert !classifier.matches_conditions(['New York', '<30', 'M', 'Y'], {"age_range" => "[50-80]"})
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/zero_r'
|
3
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/data/data_set'
|
4
|
+
|
5
|
+
class ZeroRTest < Test::Unit::TestCase
|
6
|
+
|
7
|
+
include Ai4r::Classifiers
|
8
|
+
include Ai4r::Data
|
9
|
+
|
10
|
+
@@data_examples = [ ['New York', '<30', 'M', 'Y'],
|
11
|
+
['Chicago', '<30', 'M', 'Y'],
|
12
|
+
['New York', '<30', 'M', 'Y'],
|
13
|
+
['New York', '[30-50)', 'F', 'N'],
|
14
|
+
['Chicago', '[30-50)', 'F', 'Y'],
|
15
|
+
['New York', '[30-50)', 'F', 'N'],
|
16
|
+
['Chicago', '[50-80]', 'M', 'N'],
|
17
|
+
]
|
18
|
+
|
19
|
+
@@data_labels = [ 'city', 'age_range', 'gender', 'marketing_target' ]
|
20
|
+
|
21
|
+
def test_build
|
22
|
+
assert_raise(ArgumentError) { ZeroR.new.build(DataSet.new) }
|
23
|
+
classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples))
|
24
|
+
assert_equal("Y", classifier.class_value)
|
25
|
+
assert_equal("attribute_1", classifier.data_set.data_labels.first)
|
26
|
+
assert_equal("class_value", classifier.data_set.data_labels.last)
|
27
|
+
classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples,
|
28
|
+
:data_labels => @@data_labels))
|
29
|
+
assert_equal("Y", classifier.class_value)
|
30
|
+
assert_equal("city", classifier.data_set.data_labels.first)
|
31
|
+
assert_equal("marketing_target", classifier.data_set.data_labels.last)
|
32
|
+
end
|
33
|
+
|
34
|
+
def test_eval
|
35
|
+
classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples))
|
36
|
+
assert_equal('Y', classifier.eval(@@data_examples.first) )
|
37
|
+
assert_equal('Y', classifier.eval(@@data_examples.last) )
|
38
|
+
end
|
39
|
+
|
40
|
+
def test_get_rules
|
41
|
+
classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples,
|
42
|
+
:data_labels => @@data_labels))
|
43
|
+
marketing_target = nil
|
44
|
+
eval(classifier.get_rules)
|
45
|
+
assert_equal('Y', marketing_target)
|
46
|
+
end
|
47
|
+
|
48
|
+
end
|
49
|
+
|
@@ -0,0 +1,51 @@
|
|
1
|
+
# Author:: Sergio Fierens (implementation)
|
2
|
+
# License:: MPL 1.1
|
3
|
+
# Project:: ai4r
|
4
|
+
# Url:: http://ai4r.rubyforge.org/
|
5
|
+
#
|
6
|
+
# You can redistribute it and/or modify it under the terms of
|
7
|
+
# the Mozilla Public License version 1.1 as published by the
|
8
|
+
# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
|
9
|
+
|
10
|
+
require 'test/unit'
|
11
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/average_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::AverageLinkage < Ai4r::Clusterers::SingleLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix
|
15
|
+
end
|
16
|
+
|
17
|
+
class AverageLinkageTest < Test::Unit::TestCase
|
18
|
+
|
19
|
+
include Ai4r::Clusterers
|
20
|
+
include Ai4r::Data
|
21
|
+
|
22
|
+
@@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
|
23
|
+
[1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
|
24
|
+
|
25
|
+
@@expected_distance_matrix = [
|
26
|
+
[98.0],
|
27
|
+
[89.0, 5.0],
|
28
|
+
[68.0, 26.0, 9.0],
|
29
|
+
[74.0, 4.0, 1.0, 10.0],
|
30
|
+
[0.0, 98.0, 89.0, 68.0, 74.0],
|
31
|
+
[81.0, 53.0, 26.0, 5.0, 29.0, 81.0],
|
32
|
+
