ai4r 1.2 → 1.3

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

@@ -14,7 +14,6 @@
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.
-
 -->
 <!DOCTYPE document PUBLIC "-//APACHE//DTD Documentation V2.0//EN" "http://forrest.apache.org/dtd/document-v20.dtd">
 <document>
@@ -39,6 +38,12 @@
 				<li><a href="http://en.wikipedia.org/wiki/Association_rule_learning#Zero-attribute-rule">ZeroR</a></li>
 			</ul>
 		</li>
+		<li><a href="machineLearning.html">Data clustering</a>
+			<ul>
+				<li><a href="http://en.wikipedia.org/wiki/k_means">K-means algorithm</a></li>
+        <li><a href="http://en.wikipedia.org/wiki/k_means">Bisecting k-means</a></li>
+			</ul>
+		</li>    
 	</ul>
     </section>
 
@@ -72,22 +77,25 @@
       <p>2. Include require statements in your code:</p>
       <source>
 require "rubygems"
-require "ai4r/classifiers/id3"en 
-require "ai4r/classifiers/prism"
-require "ai4r/classifiers/one_r"
-require "ai4r/classifiers/zero_r"
-require "ai4r/neural_network/backpropagation"
-require "ai4r/genetic_algorithm/genetic_algorithm"
+require "ai4r"
       </source>
     </section>
 
     <section id="ContactMe">
       <title>Contact me</title>
       <p>
-        If you have some constructive comments about this project, please do send those to me: 
+        If you have questions or constructive comments about this project, 
+        please post them in the 
+        <a href="http://forum.jadeferret.com/viewforum.php?f=3" title="Ai4r Forum">forum</a>. 
+        I get an email notification when you post, and I do my best to answer as soon as possible.
+        </p>
+        <p>
+        If you do not want to make it public, send it to me: 
         Sergio Fierens, email address:	<img src="images/my_email.png" alt="(sergio (dot) fierens (at) gmail (dot) com)" 
-	title="Sergio Fierens contact email" />
-      </p>
+	title="Sergio Fierens contact email" />. But please, try to post them in the 
+        forum. I get tons of emails and it would be great to make them
+        public to help everyone.
+        </p>
     </section>
 
     <section id="warranty">

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

@@ -59,7 +59,7 @@ The only information that you have is a collection of examples, provided by a ma
 	and identify new posible marketing targets:</p>
 <source>
 <![CDATA[
-  id3.to_s
+  id3.get_rules
     # =>  if age_range=='<30' then marketing_target='Y'
           elsif age_range=='[30-50)' and city=='Chicago' then marketing_target='Y'
           elsif age_range=='[30-50)' and city=='New York' then marketing_target='N'
@@ -104,7 +104,8 @@ id3.eval(['New York', '<30', 'M'])
     # =>  'Y'
 ]]></source>
 <p>
-But instead of going through the tree every time, you can take advantage of the fact that the method "to_s" generates proper ruby code!
+But instead of going through the tree every time, you can take advantage of the 
+fact that the method "get_rules" generates proper ruby code!
 	</p>
 <source>
 <![CDATA[
@@ -113,7 +114,7 @@ But instead of going through the tree every time, you can take advantage of the
     city = 'New York'
     gender = 'M'
     marketing_target = nil
-    eval id3.to_s
+    eval id3.get_rules
     puts marketing_target
       # =>  'Y'
 ]]></source>

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

@@ -46,7 +46,8 @@ See http://forrest.apache.org/docs/linking.html for more info
 		<neuralNetworks label="Neural Networks" href="neuralNetworks.html" description="Backpropagation Neural Network in ruby" />
 	</practicalExamples>		
     <download label="Downloads" href="downloads.html" description="ai4r - Download Files"/> 
-    <download label="Forum" href="forum.html" description="ai4r - Forum"/> 
+    <forum label="Forum" href="http://forum.jadeferret.com/viewforum.php?f=3" description="Ai4r Forum"/> 
+    <rdoc label="API doc (Rdoc)" href="http://ai4r.rubyforge.org/rdoc/index.html" description="Ai4 RDoc docs"/>
     <svn label="Source Code repository" href="svn.html" description="ai4r Subversion repository"/>
     <ai4r_site_pdf label="ai4r project PDF" href="wholesite.pdf"/>
   </about>

data/test/classifiers/id3_test.rb

@@ -18,7 +18,7 @@ require 'test/unit'
 
