ai4r 1.1 → 1.2

data/site/src/documentation/content/xdocs/site.xml

@@ -39,12 +39,15 @@ See http://forrest.apache.org/docs/linking.html for more info
 <site label="ai4r" href="" xmlns="http://apache.org/forrest/linkmap/1.0"
   tab="">
   <about label="Home">
-    <index label="Index" href="index.html" description="ai4r - Artificial Intelligence for Ruby"/>     
-    <geneticAlgorithms label="Genetic Algorithms" href="geneticAlgorithms.html" description="Genetic Algorithms in ruby"/>
-    <machineLearning label="Machine Learning" href="machineLearning.html" description="ID3 Decision Trees in ruby"/>
-    <neuralNetworks label="Neural Networks" href="neuralNetworks.html" description="Backpropagation Neural Network in ruby" />
+    <index label="Index" href="index.html" description="ai4r - Artificial Intelligence for Ruby"/> 
+	<practicalExamples label="Practical Examples">
+		<geneticAlgorithms label="Genetic Algorithms" href="geneticAlgorithms.html" description="Genetic Algorithms in ruby"/>
+		<machineLearning label="Machine Learning" href="machineLearning.html" description="ID3 Decision Trees in ruby"/>
+		<neuralNetworks label="Neural Networks" href="neuralNetworks.html" description="Backpropagation Neural Network in ruby" />
+	</practicalExamples>		
     <download label="Downloads" href="downloads.html" description="ai4r - Download Files"/> 
-    <svn label="Subversion (svn)" href="svn.html" description="ai4r Subversion repository"/>
+    <download label="Forum" href="forum.html" description="ai4r - Forum"/> 
+    <svn label="Source Code repository" href="svn.html" description="ai4r Subversion repository"/>
     <ai4r_site_pdf label="ai4r project PDF" href="wholesite.pdf"/>
   </about>
   

data/site/src/documentation/content/xdocs/svn.xml

@@ -24,7 +24,17 @@
 
     <section id="moreinfor">
       <title>More info on Subversion (svn)</title>
-      <p>If you need help about using Subversion (svn), the (IMO) best documentation is available <a href="http://svnbook.red-bean.com/">here</a>.
+      <p>If you need help about using Subversion (svn), the (IMO) best documentation is available <a href="http://svnbook.red-bean.com/">here</a>.</p>
+      <p>If you work in SCM, you may find <a href="http://scm.jadeferret.com">Jade Ferret’s SCM initiative</a>
+      intresting.</p>
+    </section>
+    
+    <section id="softsizo_report">
+      <title>Source code evolution</title>
+      <p><a href="http://softsizo.jadeferret.com">Soft Sizo</a> is a report generation tool that extends the concept 
+      of Lines Of Code (LOC) metrics, using changes information stored in a Subversion repository.</p>
+      <p>You can access <a href="http://softsizo.jadeferret.com/examples/ai4r/index.html">AI4R Soft Sizo report</a>
+      for some AI4R source code evolution metrics.
       </p>
     </section>
   </body>

