kmeans 0.1.0 → 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4fbc7ab793536851044ea1626026c48614b3021d
+  data.tar.gz: e701c25efe30f3572cd36393bd5f5e376291ace4
+SHA512:
+  metadata.gz: f318ee63dce722aa3ca763eedf1ae4268d1575e9f0a7bb3c9df28df34beac941cbf49cd4dffc43253cab7cfb1dfb9a904ef67ee49504c9168faa949d83e8c7e9
+  data.tar.gz: ac3a2c27e106f41928808fc9c2074c6ed4a5e2a5a5245cba24c3611106d6c81dab04242ba552aeff93e995d36859382443c259f4f87b7fffef1c1636b7d76420

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.1.1

data/doc/ChangeLog

@@ -1,3 +1,8 @@
+=== 0.1.1 / 2013-09-30
+
+* Correspond to empty hash.
+
+
 === 0.1.0 / 2013-07-09
 
 * Append tutorial, demo script.

data/kmeans.gemspec

@@ -2,14 +2,15 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
+# stub: kmeans 0.1.1 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "kmeans"
-  s.version = "0.1.0"
+  s.version = "0.1.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["id774"]
-  s.date = "2013-07-09"
+  s.date = "2013-09-30"
   s.description = "K-means clustering"
   s.email = "idnanashi@gmail.com"
   s.extra_rdoc_files = [
@@ -48,11 +49,11 @@ Gem::Specification.new do |s|
   s.homepage = "http://github.com/id774/kmeans"
   s.licenses = ["GPL"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.24"
+  s.rubygems_version = "2.1.3"
   s.summary = "kmeans"
 
   if s.respond_to? :specification_version then
-    s.specification_version = 3
+    s.specification_version = 4
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_development_dependency(%q<cucumber>, [">= 0"])

data/lib/kmeans.rb

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 module Kmeans
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
   require File.dirname(__FILE__) +  "/kmeans/pair"
   require File.dirname(__FILE__) +  "/kmeans/pearson"
   require File.dirname(__FILE__) +  "/kmeans/cluster"

data/lib/kmeans/cluster.rb

@@ -23,9 +23,8 @@ module Kmeans
       old_centroids = nil
       until (@centroids == old_centroids) or (@options[:loop_max] < loop_counter)
         loop_counter += 1
-        attach_urls_to_nearest_centroid
+        attach_keys_to_nearest_centroid
         old_centroids = Marshal.load(Marshal.dump(@centroids))
-
         @centroids.each_key {|centroid|
           @centroids[centroid] = average_attached(centroid) if @cluster[centroid].any?
         }
@@ -33,11 +32,12 @@ module Kmeans
     end
 
     private
+
     def min_and_max_in_word_counts
       all_counts = Hash.new {|hash, key| hash[key] = []}
       min_and_max = {}
 
-      @word_counts.each {|url, counts|
+      @word_counts.each {|key, counts|
         counts.each {|word, count|
           all_counts[word] << count.to_i
         }
@@ -46,7 +46,8 @@ module Kmeans
       all_counts.each {|word, counts|
         min_and_max[word] = Pair.new [counts.min, counts.max]
       }
-      min_and_max
+
+      return min_and_max
     end
 
     def random_centroids
@@ -59,42 +60,45 @@ module Kmeans
         }
         centroids[centroid] = random_counts
       }
-      centroids
+
+      return centroids
     end
 
-    def attach_urls_to_nearest_centroid
+    def attach_keys_to_nearest_centroid
       @cluster.clear
 
-      @word_counts.each_key {|url|
-        @cluster[nearest_centroid(url)] << url
+      @word_counts.each_key {|key|
+        @cluster[nearest_centroid(key)] << key
       }
     end
 
-    def nearest_centroid(url)
+    def nearest_centroid(key)
       correlations = @centroids.map {|centroid, centroid_word_count|
-        web_counts = []
+        all_counts = []
         centroid_counts = []
 
-        @word_counts[url].each {|word, count|
+        @word_counts[key].each {|word, count|
           count = 0 unless count.class == Fixnum
-          web_counts << count
+          all_counts << count
           centroid_counts << centroid_word_count[word]
         }
-        1 - Pearson.calc(web_counts, centroid_counts)
+        centroid_counts.empty? ? 0 : 1 - Pearson.calc(all_counts, centroid_counts)
       }
-      correlations.rindex(correlations.min {|x, y| x.abs <=> y.abs })
+
+      return correlations.rindex(correlations.min {|x, y| x.abs <=> y.abs })
     end
 
     def average_attached(centroid)
-      average_word_counts = @cluster[centroid].map {|url|
-        @centroids[centroid].keys.map {|word| @word_counts[url][word]}
+      average_word_counts = @cluster[centroid].map {|key|
+        @centroids[centroid].keys.map {|word| @word_counts[key][word]}
       }.transpose.map {|all_counts|
         all_counts.inject(0) {|sum, count|
           count = 0 unless count.class == Fixnum
           sum + count
         }.quo(all_counts.size)
       }
-      Hash[*@centroids[centroid].keys.zip(average_word_counts).flatten]
+
+      return Hash[*@centroids[centroid].keys.zip(average_word_counts).flatten]
     end
   end
 end