 DATA_LABELS = [ 'city', 'age_range', 'gender', 'marketing_target'  ]
 
-DATA_SET = [  ['New York',  '<30',      'M', 'Y'],
+DATA_ITEMS = [  ['New York',  '<30',      'M', 'Y'],
               ['Chicago',     '<30',      'M', 'Y'],
               ['Chicago',     '<30',      'F', 'Y'],
               ['New York',  '<30',      'M', 'Y'],
@@ -35,7 +35,7 @@ DATA_SET = [  ['New York',  '<30',      'M', 'Y'],
               ['Chicago',     '>80',      'F', 'Y']
             ]
 
-SPLIT_DATA_SET_BY_CITY = [  [
+SPLIT_DATA_ITEMS_BY_CITY = [  [
                               ["New York", "<30", "M", "Y"], 
                               ["New York", "<30", "M", "Y"], 
                               ["New York", "<30", "M", "Y"], 
@@ -54,7 +54,7 @@ SPLIT_DATA_SET_BY_CITY = [  [
                               ["Chicago", ">80", "F", "Y"]]
                           ]
                           
-SPLIT_DATA_SET_BY_AGE = [   [
+SPLIT_DATA_ITEMS_BY_AGE = [   [
                               ["New York", "<30", "M", "Y"], 
                               ["Chicago", "<30", "M", "Y"], 
                               ["Chicago", "<30", "F", "Y"], 
@@ -87,6 +87,7 @@ Ai4r::Classifiers::ID3.send(:public, *Ai4r::Classifiers::ID3.protected_instance_
 Ai4r::Classifiers::ID3.send(:public, *Ai4r::Classifiers::ID3.private_instance_methods)
 
 include Ai4r::Classifiers
+include Ai4r::Data
 
 class ID3Test < Test::Unit::TestCase
   
@@ -102,75 +103,75 @@ class ID3Test < Test::Unit::TestCase
   end
 
   def test_data_labels
-    id3 = ID3.new.build(DATA_SET)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS))
     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)
+    assert_equal(expected_default, id3.data_set.data_labels)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
+    assert_equal(DATA_LABELS, id3.data_set.data_labels)
   end
 
   def test_domain
-    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => 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)
+    assert_equal expected_domain, id3.domain(DATA_ITEMS)
   end
 
   def test_grid
-    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
     expected_grid = [[3, 5], [5, 2]]
-    domain = id3.domain(DATA_SET)
-    assert_equal expected_grid, id3.freq_grid(0, DATA_SET, domain)
+    domain = id3.domain(DATA_ITEMS)
+    assert_equal expected_grid, id3.freq_grid(0, DATA_ITEMS, domain)
     expected_grid = [[5, 0], [2, 2], [0, 5], [1, 0]]
-    assert_equal expected_grid, id3.freq_grid(1, DATA_SET, domain)
+    assert_equal expected_grid, id3.freq_grid(1, DATA_ITEMS, domain)
   end
 
   def test_entropy
-    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => 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
+    domain = id3.domain(DATA_ITEMS)
+    freq_grid = id3.freq_grid(0, DATA_ITEMS, domain)
+    assert expected_entropy - id3.entropy(freq_grid, DATA_ITEMS.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
+    freq_grid = id3.freq_grid(1, DATA_ITEMS, domain)
+    assert expected_entropy - id3.entropy(freq_grid, DATA_ITEMS.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
+    freq_grid = id3.freq_grid(2, DATA_ITEMS, domain)
+    assert expected_entropy - id3.entropy(freq_grid, DATA_ITEMS.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])
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
+    domain = id3.domain(DATA_ITEMS)
+    assert_equal 1, id3.min_entropy_index(DATA_ITEMS, domain)
+    assert_equal 0, id3.min_entropy_index(DATA_ITEMS, domain, [1])
+    assert_equal 2, id3.min_entropy_index(DATA_ITEMS, 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)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
+    domain = id3.domain(DATA_ITEMS)
+    res = id3.split_data_examples(DATA_ITEMS, domain, 0)
+    assert_equal(SPLIT_DATA_ITEMS_BY_CITY, res)
+    res = id3.split_data_examples(DATA_ITEMS, domain, 1)
+    assert_equal(SPLIT_DATA_ITEMS_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)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
+    domain = id3.domain(DATA_ITEMS)
+    assert_equal 'Y', id3.most_freq(DATA_ITEMS, domain)
+    assert_equal 'Y', id3.most_freq(SPLIT_DATA_ITEMS_BY_AGE[3], domain)
+    assert_equal 'N', id3.most_freq(SPLIT_DATA_ITEMS_BY_AGE[2], domain)
   end
 
