ai4r 1.13 → 2.0

data/test/clusterers/k_means_test.rb

@@ -1,167 +0,0 @@
-# Author::    Sergio Fierens (implementation)
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://www.ai4r.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require 'ai4r/clusterers/k_means'
-
-class KMeansTest < Test::Unit::TestCase
-  
-  include Ai4r::Clusterers
-  include Ai4r::Data
-
-  @@data = [  [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
-              [1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
-              
-  # k-means will generate an empty cluster with this data and initial centroid assignment            
-  @@empty_cluster_data = [[-0.1, 0], [0, 0], [0.1, 0], [-0.1, 10], [0.1, 10], [0.2, 10]]
-  @@empty_centroid_indices = [0,1,2]
-              
-  def test_build
-    data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
-    clusterer = KMeans.new.build(data_set, 4)
-    #draw_map(clusterer)
-    # Verify that all 4 clusters are created
-    assert_equal 4, clusterer.clusters.length
-    assert_equal 4, clusterer.centroids.length
-    # The addition of all instances of every cluster must be equal to
-    # the number of data points
-    total_length = 0
-    clusterer.clusters.each do |cluster| 
-      total_length += cluster.data_items.length
-    end
-    assert_equal @@data.length, total_length
-    # Data inside clusters must be the same as original data
-    clusterer.clusters.each do |cluster| 
-     cluster.data_items.each do |data_item|
-       assert @@data.include?(data_item)
-     end
-    end
-  end
-
-  def test_build_and_eliminate_empty_clusters
-    data_set = DataSet.new(:data_items => @@empty_cluster_data, :data_labels => ["X", "Y"])
-    # :eliminate is the :on_empty default, so we don't need to pass it as a parameter for it
-    clusterer = KMeans.new.set_parameters({:centroid_indices=>@@empty_centroid_indices}).build(data_set, @@empty_centroid_indices.size)
-    
-    # Verify that one cluster was eliminated
-    assert_equal @@empty_centroid_indices.size - 1, clusterer.clusters.length
-    assert_equal @@empty_centroid_indices.size - 1, clusterer.centroids.length
-    
-    # The addition of all instances of every cluster must be equal to
-    # the number of data points
-    total_length = 0
-    clusterer.clusters.each do |cluster| 
-      total_length += cluster.data_items.length
-    end
-    assert_equal @@empty_cluster_data.length, total_length
-    # Data inside clusters must be the same as original data
-    clusterer.clusters.each do |cluster| 
-     cluster.data_items.each do |data_item|
-       assert @@empty_cluster_data.include?(data_item)
-     end
-    end
-  end
-
-  def test_eval
-    data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
-    clusterer = KMeans.new.build(data_set, 4)
-    item = [10,0]
-    cluster_index = clusterer.eval(item)
-    # Must return a valid cluster index [0-3]
-    assert cluster_index >= 0 && cluster_index < 4
-    # Distance to cluster centroid must be less than distance to any other
-    # centroid
-    min_distance = clusterer.distance(clusterer.centroids[cluster_index], item)
-    clusterer.centroids.each do |centroid|
-      assert clusterer.distance(centroid, item) >= min_distance
-    end
-  end
-
-  def test_distance
-    clusterer = KMeans.new
-    # By default, distance returns the euclidean distance to the power of 2
-    assert_equal 2385, clusterer.distance(
-      [1, 10, "Chicago", 2], 
-      [10, 10, "London", 50])
-    
-    # Ensure default distance raises error for nil argument
-    exception = assert_raise(TypeError) {clusterer.distance([1, 10], [nil, nil])}
-    assert_equal("nil can't be coerced into Fixnum", exception.message)
