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 +1,53 @@
|
|
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/median_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::MedianLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
|
15
|
+
end
|
16
|
+
|
17
|
+
class Ai4r::Clusterers::MedianLinkageTest < 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::MedianLinkage.send(:public,
|
40
|
+
*Ai4r::Clusterers::MedianLinkage.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::MedianLinkage.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 +1,122 @@
|
|
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/single_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::SingleLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix
|
15
|
+
end
|
16
|
+
|
17
|
+
class SingleLinkageTest < 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
|
+
SingleLinkage.send(:public, *SingleLinkage.protected_instance_methods)
|
40
|
+
end
|
41
|
+
|
42
|
+
def test_build
|
43
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
44
|
+
clusterer.build(DataSet.new(:data_items => @@data), 4)
|
45
|
+
#draw_map(clusterer)
|
46
|
+
assert_equal 4, clusterer.clusters.length
|
47
|
+
end
|
48
|
+
|
49
|
+
def test_eval
|
50
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
51
|
+
clusterer.build(DataSet.new(:data_items => @@data), 4)
|
52
|
+
assert_equal 2, clusterer.eval([0,8])
|
53
|
+
assert_equal 0, clusterer.eval([8,0])
|
54
|
+
end
|
55
|
+
|
56
|
+
def test_create_distance_matrix
|
57
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
58
|
+
clusterer.create_distance_matrix(DataSet.new(:data_items => @@data))
|
59
|
+
assert clusterer.distance_matrix
|
60
|
+
clusterer.distance_matrix.each_with_index do |row, row_index|
|
61
|
+
assert_equal row_index+1, row.length
|
62
|
+
end
|
63
|
+
assert_equal @@expected_distance_matrix, clusterer.distance_matrix
|
64
|
+
end
|
65
|
+
|
66
|
+
def test_read_distance_matrix
|
67
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
68
|
+
clusterer.distance_matrix = @@expected_distance_matrix
|
69
|
+
assert_equal 9.0, clusterer.read_distance_matrix(3, 2)
|
70
|
+
assert_equal 9.0, clusterer.read_distance_matrix(2, 3)
|
71
|
+
assert_equal 0, clusterer.read_distance_matrix(5, 5)
|
72
|
+
end
|
73
|
+
|
74
|
+
def test_linkage_distance
|
75
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
76
|
+
clusterer.distance_matrix = @@expected_distance_matrix
|
77
|
+
assert_equal 89, clusterer.linkage_distance(0,1,2)
|
78
|
+
assert_equal 1, clusterer.linkage_distance(4,2,5)
|
79
|
+
end
|
80
|
+
|
81
|
+
def test_get_closest_clusters
|
82
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
83
|
+
clusterer.distance_matrix = @@expected_distance_matrix
|
84
|
+
assert_equal [1,0], clusterer.get_closest_clusters([[0,1], [3,4]])
|
85
|
+
assert_equal [2,1], clusterer.get_closest_clusters([[3,4], [0,1], [5,6]])
|
86
|
+
end
|
87
|
+
|
88
|
+
def test_create_initial_index_clusters
|
89
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
90
|
+
clusterer.data_set = DataSet.new :data_items => @@data
|
91
|
+
index_clusters = clusterer.create_initial_index_clusters
|
92
|
+
assert_equal @@data.length, index_clusters.length
|
93
|
+
assert_equal 0, index_clusters.first.first
|
94
|
+
assert_equal @@data.length-1, index_clusters.last.first
|
95
|
+
end
|
96
|
+
|
97
|
+
def test_merge_clusters
|
98
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
