ai4r 1.2 → 1.3

data/lib/ai4r/data/data_set.rb

@@ -0,0 +1,250 @@
+# 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 'csv'
+require 'set'
+
+module Ai4r
+  module Data
+    class DataSet
+      
+      attr_reader :data_labels, :data_items 
+      
+      # Create a new DataSet. By default, empty.
+      # Optionaly, you can provide the initial data items and data labels.
+      # 
+      # e.g. DataSet.new(:data_items => data_items, :data_labels => labels)
+      # 
+      # If you provide data items, but no data labels, the data set will
+      # use the default data label values (see set_data_labels)
+      def initialize(options = {})
+        @data_labels = options[:data_labels] || []
+        @data_items = options[:data_items] || []
+        set_data_labels(options[:data_labels]) if options[:data_labels]
+        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.
+      def [](index)
+        return @data_items[index]
+      end
+      
+      # Load data items from csv file
+      def load_data_from_csv(filepath)
+        items = []
+        CSV::Reader.parse(File.open(filepath, 'r')) do |row|
+          items << row
+        end
+        set_data_items(items)
+      end
+      
+      # Load data items from csv file. The first row is used as data labels.
+      def load_data_and_labels_from_csv(filepath)
+        load_data_from_csv(filepath)
+        @data_labels = @data_items.shift
+        return self
+      end
+      
+      # Set data labels.
+      # Data labels must have the following format:
+      #     [ 'city', 'age_range', 'gender', 'marketing_target'  ]
+      #
+      # If you do not provide labels for you data, the following labels will
+      # be created by default:
+      #     [ 'attribute_1', 'attribute_2', 'attribute_3', 'class_value'  ]      
+      def set_data_labels(labels)
+        check_data_labels(labels)
+        @data_labels = labels
+        return self
+      end
+
+      # Set the data items.
+      # M data items with  N attributes must have the following 
+      # format:
+      # 
+      #     [   [ATT1_VAL1, ATT2_VAL1, ATT3_VAL1, ... , ATTN_VAL1,  CLASS_VAL1], 
+      #         [ATT1_VAL2, ATT2_VAL2, ATT3_VAL2, ... , ATTN_VAL2,  CLASS_VAL2], 
+      #         ...
+      #         [ATTM1_VALM, ATT2_VALM, ATT3_VALM, ... , ATTN_VALM, CLASS_VALM], 
+      #     ]
+      #     
+      # e.g.
+      #     [   ['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']
+      #        ]
+      # 
+      # This method returns the classifier (self), allowing method chaining.
+      def set_data_items(items)
+        check_data_items(items)
+        @data_labels = default_data_labels(items) if @data_labels.empty?
+        @data_items = items
+        return self
+      end
+
+      # Returns an array with the domain of each attribute (Set instance 
+      # containing all possible values)
+      # Return example:
+      # => [#<Set: {"New York", "Chicago"}>, 
+      #     #<Set: {"<30", "[30-50)", "[50-80]", ">80"}>, 
+      #     #<Set: {"M", "F"}>, 
+      #     #<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
+      end
+      
+      # Returns a Set instance containing all possible values for an attribute
+      # The parameter can be an attribute label or index (0 based).
+      # 
+      #   build_domain("city")
+      #   => #<Set: {"New York", "Chicago"}>
+      # 
+      #   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]
+        end
+        return domain
+      end
+      
+      # Returns attributes number, including class attribute
+      def num_attributes
+        return (@data_items.empty?) ? 0 : @data_items.first.size
+      end
+      
+      # Returns the index of a given attribute (0-based).
+      # For example, if "gender" is the third attribute, then:
+      #   get_index("gender") 
+      #   => 2
+      def get_index(attr)
+        return (attr.is_a?(String)) ? @data_labels.index(attr) : attr
+      end
+      
+      # Raise an exception if there is no data item.
+      def check_not_empty
+        if @data_items.empty?
+          raise ArgumentError,"Examples data set must not be empty."
+        end
+      end
+
+      # Add a data item to the data set
+      def << data_item
+        if data_item.nil? || !data_item.is_a?(Array) || data_item.empty?
+          raise ArgumentError,"Data must not be an non empty array."
+        elsif @data_items.empty?
+          set_data_items([data_item])
+        elsif data_item.length != num_attributes
+          raise ArgumentError,"Number of attributes do not match. " + 
+            "#{data_item.length} attributes provided, " + 
+            "#{num_attributes} attributes expected."
+        else 
+          @data_items << data_item
+        end
+      end
+      
+      def get_attribute_mean(attribute)
+        index = get_index(attribute)
+        mean = 0.0
+        @data_items.each { |data_item| mean += data_item[index] }
+        mean /= @data_items.length
+        return mean
+      end
+      
+      def get_attribute_mode(attribute)
+        index = get_index(attribute)
+        domain = build_domain(attribute)
+        count = {}
+        domain.each {|value| count[value]=0}
+        @data_items.each { |data_item| count[data_item[index]] += 1 }
+        max_count = 0
+        mode = nil
+        count.each_pair do |value, value_count|
+          if value_count > max_count
+            mode = value
+            max_count = value_count
+          end
+        end
+        return mode
+      end
+      
+      def get_attribute_mean_or_mode(attribute)
+        index = get_index(attribute)
+        if @data_items.first[index].is_a?(Numeric)
+          return get_attribute_mean(attribute)
+        else
+          return get_attribute_mode(attribute)
+        end
+      end
+      
+      def get_mean_or_mode
+        mean = []
+        num_attributes.times {|i| mean[i] = get_attribute_mean_or_mode(i) }
+        return mean
+      end
+      
+      protected
+      def check_data_items(data_items)
+        if !data_items || data_items.empty?
+          raise ArgumentError,"Examples data set must not be empty." 
+        elsif !data_items.first.is_a?(Array)
+          raise ArgumentError,"Unkown format for example data." 
+        end
+        attributes_num = data_items.first.length
+        data_items.each_index do |index|
+          if data_items[index].length != attributes_num
+            raise ArgumentError,
+                "Quantity of attributes is inconsistent. " + 
+                "The first item has #{attributes_num} attributes "+ 
+                "and row #{index} has #{data_items[index].length} attributes"  
+          end
+        end
+      end
+      
+      def check_data_labels(labels)
+        if !@data_items.empty?
+          if labels.length != @data_items.first.length
+            raise ArgumentError,
+              "Number of labels and attributes do not match. " + 
+              "#{labels.length} labels and " + 
+              "#{@data_items.first.length} attributes found."  
+          end
+        end
+      end
+      
+      def default_data_labels(data_items)
+        data_labels = []
+        data_items[0][0..-2].each_index do |i|
+          data_labels[i] = "attribute_#{i+1}" 
+        end
+        data_labels[data_labels.length]="class_value"
+        return data_labels
+      end
+      
+    end
+  end
+end