[8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0],
|
33
|
+
[100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0],
|
34
|
+
[68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0],
|
35
|
+
[49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0],
|
36
|
+
[2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
|
37
|
+
|
38
|
+
def setup
|
39
|
+
Ai4r::Clusterers::AverageLinkage.send(:public,
|
40
|
+
*Ai4r::Clusterers::AverageLinkage.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::AverageLinkage.new
|
45
|
+
clusterer.distance_matrix = @@expected_distance_matrix
|
46
|
+
assert_equal 93.5, clusterer.linkage_distance(0,1,2)
|
47
|
+
assert_equal 37.5, clusterer.linkage_distance(4,2,5)
|
48
|
+
end
|
49
|
+
|
50
|
+
end
|
51
|
+
|
@@ -0,0 +1,66 @@
|
|
1
|
+
# Author:: Sergio Fierens (implementation)
|
2
|
+
# License:: MPL 1.1
|
3
|
+
# Project:: ai4r
|
4
|
+
# Url:: http://ai4r.rubyforge.org/
|
5
|
+
#
|
6
|
+
# You can redistribute it and/or modify it under the terms of
|
7
|
+
# the Mozilla Public License version 1.1 as published by the
|
8
|
+
# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
|
9
|
+
|
10
|
+
require 'test/unit'
|
11
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/bisecting_k_means'
|
12
|
+
|
13
|
+
class BisectingKMeansTest < Test::Unit::TestCase
|
14
|
+
|
15
|
+
include Ai4r::Clusterers
|
16
|
+
include Ai4r::Data
|
17
|
+
|
18
|
+
@@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
|
19
|
+
[1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
|
20
|
+
|
21
|
+
def test_build_without_refine
|
22
|
+
build(false)
|
23
|
+
end
|
24
|
+
|
25
|
+
def test_build_with_refine
|
26
|
+
build(true)
|
27
|
+
end
|
28
|
+
|
29
|
+
protected
|
30
|
+
def build(refine)
|
31
|
+
data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
|
32
|
+
clusterer = BisectingKMeans.new
|
33
|
+
clusterer.set_parameters :refine => refine
|
34
|
+
clusterer.build(data_set, 4)
|
35
|
+
#draw_map(clusterer)
|
36
|
+
# Verify that all 4 clusters are created
|
37
|
+
assert_equal 4, clusterer.clusters.length
|
38
|
+
assert_equal 4, clusterer.centroids.length
|
39
|
+
# The addition of all instances of every cluster must be equal than
|
40
|
+
# the number of data points
|
41
|
+
total_length = 0
|
42
|
+
clusterer.clusters.each do |cluster|
|
43
|
+
total_length += cluster.data_items.length
|
44
|
+
end
|
45
|
+
assert_equal @@data.length, total_length
|
46
|
+
# Data inside clusters must be the same as orifinal data
|
47
|
+
clusterer.clusters.each do |cluster|
|
48
|
+
cluster.data_items.each do |data_item|
|
49
|
+
assert @@data.include?(data_item)
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
private
|
55
|
+
def draw_map(clusterer)
|
56
|
+
map = Array.new(11) {Array.new(11, 0)}
|
57
|
+
clusterer.clusters.each_index do |i|
|
58
|
+
clusterer.clusters[i].data_items.each do |point|
|
59
|
+
map[point.first][point.last]=(i+1)
|
60
|
+
end
|
61
|
+
end
|
62
|
+
map.each { |row| puts row.inspect}
|
63
|
+
end
|
64
|
+
|
65
|
+
end
|
66
|
+
|
@@ -0,0 +1,53 @@
|
|
1
|
+
# Author:: Sergio Fierens (implementation)
|
2
|
+
# License:: MPL 1.1
|
3
|
+
# Project:: ai4r
|
4
|
+
# Url:: http://ai4r.rubyforge.org/
|