-    
-    # Test new distance definition
-    manhattan_distance = lambda do |a, b| 
-        dist = 0.0
-        a.each_index do |index|
-          if a[index].is_a?(Numeric) && b[index].is_a?(Numeric)
-            dist = dist + (a[index]-b[index]).abs
-          end
-        end
-        dist
-    end
-    clusterer.set_parameters({:distance_function => manhattan_distance})
-    assert_equal 57, clusterer.distance(
-      [1, 10, "Chicago", 2], 
-      [10, 10, "London", 50])
-  end
-
-  def test_max_iterations
-    data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
-    clusterer = KMeans.new.
-      set_parameters({:max_iterations=>1}).
-      build(data_set, 4)
-    assert_equal 1, clusterer.iterations
-  end
-
-  def test_centroid_indices
-    data_set = DataSet.new(:data_items => @@data, :data_labels => ["X", "Y"])
-    # centroid_indices need not be specified:
-    KMeans.new.build(data_set, 4)
-    # centroid_indices can be specified:
-    KMeans.new.set_parameters({:centroid_indices=>[0,1,2,3]}).build(data_set, 4)
-    # raises exception if number of clusters differs from length of centroid_indices:
-    exception = assert_raise(ArgumentError) {KMeans.new.set_parameters({:centroid_indices=>[0,1,2,3]}).build(data_set, 2)}
-    assert_equal('Length of centroid indices array differs from the specified number of clusters', exception.message)
-    # raises exception for bad centroid index:
-    exception = assert_raise(ArgumentError) {KMeans.new.set_parameters({:centroid_indices=>[0,1,2,@@data.size+10]}).build(data_set, 4)}
-    assert_equal("Invalid centroid index #{@@data.size+10}", exception.message)
-  end
-
-  def test_on_empty
-    data_set = DataSet.new(:data_items => @@empty_cluster_data, :data_labels => ["X", "Y"])
-    clusterer = KMeans.new.set_parameters({:centroid_indices=>@@empty_centroid_indices}).build(data_set, @@empty_centroid_indices.size)
-    # Verify that one cluster was eliminated
-    assert_equal @@empty_centroid_indices.size - 1, clusterer.clusters.length
-    # Verify that eliminate is the on_empty default
-    assert_equal 'eliminate', clusterer.on_empty
-    # Verify that invalid on_empty option throws an argument error 
-    exception = assert_raise(ArgumentError) {KMeans.new.set_parameters({:centroid_indices=>@@empty_centroid_indices, :on_empty=>'ldkfje'}).build(data_set, @@empty_centroid_indices.size)}
-    assert_equal("Invalid value for on_empty", exception.message)
-    # Verify that on_empty option 'terminate' raises an error when an empty cluster arises
-    exception = assert_raise(TypeError) {KMeans.new.set_parameters({:centroid_indices=>@@empty_centroid_indices, :on_empty=>'terminate'}).build(data_set, @@empty_centroid_indices.size)}
-    assert_equal("nil can't be coerced into Float", exception.message)
-    clusterer = KMeans.new.set_parameters({:centroid_indices=>@@empty_centroid_indices, :on_empty=>'random'}).build(data_set, @@empty_centroid_indices.size)
-    # Verify that cluster was not eliminated
-    assert_equal @@empty_centroid_indices.size, clusterer.clusters.length
-    clusterer = KMeans.new.set_parameters({:centroid_indices=>@@empty_centroid_indices, :on_empty=>'outlier'}).build(data_set, @@empty_centroid_indices.size)
-    # Verify that cluster was not eliminated
-    assert_equal @@empty_centroid_indices.size, clusterer.clusters.length
-  end
-
-  private
-  def draw_map(clusterer)
-    map = Array.new(11) {Array.new(11, 0)}
-    clusterer.clusters.each_index do |i|
-      clusterer.clusters[i].data_items.each do |point|
-        map[point.first][point.last]=(i+1)
-      end
-    end
-    map.each { |row| puts row.inspect}
-  end
-end
-

