ai4r 1.6 → 1.6.1

data/lib/ai4r/classifiers/hyperpipes.rb

@@ -8,7 +8,6 @@
 # Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
 
 require 'set'
-require File.dirname(__FILE__) + '/../data/constants'
 require File.dirname(__FILE__) + '/../data/data_set'
 require File.dirname(__FILE__) + '/../classifiers/classifier'
 
@@ -29,12 +28,13 @@ module Ai4r
       # as parameter. The last attribute of each item is considered as 
       # the item class.
       def build(data_set)
+        data_set.check_not_empty
         @data_set = data_set
         @domains = data_set.build_domains
         
         @pipes = {}
-        @domains.last.each {|cat| @pipes[cat] = build_pipe(@domains)}
-        @data_set.data_item.each {|item| update_pipe(@pipes[item.last], item) }
+        @domains.last.each {|cat| @pipes[cat] = build_pipe(@data_set)}
+        @data_set.data_items.each {|item| update_pipe(@pipes[item.last], item) }
         
         return self
       end
@@ -47,7 +47,7 @@ module Ai4r
         @pipes.each do |category, pipe|
           pipe.each_with_index do |bounds, i|
             if data[i].is_a? Numeric
-              votes[category]+=1 if data[i]>bounds[:min] && data[i]<bounds[:max]
+              votes[category]+=1 if data[i]>=bounds[:min] && data[i]<=bounds[:max]
             else
               votes[category]+=1 if bounds[data[i]]
             end
@@ -79,15 +79,15 @@ module Ai4r
           pipe.each_with_index do |bounds, i|
             rule = "votes['#{category}'] += 1 "
             if data[i].is_a? Numeric
-              rule += "if #{labels[i]} > #{bounds[:min]} && #{labels[i]} < #{bounds[:max]}"
+              rule += "if #{labels[i]} >= #{bounds[:min]} && #{labels[i]} <= #{bounds[:max]}"
             else
-              rule += "if #{bounds.inspect}['#{labels[i]}']"
+              rule += "if #{bounds.inspect}[#{labels[i]}]"
             end
             rules << rule
           end
         end
-        rules << "votes.to_a.max {|x, y| x.last <=> y.last}.first"
-        return rules.join('\n')
+        rules << "#{labels.last} = votes.to_a.max {|x, y| x.last <=> y.last}.first"
+        return rules.join("\n")
       end
       
       protected
@@ -95,7 +95,7 @@ module Ai4r
       def build_pipe(data_set)
         data_set.data_items.first[0...-1].collect do |att|
           if att.is_a? Numeric
-            {:min=>POSITIVE_INFINITY, :max=>NEGATIVE_INFINITY}
+            {:min=>1.0/0, :max=>-1.0/0}
           else
             Hash.new(false)
           end
@@ -104,7 +104,7 @@ module Ai4r
       
       def update_pipe(pipe, data_item)
         data_item[0...-1].each_with_index do |att, i|
-          if att.first.is_a? Numeric
+          if att.is_a? Numeric
             pipe[i][:min] = att if att < pipe[i][:min]
             pipe[i][:max] = att if att > pipe[i][:max]
           else

data/lib/ai4r/data/data_set.rb

@@ -121,36 +121,40 @@ module Ai4r
         return self
       end
 
-      # Returns an array with the domain of each attribute (Set instance 
-      # containing all possible values)
+      # Returns an array with the domain of each attribute:
+      # * Set instance containing all possible values for nominal attributes
+      # * Array with min and max values for numeric attributes (i.e. [min, max])
+      # 
       # Return example:
       # => [#<Set: {"New York", "Chicago"}>, 
       #     #<Set: {"<30", "[30-50)", "[50-80]", ">80"}>, 
-      #     #<Set: {"M", "F"}>, 
+      #     #<Set: {"M", "F"}>,
+      #     [5, 85], 
       #     #<Set: {"Y", "N"}>]
       def build_domains
-        domains = Array.new(num_attributes) { Set.new }
-        @data_items.each do |data|
-          data.each_index {|attr_index| domains[attr_index] << data[attr_index]}
-        end
-        return domains
+        @data_labels.collect {|attr_label| build_domain(attr_label) }
       end
       