data/site/src/documentation/skinconf.xml

@@ -59,19 +59,19 @@ which will be used to configure the chosen Forrest skin.
 <!-- mandatory project logo
        default skin: renders it at the top -->
   <project-name>ai4r</project-name>
-  <project-description>Artificial Intelligence for Ruby</project-description>
+  <project-description>AI4R - Artificial Intelligence for Ruby</project-description>
   <project-url>http://ai4r.rubyforge.org/</project-url>
   <project-logo>images/ai4r-logo.png</project-logo>
 <!-- Alternative static image:
   <project-logo>images/project-logo.gif</project-logo> -->
 <!-- optional group logo
-       default skin: renders it at the top-left corner 
-  <group-name>MyGroup</group-name>
-  <group-description>MyGroup Description</group-description>
-  <group-url>http://mygroup.org</group-url>
-  <group-logo>images/group.png</group-logo>-->
-<!-- Alternative static image:
-  <group-logo>images/group-logo.gif</group-logo> -->
+       default skin: renders it at the top-left corner -->
+  <group-name>Jade Ferret</group-name>
+  <group-description>Jade Ferret</group-description>
+  <group-url>http://www.jadeferret.com</group-url>
+  <group-logo>images/jadeferret.png</group-logo>
+<!-- Alternative static image: 
+  <group-logo>images/jadeferret.gif</group-logo> -->
 <!-- optional host logo (e.g. sourceforge logo)
        default skin: renders it at the bottom-left corner -->
   <host-url>http://rubyforge.org/projects/ai4r/</host-url>
@@ -82,10 +82,8 @@ which will be used to configure the chosen Forrest skin.
   <disable-copyright-footer>false</disable-copyright-footer>
 <!-- @inception enable automatic generation of a date-range to current date -->
   <year inception="true">2007</year>
-  <vendor>Sergio Fierens</vendor>
-<!-- The optional copyright-link URL will be used as a link in the
-    copyright statement 
-  <copyright-link>http://www.example.org/</copyright-link>-->
+  <vendor>Sergio Fierens, Jade Ferret</vendor>
+  <copyright-link>http://www.jadeferret.com/</copyright-link>
 <!-- Some skins use this to form a 'breadcrumb trail' of links.
     Use location="alt" to move the trail to an alternate location
     (if the skin supports it).
@@ -208,8 +206,8 @@ which will be used to configure the chosen Forrest skin.
      pelt: body: any remaining parts, e.g. the bottom of the page
      pelt: footer: the second from bottom strip containing credit logos and published date
      pelt: feedback: the optional bottom strip containing feedback link
-  -->
-<!--
+ 
+
     <color name="breadtrail" value="#cedfef" font="#0F3660" link="#0F3660" vlink="#0F3660" hlink="#000066"/>
     <color name="header" value="#294563"/>
     <color name="tab-selected" value="#4a6d8c" link="#0F3660" vlink="#0F3660" hlink="#000066"/>
@@ -235,9 +233,9 @@ which will be used to configure the chosen Forrest skin.
     <color name="warning" value="#990000"/>
     <color name="code" value="#CFDCED"/>
     <color name="footer" value="#cedfef"/>
--->
+ -->
 <!-- Color group: Krysalis -->
-<!--
+
     <color name="header"    value="#FFFFFF"/>
 
     <color name="tab-selected" value="#a5b6c6" link="#000000" vlink="#000000" hlink="#000000"/>
@@ -266,8 +264,8 @@ which will be used to configure the chosen Forrest skin.
     <color name="code" value="#a5b6c6"/>
         
     <color name="footer" value="#a5b6c6"/>
--->
-<!-- Color group: Collabnet -->
+
+<!-- Color group: Collabnet 
 
     <color name="header"    value="#003366"/>
 
@@ -297,6 +295,8 @@ which will be used to configure the chosen Forrest skin.
     <color name="code" value="#003366"/>
         