data/lib/ai4r/genetic_algorithm/genetic_algorithm.rb

@@ -1,14 +1,4 @@
 # 
-# The GeneticAlgorithm module implements the GeneticSearch and Chromosome 
-# classes. The GeneticSearch is a generic class, and can be used to solved 
-# any kind of problems. The GeneticSearch class performs a stochastic search 
-# of the solution of a given problem.
-# 
-# The Chromosome is "problem specific". Ai4r built-in Chromosomeclass was 
-# designed to model the Travelling salesman problem. If you want to solve other 
-# type of problem, you will have to modify the Chromosome class, by overwriting 
-# its fitness, reproduce, and mutate functions, to model you specific problem.
-# 
 # Author::    Sergio Fierens
 # License::   MPL 1.1
 # Project::   ai4r
@@ -19,7 +9,16 @@
 # Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
 
 module Ai4r
-
+  
+  # The GeneticAlgorithm module implements the GeneticSearch and Chromosome 
+  # classes. The GeneticSearch is a generic class, and can be used to solved 
+  # any kind of problems. The GeneticSearch class performs a stochastic search 
+  # of the solution of a given problem.
+  # 
+  # The Chromosome is "problem specific". Ai4r built-in Chromosomeclass was 
+  # designed to model the Travelling salesman problem. If you want to solve other 
+  # type of problem, you will have to modify the Chromosome class, by overwriting 
+  # its fitness, reproduce, and mutate functions, to model you specific problem.
   module GeneticAlgorithm
 
