som 0.0.1 → 0.0.2

data/README.rdoc

@@ -12,8 +12,10 @@ A pure Ruby implementation of the Self Organising Map machine learning Algorithm
   require 'rubygems'
   require 'som'
   
-  a = SOM.new(:number_of_nodes => 4, :dimensions => 3)
-  a.train(data)
+  data = [[1,2,3], [4,5,6]...]
+  
+  a = SOM.new(data, :number_of_nodes => 4, :dimensions => 3)
+  a.train
 
   # Returns the index of the data you gave it
   a.inspect

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.0.2

data/examples/example.rb

@@ -1,10 +1,30 @@
+require File.expand_path(File.dirname(__FILE__) + '/som_data')
 require File.expand_path(File.dirname(__FILE__) + '/../lib/som')
+require 'benchmark'
 
-data = Array.new(100) {Array.new(3) {rand}}
+require 'rubygems'
+require 'normalizer'
 
-a = SOM.new(:number_of_nodes => 4, :dimensions => 3)
+min, max = Normalizer.find_min_and_max(SOM_DATA)
 
-a.train(data)
+normalizer = Normalizer.new(:min => min, :max => max)
 
-# Returns the index of the data you gave it
-puts a.inspect.inspect
+data = []
+
+SOM_DATA.each do |n|
+  data << normalizer.normalize(n)
+end
+  
+a = SOM.new(data, :nodes => 10, :dimensions => data[0].size)
+
+puts a.nodes.inspect
+
+puts a.global_distance_error
+
+times = Benchmark.measure do
+  a.train
+end
+
+puts a.global_distance_error
+
+puts times

