ai4r 1.3 → 1.4

data/README.rdoc

@@ -16,18 +16,12 @@ http://ai4r.rubyforge.org
 2. Include require statements in your code:
 
   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"
-
-= Feedback
-
-If you have questions or constructive comments about this project, 
-please post them in the forum. If you do not want to make it public, 
-send it to me: Sergio Fierens (sergio(dot)fierens(at)gmail(dot)com) 
+  require "ai4r"
+  
+= More Info
+
+ * AI4R wiki: http://wiki.jadeferret.com/Category:AI4R  
+ * AI4R Project site: http://ai4r.rubyforge.org
 
 = Warranty
 

data/examples/neural_network/backpropagation_example.rb

@@ -15,25 +15,28 @@ require 'benchmark'
 
 times = Benchmark.measure do
   
+    srand 1
+  
     net = Ai4r::NeuralNetwork::Backpropagation.new([256, 3])
+  
+    tr_input = TRIANGLE.flatten.collect { |input| input.to_f / 5.0}
+    sq_input = SQUARE.flatten.collect { |input| input.to_f / 5.0}
+    cr_input = CROSS.flatten.collect { |input| input.to_f / 5.0}
 
-    tr_input = TRIANGLE.flatten.collect { |input| input.to_f / 10}
-    sq_input = SQUARE.flatten.collect { |input| input.to_f / 10}
-    cr_input = CROSS.flatten.collect { |input| input.to_f / 10}
-
-    tr_with_noise = TRIANGLE_WITH_NOISE.flatten.collect { |input| input.to_f / 10}
-    sq_with_noise = SQUARE_WITH_NOISE.flatten.collect { |input| input.to_f / 10}
-    cr_with_noise = CROSS_WITH_NOISE.flatten.collect { |input| input.to_f / 10}
+    tr_with_noise = TRIANGLE_WITH_NOISE.flatten.collect { |input| input.to_f / 5.0}
+    sq_with_noise = SQUARE_WITH_NOISE.flatten.collect { |input| input.to_f / 5.0}
+    cr_with_noise = CROSS_WITH_NOISE.flatten.collect { |input| input.to_f / 5.0}
 
-    tr_with_base_noise = TRIANGLE_WITH_BASE_NOISE.flatten.collect { |input| input.to_f / 10}
-    sq_with_base_noise = SQUARE_WITH_BASE_NOISE.flatten.collect { |input| input.to_f / 10}
-    cr_with_base_noise = CROSS_WITH_BASE_NOISE.flatten.collect { |input| input.to_f / 10}
+    tr_with_base_noise = TRIANGLE_WITH_BASE_NOISE.flatten.collect { |input| input.to_f / 5.0}
+    sq_with_base_noise = SQUARE_WITH_BASE_NOISE.flatten.collect { |input| input.to_f / 5.0}
+    cr_with_base_noise = CROSS_WITH_BASE_NOISE.flatten.collect { |input| input.to_f / 5.0}
 
     puts "Training the network, please wait."
-    200.times do
-      net.train(tr_input, [1,0,0])
-      net.train(sq_input, [0,1,0])
-      net.train(cr_input, [0,0,1])
+    101.times do |i|
+      error = net.train(tr_input, [1,0,0])
+      error = net.train(sq_input, [0,1,0])
+      error = net.train(cr_input, [0,0,1])
+      puts "Error after iteration #{i}:\t#{error}" if i%20 == 0
     end
 
     def result_label(result)
@@ -58,8 +61,7 @@ times = Benchmark.measure do
     puts "#{net.eval(tr_with_base_noise).inspect} => #{result_label(net.eval(tr_with_base_noise))}"
     puts "#{net.eval(sq_with_base_noise).inspect} => #{result_label(net.eval(sq_with_base_noise))}"
     puts "#{net.eval(cr_with_base_noise).inspect} => #{result_label(net.eval(cr_with_base_noise))}"
-    
   
 end
 
-  puts "Elapsed time: #{times}"
+puts "Elapsed time: #{times}"

data/examples/neural_network/xor_example.rb

@@ -1,25 +1,35 @@
-require File.dirname(__FILE__) + '/training_patterns'
-require File.dirname(__FILE__) + '/patterns_with_noise'
-require File.dirname(__FILE__) + '/patterns_with_base_noise'
-require File.dirname(__FILE__) + '/../../lib/ai4r/neural_network/backpropagation'
+# 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
 
-examples = [
-    [[0, 0], [0, 1]],
-    [[0, 1], [1, 0]],
-    [[1, 0], [1, 0]],
-    [[1, 1], [0, 0]]
-]
+require File.dirname(__FILE__) + '/../../lib/ai4r/neural_network/backpropagation'
+require 'benchmark'
 
-net = Ai4r::NeuralNetwork::Backpropagation.new([2, 1, 2, 1])
+times = Benchmark.measure do
 
