knn 0.0.0 → 0.0.1

data/README.rdoc

@@ -26,6 +26,32 @@ Simple KNN Ruby implementation
   data[4837]
     #=> [0.966558570073977, 0.903158898673566, 0.954567901514261, 0.988114355901207]
 
+== Distance Measurements
+
+KNN uses the Distance Measures Gem (http://github.com/reddavis/Distance-Measures) so we get quite a range of distance measurements.
+
+The measurements currently available are:
+
+  euclidean_distance
+
+  cosine_similarity
+
+  jaccard_index
+
+  jaccard_distance
+
+  binary_jaccard_index
+
+  binary_jaccard_distance
+
+  tanimoto_coefficient
+
+To specify a particular one to use in the KNN algorithm, just provide it as an option:
+
+  KNN.new(@data, :distance_measure => :jaccard_index)
+  KNN.new(@data, :distance_measure => :cosine_similarity)
+  KNN.new(@data, :distance_measure => :tanimoto_coefficient)
+
 == Copyright
 
 Copyright (c) 2009 Red Davis. See LICENSE for details.

data/Rakefile

@@ -11,6 +11,7 @@ begin
     gem.homepage = "http://github.com/reddavis/knn"
     gem.authors = ["reddavis"]
     gem.add_development_dependency "rspec", ">= 1.2.9"
+    gem.add_dependency('distance_measures', '>= 0.0.0')
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
   end
   Jeweler::GemcutterTasks.new

data/VERSION

@@ -1 +1 @@
-0.0.0
+0.0.1

data/knn.gemspec

@@ -0,0 +1,60 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{knn}
+  s.version = "0.0.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["reddavis"]
+  s.date = %q{2010-01-26}
+  s.description = %q{Simple K Nearest Neighbour algorithm}
+  s.email = %q{reddavis@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "examples/example_one.rb",
+     "knn.gemspec",
+     "lib/knn.rb",
+     "spec/knn_spec.rb",
+     "spec/spec.opts",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/reddavis/knn}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Simple K Nearest Neighbour algorithm}
+  s.test_files = [
+    "spec/knn_spec.rb",
+     "spec/spec_helper.rb",
+     "examples/example_one.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_runtime_dependency(%q<distance_measures>, [">= 0.0.0"])
+    else
+      s.add_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_dependency(%q<distance_measures>, [">= 0.0.0"])
+    end
+  else
+    s.add_dependency(%q<rspec>, [">= 1.2.9"])
+    s.add_dependency(%q<distance_measures>, [">= 0.0.0"])
+  end
+end
+

data/lib/knn.rb

@@ -1,8 +1,9 @@
-require File.expand_path(File.dirname(__FILE__) + '/ext/array')
+require 'distance_measures'
 
 class KNN
-  def initialize(data)
+  def initialize(data, options={})
     @data = data
+    @distance_measure = options[:distance_measure] || :euclidean_distance
   end
   
   def nearest_neighbours(input, k=4)
@@ -12,13 +13,17 @@ class KNN
   private
   
   def find_closest_data(input, k)
-    calculated_distances = []
+    begin
+      calculated_distances = []
     
-    @data.each_with_index do |datum, index| #Ye olde english
-      distance = input.euclidean_distance_from(datum)
-      calculated_distances << [index, distance, datum]
-    end
+      @data.each_with_index do |datum, index| #Ye olde english
+        distance = input.send(@distance_measure, datum)
+        calculated_distances << [index, distance, datum]
+      end
     
-    calculated_distances.sort {|x, y| x[1] <=> y[1]}.first(k)
+      calculated_distances.sort {|x, y| x[1] <=> y[1]}.first(k)
+    rescue NoMethodError
+      raise "Hey, that's not a measurement. Read the README for available measurements"
+    end
   end  
 end

data/spec/knn_spec.rb

@@ -11,6 +11,14 @@ describe "KNN" do
     neighbours.map {|x| x[2]}.should include([50,52], [10,11])
   end
   
+  describe "Providing a wrong distance measure" do
+    it "should raise an error" do
+      lambda do
+        KNN.new(data, :distance_measure => :wrong).nearest_neighbours([2,2])
+      end.should raise_error
+    end
+  end
+  
   private
   
   def data

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: knn
 version: !ruby/object:Gem::Version 
-  version: 0.0.0
+  version: 0.0.1
 platform: ruby
 authors: 
 - reddavis
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-07 00:00:00 +00:00
+date: 2010-01-26 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -22,6 +22,16 @@ dependencies:
       - !ruby/object:Gem::Version 
         version: 1.2.9
     version: 
+- !ruby/object:Gem::Dependency 
+  name: distance_measures
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+    version: 
 description: Simple K Nearest Neighbour algorithm
 email: reddavis@gmail.com
 executables: []
@@ -39,9 +49,8 @@ files:
 - Rakefile
 - VERSION
 - examples/example_one.rb
-- lib/ext/array.rb
+- knn.gemspec
 - lib/knn.rb
-- spec/ext/array_spec.rb
 - spec/knn_spec.rb
 - spec/spec.opts
 - spec/spec_helper.rb
@@ -74,7 +83,6 @@ signing_key:
 specification_version: 3
 summary: Simple K Nearest Neighbour algorithm
 test_files: 
-- spec/ext/array_spec.rb
 - spec/knn_spec.rb
 - spec/spec_helper.rb
 - examples/example_one.rb

data/lib/ext/array.rb

@@ -1,9 +0,0 @@
-class Array
-  def euclidean_distance_from(other)
-    sum = 0.0
-    self.each_with_index do |datum, index|
-      sum += (datum - other[index]) ** 2
-    end
-    Math.sqrt(sum)
-  end
-end

data/spec/ext/array_spec.rb

@@ -1,13 +0,0 @@
-require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
-
-describe "Array" do
-  describe "Euclidean Distance" do
-    it "should return 0" do
-      [0,0].euclidean_distance_from([0,0]).should == 0
-    end
-    
-    it "should return 1" do
-      [0,0].euclidean_distance_from([0,1]).should == 1
-    end
-  end
-end