hyperloglog 0.0.1

data/spec/hyperloglog_spec.rb

@@ -0,0 +1,48 @@
+require 'lib/hyperloglog'
+
+def load_data(name)
+  File.readlines(File.join(File.dirname(__FILE__), 'data', "#{name}.txt"))
+end
+
+describe 'A HyperBuilder' do
+  before(:each) do
+    @builder = HyperBuilder.new(11)
+    0.upto(9) {|index| @builder.offer(index.to_s)}
+  end
+  
+  it 'should put to_s' do
+    @builder.to_s.should_not == nil
+  end
+  
+  it 'should serialize' do
+    @builder.serialize.should_not == nil
+  end
+  
+  it 'should generate an estimator' do
+    @builder.estimator.should_not == nil
+  end
+  
+  it 'should create the proper estimator' do
+    @builder.to_s.should == @builder.estimator.to_s
+  end
+end
+
+describe 'A HyperEstimator' do
+  it 'should generate good estimates' do
+    items = load_data('small_integers')
+    total_items = items.uniq.length
+    
+    4.upto(20) do |m|
+      se = total_items * (1.04 / Math.sqrt(2**m))
+      
+      builder = HyperBuilder.new(m)
+      items.each{|item| builder.offer(item.to_s)}
+      
+      estimate = HyperEstimator.estimate(builder.estimator)
+      
+      # puts "For m = #{m} we should have #{estimate} in [#{total_items - (3 * se)}, #{total_items + (3 * se)}]"
+      estimate.should be >= total_items - (3 * se)
+      estimate.should be <= total_items + (3 * se)
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--colour
+--format progress

metadata

@@ -0,0 +1,92 @@
+--- !ruby/object:Gem::Specification 
+name: hyperloglog
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Josh Ferguson
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-04-24 00:00:00 Z
+dependencies: []
+
+description: An efficient implementation of the HyperLogLog cardinality estimator
+email: josh@besquared.net
+executables: []
+
+extensions: 
+- ext/extconf.rb
+extra_rdoc_files: 
+- CHANGELOG
+- README.md
+- ext/boolarray.h
+- ext/ewah.h
+- ext/extconf.rb
+- ext/hyperloglog.cpp
+- ext/murmur3.h
+files: 
+- CHANGELOG
+- Manifest
+- README.md
+- Rakefile
+- ext/boolarray.h
+- ext/ewah.h
+- ext/extconf.rb
+- ext/hyperloglog.cpp
+- ext/murmur3.h
+- spec/data/integers.txt
+- spec/data/small_integers.txt
+- spec/data/small_integers2.txt
+- spec/hyperloglog_spec.rb
+- spec/spec.opts
+- hyperloglog.gemspec
+homepage: http://www.github.com/besquared/hyperloglog/
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --line-numbers
+- --inline-source
+- --title
+- Hyperloglog
+- --main
+- README.md
+require_paths: 
+- lib
+- ext
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 11
+      segments: 
+      - 1
+      - 2
+      version: "1.2"
+requirements: []
+
+rubyforge_project: hyperloglog
+rubygems_version: 1.8.15
+signing_key: 
+specification_version: 3
+summary: An efficient implementation of the HyperLogLog cardinality estimator
+test_files: []
+