-  def test_to_s
+  def test_get_rules
     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
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
+    assert_equal EXPECTED_RULES_STRING, id3.get_rules
   end
 
   def test_eval
-    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => 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'])
@@ -189,16 +190,16 @@ class ID3Test < Test::Unit::TestCase
   end
 
   def test_rules_eval
-    id3 = ID3.new.build(DATA_SET, DATA_LABELS)
+    id3 = ID3.new.build(DataSet.new(:data_items =>DATA_ITEMS, :data_labels => DATA_LABELS))
     #if age_range='<30' then marketing_target='Y'
     age_range = '<30'
     marketing_target = nil
-    eval id3.to_s
+    eval id3.get_rules
     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
+    eval id3.get_rules
     assert_equal 'N', marketing_target
   end
 end

data/test/classifiers/one_r_test.rb

@@ -6,6 +6,7 @@ require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/one_r'
 class OneRTest < Test::Unit::TestCase
   
   include Ai4r::Classifiers
+  include Ai4r::Data
   
   @@data_examples = [   ['New York',  '<30',      'M', 'Y'],
                 ['Chicago',     '<30',      'M', 'Y'],
@@ -19,42 +20,43 @@ class OneRTest < Test::Unit::TestCase
   @@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_raise(ArgumentError) { OneR.new.build(DataSet.new) } 
+    classifier = OneR.new.build(DataSet.new(:data_items => @@data_examples))
+    assert_not_nil(classifier.data_set.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_equal("attribute_1", classifier.data_set.data_labels.first)
+    assert_equal("class_value", classifier.data_set.data_labels.last)
+    classifier = OneR.new.build(DataSet.new(:data_items => @@data_examples,
+      :data_labels => @@data_labels))
+    assert_not_nil(classifier.data_set.data_labels)
     assert_not_nil(classifier.rule)
-    assert_equal("city", classifier.data_labels.first)
-    assert_equal("marketing_target", classifier.data_labels.last)
+    assert_equal("city", classifier.data_set.data_labels.first)
+    assert_equal("marketing_target", classifier.data_set.data_labels.last)
     assert_equal(1, classifier.rule[:attr_index])
   end
   
   def test_eval
-    classifier = OneR.new.build(@@data_examples)   
+    classifier = OneR.new.build(DataSet.new(:data_items => @@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)
+  def test_get_rules
+    classifier = OneR.new.build(DataSet.new(:data_items => @@data_examples,
+      :data_labels => @@data_labels))
     marketing_target = nil
     age_range = nil
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_nil(marketing_target)
     age_range = '<30'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("Y", marketing_target)
     age_range = '[30-50)'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("N", marketing_target)
     age_range = '[50-80]'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("N", marketing_target)    
   end
   

data/test/classifiers/prism_test.rb

@@ -9,6 +9,7 @@ Ai4r::Classifiers::Prism.send(:public, *Ai4r::Classifiers::Prism.private_instanc
 class PrismTest < Test::Unit::TestCase
   
