ai4r 1.1 → 1.2

data/site/build/tmp/brokenlinks.xml

@@ -1,2 +0,0 @@
-<broken-links>
-</broken-links>

data/test/decision_tree/id3_test.rb

@@ -1,209 +0,0 @@
-# 
-# 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/decision_tree/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"
-    
-                  
-  DecisionTree::ID3.send(:public, *DecisionTree::ID3.protected_instance_methods)  
-  DecisionTree::ID3.send(:public, *DecisionTree::ID3.private_instance_methods)
-
-module DecisionTree
-  
-  class ID3Test < Test::Unit::TestCase
-
-    def test_log2
-      assert_equal 1.0, DecisionTree::ID3.log2(2)
-      assert_equal 0.0, DecisionTree::ID3.log2(0)
-      assert 1.585 - DecisionTree::ID3.log2(3) < 0.001
-    end
-
-    def test_sum
-      assert_equal 28, DecisionTree::ID3.sum([5, 0, 22, 1])
-      assert_equal 0, DecisionTree::ID3.sum([])
-    end
-    
-    def test_data_labels
-      id3 = DecisionTree::ID3.new(DATA_SET)
-      expected_default = [ 'ATTRIBUTE_1', 'ATTRIBUTE_2', 'ATTRIBUTE_3', 'CATEGORY' ]
-      assert_equal(expected_default, id3.data_labels)
-      id3 = DecisionTree::ID3.new(DATA_SET, DATA_LABELS)
-      assert_equal(DATA_LABELS, id3.data_labels)
-    end
-    
-    def test_domain
-      id3 = DecisionTree::ID3.new(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 = DecisionTree::ID3.new(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 = DecisionTree::ID3.new(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 = DecisionTree::ID3.new(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 = DecisionTree::ID3.new(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 = DecisionTree::ID3.new(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'"]], DecisionTree::CategoryNode.new('marketing_target', 'N').get_rules
-      id3 = DecisionTree::ID3.new(DATA_SET, DATA_LABELS)
-      assert_equal EXPECTED_RULES_STRING, id3.to_s
-    end
-    
-    def test_eval
-      id3 = DecisionTree::ID3.new(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 = DecisionTree::ID3.new(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
-
-end
-