-i=0
-200.times {
-    examples.each do |ex|
-        2000.times {net.train(ex[0], [ex[1].first])}
+    srand 1
+    
+    net = Ai4r::NeuralNetwork::Backpropagation.new([2, 2, 1])
+      
+    puts "Training the network, please wait."
+    2001.times do |i|
+      net.train([0,0], [0])
+      net.train([0,1], [1])
+      net.train([1,0], [1])
+      error = net.train([1,1], [0])      
+      puts "Error after iteration #{i}:\t#{error}" if i%200 == 0
     end
-    puts(i=i+1)
-}
+  
+    puts "Test data"
+    puts "[0,0] = > #{net.eval([0,0]).inspect}"
+    puts "[0,1] = > #{net.eval([0,1]).inspect}"
+    puts "[1,0] = > #{net.eval([1,0]).inspect}"
+    puts "[1,1] = > #{net.eval([1,1]).inspect}"
+end
 
-examples.each do |ex|
-    print ex[0], ' => ', net.eval(ex[0]).inspect, ', should be ', ex[1].first, "\n"
-end       
+  puts "Elapsed time: #{times}"

data/lib/ai4r/classifiers/classifier.rb

@@ -1,19 +1,23 @@
 # Author::    Sergio Fierens
 # License::   MPL 1.1
 # Project::   ai4r
-# Url::       http://ai4r.rubyforge.org/
+# 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__) + '/../data/parameterizable' 
+ 
 module Ai4r
   module Classifiers
-    
-    # The only purpose of this class is to define a common API for classifiers.
+  
+    # This class defines a common API for classifiers.
     # All methods in this class must be implemented in subclasses.
     class Classifier
 
+      include Ai4r::Data::Parameterizable  
+    
       # Build a new classifier, using data examples found in data_set.
       def build(data_set)
         raise NotImplementedError
@@ -30,9 +34,16 @@ module Ai4r
       # e.g.
       #   
       #   classifier.get_rules
-      #     # =>  marketing_target='Y'
+      #     # =>  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'
+      #           elsif age_range=='[50-80]' then marketing_target='N'
+      #           elsif age_range=='>80' then marketing_target='Y'
+      #           else raise 'There was not enough information during training to do a proper induction for this data element' end
       #
       # It is a nice way to inspect induction results, and also to execute them:  
+      #     age_range = '<30'
+      #     city='New York'
       #     marketing_target = nil
       #     eval classifier.get_rules   
       #     puts marketing_target

data/lib/ai4r/classifiers/id3.rb

@@ -28,24 +28,26 @@ module Ai4r
     #   
     #   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']
-    #          ]
+    #   DATA_ITEMS = [  
+    #          ['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']
+    #        ]
     #   
-    #   id3 = Ai4r::Classifiers::ID3.new(DATA_SET, DATA_LABELS)
+    #   data_set = DataSet.new(:data_items=>DATA_SET, :data_labels=>DATA_LABELS)
+    #   id3 = Ai4r::Classifiers::ID3.new.build(data_set)
     #   
     #   id3.get_rules
     #     # =>  if age_range=='<30' then marketing_target='Y'
@@ -64,22 +66,20 @@ module Ai4r
     # attributes. Consider moving your data to an external CSV (comma separate 
     # values) file.
     #                 
-    #   data_set = []
-    #   CSV::Reader.parse(File.open("#{File.dirname(__FILE__)}/data_set.csv", 'r')) do |row|
-    #     data_set << row
-    #   end
-    #   data_labels = data_set.shift
-    #   
-    #   id3 = Ai4r::Classifiers::ID3.new(data_set, data_labels)      
+    #   data_file = "#{File.dirname(__FILE__)}/data_set.csv"
+    #   data_set = DataSet.load_data_and_labels_from_csv data_file
+    #   id3 = Ai4r::Classifiers::ID3.new.build(data_set)      
     #   
     # = A nice tip for data evaluation
     # 
-    #   id3 = Ai4r::Classifiers::ID3.new(DATA_SET, DATA_LABELS)
-    #     age_range = '<30'
-    #     marketing_target = nil
-    #     eval id3.get_rules   
-    #     puts marketing_target
-    #       # =>  'Y'  
+    #   id3 = Ai4r::Classifiers::ID3.new.build(data_set)
+    #
+    #   age_range = '<30'
+    #   marketing_target = nil
+    #   eval id3.get_rules   
+    #   puts marketing_target
+    #     # =>  'Y'  
+    #
     # = More about ID3 and decision trees
     # 
     # * http://en.wikipedia.org/wiki/Decision_tree
@@ -92,7 +92,7 @@ module Ai4r
     class ID3 < Classifier
       
       attr_reader :data_set
-      
+       
       # Create a new ID3 classifier. You must provide a DataSet instance
       # as parameter.
       def build(data_set)

data/lib/ai4r/clusterers/clusterer.rb

@@ -7,6 +7,8 @@
 # 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__) + '/../data/parameterizable'
+
 module Ai4r
   module Clusterers
     
@@ -14,7 +16,9 @@ module Ai4r
     # All methods in this class (other than eval) must be implemented in 
     # subclasses. 
     class Clusterer
-      
+
+      include Ai4r::Data::Parameterizable
+    
       # Build a new clusterer, using data examples found in data_set.
       # Data items will be clustered in "number_of_clusters" different
       # clusters.
@@ -27,29 +31,6 @@ module Ai4r
         raise NotImplementedError
       end
       