data/test/clusterers/median_linkage_test.rb

@@ -1,53 +0,0 @@
-# Author::    Sergio Fierens (implementation)
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://ai4r.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require 'ai4r/clusterers/median_linkage'
-
-class Ai4r::Clusterers::MedianLinkage
-  attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
-end
-
-class Ai4r::Clusterers::MedianLinkageTest < Test::Unit::TestCase
-  
-  include Ai4r::Clusterers
-  include Ai4r::Data
-
-  @@data = [  [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
-              [1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
-            
-  @@expected_distance_matrix = [ 
-        [98.0], 
-        [89.0, 5.0], 
-        [68.0, 26.0, 9.0], 
-        [74.0, 4.0, 1.0, 10.0], 
-        [0.0, 98.0, 89.0, 68.0, 74.0], 
-        [81.0, 53.0, 26.0, 5.0, 29.0, 81.0], 
-        [8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0], 
-        [100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0], 
-        [68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0], 
-        [49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0], 
-        [2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
-      
-   def setup
-     Ai4r::Clusterers::MedianLinkage.send(:public, 
-       *Ai4r::Clusterers::MedianLinkage.protected_instance_methods)  
-   end
-  
-   def test_linkage_distance
-    clusterer = Ai4r::Clusterers::MedianLinkage.new
-    clusterer.data_set = DataSet.new :data_items => @@data
-    clusterer.index_clusters = clusterer.create_initial_index_clusters
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_equal 92.25, clusterer.linkage_distance(0,1,2)
-    assert_equal 15.25, clusterer.linkage_distance(4,2,5)
-  end
-
-end
-

data/test/clusterers/single_linkage_test.rb

@@ -1,122 +0,0 @@
-# Author::    Sergio Fierens (implementation)
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://ai4r.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require 'ai4r/clusterers/single_linkage'
- 
-class Ai4r::Clusterers::SingleLinkage
-  attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix
-end
- 
-class SingleLinkageTest < Test::Unit::TestCase
-  
-  include Ai4r::Clusterers
-  include Ai4r::Data
- 
-  @@data = [ [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
-              [1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
-            
-  @@expected_distance_matrix = [
-        [98.0],
-        [89.0, 5.0],
-        [68.0, 26.0, 9.0],
-        [74.0, 4.0, 1.0, 10.0],
-        [0.0, 98.0, 89.0, 68.0, 74.0],
-        [81.0, 53.0, 26.0, 5.0, 29.0, 81.0],
-        [8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0],
-        [100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0],
-        [68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0],
-        [49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0],
-        [2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
-  
-  def setup
-    SingleLinkage.send(:public, *SingleLinkage.protected_instance_methods)
-  end
-  
-  def test_build
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.build(DataSet.new(:data_items => @@data), 4)
-    #draw_map(clusterer)
-    assert_equal 4, clusterer.clusters.length
-  end
-  
-  def test_eval
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.build(DataSet.new(:data_items => @@data), 4)
-    assert_equal 2, clusterer.eval([0,8])
-    assert_equal 0, clusterer.eval([8,0])
-  end
- 
-  def test_create_distance_matrix
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.create_distance_matrix(DataSet.new(:data_items => @@data))
-    assert clusterer.distance_matrix
-    clusterer.distance_matrix.each_with_index do |row, row_index|
-      assert_equal row_index+1, row.length
-    end
-    assert_equal @@expected_distance_matrix, clusterer.distance_matrix
-  end
-  
-  def test_read_distance_matrix
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_equal 9.0, clusterer.read_distance_matrix(3, 2)
-    assert_equal 9.0, clusterer.read_distance_matrix(2, 3)
-    assert_equal 0, clusterer.read_distance_matrix(5, 5)
-  end
-  
-  def test_linkage_distance
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_equal 89, clusterer.linkage_distance(0,1,2)
-    assert_equal 1, clusterer.linkage_distance(4,2,5)
-  end
-  
-  def test_get_closest_clusters
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_equal [1,0], clusterer.get_closest_clusters([[0,1], [3,4]])
-    assert_equal [2,1], clusterer.get_closest_clusters([[3,4], [0,1], [5,6]])
-   end
-   
-  def test_create_initial_index_clusters
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusterer.data_set = DataSet.new :data_items => @@data
-    index_clusters = clusterer.create_initial_index_clusters
-    assert_equal @@data.length, index_clusters.length
-    assert_equal 0, index_clusters.first.first
-    assert_equal @@data.length-1, index_clusters.last.first
-  end
-  
-  def test_merge_clusters
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    clusters = clusterer.merge_clusters(1,2, [[1,2],[3,4],[5,6]])
-    assert_equal [[1,2], [3,4,5,6]], clusters.collect {|x| x.sort}
-    clusters = clusterer.merge_clusters(2,1, [[1,2],[3,4],[5,6]])
-    assert_equal [[1,2], [3,4,5,6]], clusters.collect {|x| x.sort}
-  end
-  
-  def test_distance_between_item_and_cluster
-    clusterer = Ai4r::Clusterers::SingleLinkage.new
-    assert_equal 8.0, clusterer.distance_between_item_and_cluster([1,2],
-      DataSet.new(:data_items => [[3,4],[5,6]]))
-  end
-  
-  private
-  def draw_map(clusterer)
-    map = Array.new(11) {Array.new(11, 0)}
-    clusterer.clusters.each_index do |i|
-      clusterer.clusters[i].data_items.each do |point|
-        map[point.first][point.last]=(i+1)
-      end
-    end
-    map.each { |row| puts row.inspect}
-  end
-  
-end