data/lib/kmeans/dendrogram.rb

@@ -34,6 +34,8 @@ module Kmeans
       img.write(@options[:imagefile])
     end
 
+    private
+
     def drawnode(draw, clust, x, y, scaling, labels)
       if clust.id < 0
         h1 = getheight(clust.left) * 20

data/lib/kmeans/hcluster.rb

@@ -33,6 +33,7 @@ module Kmeans
       end
       printclust(clust.left, labels, n+1) if clust.left != nil
       printclust(clust.right, labels, n+1) if clust.right != nil
+
       return @out
     end
 
@@ -76,6 +77,7 @@ module Kmeans
         clust.delete_at(lowestpair[0])
         clust.push(newcluster)
       end
+
       return clust[0]
     end
   end

data/spec/lib/kmeans/cluster_spec.rb

@@ -135,6 +135,41 @@ describe Kmeans::Cluster do
          nil=>"1"
         },
       }
+
+    @empty_hash = {
+      "test01"=>
+        {"hoge"=>0,
+         "fuga"=>1,
+         "piyo"=>0
+        },
+      "test02"=>
+        {"hoge"=>2,
+         "fuga"=>1,
+         "piyo"=>3
+        },
+      "test03"=>
+        {"hoge"=>3,
+         "fuga"=>0,
+         "poyo"=>1
+        },
+      "test04"=>
+        {"puyo"=>0,
+         "fuga"=>2,
+         "piyo"=>0
+        },
+      "test05"=>
+        {"hoge"=>4,
+         "fuga"=>2,
+         "poyo"=>3
+        },
+      "test06"=>
+        {},
+      "test07"=>
+        {},
+      "test08"=>
+        {}
+      }
+
   end
 
   context 'の Cluster クラスにおいて' do
@@ -217,5 +252,25 @@ describe Kmeans::Cluster do
         result.cluster.values.class.should be_equal Array
       end
     end
+
+    describe '空のハッシュを含む不均一な二次元ハッシュを渡しても' do
+      it "Kmeans::Cluster クラスが返却される" do
+        result = Kmeans::Cluster.new(@empty_hash, {
+          :centroids => 5,
+          :loop_max => 10
+          })
+        result.class.should be_equal Kmeans::Cluster
+      end
+
+      it "ハッシュの配列が返却される (結果は実行ごとに異なる)" do
+        result = Kmeans::Cluster.new(@empty_hash, {
+          :centroids => 5,
+          :loop_max => 10
+          })
+        result.make_cluster
+        result.cluster.class.should be_equal Hash
+        result.cluster.values.class.should be_equal Array
+      end
+    end
   end
 end

data/spec/lib/kmeans/pair_spec.rb

@@ -10,8 +10,8 @@ describe Kmeans::Pair do
         max = 4
         expect = [0, 4]
         result = Kmeans::Pair.new([min, max])
-        result[0].should == expect[0]
-        result[1].should == expect[1]
+        result[0].should eql expect[0]
+        result[1].should eql expect[1]
       end
 
       it "ペアが返却される" do
@@ -19,8 +19,8 @@ describe Kmeans::Pair do
         max = 3
         expect = [1, 3]
         result = Kmeans::Pair.new([min, max])
-        result[0].should == expect[0]
-        result[1].should == expect[1]
+        result[0].should eql expect[0]
+        result[1].should eql expect[1]
       end
     end
 
@@ -31,8 +31,8 @@ describe Kmeans::Pair do
         unexpected = 6
         expect = [2, 4]
         result = Kmeans::Pair.new([min, max, unexpected])
-        result[0].should == expect[0]
-        result[1].should == expect[1]
+        result[0].should eql expect[0]
+        result[1].should eql expect[1]
       end
     end
 
@@ -42,8 +42,8 @@ describe Kmeans::Pair do
         max = 5
         expect = [5, 5]
         result = Kmeans::Pair.new([min, max])
-        result[0].should == expect[0]
-        result[1].should == expect[1]
+        result[0].should eql expect[0]
+        result[1].should eql expect[1]
       end
     end
   end

data/spec/lib/kmeans/pearson_spec.rb

@@ -6,259 +6,259 @@ describe Kmeans::Pearson do
   context 'の Pearson クラスにおいて' do
     describe '相関係数 0.0 となる集合を渡す場合' do
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [4,2,3]
         v2 = [0,0,1]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [0, 2, 0]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [0, 2, 0]
         v2 = [(3/2), (1/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [4, 2, 3]
         v2 = [(3/2), (3/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [2, 1, 3]
         v2 = [(10/3), (1/1), (5/3)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [0, 1, 0]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [0, 1, 0]
         v2 = [(10/3), (1/1), (5/3)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.0
+        expected = 0.0
         v1 = [0, 2, 0]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
     end
 