99
|
+
clusters = clusterer.merge_clusters(1,2, [[1,2],[3,4],[5,6]])
|
100
|
+
assert_equal [[1,2], [3,4,5,6]], clusters.collect {|x| x.sort}
|
101
|
+
clusters = clusterer.merge_clusters(2,1, [[1,2],[3,4],[5,6]])
|
102
|
+
assert_equal [[1,2], [3,4,5,6]], clusters.collect {|x| x.sort}
|
103
|
+
end
|
104
|
+
|
105
|
+
def test_distance_between_item_and_cluster
|
106
|
+
clusterer = Ai4r::Clusterers::SingleLinkage.new
|
107
|
+
assert_equal 8.0, clusterer.distance_between_item_and_cluster([1,2],
|
108
|
+
DataSet.new(:data_items => [[3,4],[5,6]]))
|
109
|
+
end
|
110
|
+
|
111
|
+
private
|
112
|
+
def draw_map(clusterer)
|
113
|
+
map = Array.new(11) {Array.new(11, 0)}
|
114
|
+
clusterer.clusters.each_index do |i|
|
115
|
+
clusterer.clusters[i].data_items.each do |point|
|
116
|
+
map[point.first][point.last]=(i+1)
|
117
|
+
end
|
118
|
+
end
|
119
|
+
map.each { |row| puts row.inspect}
|
120
|
+
end
|
121
|
+
|
122
|
+
end
|
@@ -0,0 +1,61 @@
|
|
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/ward_linkage_hierarchical'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::WardLinkageHierarchical
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
|
15
|
+
end
|
16
|
+
|
17
|
+
class Ai4r::Clusterers::WardLinkageHierarchicalTest < 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::WardLinkageHierarchical.send(:public,
|
40
|
+
*Ai4r::Clusterers::WardLinkageHierarchical.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::WardLinkageHierarchical.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_in_delta 123.4166, clusterer.linkage_distance(0,1,2), 0.0001
|
49
|
+
assert_equal 27.75, clusterer.linkage_distance(4,2,5)
|
50
|
+
end
|
51
|
+
|
52
|
+
def test_cluster_tree
|
53
|
+
clusterer = Ai4r::Clusterers::WardLinkageHierarchical.new
|
54
|
+
clusterer.build(DataSet.new(:data_items => @@data), 1)
|
55
|
+
|
56
|
+
assert_equal clusterer.cluster_tree.length, @@data.length - 1
|
57
|
+
end
|
58
|
+
|
59
|
+
|
60
|
+
end
|
61
|
+
|
@@ -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/ward_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::WardLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
|
15
|
+
end
|
16
|
+
|
17
|
+
class Ai4r::Clusterers::WardLinkageTest < 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::WardLinkage.send(:public,
|
40
|
+
*Ai4r::Clusterers::WardLinkage.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::WardLinkage.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_in_delta 123.4166, clusterer.linkage_distance(0,1,2), 0.0001
|
49
|
+
assert_equal 27.75, clusterer.linkage_distance(4,2,5)
|
50
|
+
end
|
51
|
+
|
52
|
+
end
|
53
|
+
|
@@ -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/weighted_average_linkage'
|
12
|
+
|
13
|
+
class Ai4r::Clusterers::WeightedAverageLinkage
|
14
|
+
attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
|
15
|
+
end
|
16
|
+
|
17
|
+
class Ai4r::Clusterers::WeightedAverageLinkageTest < 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::WeightedAverageLinkage.send(:public,
|
40
|
+
*Ai4r::Clusterers::WeightedAverageLinkage.protected_instance_methods)
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_linkage_distance
|
44
|
+
clusterer = Ai4r::Clusterers::WeightedAverageLinkage.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 93.5, clusterer.linkage_distance(0,1,2)
|
49
|
+
assert_equal 37.5, clusterer.linkage_distance(4,2,5)
|
50
|
+
end
|
51
|
+
|
52
|
+
end