       # Returns a Set instance containing all possible values for an attribute
       # The parameter can be an attribute label or index (0 based).
+      # * Set instance containing all possible values for nominal attributes
+      # * Array with min and max values for numeric attributes (i.e. [min, max])
       # 
       #   build_domain("city")
       #   => #<Set: {"New York", "Chicago"}>
+      #   
+      #   build_domain("age")
+      #   => [5, 85]
       # 
       #   build_domain(2) # In this example, the third attribute is gender
       #   => #<Set: {"M", "F"}>
       def build_domain(attr)
         index = get_index(attr)
-        domain = Set.new
-        @data_items.each do |data|
-          domain << data[index]
+        if @data_items.first[index].is_a?(Numeric)
+          return [Statistics.min(self, index), Statistics.max(self, index)]
+        else
+          return @data_items.inject(Set.new){|domain, x| domain << x[index]}
         end
-        return domain
       end
       
       # Returns attributes number, including class attribute

data/test/classifiers/hyperpipes_test.rb

@@ -0,0 +1,84 @@
+# Author::    Sergio Fierens
+# 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 File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/hyperpipes'
+require 'test/unit'
+
+class Ai4r::Classifiers::Hyperpipes
+  attr_accessor :data_set, :pipes
+end
+
+include Ai4r::Classifiers
+include Ai4r::Data
+
+class HyperpipesTest < Test::Unit::TestCase
+
+  @@data_labels = [ 'city', 'age', 'gender', 'marketing_target'  ]
+
+  @@data_items = [['New York',  25, 'M', 'Y'],
+              ['New York',  23, 'M', 'Y'],
+              ['New York',  18, 'M', 'Y'],
+              ['Chicago',   43, 'M', 'Y'],
+              ['New York',  34, 'F', 'N'],
+              ['Chicago',   33, 'F', 'Y'],
+              ['New York',  31, 'F', 'N'],
+              ['Chicago',   55, 'M', 'N'],
+              ['New York',  58, 'F', 'N'],
+              ['New York',  59, 'M', 'N'],
+              ['Chicago',   71, 'M', 'N'],
+              ['New York',  60, 'F', 'N'],
+              ['Chicago',   85, 'F', 'Y']
+            ]
+  
+  
+  def setup
+    Hyperpipes.send(:public, *Hyperpipes.protected_instance_methods)
+    @data_set = DataSet.new(:data_items => @@data_items, :data_labels => @@data_labels)
+  end
+  
+  def test_build_pipe
+    classifier = Hyperpipes.new
+    assert_equal [{}, {:max=>-1.0/0, :min=>1.0/0}, {}], classifier.build_pipe(@data_set)
+  end
+  
+  def test_get_rules
+    
+  end
+  
+  def test_build
+    assert_raise(ArgumentError) { Hyperpipes.new.build(DataSet.new) }
+    classifier = Hyperpipes.new.build(@data_set)
+    assert classifier.pipes.include?("Y")
+    assert classifier.pipes.include?("N")
+  end
+
+  def test_eval
+    classifier = Hyperpipes.new.build(@data_set)
+    assert classifier
+    assert_equal('N', classifier.eval(['Chicago',  55, 'M']))
+    assert_equal('N', classifier.eval(['New York', 35, 'F']))
+    assert_equal('Y', classifier.eval(['New York', 25, 'M']))
+    assert_equal('Y', classifier.eval(['Chicago',  85, 'F'])) 
+  end
+
+  def test_get_rules
+    classifier = Hyperpipes.new.build(@data_set)
+    age = 28
+    gender = "M"
+    marketing_target = nil
+    eval classifier.get_rules
+    assert_equal 'Y', marketing_target
+    age = 44 
+    city='New York'
+    eval classifier.get_rules
+    assert_equal 'N', marketing_target
+  end
+end
+
+  