data/test/clusterers/ward_linkage_hierarchical_test.rb

@@ -1,81 +0,0 @@
-# Author::    Sergio Fierens (implementation)
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://ai4r.rubyforge.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require File.dirname(__FILE__) + '/../../lib/ai4r/clusterers/ward_linkage_hierarchical'
-
-class Ai4r::Clusterers::WardLinkageHierarchical
-  attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
-end
-
-class Ai4r::Clusterers::WardLinkageHierarchicalTest < Test::Unit::TestCase
-  
-  include Ai4r::Clusterers
-  include Ai4r::Data
-
-  @@data = [  [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
-              [1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
-            
-  @@expected_distance_matrix = [ 
-        [98.0], 
-        [89.0, 5.0], 
-        [68.0, 26.0, 9.0], 
-        [74.0, 4.0, 1.0, 10.0], 
-        [0.0, 98.0, 89.0, 68.0, 74.0], 
-        [81.0, 53.0, 26.0, 5.0, 29.0, 81.0], 
-        [8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0], 
-        [100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0], 
-        [68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0], 
-        [49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0], 
-        [2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
-      
-   def setup
-     Ai4r::Clusterers::WardLinkageHierarchical.send(:public, 
-       *Ai4r::Clusterers::WardLinkageHierarchical.protected_instance_methods)  
-   end
-   
-  def test_linkage_distance
-    clusterer = Ai4r::Clusterers::WardLinkageHierarchical.new
-    clusterer.data_set = DataSet.new :data_items => @@data
-    clusterer.index_clusters = clusterer.create_initial_index_clusters
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_in_delta 123.4166, clusterer.linkage_distance(0,1,2), 0.0001
-    assert_equal 27.75, clusterer.linkage_distance(4,2,5)
-  end
-
-  def test_cluster_tree
-    clusterer = Ai4r::Clusterers::WardLinkageHierarchical.new
-    clusterer.build(DataSet.new(:data_items => @@data), 1)
-    assert_equal @@data.length, clusterer.cluster_tree.length
-  end
-    
-  def test_cluster_tree_limit
-    depth = 5
-    clusterer = Ai4r::Clusterers::WardLinkageHierarchical.new(5)
-    clusterer.build(DataSet.new(:data_items => @@data), 1)
-    assert_equal 5, clusterer.cluster_tree.length
-  end
-    
-  def test_cluster_tree_first_length
-    depth = 5
-    clusterer = Ai4r::Clusterers::WardLinkageHierarchical.new(5)
-    clusterer.build(DataSet.new(:data_items => @@data), 1)
-    assert_equal 1, clusterer.cluster_tree.first.length
-  end
-    
-  def test_cluster_tree_last_length
-    depth = 5
-    clusterer = Ai4r::Clusterers::WardLinkageHierarchical.new(5)
-    clusterer.build(DataSet.new(:data_items => @@data), 1)
-    assert_equal 5, clusterer.cluster_tree.last.length
-  end
-    
-
-end
-