     <color name="footer" value="#ffffff"/>
+    
+    -->
 
 <!-- Color group: Lenya using pelt-->
 <!--

data/test/classifiers/id3_test.rb

@@ -0,0 +1,206 @@
+# 
+# id3_test.rb
+# 
+# This is a unit test file for the ID3 algorithm (Quinlan) implemented
+# in ai4r  
+# 
+# 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/id3'
+require 'test/unit'
+
+DATA_LABELS = [ 'city', 'age_range', 'gender', 'marketing_target'  ]
+
+DATA_SET = [  ['New York',  '<30',      'M', 'Y'],
+              ['Chicago',     '<30',      'M', 'Y'],
+              ['Chicago',     '<30',      'F', 'Y'],
+              ['New York',  '<30',      'M', 'Y'],
+              ['New York',  '<30',      'M', 'Y'],
+              ['Chicago',     '[30-50)',  'M', 'Y'],
+              ['New York',  '[30-50)',  'F', 'N'],
+              ['Chicago',     '[30-50)',  'F', 'Y'],
+              ['New York',  '[30-50)',  'F', 'N'],
+              ['Chicago',     '[50-80]', 'M', 'N'],
+              ['New York',  '[50-80]', 'F', 'N'],
+              ['New York',  '[50-80]', 'M', 'N'],
+              ['Chicago',     '[50-80]', 'M', 'N'],
+              ['New York',  '[50-80]', 'F', 'N'],
+              ['Chicago',     '>80',      'F', 'Y']
+            ]
+
+SPLIT_DATA_SET_BY_CITY = [  [
+                              ["New York", "<30", "M", "Y"], 
+                              ["New York", "<30", "M", "Y"], 
+                              ["New York", "<30", "M", "Y"], 
+                              ["New York", "[30-50)", "F", "N"], 
+                              ["New York", "[30-50)", "F", "N"], 
+                              ["New York", "[50-80]", "F", "N"], 
+                              ["New York", "[50-80]", "M", "N"], 
+                              ["New York", "[50-80]", "F", "N"]], 
+                            [
+                              ["Chicago", "<30", "M", "Y"], 
+                              ["Chicago", "<30", "F", "Y"], 
+                              ["Chicago", "[30-50)", "M", "Y"], 
+                              ["Chicago", "[30-50)", "F", "Y"], 
+                              ["Chicago", "[50-80]", "M", "N"], 
+                              ["Chicago", "[50-80]", "M", "N"], 
+                              ["Chicago", ">80", "F", "Y"]]
+                          ]
+                          
+SPLIT_DATA_SET_BY_AGE = [   [
+                              ["New York", "<30", "M", "Y"], 
+                              ["Chicago", "<30", "M", "Y"], 
+                              ["Chicago", "<30", "F", "Y"], 
+                              ["New York", "<30", "M", "Y"], 
+                              ["New York", "<30", "M", "Y"]], 
+                            [
+                              ["Chicago", "[30-50)", "M", "Y"], 
+                              ["New York", "[30-50)", "F", "N"], 
+                              ["Chicago", "[30-50)", "F", "Y"], 
+                              ["New York", "[30-50)", "F", "N"]], 
+                            [
+                              ["Chicago", "[50-80]", "M", "N"], 
+                              ["New York", "[50-80]", "F", "N"], 
+                              ["New York", "[50-80]", "M", "N"], 
+                              ["Chicago", "[50-80]", "M", "N"], 
+                              ["New York", "[50-80]", "F", "N"]], 
+                            [
+                              ["Chicago", ">80", "F", "Y"]]
+                         ]
+
+  EXPECTED_RULES_STRING =  
+    "if age_range=='<30' then marketing_target='Y'\n"+
+    "elsif age_range=='[30-50)' and city=='Chicago' then marketing_target='Y'\n"+
+    "elsif age_range=='[30-50)' and city=='New York' then marketing_target='N'\n"+
+    "elsif age_range=='[50-80]' then marketing_target='N'\n"+
+    "elsif age_range=='>80' then marketing_target='Y'\n"+
+    "else raise 'There was not enough information during training to do a proper induction for this data element' end"
+    
+Ai4r::Classifiers::ID3.send(:public, *Ai4r::Classifiers::ID3.protected_instance_methods)  
+Ai4r::Classifiers::ID3.send(:public, *Ai4r::Classifiers::ID3.private_instance_methods)
+
+include Ai4r::Classifiers
+
+class ID3Test < Test::Unit::TestCase
+  
+  def test_log2
+    assert_equal 1.0, ID3.log2(2)
+    assert_equal 0.0, ID3.log2(0)
+    assert 1.585 - ID3.log2(3) < 0.001
+  end
+
+  def test_sum
+    assert_equal 28, ID3.sum([5, 0, 22, 1])
+    assert_equal 0, ID3.sum([])
+  end
+
+  def test_data_labels
+    id3 = ID3.new.build(DATA_SET)
+    expected_default = [ 'attribute_1', 'attribute_2', 'attribute_3', 'class_value' ]
+    assert_equal(expected_default, id3.data_labels)
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    assert_equal(DATA_LABELS, id3.data_labels)
+  end
+
+  def test_domain
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    expected_domain = [["New York", "Chicago"], ["<30", "[30-50)", "[50-80]", ">80"], ["M", "F"], ["Y", "N"]]
+    assert_equal expected_domain, id3.domain(DATA_SET)
+  end
+
+  def test_grid
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    expected_grid = [[3, 5], [5, 2]]
+    domain = id3.domain(DATA_SET)
+    assert_equal expected_grid, id3.freq_grid(0, DATA_SET, domain)
+    expected_grid = [[5, 0], [2, 2], [0, 5], [1, 0]]
+    assert_equal expected_grid, id3.freq_grid(1, DATA_SET, domain)
+  end
+
+  def test_entropy
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    expected_entropy = 0.9118
+    domain = id3.domain(DATA_SET)
+    freq_grid = id3.freq_grid(0, DATA_SET, domain)
+    assert expected_entropy - id3.entropy(freq_grid, DATA_SET.length) < 0.0001
+    expected_entropy = 0.2667
+    freq_grid = id3.freq_grid(1, DATA_SET, domain)
+    assert expected_entropy - id3.entropy(freq_grid, DATA_SET.length) < 0.0001
+    expected_entropy = 0.9688
+    freq_grid = id3.freq_grid(2, DATA_SET, domain)
+    assert expected_entropy - id3.entropy(freq_grid, DATA_SET.length) < 0.0001
+  end
+
+  def test_min_entropy_index
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    domain = id3.domain(DATA_SET)
+    assert_equal 1, id3.min_entropy_index(DATA_SET, domain)
+    assert_equal 0, id3.min_entropy_index(DATA_SET, domain, [1])
+    assert_equal 2, id3.min_entropy_index(DATA_SET, domain, [1, 0])
+  end
+
+  def test_split_data_examples
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    domain = id3.domain(DATA_SET)
+    res = id3.split_data_examples(DATA_SET, domain, 0)
+    assert_equal(SPLIT_DATA_SET_BY_CITY, res)
+    res = id3.split_data_examples(DATA_SET, domain, 1)
+    assert_equal(SPLIT_DATA_SET_BY_AGE, res)
+  end
+
+  def test_most_freq
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    domain = id3.domain(DATA_SET)
+    assert_equal 'Y', id3.most_freq(DATA_SET, domain)
+    assert_equal 'Y', id3.most_freq(SPLIT_DATA_SET_BY_AGE[3], domain)
+    assert_equal 'N', id3.most_freq(SPLIT_DATA_SET_BY_AGE[2], domain)
+  end
+
+  def test_to_s
+    assert_equal [["marketing_target='N'"]], CategoryNode.new('marketing_target', 'N').get_rules
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    assert_equal EXPECTED_RULES_STRING, id3.to_s
+  end
+
+  def test_eval
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    #if age_range='<30' then marketing_target='Y'
+    assert_equal 'Y', id3.eval(['New York', '<30', 'F'])
+    assert_equal 'Y', id3.eval(['Chicago', '<30', 'M'])
+    #if age_range='[30-50)' and city='Chicago' then marketing_target='Y'
+    assert_equal 'Y', id3.eval(['Chicago', '[30-50)', 'F'])
+    assert_equal 'Y', id3.eval(['Chicago', '[30-50)', 'M'])
+    #if age_range='[30-50)' and city='New York' then marketing_target='N'
+    assert_equal 'N', id3.eval(['New York', '[30-50)', 'F'])
+    assert_equal 'N', id3.eval(['New York', '[30-50)', 'M'])      
+    #if age_range='[50-80]' then marketing_target='N'
+    assert_equal 'N', id3.eval(['New York', '[50-80]', 'F'])
+    assert_equal 'N', id3.eval(['Chicago', '[50-80]', 'M'])      
+    #if age_range='>80' then marketing_target='Y'
+    assert_equal 'Y', id3.eval(['New York', '>80', 'M'])      
+    assert_equal 'Y', id3.eval(['Chicago', '>80', 'F'])      
+  end
+
+  def test_rules_eval
+    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    #if age_range='<30' then marketing_target='Y'
+    age_range = '<30'
+    marketing_target = nil
+    eval id3.to_s
+    assert_equal 'Y', marketing_target
+    #if age_range='[30-50)' and city='New York' then marketing_target='N'
+    age_range='[30-50)' 
+    city='New York'
+    eval id3.to_s
+    assert_equal 'N', marketing_target
+  end
+end
+
+  