data/test/clusterers/diana_test.rb

@@ -1,69 +1,69 @@
-# 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/diana'
-
-class Ai4r::Clusterers::Diana
-  attr_accessor :data_set, :number_of_clusters, :clusters
-end
-
-class DianaTest < Test::Unit::TestCase
-
-  @@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]]
-              
-  include Ai4r::Clusterers
-  include Ai4r::Data
-
-  def setup
-    Diana.send(:public, *Diana.protected_instance_methods)
-    @data_set = DataSet.new(:data_items => @@data.clone)
-  end
-          
-  def test_build
-    clusterer = Diana.new.build(@data_set, 4)
-    assert_equal 4, clusterer.clusters.length
-  end
-  
-  def test_eval
-    clusterer = Diana.new.build(@data_set, 4)
-    assert_equal 0, clusterer.eval([0, 0])
-    assert_equal 1, clusterer.eval([9, 3])
-    assert_equal 2, clusterer.eval([0,10])
-    assert_equal 3, clusterer.eval([8, 0])
-  end
-  
-  def test_cluster_diameter
-    clusterer = Diana.new
-    assert_equal 106, clusterer.cluster_diameter(@data_set)
-    assert_equal 98, clusterer.cluster_diameter(@data_set[0..2])
-  end
-  
-  def test_max_diameter_cluster
-    clusterer = Diana.new
-    assert_equal 0, clusterer.max_diameter_cluster([@data_set, @data_set[0..2]])
-    assert_equal 1, clusterer.max_diameter_cluster([@data_set[0..2], @data_set])
-  end 
-
-  def test_init_splinter_cluster
-    clusterer = Diana.new 
-    assert_equal [10,3], clusterer.
-      init_splinter_cluster(@data_set).data_items[0]
-  end
-  
-  def test_max_distance_difference
-    clusterer = Diana.new 
-    data_set_a = @data_set[1..-1]
-    data_set_b = @data_set[0]
-    assert_equal [63.7, 4], clusterer.
-      max_distance_difference(data_set_a, data_set_b)
-  end
-  
+# 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/diana'
+
+class Ai4r::Clusterers::Diana
+  attr_accessor :data_set, :number_of_clusters, :clusters
+end
+
+class DianaTest < Test::Unit::TestCase
+
+  @@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]]
+              
+  include Ai4r::Clusterers
+  include Ai4r::Data
+
+  def setup
+    Diana.send(:public, *Diana.protected_instance_methods)
+    @data_set = DataSet.new(:data_items => @@data.clone)
+  end
+          
+  def test_build
+    clusterer = Diana.new.build(@data_set, 4)
+    assert_equal 4, clusterer.clusters.length
+  end
+  
+  def test_eval
+    clusterer = Diana.new.build(@data_set, 4)
+    assert_equal 0, clusterer.eval([0, 0])
+    assert_equal 1, clusterer.eval([9, 3])
+    assert_equal 2, clusterer.eval([0,10])
+    assert_equal 3, clusterer.eval([8, 0])
+  end
+  
+  def test_cluster_diameter
+    clusterer = Diana.new
+    assert_equal 106, clusterer.cluster_diameter(@data_set)
+    assert_equal 98, clusterer.cluster_diameter(@data_set[0..2])
+  end
+  
+  def test_max_diameter_cluster
+    clusterer = Diana.new
+    assert_equal 0, clusterer.max_diameter_cluster([@data_set, @data_set[0..2]])
+    assert_equal 1, clusterer.max_diameter_cluster([@data_set[0..2], @data_set])
+  end 
+
+  def test_init_splinter_cluster
+    clusterer = Diana.new 
+    assert_equal [10,3], clusterer.
+      init_splinter_cluster(@data_set).data_items[0]
+  end
+  
+  def test_max_distance_difference
+    clusterer = Diana.new 
+    data_set_a = @data_set[1..-1]
+    data_set_b = @data_set[0]
+    assert_equal [63.7, 4], clusterer.
+      max_distance_difference(data_set_a, data_set_b)
+  end
+  
 end

data/test/data/data_set_test.rb

@@ -23,19 +23,21 @@ module Ai4r
       def test_build_domains
         domains =  [  Set.new(["New York", "Chicago"]), 
                       Set.new(["M", "F"]), 
+                      [5, 85],
                       Set.new(["Y", "N"]) ]
-        data = [  [ "New York", "M", "Y"],
-                  [ "Chicago", "M", "Y"],
-                  [ "New York", "F", "Y"],
-                  [ "New York", "M", "N"],
-                  [ "Chicago", "M", "N"],
-                  [ "Chicago", "F", "Y"] ]
-        labels = ["city", "gender", "result"]
+        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("result")
+        assert_equal domains[2], set.build_domain("age")
+        assert_equal domains[3], set.build_domain("result")
       end
       