5
|
+
#
|
6
|
+
# You can redistribute it and/or modify it under the terms of
|
7
|
+
# the Mozilla Public License version 1.1 as published by the
|
8
|
+
# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
|
9
|
+
|
10
|
+
require 'test/unit'
|
11
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/centroid_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::CentroidLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
|
15
|
+
end
|
16
|
+
|
17
|
+
class Ai4r::Clusterers::CentroidLinkageTest < Test::Unit::TestCase
|
18
|
+
|
19
|
+
include Ai4r::Clusterers
|
20
|
+
include Ai4r::Data
|
21
|
+
|
22
|
+
@@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
|
23
|
+
[1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
|
24
|
+
|
25
|
+
@@expected_distance_matrix = [
|
26
|
+
[98.0],
|
27
|
+
[89.0, 5.0],
|
28
|
+
[68.0, 26.0, 9.0],
|
29
|
+
[74.0, 4.0, 1.0, 10.0],
|
30
|
+
[0.0, 98.0, 89.0, 68.0, 74.0],
|
31
|
+
[81.0, 53.0, 26.0, 5.0, 29.0, 81.0],
|
32
|
+
[8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0],
|
33
|
+
[100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0],
|
34
|
+
[68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0],
|
35
|
+
[49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0],
|
36
|
+
[2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
|
37
|
+
|
38
|
+
def setup
|
39
|
+
Ai4r::Clusterers::CentroidLinkage.send(:public,
|
40
|
+
*Ai4r::Clusterers::CentroidLinkage.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::CentroidLinkage.new
|
45
|
+
clusterer.data_set = DataSet.new :data_items => @@data
|
46
|
+
clusterer.index_clusters = clusterer.create_initial_index_clusters
|
47
|
+
clusterer.distance_matrix = @@expected_distance_matrix
|
48
|
+
assert_equal 92.25, clusterer.linkage_distance(0,1,2)
|
49
|
+
assert_equal 15.25, clusterer.linkage_distance(4,2,5)
|
50
|
+
end
|
51
|
+
|
52
|
+
end
|
53
|
+
|
@@ -0,0 +1,57 @@
|
|
1
|
+
# Author:: Sergio Fierens (implementation)
|
2
|
+
# License:: MPL 1.1
|
3
|
+
# Project:: ai4r
|
4
|
+
# Url:: http://ai4r.rubyforge.org/
|
5
|
+
#
|
6
|
+
# You can redistribute it and/or modify it under the terms of
|
7
|
+
# the Mozilla Public License version 1.1 as published by the
|
8
|
+
# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
|
9
|
+
|
10
|
+
require 'test/unit'
|
11
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/complete_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::CompleteLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix
|
15
|
+
end
|
16
|
+
|
17
|
+
class CompleteLinkageTest < Test::Unit::TestCase
|
18
|
+
|
19
|
+
include Ai4r::Clusterers
|
20
|
+
include Ai4r::Data
|
21
|
+
|
22
|
+
@@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
|
23
|
+
[1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
|
24
|
+
|
25
|
+
@@expected_distance_matrix = [
|
26
|
+
[98.0],
|
27
|
+
[89.0, 5.0],
|
28
|
+
[68.0, 26.0, 9.0],
|
29
|
+
[74.0, 4.0, 1.0, 10.0],
|
30
|
+
[0.0, 98.0, 89.0, 68.0, 74.0],
|
31
|
+
[81.0, 53.0, 26.0, 5.0, 29.0, 81.0],
|
32
|
+
[8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0],
|
33
|
+
[100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0],
|
34
|
+
[68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0],