   include Ai4r::Classifiers
+  include Ai4r::Data
   
   @@data_examples = [   ['New York',  '<30',      'M', 'Y'],
                 ['Chicago',     '<30',      'M', 'Y'],
@@ -30,52 +31,53 @@ class PrismTest < Test::Unit::TestCase
   @@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_raise(ArgumentError) { Prism.new.build(DataSet.new) } 
+    classifier = Prism.new.build(DataSet.new(:data_items=>@@data_examples))
+    assert_not_nil(classifier.data_set.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_equal("attribute_1", classifier.data_set.data_labels.first)
+    assert_equal("class_value", classifier.data_set.data_labels.last)
+    classifier = Prism.new.build(DataSet.new(:data_items => @@data_examples, 
+        :data_labels => @@data_labels))
+    assert_not_nil(classifier.data_set.data_labels)
     assert_not_nil(classifier.rules)
-    assert_equal("city", classifier.data_labels.first)
-    assert_equal("marketing_target", classifier.data_labels.last)
+    assert_equal("city", classifier.data_set.data_labels.first)
+    assert_equal("marketing_target", classifier.data_set.data_labels.last)
     assert !classifier.rules.empty?
   end
   
   def test_eval
-    classifier = Prism.new.build(@@data_examples)   
+    classifier = Prism.new.build(DataSet.new(:data_items=>@@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)
+  def test_get_rules
+    classifier = Prism.new.build(DataSet.new(:data_items => @@data_examples, 
+        :data_labels => @@data_labels))
     marketing_target = nil
     age_range = nil
     city = 'Chicago'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     age_range = '<30'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("Y", marketing_target)
     age_range = '[30-50)'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("Y", marketing_target)
     age_range = '[30-50)'
     city = 'New York'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("N", marketing_target)
     age_range = '[50-80]'
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal("N", marketing_target)   
   end
     
   def test_matches_conditions
-    classifier = Prism.new   
-    classifier.data_labels = @@data_labels
+    classifier = Prism.new.build(DataSet.new(:data_labels => @@data_labels,
+      :data_items => @@data_examples))
     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

data/test/classifiers/zero_r_test.rb

@@ -2,10 +2,12 @@ $:.unshift File.join(File.dirname(__FILE__),'..','lib')
 
 require 'test/unit'
 require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/zero_r'
+require File.dirname(__FILE__) + '/../../lib/ai4r/data/data_set'
 
 class ZeroRTest < Test::Unit::TestCase
   
   include Ai4r::Classifiers
+  include Ai4r::Data
   
   @@data_examples = [   ['New York',  '<30',      'M', 'Y'],
                 ['Chicago',     '<30',      'M', 'Y'],
@@ -19,28 +21,29 @@ class ZeroRTest < Test::Unit::TestCase
   @@data_labels = [ 'city', 'age_range', 'gender', 'marketing_target'  ]
   
   def test_build
-    assert_raise(ArgumentError) { ZeroR.new.build(nil) } 
-    assert_raise(ArgumentError) { ZeroR.new.build([]) } 
-    classifier = ZeroR.new.build(@@data_examples)
+    assert_raise(ArgumentError) { ZeroR.new.build(DataSet.new) } 
+    classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples))
     assert_equal("Y", classifier.class_value)
-    assert_equal("attribute_1", classifier.data_labels.first)
-    assert_equal("class_value", classifier.data_labels.last)
-    classifier = ZeroR.new.build(@@data_examples, @@data_labels)
+    assert_equal("attribute_1", classifier.data_set.data_labels.first)
+    assert_equal("class_value", classifier.data_set.data_labels.last)
+    classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples, 
+        :data_labels => @@data_labels))
     assert_equal("Y", classifier.class_value)
-    assert_equal("city", classifier.data_labels.first)
-    assert_equal("marketing_target", classifier.data_labels.last)
+    assert_equal("city", classifier.data_set.data_labels.first)
+    assert_equal("marketing_target", classifier.data_set.data_labels.last)
   end
   
   def test_eval
-    classifier = ZeroR.new.build(@@data_examples)
+    classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples))
     assert_equal('Y', classifier.eval(@@data_examples.first) )
     assert_equal('Y', classifier.eval(@@data_examples.last) )
   end
   
-  def test_to_s
-    classifier = ZeroR.new.build(@@data_examples, @@data_labels)
+  def test_get_rules
+    classifier = ZeroR.new.build(DataSet.new(:data_items => @@data_examples,
+      :data_labels => @@data_labels))
     marketing_target = nil
-    eval(classifier.to_s) 
+    eval(classifier.get_rules) 
     assert_equal('Y', marketing_target)
   end