hyperloglog 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +1 -0
- data/Manifest +14 -0
- data/README.md +21 -0
- data/Rakefile +18 -0
- data/ext/boolarray.h +179 -0
- data/ext/ewah.h +1763 -0
- data/ext/extconf.rb +7 -0
- data/ext/hyperloglog.cpp +263 -0
- data/ext/murmur3.h +104 -0
- data/hyperloglog.gemspec +30 -0
- data/spec/data/integers.txt +62382 -0
- data/spec/data/small_integers.txt +1000 -0
- data/spec/data/small_integers2.txt +1000 -0
- data/spec/hyperloglog_spec.rb +48 -0
- data/spec/spec.opts +2 -0
- metadata +92 -0
@@ -0,0 +1,48 @@
|
|
1
|
+
require 'lib/hyperloglog'
|
2
|
+
|
3
|
+
def load_data(name)
|
4
|
+
File.readlines(File.join(File.dirname(__FILE__), 'data', "#{name}.txt"))
|
5
|
+
end
|
6
|
+
|
7
|
+
describe 'A HyperBuilder' do
|
8
|
+
before(:each) do
|
9
|
+
@builder = HyperBuilder.new(11)
|
10
|
+
0.upto(9) {|index| @builder.offer(index.to_s)}
|
11
|
+
end
|
12
|
+
|
13
|
+
it 'should put to_s' do
|
14
|
+
@builder.to_s.should_not == nil
|
15
|
+
end
|
16
|
+
|
17
|
+
it 'should serialize' do
|
18
|
+
@builder.serialize.should_not == nil
|
19
|
+
end
|
20
|
+
|
21
|
+
it 'should generate an estimator' do
|
22
|
+
@builder.estimator.should_not == nil
|
23
|
+
end
|
24
|
+
|
25
|
+
it 'should create the proper estimator' do
|
26
|
+
@builder.to_s.should == @builder.estimator.to_s
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
describe 'A HyperEstimator' do
|
31
|
+
it 'should generate good estimates' do
|
32
|
+
items = load_data('small_integers')
|
33
|
+
total_items = items.uniq.length
|
34
|
+
|
35
|
+
4.upto(20) do |m|
|
36
|
+
se = total_items * (1.04 / Math.sqrt(2**m))
|
37
|
+
|
38
|
+
builder = HyperBuilder.new(m)
|
39
|
+
items.each{|item| builder.offer(item.to_s)}
|
40
|
+
|
41
|
+
estimate = HyperEstimator.estimate(builder.estimator)
|
42
|
+
|
43
|
+
# puts "For m = #{m} we should have #{estimate} in [#{total_items - (3 * se)}, #{total_items + (3 * se)}]"
|
44
|
+
estimate.should be >= total_items - (3 * se)
|
45
|
+
estimate.should be <= total_items + (3 * se)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
data/spec/spec.opts
ADDED
metadata
ADDED
@@ -0,0 +1,92 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: hyperloglog
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 29
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 1
|
10
|
+
version: 0.0.1
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Josh Ferguson
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2012-04-24 00:00:00 Z
|
19
|
+
dependencies: []
|
20
|
+
|
21
|
+
description: An efficient implementation of the HyperLogLog cardinality estimator
|
22
|
+
email: josh@besquared.net
|
23
|
+
executables: []
|
24
|
+
|
25
|
+
extensions:
|
26
|
+
- ext/extconf.rb
|
27
|
+
extra_rdoc_files:
|
28
|
+
- CHANGELOG
|
29
|
+
- README.md
|
30
|
+
- ext/boolarray.h
|
31
|
+
- ext/ewah.h
|
32
|
+
- ext/extconf.rb
|
33
|
+
- ext/hyperloglog.cpp
|
34
|
+
- ext/murmur3.h
|
35
|
+
files:
|
36
|
+
- CHANGELOG
|
37
|
+
- Manifest
|
38
|
+
- README.md
|
39
|
+
- Rakefile
|
40
|
+
- ext/boolarray.h
|
41
|
+
- ext/ewah.h
|
42
|
+
- ext/extconf.rb
|
43
|
+
- ext/hyperloglog.cpp
|
44
|
+
- ext/murmur3.h
|
45
|
+
- spec/data/integers.txt
|
46
|
+
- spec/data/small_integers.txt
|
47
|
+
- spec/data/small_integers2.txt
|
48
|
+
- spec/hyperloglog_spec.rb
|
49
|
+
- spec/spec.opts
|
50
|
+
- hyperloglog.gemspec
|
51
|
+
homepage: http://www.github.com/besquared/hyperloglog/
|
52
|
+
licenses: []
|
53
|
+
|
54
|
+
post_install_message:
|
55
|
+
rdoc_options:
|
56
|
+
- --line-numbers
|
57
|
+
- --inline-source
|
58
|
+
- --title
|
59
|
+
- Hyperloglog
|
60
|
+
- --main
|
61
|
+
- README.md
|
62
|
+
require_paths:
|
63
|
+
- lib
|
64
|
+
- ext
|
65
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
66
|
+
none: false
|
67
|
+
requirements:
|
68
|
+
- - ">="
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
hash: 3
|
71
|
+
segments:
|
72
|
+
- 0
|
73
|
+
version: "0"
|
74
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
75
|
+
none: false
|
76
|
+
requirements:
|
77
|
+
- - ">="
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
hash: 11
|
80
|
+
segments:
|
81
|
+
- 1
|
82
|
+
- 2
|
83
|
+
version: "1.2"
|
84
|
+
requirements: []
|
85
|
+
|
86
|
+
rubyforge_project: hyperloglog
|
87
|
+
rubygems_version: 1.8.15
|
88
|
+
signing_key:
|
89
|
+
specification_version: 3
|
90
|
+
summary: An efficient implementation of the HyperLogLog cardinality estimator
|
91
|
+
test_files: []
|
92
|
+
|