|
35
|
+
[49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0],
|
36
|
+
[2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
|
37
|
+
|
38
|
+
def setup
|
39
|
+
Ai4r::Clusterers::CompleteLinkage.send(:public,
|
40
|
+
*Ai4r::Clusterers::CompleteLinkage.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::CompleteLinkage.new
|
45
|
+
clusterer.distance_matrix = @@expected_distance_matrix
|
46
|
+
assert_equal 98, clusterer.linkage_distance(0,1,2)
|
47
|
+
assert_equal 74, clusterer.linkage_distance(4,2,5)
|
48
|
+
end
|
49
|
+
|
50
|
+
def test_distance_between_item_and_cluster
|
51
|
+
clusterer = CompleteLinkage.new
|
52
|
+
assert_equal 32.0, clusterer.distance_between_item_and_cluster([1,2],
|
53
|
+
DataSet.new(:data_items => [[3,4],[5,6]]))
|
54
|
+
end
|
55
|
+
|
56
|
+
end
|
57
|
+
|
@@ -0,0 +1,69 @@
|
|
1
|
+
# Author:: Sergio Fierens (implementation)
|
2
|
+
# License:: MPL 1.1
|
3
|
+
# Project:: ai4r
|
4
|
+
# Url:: http://ai4r.rubyforge.org/
|
5
|
+
#
|
6
|
+
# You can redistribute it and/or modify it under the terms of
|
7
|
+
# the Mozilla Public License version 1.1 as published by the
|
8
|
+
# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
|
9
|
+
|
10
|
+
require 'test/unit'
|
11
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/diana'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::Diana
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters
|
15
|
+
end
|
16
|
+
|
17
|
+
class DianaTest < Test::Unit::TestCase
|
18
|
+
|
19
|
+
@@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
|
20
|
+
[1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
|
21
|
+
|
22
|
+
include Ai4r::Clusterers
|
23
|
+
include Ai4r::Data
|
24
|
+
|
25
|
+
def setup
|
26
|
+
Diana.send(:public, *Diana.protected_instance_methods)
|
27
|
+
@data_set = DataSet.new(:data_items => @@data.clone)
|
28
|
+
end
|
29
|
+
|
30
|
+
def test_build
|
31
|
+
clusterer = Diana.new.build(@data_set, 4)
|
32
|
+
assert_equal 4, clusterer.clusters.length
|
33
|
+
end
|
34
|
+
|
35
|
+
def test_eval
|
36
|
+
clusterer = Diana.new.build(@data_set, 4)
|
37
|
+
assert_equal 0, clusterer.eval([0, 0])
|
38
|
+
assert_equal 1, clusterer.eval([9, 3])
|
39
|
+
assert_equal 2, clusterer.eval([0,10])
|
40
|
+
assert_equal 3, clusterer.eval([8, 0])
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_cluster_diameter
|
44
|
+
clusterer = Diana.new
|
45
|
+
assert_equal 106, clusterer.cluster_diameter(@data_set)
|
46
|
+
assert_equal 98, clusterer.cluster_diameter(@data_set[0..2])
|
47
|
+
end
|
48
|
+
|
49
|
+
def test_max_diameter_cluster
|
50
|
+
clusterer = Diana.new
|
51
|
+
assert_equal 0, clusterer.max_diameter_cluster([@data_set, @data_set[0..2]])
|
52
|
+
assert_equal 1, clusterer.max_diameter_cluster([@data_set[0..2], @data_set])
|
53
|
+
end
|
54
|
+
|
55
|
+
def test_init_splinter_cluster
|
56
|
+
clusterer = Diana.new
|
57
|
+
assert_equal [10,3], clusterer.
|
58
|
+
init_splinter_cluster(@data_set).data_items[0]
|
59
|
+
end
|
60
|
+
|
61
|
+
def test_max_distance_difference
|
62
|
+
clusterer = Diana.new
|
63
|
+
data_set_a = @data_set[1..-1]
|
64
|
+
data_set_b = @data_set[0]
|
65
|
+
assert_equal [63.7, 4], clusterer.