|
53
|
+
|
@@ -0,0 +1,96 @@
|
|
1
|
+
# Author:: Sergio Fierens
|
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/data/data_set'
|
12
|
+
|
13
|
+
module Ai4r
|
14
|
+
module Data
|
15
|
+
class DataSetTest < Test::Unit::TestCase
|
16
|
+
|
17
|
+
def test_load_csv_with_labels
|
18
|
+
set = DataSet.new.load_csv_with_labels("#{File.dirname(__FILE__)}/data_set.csv")
|
19
|
+
assert_equal 120, set.data_items.length
|
20
|
+
assert_equal ["zone", "rooms", "size", "price"], set.data_labels
|
21
|
+
end
|
22
|
+
|
23
|
+
def test_build_domains
|
24
|
+
domains = [ Set.new(["New York", "Chicago"]),
|
25
|
+
Set.new(["M", "F"]),
|
26
|
+
[5, 85],
|
27
|
+
Set.new(["Y", "N"]) ]
|
28
|
+
data = [ [ "New York", "M", 23, "Y"],
|
29
|
+
[ "Chicago", "M", 85, "Y"],
|
30
|
+
[ "New York", "F", 32, "Y"],
|
31
|
+
[ "New York", "M", 5, "N"],
|
32
|
+
[ "Chicago", "M", 15, "N"],
|
33
|
+
[ "Chicago", "F", 45, "Y"] ]
|
34
|
+
labels = ["city", "gender", "age", "result"]
|
35
|
+
set = DataSet.new({:data_items => data, :data_labels => labels})
|
36
|
+
assert_equal domains, set.build_domains
|
37
|
+
assert_equal domains[0], set.build_domain("city")
|
38
|
+
assert_equal domains[1], set.build_domain(1)
|
39
|
+
assert_equal domains[2], set.build_domain("age")
|
40
|
+
assert_equal domains[3], set.build_domain("result")
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_set_data_labels
|
44
|
+
labels = ["A", "B"]
|
45
|
+
set = DataSet.new.set_data_labels(labels)
|
46
|
+
assert_equal labels, set.data_labels
|
47
|
+
set = DataSet.new(:data_labels => labels)
|
48
|
+
assert_equal labels, set.data_labels
|
49
|
+
set = DataSet.new(:data_items => [[ 1, 2, 3]])
|
50
|
+
assert_raise(ArgumentError) { set.set_data_labels(labels) }
|
51
|
+
end
|
52
|
+
|
53
|
+
def test_set_data_items
|
54
|
+
items = [ [ "New York", "M", "Y"],
|
55
|
+
[ "Chicago", "M", "Y"],
|
56
|
+
[ "New York", "F", "Y"],
|
57
|
+
[ "New York", "M", "N"],
|
58
|
+
[ "Chicago", "M", "N"],
|
59
|
+
[ "Chicago", "F", "Y"] ]
|
60
|
+
set = DataSet.new.set_data_items(items)
|
61
|
+
assert_equal items, set.data_items
|
62
|
+
assert_equal 3, set.data_labels.length
|
63
|
+
items << items.first[0..-2]
|
64
|
+
assert_raise(ArgumentError) { set.set_data_items(items) }
|
65
|
+
assert_raise(ArgumentError) { set.set_data_items(nil) }
|
66
|
+
assert_raise(ArgumentError) { set.set_data_items([1]) }
|
67
|
+
end
|
68
|
+
|
69
|
+
def test_get_mean_or_mode
|
70
|
+
items = [ [ "New York", 25, "Y"],
|
71
|
+
[ "New York", 55, "Y"],
|
72
|
+
[ "Chicago", 23, "Y"],
|
73
|
+
[ "Boston", 23, "N"],
|
74
|
+
[ "Chicago", 12, "N"],
|
75
|
+
[ "Chicago", 87, "Y"] ]
|
76
|
+
set = DataSet.new.set_data_items(items)
|
77
|
+
assert_equal ["Chicago", 37.5, "Y"], set.get_mean_or_mode
|
78
|
+
end
|
79
|
+
|
80
|
+
def test_index
|
81
|
+
items = [ [ "New York", 25, "Y"],
|
82
|
+
[ "New York", 55, "Y"],
|
83
|
+
[ "Chicago", 23, "Y"],
|
84
|
+
[ "Boston", 23, "N"],
|
85
|
+
[ "Chicago", 12, "N"],
|
86
|
+
[ "Chicago", 87, "Y"] ]
|
87
|
+
set = DataSet.new.set_data_items(items)
|
88
|
+
assert_equal set.data_labels, set[0].data_labels
|
89
|
+
assert_equal [[ "New York", 25, "Y"]], set[0].data_items
|
90
|
+
assert_equal [[ "Chicago", 23, "Y"],[ "Boston", 23, "N"]], set[2..3].data_items
|
91
|
+
assert_equal items[1..-1], set[1..-1].data_items
|
92
|
+
end
|
93
|
+
|
94
|
+
end
|
95
|
+
end
|
96
|
+
end
|
@@ -0,0 +1,81 @@
|
|
1
|
+
# Author:: Sergio Fierens
|