       def test_set_data_labels

metadata

@@ -1,116 +1,123 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.4
-specification_version: 1
 name: ai4r
 version: !ruby/object:Gem::Version 
-  version: "1.6"
-date: 2009-04-08 00:00:00 +01:00
-summary: Ruby implementations of algorithms covering several Artificial intelligence fields, including Genetic algorithms, Neural Networks, machine learning, and clustering.
-require_paths: 
-- lib
-email: sergio@jadeferret.com
-homepage: http://ai4r.rubyforge.org
-rubyforge_project: ai4r
-description: 
-autorequire: 
-default_executable: 
-bindir: bin
-has_rdoc: true
-required_ruby_version: !ruby/object:Gem::Version::Requirement 
-  requirements: 
-  - - ">"
-    - !ruby/object:Gem::Version 
-      version: 0.0.0
-  version: 
+  version: 1.6.1
 platform: ruby
-signing_key: 
-cert_chain: 
-post_install_message: 
 authors: 
 - Sergio Fierens
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-04-09 00:00:00 +01:00
+default_executable: 
+dependencies: []
+
+description: 
+email: sergio@jadeferret.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.rdoc
 files: 
 - examples/clusterers
 - examples/clusterers/simple_website_clustering.rb
+- examples/neural_network
+- examples/neural_network/backpropagation_example.rb
+- examples/neural_network/patterns_with_base_noise.rb
+- examples/neural_network/xor_example.rb
+- examples/neural_network/patterns_with_noise.rb
+- examples/neural_network/training_patterns.rb
 - examples/decision_trees
 - examples/decision_trees/data_set.csv
-- examples/decision_trees/id3_example.rb
 - examples/decision_trees/results.txt
+- examples/decision_trees/id3_example.rb
 - examples/genetic_algorithm
 - examples/genetic_algorithm/genetic_algorithm_example.rb
 - examples/genetic_algorithm/travel_cost.csv
-- examples/neural_network
-- examples/neural_network/backpropagation_example.rb
-- examples/neural_network/patterns_with_base_noise.rb
-- examples/neural_network/patterns_with_noise.rb
-- examples/neural_network/training_patterns.rb
-- examples/neural_network/xor_example.rb
+- lib/ai4r.rb
 - lib/ai4r
-- lib/ai4r/classifiers
-- lib/ai4r/classifiers/classifier.rb
-- lib/ai4r/classifiers/hyperpipes.rb
-- lib/ai4r/classifiers/id3.rb
-- lib/ai4r/classifiers/multilayer_perceptron.rb
-- lib/ai4r/classifiers/one_r.rb
-- lib/ai4r/classifiers/prism.rb
-- lib/ai4r/classifiers/zero_r.rb
 - lib/ai4r/clusterers
 - lib/ai4r/clusterers/average_linkage.rb
-- lib/ai4r/clusterers/bisecting_k_means.rb
+- lib/ai4r/clusterers/median_linkage.rb
 - lib/ai4r/clusterers/centroid_linkage.rb
-- lib/ai4r/clusterers/clusterer.rb
+- lib/ai4r/clusterers/weighted_average_linkage.rb
 - lib/ai4r/clusterers/complete_linkage.rb
 - lib/ai4r/clusterers/diana.rb
-- lib/ai4r/clusterers/k_means.rb
-- lib/ai4r/clusterers/median_linkage.rb
-- lib/ai4r/clusterers/single_linkage.rb
+- lib/ai4r/clusterers/bisecting_k_means.rb
 - lib/ai4r/clusterers/ward_linkage.rb
-- lib/ai4r/clusterers/weighted_average_linkage.rb
-- lib/ai4r/data
-- lib/ai4r/data/constants.rb
-- lib/ai4r/data/data_set.rb
-- lib/ai4r/data/parameterizable.rb
-- lib/ai4r/data/proximity.rb
-- lib/ai4r/data/statistics.rb
+- lib/ai4r/clusterers/single_linkage.rb