data/test/classifiers/one_r_test.rb

@@ -0,0 +1,62 @@
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+require 'test/unit'
+require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/one_r'
+
+class OneRTest < Test::Unit::TestCase
+  
+  include Ai4r::Classifiers
+  
+  @@data_examples = [   ['New York',  '<30',      'M', 'Y'],
+                ['Chicago',     '<30',      'M', 'Y'],
+                ['New York',  '<30',      'M', 'Y'],
+                ['New York',  '[30-50)',  'F', 'N'],
+                ['Chicago',     '[30-50)',  'F', 'Y'],
+                ['New York',  '[30-50)',  'F', 'N'],
+                ['Chicago',     '[50-80]', 'M', 'N']
+              ]
+
+  @@data_labels = [ 'city', 'age_range', 'gender', 'marketing_target'  ]
+  
+  def test_build
+    assert_raise(ArgumentError) { OneR.new.build(nil) } 
+    assert_raise(ArgumentError) { OneR.new.build([]) } 
+    classifier = OneR.new.build(@@data_examples)
+    assert_not_nil(classifier.data_labels)
+    assert_not_nil(classifier.rule)
+    assert_equal("attribute_1", classifier.data_labels.first)
+    assert_equal("class_value", classifier.data_labels.last)
+    classifier = OneR.new.build(@@data_examples, @@data_labels)
+    assert_not_nil(classifier.data_labels)
+    assert_not_nil(classifier.rule)
+    assert_equal("city", classifier.data_labels.first)
+    assert_equal("marketing_target", classifier.data_labels.last)
+    assert_equal(1, classifier.rule[:attr_index])
+  end
+  
+  def test_eval
+    classifier = OneR.new.build(@@data_examples)   
+    assert_equal("Y", classifier.eval(['New York',  '<30',      'M']))
+    assert_equal("N", classifier.eval(['New York',  '[30-50)',      'M']))
+    assert_equal("N", classifier.eval(['Chicago',  '[50-80]',      'M']))
+  end
+  
+  def test_to_s
+    classifier = OneR.new.build(@@data_examples, @@data_labels)
+    marketing_target = nil
+    age_range = nil
+    eval(classifier.to_s) 
+    assert_nil(marketing_target)
+    age_range = '<30'
+    eval(classifier.to_s) 
+    assert_equal("Y", marketing_target)
+    age_range = '[30-50)'
+    eval(classifier.to_s) 
+    assert_equal("N", marketing_target)
+    age_range = '[50-80]'
+    eval(classifier.to_s) 
+    assert_equal("N", marketing_target)    
+  end
+  
+end
+