-      # Get info on what can be parameterized on this clusterer.
-      # It returns a hash with the following format:
-      # { :param_name => "Info on the parameter" }
-      def get_parameters_info
-        raise NotImplementedError
-      end
-      
-      # Set parameter values on this clusterer instance.
-      # You must provide a hash with the folowing format:
-      # { :param_name => parameter_value }
-      def set_parameters(parameters)
-        raise NotImplementedError
-      end
-      
-      # Get parameter values on this clusterer instance.
-      # Returns a hash with the folowing format:
-      # { :param_name => parameter_value }
-      def get_parameters
-        raise NotImplementedError
-      end
-      
-      
     end
-    
   end
 end

data/lib/ai4r/clusterers/k_means.rb

@@ -23,8 +23,13 @@ module Ai4r
       
       attr_reader :data_set, :number_of_clusters
       attr_reader :clusters, :centroids, :iterations
-      attr_accessor :max_iterations
-      attr_accessor :distance_function
+      
+      parameters_info :max_iterations => "Maximum number of iterations to " + 
+        "build the clusterer. By default it is uncapped.",
+        :distance_function => "Custom implementation of distance function. " +
+          "It must be a closure receiving two data items and return the " +
+          "distance bewteen them. By default, this algorithm uses " + 
+          "ecuclidean distance of numeric attributes to the power of 2."
       
       # Build a new clusterer, using data examples found in data_set.
       # Items will be clustered in "number_of_clusters" different
@@ -50,42 +55,6 @@ module Ai4r
             distance(data_item, centroid)})
       end
       
-      # Get info on what can be parameterized on this clusterer algorithm.
-      # It returns a hash with the following format:
-      # { :param_name => "Info on the parameter" }
-      def get_parameters_info
-        { :max_iterations => "Maximum number of iterations to build the " + 
-          "clusterer. By default it is uncapped.",
-          :distance_function => "Custom implementation of distance function. " + 
-            "It must be a closure receiving two data items and return the " +
-            "distance bewteen them. By default, this algorithm uses " + 
-            "ecuclidean distance of numeric attributes to the power of 2."
-          }
-      end
-      
-      # Set parameters on this clusterer instance.
-      # You must provide a hash with the folowing format:
-      # { :param_name => parameter_value }
-      # 
-      # Use get_parameters_info to know what parameters are accepted.
-      def set_parameters(parameters)
-        if parameters.has_key?(:max_iterations)
-          @max_iterations = parameters[:max_iterations] 
-        end
-        if parameters.has_key?(:distance_function)
-          @distance_function = parameters[:distance_function] 
-        end
-        return self
-      end
-      
-      # Get parameter values on this clusterer instance.
-      # Returns a hash with the folowing format:
-      # { :param_name => parameter_value }
-      def get_parameters
-        { :max_iterations => @max_iterations,
-          :distance_function => @distance_function }
-      end
-      
       # This function calculates the distance between 2 different
       # instances. By default, it returns the euclidean distance to the 
       # power of 2.

data/lib/ai4r/data/data_set.rb

@@ -30,9 +30,11 @@ module Ai4r
         set_data_items(options[:data_items]) if options[:data_items]
       end
 
-      # Retrieve data item(s) by index. You can specify a an index range, too.
+      # Retrieve a new DataSet, with the item(s) selected by the provided 
+      # index. You can specify an index range, too.
       def [](index)
-        return @data_items[index]
+        return DataSet.new(:data_items=>@data_items[index], 
+          :data_labels =>@data_labels)
       end
       
       # Load data items from csv file

data/lib/ai4r/data/parameterizable.rb

@@ -0,0 +1,64 @@
+# 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
+    module Parameterizable
+	
+      module ClassMethods
+        
+        # Get info on what can be parameterized on this algorithm.
+        # It returns a hash with the following format:
+        # { :param_name => "Info on the parameter" }
+        def get_parameters_info
+          return @_params_info_ || {}
+        end
+        
+        # Set info on what can be parameterized on this algorithm.
+        # You must provide a hash with the following format:
+        # { :param_name => "Info on the parameter" }        
+        def parameters_info(params_info)
+          @_params_info_ = params_info
+          params_info.keys.each do |param|
+            attr_accessor param
+          end
+        end
+      end
+  
+      # Set parameter values on this algorithm instance.
+      # You must provide a hash with the folowing format:
+      # { :param_name => parameter_value }
+      def set_parameters(params)
+        self.class.get_parameters_info.keys.each do | key |
+          if self.respond_to?("#{key}=".to_sym)
+            send("#{key}=".to_sym, params[key]) if params.has_key? key
+          end
+        end
+        return self
+      end
+      
+      # Get parameter values on this algorithm instance.
+      # Returns a hash with the folowing format:
+      # { :param_name => parameter_value }
+      def get_parameters
+        params = {}
+        self.class.get_parameters_info.keys.each do | key |
+          params[key] = send(key) if self.respond_to?(key)
+        end
+        return params
+      end
+
+      def self.included(base)
+        base.extend(ClassMethods)
+      end
+  
+    end
+  end
+end
+