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/data/proximity'
|
12
|
+
|
13
|
+
module Ai4r
|
14
|
+
module Data
|
15
|
+
class ProximityTest < Test::Unit::TestCase
|
16
|
+
|
17
|
+
@@delta = 0.0001
|
18
|
+
@@data1 = [rand*10, rand*10, rand*-10]
|
19
|
+
@@data2 = [rand*10, rand*-10, rand*10]
|
20
|
+
|
21
|
+
def test_squared_euclidean_distance
|
22
|
+
assert_equal 0, Proximity.squared_euclidean_distance(@@data1, @@data1)
|
23
|
+
assert_equal Proximity.squared_euclidean_distance(@@data1, @@data2),
|
24
|
+
Proximity.squared_euclidean_distance(@@data2, @@data1)
|
25
|
+
assert 0 <= Proximity.squared_euclidean_distance(@@data1, @@data1)
|
26
|
+
assert_equal 2, Proximity.squared_euclidean_distance([1,1], [2,2])
|
27
|
+
assert_equal 9, Proximity.squared_euclidean_distance([3], [0])
|
28
|
+
end
|
29
|
+
|
30
|
+
def test_euclidean_distance
|
31
|
+
assert_equal 0, Proximity.euclidean_distance(@@data1, @@data1)
|
32
|
+
assert_equal Proximity.euclidean_distance(@@data1, @@data2),
|
33
|
+
Proximity.euclidean_distance(@@data2, @@data1)
|
34
|
+
assert 0 <= Proximity.euclidean_distance(@@data1, @@data1)
|
35
|
+
assert_equal Math.sqrt(2), Proximity.euclidean_distance([1,1], [2,2])
|
36
|
+
assert_equal 3, Proximity.euclidean_distance([3], [0])
|
37
|
+
end
|
38
|
+
|
39
|
+
def test_manhattan_distance
|
40
|
+
assert_equal 0, Proximity.manhattan_distance(@@data1, @@data1)
|
41
|
+
assert_equal Proximity.manhattan_distance(@@data1, @@data2),
|
42
|
+
Proximity.manhattan_distance(@@data2, @@data1)
|
43
|
+
assert 0 <= Proximity.manhattan_distance(@@data1, @@data1)
|
44
|
+
assert_equal 2, Proximity.manhattan_distance([1,1], [2,2])
|
45
|
+
assert_equal 9, Proximity.manhattan_distance([1,10], [2,2])
|
46
|
+
assert_equal 3, Proximity.manhattan_distance([3], [0])
|
47
|
+
end
|
48
|
+
|
49
|
+
def test_sup_distance
|
50
|
+
assert_equal 0, Proximity.sup_distance(@@data1, @@data1)
|
51
|
+
assert_equal Proximity.sup_distance(@@data1, @@data2),
|
52
|
+
Proximity.sup_distance(@@data2, @@data1)
|
53
|
+
assert 0 <= Proximity.sup_distance(@@data1, @@data1)
|
54
|
+
assert_equal 1, Proximity.sup_distance([1,1], [2,2])
|
55
|
+
assert_equal 8, Proximity.sup_distance([1,10], [2,2])
|
56
|
+
assert_equal 3, Proximity.sup_distance([3], [0])
|
57
|
+
end
|
58
|
+
|
59
|
+
def test_hamming_distance
|
60
|
+
assert_equal 0, Proximity.hamming_distance(@@data1, @@data1)
|
61
|
+
assert_equal Proximity.hamming_distance(@@data1, @@data2),
|
62
|
+
Proximity.hamming_distance(@@data2, @@data1)
|
63
|
+
assert 0 <= Proximity.hamming_distance(@@data1, @@data1)
|
64
|
+
assert_equal 1, Proximity.hamming_distance([1,1], [0,1])
|
65
|
+
assert_equal 2, Proximity.hamming_distance([1,10], [2,2])
|
66
|
+
assert_equal 1, Proximity.hamming_distance([3], [0])
|
67
|
+
end
|
68
|
+
|
69
|
+
def test_simple_matching_distance
|
70
|
+
assert_equal 0, Proximity.simple_matching_distance(@@data1, @@data1)
|
71
|
+
assert_equal Proximity.simple_matching_distance(@@data1, @@data2),
|
72
|
+
Proximity.simple_matching_distance(@@data2, @@data1)
|
73
|
+
assert 0 <= Proximity.simple_matching_distance(@@data1, @@data1)
|
74
|
+
assert_equal 1, Proximity.simple_matching_distance([1,2], [0,1])
|
75
|
+
assert_equal 1.0/0, Proximity.simple_matching_distance([1,10], [2,2])
|
76
|
+
assert_equal 1.0/0, Proximity.simple_matching_distance([3], [0])
|
77
|
+
end
|
78
|
+
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|