buncher 1.0.1 → 1.0.2

data/lib/buncher.rb

@@ -1,6 +1,6 @@
 require 'buncher/buncher'
 module Buncher
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
   # your cluster needs to look like this. Make a bunch of them and pass them in. It's ok to pass in empty elements to start.
   class Cluster
     attr_accessor :elements
@@ -46,9 +46,9 @@ module Buncher
     end
   end
 
-  def self.fK(centers,last_sK, last_aK)
+  def self.fK(centers,last_sK, last_aK,weights)
     # from here - http://www.ee.columbia.edu/~dpwe/papers/PhamDN05-kmeans.pdf
-    sK = centers.inject(0) {|acc, val| acc + val.distortion}
+    sK = centers.inject(0) {|acc, val| acc + val.distortion(weights)}
     aK = calc_aK(centers, last_aK) if centers.size > 1
     if centers.size == 1 || (last_sK||0).zero?
       [1,sK, aK || 0]
@@ -60,21 +60,21 @@ module Buncher
 
   # run the clustering algorithm until have calculated the current number of clusters, taken from this paper:
   # http://papers.nips.cc/paper/2526-learning-the-k-in-k-means.pdf
-  def self.cluster(elements)
+  def self.cluster(elements, weights)
     changed=true
     round=0
     solutions={}
     # try all the sizes of clusters up to #elements. Ok, sure we could probably do something like 25% .. ok, I did
     # that.
     not_clustered = last_sK = last_aK =last_fK=nil
-    max_clusters=[1,elements.size].max
+    max_clusters=[1,(elements.size/2).floor].max
     (1..max_clusters).each do |number_clusters|
-      initial_centers = choose_centers(elements, number_clusters) # C++ Native code
+      initial_centers = choose_centers(elements, weights, number_clusters) # C++ Native code
       centers = initial_centers.map(&:dup)
-      centers = kmeans(centers,elements) ## C++ Native code
+      centers = kmeans(centers,elements,weights) ## C++ Native code
       yield(elements, centers, initial_centers) if block_given?
       not_clustered ||=centers
-      last_fK, last_sK, last_aK = fK(centers,last_sK, last_aK)
+      last_fK, last_sK, last_aK = fK(centers,last_sK, last_aK,weights)
       puts "summary #{number_clusters}: fK() = #{last_fK}, last_sK=#{last_sK} last_aK=#{last_aK} "
       puts
       solutions[last_fK]=centers

data/test/test_buncher.rb

@@ -64,11 +64,17 @@ def plot(file_name,points,centers, initial_centers=nil)
 end
 
 class TestBuncher < Minitest::Test
-WORKING=<<-'EOS'
+   # WORKING=<<-'EOS'
+  def test_distance
+    element1= [1.0, 0.5, 0.533333333333333, 1.0, 0.0, 0.0, 0.333333333333333, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.333333333333333, 0.333333333333333, 0.666666666666667, 0.0, 0.0, 1.0, 0.333333333333333, 0.333333333333333, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.333333333333333, 0.0, 0.0, 0.0, 0.0, 0.0, 0.333333333333333, 0.0, 0.333333333333333, 0.0, 0.4, 0.0, 0.0, 0.0, 0.0, 0.0, 0.333333333333333, 0.333333333333333, 0.0, 0.333333333333333, 0.4, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4, 0.333333333333333, 0.0, 0.666666666666667, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
+    element2= [1.0, 1.0, 0.5, 1.0, 0.0, 0.0, 1.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5, 1.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
+    weights= [0.12158054711246201, 0.060790273556231005, 0.060790273556231005, 0.060790273556231005, 0.060790273556231005, 0.060790273556231005, 0.060790273556231005, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.0060790273556231, 0.0060790273556231, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.0121580547112462, 0.0060790273556231, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155, 0.00303951367781155]
+    assert_in_delta(Buncher::distance(element1,element2, weights),0.098,0.001)
+  end
   def test_should_find_the_one_center
       elements = [[1,1]]
       starting_centers = elements.sample(1).map {|aaa| Buncher::Cluster.new(aaa)}
-      new_centers = Buncher::kmeans(starting_centers, elements)
+      new_centers = Buncher::kmeans(starting_centers, elements, [1]*2)
       dump(new_centers)
       assert_in_delta(new_centers.first.center[0],1.0,0.01)
       assert_in_delta(new_centers.first.center[1],1.0,0.01)
@@ -76,32 +82,35 @@ WORKING=<<-'EOS'
 
   def test_choose_centers_wrapper
       elements = [[1,1]]
-      new_centers = Buncher::choose_centers(elements, 1)
+      new_centers = Buncher::choose_centers(elements,[1]*2, 1)
       dump(new_centers)
       assert_in_delta(new_centers.first.center[1],1.0,0.01)
       assert_in_delta(new_centers.first.center[1],1.0,0.01)
   end
   def test_choose_centers_wrapper2
       elements = init_data(100,3)
-      new_centers = Buncher::choose_centers(elements, 3)
+      new_centers = Buncher::choose_centers(elements, [1]*2, 3)
       dump(new_centers)
       assert_equal(new_centers.size,3)
   end
+  # EOS
   def test_should_find_one_cluster
       elements = [[1,1]]
-      new_centers = Buncher::cluster(elements)
+      new_centers = Buncher::cluster(elements,[1]*2)
       dump(new_centers)
       assert_equal(new_centers.size,1)
   end
+
+  # WWW=<<-'EOS'
+
   def test_choose_centers_wrapper2
       elements = init_data(100,3)
-      new_centers = Buncher::choose_centers(elements, 3)
+      new_centers = Buncher::choose_centers(elements, [1]*2, 3)
       plot("/tmp/kmeans_initial_#{new_centers.size}.png",elements, new_centers)
       dump(new_centers)
       `open /tmp/kmeans_initial_#{new_centers.size}.png`
       assert_equal(new_centers.size,3)
   end
-EOS
 
   def test_gaussian_distribution_of_100_points_in_3_clusters
     12.times do |run|
@@ -109,7 +118,7 @@ EOS
       elements = init_data(100,3)
       # elements.each {|eee| puts "#{eee[0]},#{eee[1]}"}
       # new_centers = Buncher::cluster(elements) {|elements,centers, initial_centers| puts "run #{run} setup";plot("/tmp/#{run}_centers_#{centers.size}.png",elements,initial_centers)}
-      new_centers = Buncher::cluster(elements) {|elements,centers, initial_centers| 
+      new_centers = Buncher::cluster(elements,[1]*2) {|elements,centers, initial_centers| 
         plot("/tmp/#{run}_centers_#{centers.size}.png",elements,centers, initial_centers)
       }
       puts "run #{run}: k is #{new_centers.size}, seed was #{srand}"
@@ -118,4 +127,5 @@ EOS
       assert_equal(3,new_centers.size)
     end
   end
+  # EOS
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: buncher
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-24 00:00:00.000000000 Z
+date: 2015-04-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: minitest