data/test/clusterers/ward_linkage_test.rb

@@ -1,53 +0,0 @@
-# Author::    Sergio Fierens (implementation)
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://ai4r.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require 'ai4r/clusterers/ward_linkage'
-
-class Ai4r::Clusterers::WardLinkage
-  attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
-end
-
-class Ai4r::Clusterers::WardLinkageTest < Test::Unit::TestCase
-  
-  include Ai4r::Clusterers
-  include Ai4r::Data
-
-  @@data = [  [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
-              [1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
-            
-  @@expected_distance_matrix = [ 
-        [98.0], 
-        [89.0, 5.0], 
-        [68.0, 26.0, 9.0], 
-        [74.0, 4.0, 1.0, 10.0], 
-        [0.0, 98.0, 89.0, 68.0, 74.0], 
-        [81.0, 53.0, 26.0, 5.0, 29.0, 81.0], 
-        [8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0], 
-        [100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0], 
-        [68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0], 
-        [49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0], 
-        [2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
-      
-   def setup
-     Ai4r::Clusterers::WardLinkage.send(:public, 
-       *Ai4r::Clusterers::WardLinkage.protected_instance_methods)  
-   end
-   
-   def test_linkage_distance
-    clusterer = Ai4r::Clusterers::WardLinkage.new
-    clusterer.data_set = DataSet.new :data_items => @@data
-    clusterer.index_clusters = clusterer.create_initial_index_clusters
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_in_delta 123.4166, clusterer.linkage_distance(0,1,2), 0.0001
-    assert_equal 27.75, clusterer.linkage_distance(4,2,5)
-  end
-
-end
-

data/test/clusterers/weighted_average_linkage_test.rb

@@ -1,53 +0,0 @@
-# Author::    Sergio Fierens (implementation)
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://ai4r.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require 'ai4r/clusterers/weighted_average_linkage'
-
-class Ai4r::Clusterers::WeightedAverageLinkage
-  attr_accessor :data_set, :number_of_clusters, :clusters, :distance_matrix, :index_clusters
-end
-
-class Ai4r::Clusterers::WeightedAverageLinkageTest < Test::Unit::TestCase
-  
-  include Ai4r::Clusterers
-  include Ai4r::Data
-
-  @@data = [  [10, 3], [3, 10], [2, 8], [2, 5], [3, 8], [10, 3],
-              [1, 3], [8, 1], [2, 9], [2, 5], [3, 3], [9, 4]]
-            
-  @@expected_distance_matrix = [ 
-        [98.0], 
-        [89.0, 5.0], 
-        [68.0, 26.0, 9.0], 
-        [74.0, 4.0, 1.0, 10.0], 
-        [0.0, 98.0, 89.0, 68.0, 74.0], 
-        [81.0, 53.0, 26.0, 5.0, 29.0, 81.0], 
-        [8.0, 106.0, 85.0, 52.0, 74.0, 8.0, 53.0], 
-        [100.0, 2.0, 1.0, 16.0, 2.0, 100.0, 37.0, 100.0], 
-        [68.0, 26.0, 9.0, 0.0, 10.0, 68.0, 5.0, 52.0, 16.0], 
-        [49.0, 49.0, 26.0, 5.0, 25.0, 49.0, 4.0, 29.0, 37.0, 5.0], 
-        [2.0, 72.0, 65.0, 50.0, 52.0, 2.0, 65.0, 10.0, 74.0, 50.0, 37.0]]
-      
-   def setup
-     Ai4r::Clusterers::WeightedAverageLinkage.send(:public, 
-       *Ai4r::Clusterers::WeightedAverageLinkage.protected_instance_methods)  
-   end
-  
-   def test_linkage_distance
-    clusterer = Ai4r::Clusterers::WeightedAverageLinkage.new
-    clusterer.data_set = DataSet.new :data_items => @@data
-    clusterer.index_clusters = clusterer.create_initial_index_clusters
-    clusterer.distance_matrix = @@expected_distance_matrix
-    assert_equal 93.5, clusterer.linkage_distance(0,1,2)
-    assert_equal 37.5, clusterer.linkage_distance(4,2,5)
-  end
-
-end
-