data/test/classifiers/prism_test.rb

@@ -0,0 +1,83 @@
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+require 'test/unit'
+require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/prism'
+
+Ai4r::Classifiers::Prism.send(:public, *Ai4r::Classifiers::Prism.protected_instance_methods)  
+Ai4r::Classifiers::Prism.send(:public, *Ai4r::Classifiers::Prism.private_instance_methods)
+
+class PrismTest < Test::Unit::TestCase
+  
+  include Ai4r::Classifiers
+  
+  @@data_examples = [   ['New York',  '<30',      'M', 'Y'],
+                ['Chicago',     '<30',      'M', 'Y'],
+                ['Chicago',     '<30',      'F', 'Y'],
+                ['New York',  '<30',      'M', 'Y'],
+                ['New York',  '<30',      'M', 'Y'],
+                ['Chicago',     '[30-50)',  'M', 'Y'],
+                ['New York',  '[30-50)',  'F', 'N'],
+                ['Chicago',     '[30-50)',  'F', 'Y'],
+                ['New York',  '[30-50)',  'F', 'N'],
+                ['Chicago',     '[50-80]', 'M', 'N'],
+                ['New York',  '[50-80]', 'F', 'N'],
+                ['New York',  '[50-80]', 'M', 'N'],
+                ['Chicago',     '[50-80]', 'M', 'N'],
+                ['New York',  '[50-80]', 'F', 'N'],
+                ['Chicago',     '>80',      'F', 'Y']
+              ]
+
+  @@data_labels = [ 'city', 'age_range', 'gender', 'marketing_target'  ]
+  
+  def test_build
+    assert_raise(ArgumentError) { Prism.new.build(nil) } 
+    assert_raise(ArgumentError) { Prism.new.build([]) } 
+    classifier = Prism.new.build(@@data_examples)
+    assert_not_nil(classifier.data_labels)
+    assert_not_nil(classifier.rules)
+    assert_equal("attribute_1", classifier.data_labels.first)
+    assert_equal("class_value", classifier.data_labels.last)
+    classifier = Prism.new.build(@@data_examples, @@data_labels)
+    assert_not_nil(classifier.data_labels)
+    assert_not_nil(classifier.rules)
+    assert_equal("city", classifier.data_labels.first)
+    assert_equal("marketing_target", classifier.data_labels.last)
+    assert !classifier.rules.empty?
+  end
+  
+  def test_eval
+    classifier = Prism.new.build(@@data_examples)   
+    @@data_examples.each do |data|
+      assert_equal(data.last, classifier.eval(data[0...-1]))
+    end
+  end
+  
+  def test_to_s
+    classifier = Prism.new.build(@@data_examples, @@data_labels)
+    marketing_target = nil
+    age_range = nil
+    city = 'Chicago'
+    eval(classifier.to_s) 
+    age_range = '<30'
+    eval(classifier.to_s) 
+    assert_equal("Y", marketing_target)
+    age_range = '[30-50)'
+    eval(classifier.to_s) 
+    assert_equal("Y", marketing_target)
+    age_range = '[30-50)'
+    city = 'New York'
+    eval(classifier.to_s) 
+    assert_equal("N", marketing_target)
+    age_range = '[50-80]'
+    eval(classifier.to_s) 
+    assert_equal("N", marketing_target)   
+  end
+    
+  def test_matches_conditions
+    classifier = Prism.new   
+    classifier.data_labels = @@data_labels
+    assert classifier.matches_conditions(['New York', '<30', 'M', 'Y'], {"age_range" => "<30"})
+    assert !classifier.matches_conditions(['New York', '<30', 'M', 'Y'], {"age_range" => "[50-80]"})
+  end
+end
+