     #   This class is used to automatically:
@@ -156,10 +155,10 @@ module Ai4r
 
     end
 
-    # A Chromosome is a representation of an individual solutions for a specific 
-    # problem. You will have to redifine you Chromosome representation for each
+    # A Chromosome is a representation of an individual solution for a specific 
+    # problem. You will have to redifine the Chromosome representation for each
     # particular problem, along with its fitness, mutate, reproduce, and seed 
-    # functions.
+    # methods.
     class Chromosome
 
       attr_accessor :data
@@ -169,7 +168,7 @@ module Ai4r
         @data = data
       end
 
-      # The fitness function quantifies the optimality of a solution 
+      # The fitness method quantifies the optimality of a solution 
       # (that is, a chromosome) in a genetic algorithm so that that particular 
       # chromosome may be ranked against all the other chromosomes. 
       # 
@@ -188,7 +187,7 @@ module Ai4r
         return @fitness
       end
 
-      # mutation is a function used to maintain genetic diversity from one 
+      # mutation method is used to maintain genetic diversity from one 
       # generation of a population of chromosomes to the next. It is analogous 
       # to biological mutation. 
       # 
@@ -214,8 +213,8 @@ module Ai4r
         end
       end
 
-      # Reproduction is used to vary the programming of a chromosome or 
-      # chromosomes from one generation to the next. There are several ways to
+      # Reproduction method is used to combine two chromosomes (solutions) into 
+      # a single new chromosome. There are several ways to
       # combine two chromosomes: One-point crossover, Two-point crossover,
       # "Cut and splice", edge recombination, and more. 
       # 
@@ -249,7 +248,8 @@ module Ai4r
 
       # Initializes an individual solution (chromosome) for the initial 
       # population. Usually the chromosome is generated randomly, but you can 
-      # use some problem domain knowledge, to generate better initial solutions.
+      # use some problem domain knowledge, to generate a 
+      # (probably) better initial solution.
       def self.seed
         data_size = @@costs[0].length
         available = []

data/lib/ai4r/neural_network/backpropagation.rb

@@ -1,26 +1,3 @@
-# The utility of artificial neural network 
-# models lies in the fact that they can be used 
-# to infer a function from observations. 
-# This is particularly useful in applications 
-# where the complexity of the data or task makes the 
-# design of such a function by hand impractical.
-# Neural Networks are being used in many businesses and applications. Their 
-# ability to learn by example makes them attractive in environments where 
-# the business rules are either not well defined or are hard to enumerate and 
-# define. Many people believe that Neural Networks can only solve toy problems.
-# Give them a try, and let you decide if they are good enough to solve your 
-# needs.
-# 
-# In this module you will find an implementation of neural networks
-# using the Backpropagation is a supervised learning technique (described 
-# by Paul Werbos in 1974, and further developed by David E. 
-# Rumelhart, Geoffrey E. Hinton and Ronald J. Williams in 1986)
-# 
-# More about neural networks and backpropagation:
-# 
-# * http://en.wikipedia.org/wiki/Backpropagation
-# * http://en.wikipedia.org/wiki/Neural_networks
-# 
 # Author::    Sergio Fierens
 # License::   MPL 1.1
 # Project::   ai4r
@@ -36,6 +13,28 @@
 
 module Ai4r
 
+  # The utility of artificial neural network 
+  # models lies in the fact that they can be used 
+  # to infer a function from observations. 
+  # This is particularly useful in applications 
+  # where the complexity of the data or task makes the 
+  # design of such a function by hand impractical.
+  # Neural Networks are being used in many businesses and applications. Their 
+  # ability to learn by example makes them attractive in environments where 
+  # the business rules are either not well defined or are hard to enumerate and 
+  # define. Many people believe that Neural Networks can only solve toy problems.
+  # Give them a try, and let you decide if they are good enough to solve your 
+  # needs.
+  # 
+  # In this module you will find an implementation of neural networks
+  # using the Backpropagation is a supervised learning technique (described 
+  # by Paul Werbos in 1974, and further developed by David E. 
+  # Rumelhart, Geoffrey E. Hinton and Ronald J. Williams in 1986)
+  # 
+  # More about neural networks and backpropagation:
+  # 
+  # * http://en.wikipedia.org/wiki/Backpropagation
+  # * http://en.wikipedia.org/wiki/Neural_networks
   module NeuralNetwork
 