data/test/data/data_set_test.rb

@@ -1,104 +0,0 @@
-# Author::    Sergio Fierens
-# License::   MPL 1.1
-# Project::   ai4r
-# Url::       http://www.ai4r.org/
-#
-# You can redistribute it and/or modify it under the terms of 
-# the Mozilla Public License version 1.1  as published by the 
-# Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
-
-require 'test/unit'
-require 'ai4r/data/data_set'
-
-module Ai4r
-  module Data
-    class DataSetTest < Test::Unit::TestCase
-      
-      def test_load_csv_with_labels
-        set = DataSet.new.load_csv_with_labels("#{File.dirname(__FILE__)}/data_set.csv")
-        assert_equal 120, set.data_items.length
-        assert_equal ["zone", "rooms", "size", "price"], set.data_labels
-        assert_equal ["Moron Sur (GBA)","2","[28 m2 - 39 m2]","[29K-35K]"], set.data_items.first
-      end
-
-      def test_parse_csv_with_labels
-        set = DataSet.new.parse_csv_with_labels("#{File.dirname(__FILE__)}/data_set.csv")
-        assert_equal 120, set.data_items.length
-        assert_equal ["zone", "rooms", "size", "price"], set.data_labels
-        assert_equal ["Moron Sur (GBA)",2.0,"[28 m2 - 39 m2]","[29K-35K]"], set.data_items.first
-      end
-      
-      def test_build_domains
-        domains =  [  Set.new(["New York", "Chicago"]), 
-                      Set.new(["M", "F"]), 
-                      [5, 85],
-                      Set.new(["Y", "N"]) ]
-        data = [  [ "New York", "M", 23, "Y"],
-                  [ "Chicago", "M", 85, "Y"],
-                  [ "New York", "F", 32, "Y"],
-                  [ "New York", "M", 5, "N"],
-                  [ "Chicago", "M", 15, "N"],
-                  [ "Chicago", "F", 45, "Y"] ]
-        labels = ["city", "gender", "age", "result"]
-        set = DataSet.new({:data_items => data, :data_labels => labels})
-        assert_equal domains, set.build_domains
-        assert_equal domains[0], set.build_domain("city")
-        assert_equal domains[1], set.build_domain(1)
-        assert_equal domains[2], set.build_domain("age")
-        assert_equal domains[3], set.build_domain("result")
-      end
-      
-      def test_set_data_labels
-        labels = ["A", "B"]
-        set = DataSet.new.set_data_labels(labels)
-        assert_equal labels, set.data_labels
-        set = DataSet.new(:data_labels => labels)
-        assert_equal labels, set.data_labels
-        set = DataSet.new(:data_items => [[ 1, 2, 3]])
-        assert_raise(ArgumentError) { set.set_data_labels(labels) }
-      end
-
-      def test_set_data_items
-        items = [  [ "New York", "M", "Y"],
-                  [ "Chicago", "M", "Y"],
-                  [ "New York", "F", "Y"],
-                  [ "New York", "M", "N"],
-                  [ "Chicago", "M", "N"],
-                  [ "Chicago", "F", "Y"] ]
-        set = DataSet.new.set_data_items(items)
-        assert_equal items, set.data_items
-        assert_equal 3, set.data_labels.length
-        items << items.first[0..-2]
-        assert_raise(ArgumentError) { set.set_data_items(items) }
-        assert_raise(ArgumentError) { set.set_data_items(nil) }
-        assert_raise(ArgumentError) { set.set_data_items([1]) }
-      end
-     
-      def test_get_mean_or_mode
-                items = [  [ "New York", 25, "Y"],
-                  [ "New York", 55, "Y"],
-                  [ "Chicago", 23, "Y"],
-                  [ "Boston", 23, "N"],
-                  [ "Chicago", 12, "N"],
-                  [ "Chicago", 87, "Y"] ]
-        set = DataSet.new.set_data_items(items)
-        assert_equal ["Chicago", 37.5, "Y"], set.get_mean_or_mode
-      end
-      
-      def test_index
-        items = [  [ "New York", 25, "Y"],
-                  [ "New York", 55, "Y"],
-                  [ "Chicago", 23, "Y"],
-                  [ "Boston", 23, "N"],
-                  [ "Chicago", 12, "N"],
-                  [ "Chicago", 87, "Y"] ]
-        set = DataSet.new.set_data_items(items)
-        assert_equal set.data_labels, set[0].data_labels
-        assert_equal [[ "New York", 25, "Y"]], set[0].data_items
-        assert_equal [[ "Chicago", 23, "Y"],[ "Boston", 23, "N"]], set[2..3].data_items
-        assert_equal items[1..-1], set[1..-1].data_items
-      end
-     
-    end
-  end
-end