+- lib/ai4r/clusterers/k_means.rb
+- lib/ai4r/clusterers/clusterer.rb
 - lib/ai4r/experiment
 - lib/ai4r/experiment/classifier_evaluator.rb
-- lib/ai4r/genetic_algorithm
-- lib/ai4r/genetic_algorithm/genetic_algorithm.rb
 - lib/ai4r/neural_network
 - lib/ai4r/neural_network/backpropagation.rb
-- lib/ai4r.rb
+- lib/ai4r/classifiers
+- lib/ai4r/classifiers/hyperpipes.rb
+- lib/ai4r/classifiers/multilayer_perceptron.rb
+- lib/ai4r/classifiers/prism.rb
+- lib/ai4r/classifiers/one_r.rb
+- lib/ai4r/classifiers/zero_r.rb
+- lib/ai4r/classifiers/classifier.rb
+- lib/ai4r/classifiers/id3.rb
+- lib/ai4r/genetic_algorithm
+- lib/ai4r/genetic_algorithm/genetic_algorithm.rb
+- lib/ai4r/data
+- lib/ai4r/data/parameterizable.rb
+- lib/ai4r/data/statistics.rb
+- lib/ai4r/data/data_set.rb
+- lib/ai4r/data/proximity.rb
 - README.rdoc
+has_rdoc: true
+homepage: http://ai4r.rubyforge.org
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: ai4r
+rubygems_version: 1.3.1
+signing_key: 
+specification_version: 2
+summary: Ruby implementations of algorithms covering several Artificial intelligence fields, including Genetic algorithms, Neural Networks, machine learning, and clustering.
 test_files: 
-- test/classifiers/id3_test.rb
-- test/classifiers/multilayer_perceptron_test.rb
-- test/classifiers/one_r_test.rb
-- test/classifiers/prism_test.rb
-- test/classifiers/zero_r_test.rb
-- test/clusterers/average_linkage_test.rb
-- test/clusterers/bisecting_k_means_test.rb
-- test/clusterers/centroid_linkage_test.rb
-- test/clusterers/complete_linkage_test.rb
+- test/clusterers/single_linkage_test.rb
+- test/clusterers/weighted_average_linkage_test.rb
 - test/clusterers/diana_test.rb
-- test/clusterers/k_means_test.rb
+- test/clusterers/average_linkage_test.rb
 - test/clusterers/median_linkage_test.rb
-- test/clusterers/single_linkage_test.rb
 - test/clusterers/ward_linkage_test.rb
-- test/clusterers/weighted_average_linkage_test.rb
-- test/data/data_set_test.rb
-- test/data/proximity_test.rb
-- test/data/statistics_test.rb
+- test/clusterers/complete_linkage_test.rb
+- test/clusterers/centroid_linkage_test.rb
+- test/clusterers/k_means_test.rb
+- test/clusterers/bisecting_k_means_test.rb
 - test/experiment/classifier_evaluator_test.rb
-- test/genetic_algorithm/chromosome_test.rb
-- test/genetic_algorithm/genetic_algorithm_test.rb
 - test/neural_network/backpropagation_test.rb
-rdoc_options: []
-
-extra_rdoc_files: 
-- README.rdoc
-executables: []
-
-extensions: []
-
-requirements: []
-
-dependencies: []
-
+- test/classifiers/zero_r_test.rb
+- test/classifiers/multilayer_perceptron_test.rb
+- test/classifiers/prism_test.rb
+- test/classifiers/one_r_test.rb
+- test/classifiers/hyperpipes_test.rb
+- test/classifiers/id3_test.rb
+- test/genetic_algorithm/genetic_algorithm_test.rb
+- test/genetic_algorithm/chromosome_test.rb
+- test/data/statistics_test.rb
+- test/data/proximity_test.rb
+- test/data/data_set_test.rb

data/lib/ai4r/data/constants.rb

@@ -1,18 +0,0 @@
-# Author::    Sergio Fierens
-# 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
-
-module Ai4r
-  module Data
-    
-    POSITIVE_INFINTY = 1.0/0
-    
-    NEGATIVE_INFINTY = -1.0/0
-    
-  end
-end