data/examples/som_data.rb

@@ -0,0 +1,158 @@
+# Taken from AI4R Gem
+
+# data is from the iris dataset (http://archive.ics.uci.edu/ml/datasets/Iris)
+# it is the full dataset, removing the last column
+# website provides additional information on the dataset itself (attributes, class distribution, etc)
+
+SOM_DATA = [
+        [5.1, 3.5, 1.4, 0.2],
+        [4.9, 3.0, 1.4, 0.2],
+        [4.7, 3.2, 1.3, 0.2],
+        [4.6, 3.1, 1.5, 0.2],
+        [5.0, 3.6, 1.4, 0.2],
+        [5.4, 3.9, 1.7, 0.4],
+        [4.6, 3.4, 1.4, 0.3],
+        [5.0, 3.4, 1.5, 0.2],
+        [4.4, 2.9, 1.4, 0.2],
+        [4.9, 3.1, 1.5, 0.1],
+        [5.4, 3.7, 1.5, 0.2],
+        [4.8, 3.4, 1.6, 0.2],
+        [4.8, 3.0, 1.4, 0.1],
+        [4.3, 3.0, 1.1, 0.1],
+        [5.8, 4.0, 1.2, 0.2],
+        [5.7, 4.4, 1.5, 0.4],
+        [5.4, 3.9, 1.3, 0.4],
+        [5.1, 3.5, 1.4, 0.3],
+        [5.7, 3.8, 1.7, 0.3],
+        [5.1, 3.8, 1.5, 0.3],
+        [5.4, 3.4, 1.7, 0.2],
+        [5.1, 3.7, 1.5, 0.4],
+        [4.6, 3.6, 1.0, 0.2],
+        [5.1, 3.3, 1.7, 0.5],
+        [4.8, 3.4, 1.9, 0.2],
+        [5.0, 3.0, 1.6, 0.2],
+        [5.0, 3.4, 1.6, 0.4],
+        [5.2, 3.5, 1.5, 0.2],
+        [5.2, 3.4, 1.4, 0.2],
+        [4.7, 3.2, 1.6, 0.2],
+        [4.8, 3.1, 1.6, 0.2],
+        [5.4, 3.4, 1.5, 0.4],
+        [5.2, 4.1, 1.5, 0.1],
+        [5.5, 4.2, 1.4, 0.2],
+        [4.9, 3.1, 1.5, 0.1],
+        [5.0, 3.2, 1.2, 0.2],
+        [5.5, 3.5, 1.3, 0.2],
+        [4.9, 3.1, 1.5, 0.1],
+        [4.4, 3.0, 1.3, 0.2],
+        [5.1, 3.4, 1.5, 0.2],
+        [5.0, 3.5, 1.3, 0.3],
+        [4.5, 2.3, 1.3, 0.3],
+        [4.4, 3.2, 1.3, 0.2],
+        [5.0, 3.5, 1.6, 0.6],
+        [5.1, 3.8, 1.9, 0.4],
+        [4.8, 3.0, 1.4, 0.3],
+        [5.1, 3.8, 1.6, 0.2],
+        [4.6, 3.2, 1.4, 0.2],
+        [5.3, 3.7, 1.5, 0.2],
+        [5.0, 3.3, 1.4, 0.2],
+        [7.0, 3.2, 4.7, 1.4],
+        [6.4, 3.2, 4.5, 1.5],
+        [6.9, 3.1, 4.9, 1.5],
+        [5.5, 2.3, 4.0, 1.3],
+        [6.5, 2.8, 4.6, 1.5],
+        [5.7, 2.8, 4.5, 1.3],
+        [6.3, 3.3, 4.7, 1.6],
+        [4.9, 2.4, 3.3, 1.0],
+        [6.6, 2.9, 4.6, 1.3],
+        [5.2, 2.7, 3.9, 1.4],
+        [5.0, 2.0, 3.5, 1.0],
+        [5.9, 3.0, 4.2, 1.5],
+        [6.0, 2.2, 4.0, 1.0],
+        [6.1, 2.9, 4.7, 1.4],
+        [5.6, 2.9, 3.6, 1.3],
+        [6.7, 3.1, 4.4, 1.4],
+        [5.6, 3.0, 4.5, 1.5],
+        [5.8, 2.7, 4.1, 1.0],
+        [6.2, 2.2, 4.5, 1.5],
+        [5.6, 2.5, 3.9, 1.1],
+        [5.9, 3.2, 4.8, 1.8],
+        [6.1, 2.8, 4.0, 1.3],
+        [6.3, 2.5, 4.9, 1.5],
+        [6.1, 2.8, 4.7, 1.2],
+        [6.4, 2.9, 4.3, 1.3],
+        [6.6, 3.0, 4.4, 1.4],
+        [6.8, 2.8, 4.8, 1.4],
+        [6.7, 3.0, 5.0, 1.7],
+        [6.0, 2.9, 4.5, 1.5],
+        [5.7, 2.6, 3.5, 1.0],
+        [5.5, 2.4, 3.8, 1.1],
+        [5.5, 2.4, 3.7, 1.0],
+        [5.8, 2.7, 3.9, 1.2],
+        [6.0, 2.7, 5.1, 1.6],
+        [5.4, 3.0, 4.5, 1.5],
+        [6.0, 3.4, 4.5, 1.6],
+        [6.7, 3.1, 4.7, 1.5],
+        [6.3, 2.3, 4.4, 1.3],
+        [5.6, 3.0, 4.1, 1.3],
+        [5.5, 2.5, 4.0, 1.3],
+        [5.5, 2.6, 4.4, 1.2],
+        [6.1, 3.0, 4.6, 1.4],
+        [5.8, 2.6, 4.0, 1.2],
+        [5.0, 2.3, 3.3, 1.0],
+        [5.6, 2.7, 4.2, 1.3],
+        [5.7, 3.0, 4.2, 1.2],
+        [5.7, 2.9, 4.2, 1.3],
+        [6.2, 2.9, 4.3, 1.3],
+        [5.1, 2.5, 3.0, 1.1],
+        [5.7, 2.8, 4.1, 1.3],
+        [6.3, 3.3, 6.0, 2.5],
+        [5.8, 2.7, 5.1, 1.9],
+        [7.1, 3.0, 5.9, 2.1],
+        [6.3, 2.9, 5.6, 1.8],
+        [6.5, 3.0, 5.8, 2.2],
+        [7.6, 3.0, 6.6, 2.1],
+        [4.9, 2.5, 4.5, 1.7],
+        [7.3, 2.9, 6.3, 1.8],
+        [6.7, 2.5, 5.8, 1.8],
+        [7.2, 3.6, 6.1, 2.5],
+        [6.5, 3.2, 5.1, 2.0],
+        [6.4, 2.7, 5.3, 1.9],
+        [6.8, 3.0, 5.5, 2.1],
+        [5.7, 2.5, 5.0, 2.0],
+        [5.8, 2.8, 5.1, 2.4],
+        [6.4, 3.2, 5.3, 2.3],
+        [6.5, 3.0, 5.5, 1.8],
+        [7.7, 3.8, 6.7, 2.2],
+        [7.7, 2.6, 6.9, 2.3],
+        [6.0, 2.2, 5.0, 1.5],
+        [6.9, 3.2, 5.7, 2.3],
+        [5.6, 2.8, 4.9, 2.0],
+        [7.7, 2.8, 6.7, 2.0],
+        [6.3, 2.7, 4.9, 1.8],
+        [6.7, 3.3, 5.7, 2.1],
+        [7.2, 3.2, 6.0, 1.8],
+        [6.2, 2.8, 4.8, 1.8],
+        [6.1, 3.0, 4.9, 1.8],
+        [6.4, 2.8, 5.6, 2.1],
+        [7.2, 3.0, 5.8, 1.6],
+        [7.4, 2.8, 6.1, 1.9],
+        [7.9, 3.8, 6.4, 2.0],
+        [6.4, 2.8, 5.6, 2.2],
+        [6.3, 2.8, 5.1, 1.5],
+        [6.1, 2.6, 5.6, 1.4],
+        [7.7, 3.0, 6.1, 2.3],
+        [6.3, 3.4, 5.6, 2.4],
+        [6.4, 3.1, 5.5, 1.8],
+        [6.0, 3.0, 4.8, 1.8],
+        [6.9, 3.1, 5.4, 2.1],
+        [6.7, 3.1, 5.6, 2.4],
+        [6.9, 3.1, 5.1, 2.3],
+        [5.8, 2.7, 5.1, 1.9],
+        [6.8, 3.2, 5.9, 2.3],
+        [6.7, 3.3, 5.7, 2.5],
+        [6.7, 3.0, 5.2, 2.3],
+        [6.3, 2.5, 5.0, 1.9],
+        [6.5, 3.0, 5.2, 2.0],
+        [6.2, 3.4, 5.4, 2.3],
+        [5.9, 3.0, 5.1, 1.8],
+]