     # = Introduction
@@ -48,7 +47,7 @@ module Ai4r
     # = How to use it
     # 
     #   # Create the network
-    #   net = Backpropagation.new([4, 3, 2])  # 4 inputs
+    #   net = Ai4r::NeuralNetwork::Backpropagation.new([4, 3, 2])  # 4 inputs
     #                                         # 1 hidden layer with 3 neurons, 
     #                                         # 2 outputs
     #   # Train the network 

data/site/build/site/en/broken-links.xml

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

data/site/build/site/en/downloads.html

@@ -0,0 +1,200 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
+<meta content="Apache Forrest" name="Generator">
+<meta name="Forrest-version" content="0.8">
+<meta name="Forrest-skin-name" content="pelt">
+<meta name="generator" content="">
+<title>Artificial intelligence for ruby :: ai4r :: download page at RubyForge</title>
+<link type="text/css" href="skin/basic.css" rel="stylesheet">
+<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
+<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
+<link type="text/css" href="skin/profile.css" rel="stylesheet">
+<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
+<link rel="shortcut icon" href="">
+</head>
+<body onload="init()">
+<script type="text/javascript">ndeSetTextSize();</script>
+<div id="top">
+<!--+
+    |header
+    +-->
+<div class="header">
+<!--+
+    |start group logo
+    +-->
+<div class="grouplogo">
+<a href="http://www.jadeferret.com"><img class="logoImage" alt="Jade Ferret" src="images/jadeferret.png" title="Jade Ferret"></a>
+</div>
+<!--+
+    |end group logo
+    +-->
+<!--+
+    |start Project Logo
+    +-->
+<div class="projectlogo">
+<a href="http://ai4r.rubyforge.org/"><img class="logoImage" alt="ai4r" src="images/ai4r-logo.png" title="AI4R - Artificial Intelligence for Ruby"></a>
+</div>
+<!--+
+    |end Project Logo
+    +-->
+<!--+
+    |start Search
+    +-->
+<div class="searchbox">
+<div class="roundtopsmall">
+<form target="_top" action="http://www.google.com/custom" method="get">
+<input value="ai4r.rubyforge.org;raa.ruby-lang.org;rubyforge.org" name="domains" type="hidden"><label style="display: none" for="sbi">Enter your search terms</label><input id="sbi" value="" maxlength="255" size="31" name="q" type="text"><label style="display: none" for="sbb">Submit search form</label><input id="sbb" value="Search" name="sa" type="submit"><span style="display:none"><input id="ss0" value="" name="sitesearch" style="display=none" type="radio"><input id="ss1" checked value="ai4r.rubyforge.org" name="sitesearch" style="display=none" type="radio"><input id="ss2" value="raa.ruby-lang.org" name="sitesearch" style="display=none" type="radio"><input id="ss3" value="rubyforge.org" name="sitesearch" style="display=none" type="radio"></span><input value="pub-2578934938711895" name="client" type="hidden"><input value="1" name="forid" type="hidden"><input value="ISO-8859-1" name="ie" type="hidden"><input value="ISO-8859-1" name="oe" type="hidden"><input value="active" name="safe" type="hidden"><input value="0000" name="flav" type="hidden"><input value="XEZZoGuMPMQqvUG_" name="sig" type="hidden"><input value="GALT:#008000;GL:1;DIV:#336699;VLC:663399;AH:center;BGC:FFFFFF;LBGC:336699;ALC:0000FF;LC:0000FF;T:000000;GFNT:0000FF;GIMP:0000FF;LH:50;LW:78;L:http://ai4r.rubyforge.org/images/ai4r-logo.png;S:http://ai4r.rubyforge.org/;FORID:1" name="cof" type="hidden"><input value="en" name="hl" type="hidden">
+</form>
+</div>
+</div>
+<!--+
+    |end search
+    +-->
+<!--+
+    |start Tabs
+    +-->
+<ul id="tabs">
+<li class="current">
+<a class="selected" href="index.html">Home</a>
+</li>
+</ul>
+<!--+
+    |end Tabs
+    +-->
+</div>
+</div>
+<div id="main">
+<div id="publishedStrip">
+<!--+
