buncher 1.0.3 → 1.0.4

data/lib/buncher.rb

@@ -1,6 +1,6 @@
 require 'buncher/buncher'
 module Buncher
-  VERSION = "1.0.3"
+  VERSION = "1.0.4"
   # 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
@@ -58,7 +58,7 @@ module Buncher
     end
   end
 
-  # run the clustering algorithm until have calculated the current number of clusters, taken from this paper:
+  # run the clustering algorithm until we have calculated the best number of clusters, taken from this paper:
   # http://papers.nips.cc/paper/2526-learning-the-k-in-k-means.pdf
   def self.cluster(elements, weights,options={})
     solutions={}
@@ -76,11 +76,11 @@ module Buncher
       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} "
       solutions[last_fK]=centers if number_clusters >= min_size
-      # break if number_clusters == 2 ## debugging
+      # break if number_clusters == 3 ## debugging
     end
     min_fK =solutions.keys.sort.first || 1.0
     if min_fK > 0.85
-      nil # ie, not clustered at all
+      elements.map {|ele| Cluster.new(ele,[ele])} # ie, not clustered at all
     else
       solutions[min_fK]
     end

data/test/test_buncher.rb

@@ -1,10 +1,11 @@
 require "buncher"
 require 'rubystats'
 require 'gnuplot'
+require "minitest/focus"
 
 def dump(centers)
-  puts "centers are"
-  centers.each {|ccc| puts "center #{ccc.center.inspect} #{ccc.elements[0]}, #{ccc.elements[1]}"}
+  puts "#{centers.size} centers are"
+  centers.each {|ccc| puts "center #{ccc.center.inspect} elements #{ccc.elements[0]}, #{ccc.elements[1]}"}
 end
 
 def init_data(number_points, number_clusters)
@@ -64,13 +65,19 @@ def plot(file_name,points,centers, initial_centers=nil)
 end
 
 class TestBuncher < Minitest::Test
-   # 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_distance_nan
+    element1 = [nil, 1, 1]
+    element2 = [nil, nil, 1]
+    weights = [1] * 3
+    assert_in_delta(Buncher::distance(element1,element2, weights),0.5,0.01)
+  end
   def test_should_find_the_one_center
       elements = [[1,1]]
       starting_centers = elements.sample(1).map {|aaa| Buncher::Cluster.new(aaa)}
@@ -80,9 +87,13 @@ class TestBuncher < Minitest::Test
       assert_in_delta(new_centers.first.center[1],1.0,0.01)
   end
 
+    
   def test_choose_centers_wrapper
       elements = [[1,1]]
+      puts "test_choose_centers_wrapper - start"
       new_centers = Buncher::choose_centers(elements,[1]*2, 1)
+      puts "test_choose_centers_wrapper - well well"
+      puts new_centers.inspect
       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)
@@ -91,41 +102,34 @@ class TestBuncher < Minitest::Test
       elements = init_data(100,3)
       new_centers = Buncher::choose_centers(elements, [1]*2, 3)
       dump(new_centers)
-      assert_equal(new_centers.size,3)
+      assert_equal(3, new_centers.size)
   end
-  # EOS
+  
+  
   def test_min_size_works
-      elements =  init_data(100,4)
+      elements =  init_data(100,1)
       new_centers = Buncher::cluster(elements,[1]*2,:min_size=>2)
-      dump(new_centers)
-      assert_equal(new_centers.size,4)
-  end
-
-  # WWW=<<-'EOS'
-
-  def test_choose_centers_wrapper2
-      elements = init_data(100,3)
-      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)
+      assert(new_centers.size >=2,"at least 2 centers")
   end
-
+  focus
   def test_gaussian_distribution_of_100_points_in_3_clusters
-    12.times do |run|
+    1.times do |run|
       # srand(843284148793854177950180651080082381)
       elements = init_data(100,3)
       # elements.each {|eee| puts "#{eee[0]},#{eee[1]}"}
+      graphfile=nil;
       # 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,[1]*2) {|elements,centers, initial_centers| 
-        plot("/tmp/#{run}_centers_#{centers.size}.png",elements,centers, initial_centers)
+        graphfile = "/tmp/#{run}_centers_#{centers.size}.png"
+        plot(graphfile,elements,centers, initial_centers)
       }
       puts "run #{run}: k is #{new_centers.size}, seed was #{srand}"
       puts "ERROR "*4 if new_centers.size != 3
       puts
       assert_equal(3,new_centers.size)
+      refute(new_centers.first.elements.empty?)
+      graphfile = "/tmp/#{run}_centers_3.png"
+      `open #{graphfile}`
     end
   end
-  # EOS
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: buncher
 version: !ruby/object:Gem::Version
-  version: 1.0.3
+  version: 1.0.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-25 00:00:00.000000000 Z
+date: 2015-04-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: minitest