data/lib/som/node.rb

@@ -34,8 +34,8 @@ class Node
   private
   
   def create_weights(number_of_weights)
-    number_of_weights.times do
-      weights << (rand > 0.5 ? -rand : rand)
+    number_of_weights.times do |n|
+      weights << rand
     end
   end
   

data/lib/som.rb

@@ -2,28 +2,30 @@ require File.expand_path(File.dirname(__FILE__) + '/som/node')
 
 class SOM
   
-  def initialize(options={})
+  def initialize(training_data, options={})
+    @training_data = training_data
     @number_of_nodes = options[:nodes] || 5
     @dimensions = options[:dimensions]
     @learning_rate = options[:learning_rate] || 0.5
     @radius = options[:radius] || @number_of_nodes / 2
-    @iteration_count = 0
-    @max_iterations = options[:max_iterations] || 500
+    @iteration_count = 1
+    @max_iterations = options[:max_iterations] || 100
     # TODO: Allow a lambda so we can use different neighborhood functions
     @neighborhood_function = options[:neighborhood_function] || 1
-    create_nodes
+    
+    create_nodes(training_data)
   end
   
   def nodes
     @nodes ||= []
   end
   
-  def train(data)
-    while train_it!(data)
+  def train
+    while train_it!(@training_data)
     end
     # Place the data in the nodes buckets so we can see how
     # The data has been clustered
-    place_data_into_buckets(data)
+    place_data_into_buckets(@training_data)
   end
   
   # Returns an array of buckets containing the index of the data given
@@ -41,11 +43,18 @@ class SOM
     closest_node.bucket
   end
   
+  # Taken from AI4R SOM library #107
+  def global_distance_error
+    @training_data.inject(0) do |sum, n|
+      sum + find_closest(n)[1]
+    end
+  end
+  
   private
   
   def train_it!(data)
     return false if @iteration_count >= @max_iterations
-    
+        
     data.each do |input|
       # Update closest node
       closest_node = find_closest_node(input)
@@ -54,14 +63,12 @@ class SOM
       # Update nodes that closer than the radius
       other_nodes = nodes - [closest_node]
       other_nodes.each do |node|
-        next if @radius > node.distance_from(closest_node.weights)
+        next if decayed_radius > node.distance_from(closest_node.weights)
       
         node.update_weight(@learning_rate, input, neighborhood_function)
       end
     end
     
-    decrease_radius!
-    decrease_learning_rate!
     increase_iteration_count!
   end
   
@@ -72,14 +79,14 @@ class SOM
     end
   end
   
-  def decrease_radius!
-    @radius = 0.5 * @radius * @iteration_count / @max_iterations
+  def decayed_radius
+    @radius - (0.1 * @radius * @iteration_count / @max_iterations)
   end
   
-  def decrease_learning_rate!
-    @learning_rate = 0.5 * @learning_rate * @iteration_count / @max_iterations
+  def decayed_learning_rate
+    @learning_rate - (0.5 * @learning_rate * @iteration_count / @max_iterations)
   end
-  
+    
   def increase_iteration_count!
     @iteration_count += 1
   end
@@ -89,6 +96,10 @@ class SOM
   end
   
   def find_closest_node(data)
+    find_closest(data)[0]
+  end
+  
+  def find_closest(data)
     closest_node = [nodes[0], nodes[0].distance_from(data)]
     
     nodes[1..-1].each do |node|
@@ -97,10 +108,10 @@ class SOM
         closest_node = [node, distance]
       end
     end
-    closest_node[0]
+    closest_node
   end
-  
-  def create_nodes
+    
+  def create_nodes(data)
     @number_of_nodes.times { nodes << Node.new(@dimensions) }
   end
   