+    |start Subtabs
+    +-->
+<div id="level2tabs"></div>
+<!--+
+    |end Endtabs
+    +-->
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<!--+
+    |breadtrail
+    +-->
+<div class="breadtrail">
+
+             &nbsp;
+           </div>
+<!--+
+    |start Menu, mainarea
+    +-->
+<!--+
+    |start Menu
+    +-->
+<div id="menu">
+<div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">Home</div>
+<div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;">
+<div class="menuitem">
+<a href="index.html" title="ai4r - Artificial Intelligence for Ruby">Index</a>
+</div>
+<div onclick="SwitchMenu('menu_1.1.2', 'skin/')" id="menu_1.1.2Title" class="menutitle">Practical Examples</div>
+<div id="menu_1.1.2" class="menuitemgroup">
+<div class="menuitem">
+<a href="geneticAlgorithms.html" title="Genetic Algorithms in ruby">Genetic Algorithms</a>
+</div>
+<div class="menuitem">
+<a href="machineLearning.html" title="ID3 Decision Trees in ruby">Machine Learning</a>
+</div>
+<div class="menuitem">
+<a href="neuralNetworks.html" title="Backpropagation Neural Network in ruby">Neural Networks</a>
+</div>
+</div>
+<div class="menupage">
+<div class="menupagetitle">Downloads</div>
+</div>
+<div class="menuitem">
+<a href="http://forum.jadeferret.com/viewforum.php?f=3" title="Ai4r Forum">Forum</a>
+</div>
+<div class="menuitem">
+<a href="http://ai4r.rubyforge.org/rdoc/index.html" title="Ai4 RDoc docs">API doc (Rdoc)</a>
+</div>
+<div class="menuitem">
+<a href="svn.html" title="ai4r Subversion repository">Source Code repository</a>
+</div>
+<div class="menuitem">
+<a href="wholesite.pdf">ai4r project PDF</a>
+</div>
+</div>
+<div id="credit">
+<script type="text/javascript">
+google_ad_client = "pub-2578934938711895";
+google_ad_slot = "6111091580";
+google_ad_width = 125;
+google_ad_height = 125;
+</script><script src="http://pagead2.googlesyndication.com/pagead/show_ads.js" type="text/javascript"></script>
+<hr>
+</div>
+<div id="roundbottom">
+<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
+<!--+
+  |alternative credits
+  +-->
+<div id="credit2"></div>
+</div>
+<!--+
+    |end Menu
+    +-->
+<!--+
+    |start content
+    +-->
+<div id="content">
+<div title="Portable Document Format" class="pdflink">
+<a class="dida" href="downloads.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br>
+        PDF</a>
+</div>
+<h1>Artificial intelligence for ruby :: ai4r :: download page at RubyForge</h1>
+<div id="minitoc-area">
+<ul class="minitoc">
+<li>
+<a href="#intro">Artificial intelligence for ruby - ai4r - download page at RubyForge</a>
+</li>
+</ul>
+</div>
+<a name="N10010"></a><a name="intro"></a>
+<h2 class="boxed">Artificial intelligence for ruby - ai4r - download page at RubyForge</h2>
+<div class="section">
+<iframe frameborder="0" height="800px" src="http://rubyforge.org/frs/?group_id=4942" width="100%"></iframe>
+</div>
+</div>
+<!--+
+    |end content
+    +-->
+<div class="clearboth">&nbsp;</div>
+</div>
+<div id="footer">
+<!--+
+    |start bottomstrip
+    +-->
+<div class="lastmodified">
+<script type="text/javascript"><!--
+document.write("Last Published: " + document.lastModified);
+//  --></script>
+</div>
+<div class="copyright">
+        Copyright &copy;
+         2007-2009 <a href="http://www.jadeferret.com/">Sergio Fierens, Jade Ferret</a>
+</div>
+<div class="host">
+<a href="http://rubyforge.org/projects/ai4r/"><img class="logoImage" alt="" src="images/rubyforge.png"></a>
+</div>
+<!--+
+    |end bottomstrip
+    +-->
+</div>
+<script src="http://www.google-analytics.com/ga.js" type="text/javascript"></script><script type="text/javascript">
+var pageTracker = _gat._getTracker("UA-3234625-1");
+pageTracker._initData();
+pageTracker._trackPageview();
+</script>
+</body>
+</html>