     describe '相関係数が正となる集合を渡す場合' do
       it "ピアソン相関係数が返却される" do
-        expect = 0.31622776601683794
+        expected = 0.31622776601683794
         v1 = [3, 0, 1]
         v2 = [(2/1), (1/1), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.4472135954999579
+        expected = 0.4472135954999579
         v1 = [3, 0, 1]
         v2 = [(3/2), (3/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.8944271909999159
+        expected = 0.8944271909999159
         v1 = [3, 0, 1]
         v2 = [(3/2), (1/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.5773502691896258
+        expected = 0.5773502691896258
         v1 = [0, 2, 0]
         v2 = [(3/2), (3/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.8164965809277261
+        expected = 0.8164965809277261
         v1 = [4, 2, 3]
         v2 = [(3/1), (3/2), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.5
+        expected = 0.5
         v1 = [4, 2, 3]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.7071067811865475
+        expected = 0.7071067811865475
         v1 = [4, 2, 3]
         v2 = [(3/2), (1/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.6666666666666666
+        expected = 0.6666666666666666
         v1 = [3, 1, 1]
         v2 = [(3/1), (3/2), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.8164965809277261
+        expected = 0.8164965809277261
         v1 = [3, 1, 1]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.5773502691896258
+        expected = 0.5773502691896258
         v1 = [3, 1, 1]
         v2 = [(3/2), (3/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.31622776601683794
+        expected = 0.31622776601683794
         v1 = [3, 0, 1]
         v2 = [(2/1), (1/1), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 0.6324555320336759
+        expected = 0.6324555320336759
         v1 = [3, 0, 1]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
     end
 
     describe '相関係数が負となる集合を渡す場合' do
       it "ピアソン相関係数が返却される" do
-        expect = -0.6666666666666666
+        expected = -0.6666666666666666
         v1 = [0, 2, 0]
         v2 = [(3/1), (3/2), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = -0.4472135954999579
+        expected = -0.4472135954999579
         v1 = [3, 0, 1]
         v2 = [(0/1), (3/2), (0/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = -0.8164965809277261
+        expected = -0.8164965809277261
         v1 = [0, 2, 0]
         v2 = [(2/1), (1/1), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = -0.7071067811865475
+        expected = -0.7071067811865475
         v1 = [0, 1, 0]
         v2 = [(2/1), (1/1), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = -0.5
+        expected = -0.5
         v1 = [2, 1, 3]
         v2 = [2, 1, 0]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = -0.7071067811865475
+        expected = -0.7071067811865475
         v1 = [2, 1, 3]
         v2 = [(0/1), (3/2), (0/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
     end
 
     describe '相関係数が 1.0 の場合' do
       it "ピアソン相関係数が返却される" do
-        expect = 1.0
+        expected = 1.0
         v1 = [0, 1, 0]
         v2 = [(0/1), (3/2), (0/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 1.0
+        expected = 1.0
         v1 = [2, 1, 3]
         v2 = [(2/1), (1/1), (3/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
     end
 
     describe '相関係数が 1 を越える場合' do
       it "ピアソン相関係数が返却される" do
-        expect = 1.0327955589886444
+        expected = 1.0327955589886444
         v1 = [3, 0, 1]
         v2 = [(10/3), (1/1), (5/3)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 1.1547005383792517
+        expected = 1.1547005383792517
         v1 = [0, 2, 0]
         v2 = [(0/1), (3/2), (0/1)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
 
       it "ピアソン相関係数が返却される" do
-        expect = 1.1547005383792517
+        expected = 1.1547005383792517
         v1 = [3, 1, 1]
         v2 = [(3/2), (1/2), (1/2)]
         result = Kmeans::Pearson.calc(v1,v2)
-        result.should == expect
+        result.should eql expected
       end
     end
   end

data/spec/lib/kmeans_spec.rb

@@ -5,7 +5,7 @@ require File.dirname(__FILE__) + '/../spec_helper'
 describe Kmeans do
   context 'のバージョンを参照した場合' do
     it "バージョンが正しく表示される" do
-      expect = '0.1.0'
+      expect = '0.1.1'
       Kmeans.const_get(:VERSION).should be_true
       Kmeans.const_get(:VERSION).should == expect
     end

metadata

@@ -1,62 +1,55 @@
 --- !ruby/object:Gem::Specification
 name: kmeans
 version: !ruby/object:Gem::Version
-  version: 0.1.0
-  prerelease: 
+  version: 0.1.1
 platform: ruby
 authors:
 - id774
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-09 00:00:00.000000000 Z
+date: 2013-09-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cucumber
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: jeweler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 description: K-means clustering
@@ -97,26 +90,25 @@ files:
 homepage: http://github.com/id774/kmeans
 licenses:
 - GPL
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.1.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: kmeans
 test_files: []