data/som.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{som}
-  s.version = "0.0.1"
+  s.version = "0.0.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["reddavis"]
-  s.date = %q{2009-11-26}
+  s.date = %q{2009-11-29}
   s.description = %q{A Self Organising Map}
   s.email = %q{reddavis@gmail.com}
   s.extra_rdoc_files = [
@@ -24,6 +24,7 @@ Gem::Specification.new do |s|
      "Rakefile",
      "VERSION",
      "examples/example.rb",
+     "examples/som_data.rb",
      "lib/som.rb",
      "lib/som/node.rb",
      "som.gemspec",
@@ -41,7 +42,8 @@ Gem::Specification.new do |s|
     "spec/node_spec.rb",
      "spec/som_spec.rb",
      "spec/spec_helper.rb",
-     "examples/example.rb"
+     "examples/example.rb",
+     "examples/som_data.rb"
   ]
 
   if s.respond_to? :specification_version then

data/spec/som_spec.rb

@@ -1,54 +1,43 @@
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
-describe "Som" do
-  describe "Initialization" do
-    before do
-      @a = SOM.new(:nodes => 10, :dimensions => 5)
-    end
-    
-    it "should have 10 nodes" do
-      @a.nodes.size.should == 10
-    end
-  end
-  
+describe "Som" do  
   describe "Training" do
     before do
-      @a = SOM.new(:nodes => 1, :dimensions => 2)
-      @data = [[2,3]]
+      @data = [[0,0], [0,0.5], [2,4], [6,5]]
+      @a = SOM.new(@data, :nodes => 1, :dimensions => 2)
     end
     
     it "should change the weight of the best matching node" do
       before = @a.nodes.map {|x| x.weights.clone}
-      @a.train(@data)
+      @a.train
       after = @a.nodes.map {|x| x.weights}
       
       before.should_not == after
     end
     
-    it "should will the nodes bucket with the data" do
-      @a.train(@data)
+    it "should fill the nodes bucket with the data" do
+      @a.train
       @a.nodes[0].bucket.should_not be_empty
     end
     
     it "should preserve data indexes" do
-      data = [[0,0], [0,0.5], [2,4], [6,5]]
-      @a.train(data)
+      @a.train
       
       index_returned = @a.nodes[0].bucket[0][0]
       data_returned = @a.nodes[0].bucket[0][1]
       
-      data[index_returned].should == data_returned
+      @data[index_returned].should == data_returned
     end
   end
   
   describe "Inspect" do
     before do
-      @a = SOM.new(:nodes => 1, :dimensions => 2)
-      @data = [[2,3]]
+      data = [[2,3]]
+      @a = SOM.new(data, :nodes => 1, :dimensions => 2)
     end
     
     it "should show the clusters of data indexes" do
-      @a.train(@data)
+      @a.train
       @a.inspect.should be_an(Array)
       @a.inspect.size.should == 1
     end
@@ -56,12 +45,12 @@ describe "Som" do
   
   describe "Clustering" do
     before do
-      @a = SOM.new(:nodes => 2, :dimensions => 2)
+      data = [[0,0], [999,999]]
+      @a = SOM.new(data, :nodes => 2, :dimensions => 2)
     end
     
     it "should belong to 2 seperate nodes" do
-      data = [[0,0], [999,999]]
-      @a.train(data)
+      @a.train
       @a.inspect[0].should_not be_empty
       @a.inspect[1].should_not be_empty
     end
@@ -69,14 +58,25 @@ describe "Som" do
   
   describe "Classify" do
     before do
-      @a = SOM.new(:nodes => 2, :dimensions => 2)
+      data = [[0,0], [999,999]]
+      @a = SOM.new(data, :nodes => 2, :dimensions => 2)
     end
     
     it "should belong to 2 seperate nodes" do
-      data = [[0,0], [999,999]]
-      @a.train(data)
+      @a.train
       @a.classify([1,1]).should be_an(Array)
       @a.classify([1,1]).size.should == 1
     end
   end
+  
+  describe "Global Distance Error" do
+    before do
+      data = [[0,0], [999,999]]
+      @a = SOM.new(data, :nodes => 2, :dimensions => 2)
+    end
+    
+    it "should return an integer" do
+      @a.global_distance_error.should be_a(Float)
+    end
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: som
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors: 
 - reddavis
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-11-26 00:00:00 +00:00
+date: 2009-11-29 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -39,6 +39,7 @@ files:
 - Rakefile
 - VERSION
 - examples/example.rb
+- examples/som_data.rb
 - lib/som.rb
 - lib/som/node.rb
 - som.gemspec
@@ -79,3 +80,4 @@ test_files:
 - spec/som_spec.rb
 - spec/spec_helper.rb
 - examples/example.rb
+- examples/som_data.rb