|
66
|
+
max_distance_difference(data_set_a, data_set_b)
|
67
|
+
end
|
68
|
+
|
69
|
+
end
|
@@ -0,0 +1,100 @@
|
|
1
|
+
# Author:: Sergio Fierens (implementation)
|
2
|
+
# License:: MPL 1.1
|
3
|
+
# Project:: ai4r
|
4
|
+
# Url:: http://ai4r.rubyforge.org/
|
5
|
+
#
|
6
|
+
# You can redistribute it and/or modify it under the terms of
|
7
|
+
# the Mozilla Public License version 1.1 as published by the
|
8
|
+
# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
|
9
|
+
|
10
|
+
require 'test/unit'
|
11
|
+
require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/k_means'
|
12
|
+
|
13
|
+
class KMeansTest < Test::Unit::TestCase
|
14
|
+
|
15
|
+
include Ai4r::Clusterers
|
16
|
+
include Ai4r::Data
|
17
|
+
|
18
|
+
@@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
|
19
|
+
[1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
|
20
|
+
|
21
|
+
def test_build
|
22
|
+
data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
|
23
|
+
clusterer = KMeans.new.build(data_set, 4)
|
24
|
+
#draw_map(clusterer)
|
25
|
+
# Verify that all 4 clusters are created
|
26
|
+
assert_equal 4, clusterer.clusters.length
|
27
|
+
assert_equal 4, clusterer.centroids.length
|
28
|
+
# The addition of all instances of every cluster must be equal than
|
29
|
+
# the number of data points
|
30
|
+
total_length = 0
|
31
|
+
clusterer.clusters.each do |cluster|
|
32
|
+
total_length += cluster.data_items.length
|
33
|
+
end
|
34
|
+
assert_equal @@data.length, total_length
|
35
|
+
# Data inside clusters must be the same as orifinal data
|
36
|
+
clusterer.clusters.each do |cluster|
|
37
|
+
cluster.data_items.each do |data_item|
|
38
|
+
assert @@data.include?(data_item)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_eval
|
44
|
+
data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
|
45
|
+
clusterer = KMeans.new.build(data_set, 4)
|
46
|
+
item = [10,0]
|
47
|
+
cluster_index = clusterer.eval(item)
|
48
|
+
# Must return a valid cluster index [0-3]
|
49
|
+
assert cluster_index >= 0 && cluster_index < 4
|
50
|
+
# Distance to cluster centroid must be less than distance to any other
|
51
|
+
# centroid
|
52
|
+
min_distance = clusterer.distance(clusterer.centroids[cluster_index], item)
|
53
|
+
clusterer.centroids.each do |centroid|
|
54
|
+
assert clusterer.distance(centroid, item) >= min_distance
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def test_distance
|
59
|
+
clusterer = KMeans.new
|
60
|
+
# By default, distance returns the eucledian distance to the power of 2
|
61
|
+
assert_equal 2385, clusterer.distance(
|
62
|
+
[1, 10, "Chicago", 2],
|
63
|
+
[10, 10, "London", 50])
|
64
|
+
# Test new distance definition
|
65
|
+
manhattan_distance = lambda do |a, b|
|
66
|
+
dist = 0.0
|
67
|
+
a.each_index do |index|
|
68
|
+
if a[index].is_a?(Numeric) && b[index].is_a?(Numeric)
|
69
|
+
dist = dist + (a[index]-b[index]).abs
|
70
|
+
end
|
71
|
+
end
|
72
|
+
dist
|
73
|
+
end
|
74
|
+
clusterer.set_parameters({:distance_function => manhattan_distance})
|
75
|
+
assert_equal 57, clusterer.distance(
|
76
|
+
[1, 10, "Chicago", 2],
|
77
|
+
[10, 10, "London", 50])
|
78
|
+
end
|
79
|
+
|
80
|
+
def test_max_iterations
|
81
|
+
data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
|
82
|
+
clusterer = KMeans.new.
|
83
|
+
set_parameters({:max_iterations=>1}).
|
84
|
+
build(data_set, 4)
|
85
|
+
assert_equal 1, clusterer.iterations
|
86
|
+
end
|
87
|
+
|
88
|
+
private
|
89
|
+
def draw_map(clusterer)
|
90
|
+
map = Array.new(11) {Array.new(11, 0)}
|
91
|
+
clusterer.clusters.each_index do |i|
|
92
|
+
clusterer.clusters[i].data_items.each do |point|
|
93
|
+
map[point.first][point.last]=(i+1)
|
94
|
+
end
|
95
|
+
end
|
96
|
+
map.each { |row| puts row.inspect}
|
97
|
+
end
|
98
|
+
|
99
|
+
end
|
100
|
+
|