wilson_score 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +64 -0
- data/Rakefile +9 -0
- data/lib/wilson_score/version.rb +3 -0
- data/lib/wilson_score.rb +59 -0
- data/test/test_helper.rb +4 -0
- data/test/wilson_score_test.rb +29 -0
- data/wilson_score.gemspec +24 -0
- metadata +98 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7a66381f037f35b8c6af86cd5c654f243378f620
|
4
|
+
data.tar.gz: 8d56f3a99766730ee9baecbb0c63b39be703fd0b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 50d652c3613f6bba4dd2c685ad8c60943eb8d974276be0cee64c6fb2fab9aee514efb6b64471d9d862d527853d7d6f3cfdcc61a99aa84b376e654e3c5c6fc20f
|
7
|
+
data.tar.gz: 1734379e9da77cef40f164ba86525f98f35c991f0c3ff954e93ec82b459865a42eb5384b92289e7d8db56e618e3e6d974560f7952515f51cc29cfa0567d07199
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Andrew Kane
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
# Wilson Score
|
2
|
+
|
3
|
+
Simple, dependency-free [Wilson score](http://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval)
|
4
|
+
|
5
|
+
Inspired by [How Not To Sort By Average Rating](http://www.evanmiller.org/how-not-to-sort-by-average-rating.html) by Evan Miller
|
6
|
+
|
7
|
+
## How to Use
|
8
|
+
|
9
|
+
3 positive ratings out of 5 with 95% confidence
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
WilsonScore.interval(3, 5, 0.95)
|
13
|
+
```
|
14
|
+
|
15
|
+
[Continuity correction](http://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval_with_continuity_correction) can improve the score, especially for a small number of samples (n < 30). Set the last paramter to true to use it.
|
16
|
+
|
17
|
+
```ruby
|
18
|
+
WilsonScore.interval(3, 5, 0.95, true)
|
19
|
+
```
|
20
|
+
|
21
|
+
## Star Ratings
|
22
|
+
|
23
|
+
Imagine you have a rating system with 1 to 5 stars.
|
24
|
+
|
25
|
+
There are two ratings, a 4 star and a 5 star.
|
26
|
+
|
27
|
+
```ruby
|
28
|
+
average_rating = 4.5
|
29
|
+
total_ratings = 2
|
30
|
+
rating_range = 1..5 # 1 to 5 stars
|
31
|
+
confidence = 0.95 # 95%
|
32
|
+
|
33
|
+
WilsonScore.rating_interval(average_rating, total_ratings, rating_range, confidence)
|
34
|
+
```
|
35
|
+
|
36
|
+
Again, you can set the last parameter to `true` for continuity correction.
|
37
|
+
|
38
|
+
## Installation
|
39
|
+
|
40
|
+
Add this line to your application's Gemfile:
|
41
|
+
|
42
|
+
```ruby
|
43
|
+
gem 'wilson_score'
|
44
|
+
```
|
45
|
+
|
46
|
+
And then execute:
|
47
|
+
|
48
|
+
```sh
|
49
|
+
bundle
|
50
|
+
```
|
51
|
+
|
52
|
+
## Additional Resources
|
53
|
+
|
54
|
+
- http://www.vassarstats.net/prop1.html
|
55
|
+
- http://www.goproblems.com/test/wilson/wilson.php
|
56
|
+
|
57
|
+
## Contributing
|
58
|
+
|
59
|
+
Everyone is encouraged to help improve this project. Here are a few ways you can help:
|
60
|
+
|
61
|
+
- [Report bugs](https://github.com/instacart/wilson_score/issues)
|
62
|
+
- Fix bugs and [submit pull requests](https://github.com/instacart/wilson_score/pulls)
|
63
|
+
- Write, clarify, or fix documentation
|
64
|
+
- Suggest or add new features
|
data/Rakefile
ADDED
data/lib/wilson_score.rb
ADDED
@@ -0,0 +1,59 @@
|
|
1
|
+
require "wilson_score/version"
|
2
|
+
|
3
|
+
module WilsonScore
|
4
|
+
|
5
|
+
# http://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval
|
6
|
+
def self.interval(k, n, confidence, correction = false)
|
7
|
+
z = pnorm(1 - (1 - confidence) / 2)
|
8
|
+
phat = k / n.to_f
|
9
|
+
if correction # continuity correction
|
10
|
+
a = 1.0 / (2 * (n + z**2))
|
11
|
+
b = 2*n*phat + z**2
|
12
|
+
c = z * Math.sqrt(z**2 - 1.0/n + 4*n*phat*(1 - phat) + (4*phat - 2)) + 1
|
13
|
+
([0, a * (b - c)].max)..([1, a * (b + c)].min)
|
14
|
+
else
|
15
|
+
a = 1.0 / (1 + z ** 2 / n)
|
16
|
+
b = phat + z ** 2 / (2 * n)
|
17
|
+
c = z * Math.sqrt((phat * (1 - phat) + z ** 2 / (4 * n)) / n)
|
18
|
+
(a * (b - c))..(a * (b + c))
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.rating_interval(avg, n, score_range, confidence, correction = false)
|
23
|
+
min = score_range.first
|
24
|
+
max = score_range.last
|
25
|
+
range = max - min
|
26
|
+
interval = interval(n * (avg - min) / range, n, confidence, correction)
|
27
|
+
(min + range * interval.first)..(min + range * interval.last)
|
28
|
+
end
|
29
|
+
|
30
|
+
protected
|
31
|
+
|
32
|
+
# from the statistics2 gem
|
33
|
+
# https://github.com/abscondment/statistics2/blob/master/lib/statistics2/base.rb
|
34
|
+
# inverse of normal distribution ([2])
|
35
|
+
# Pr( (-\infty, x] ) = qn -> x
|
36
|
+
def self.pnorm(qn)
|
37
|
+
b = [1.570796288, 0.03706987906, -0.8364353589e-3,
|
38
|
+
-0.2250947176e-3, 0.6841218299e-5, 0.5824238515e-5,
|
39
|
+
-0.104527497e-5, 0.8360937017e-7, -0.3231081277e-8,
|
40
|
+
0.3657763036e-10, 0.6936233982e-12]
|
41
|
+
|
42
|
+
if(qn < 0.0 || 1.0 < qn)
|
43
|
+
$stderr.printf("Error : qn <= 0 or qn >= 1 in pnorm()!\n")
|
44
|
+
return 0.0;
|
45
|
+
end
|
46
|
+
qn == 0.5 and return 0.0
|
47
|
+
|
48
|
+
w1 = qn
|
49
|
+
qn > 0.5 and w1 = 1.0 - w1
|
50
|
+
w3 = -Math.log(4.0 * w1 * (1.0 - w1))
|
51
|
+
w1 = b[0]
|
52
|
+
1.upto 10 do |i|
|
53
|
+
w1 += b[i] * w3**i;
|
54
|
+
end
|
55
|
+
qn > 0.5 and return Math.sqrt(w1 * w3)
|
56
|
+
-Math.sqrt(w1 * w3)
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
data/test/test_helper.rb
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
require_relative "test_helper"
|
2
|
+
|
3
|
+
class TestWilsonScore < Minitest::Test
|
4
|
+
|
5
|
+
def test_wilson_score
|
6
|
+
interval = WilsonScore.interval(1, 2, 0.95)
|
7
|
+
assert_in_delta 0.0945, interval.first
|
8
|
+
assert_in_delta 0.9055, interval.last
|
9
|
+
end
|
10
|
+
|
11
|
+
def test_continuity_correction
|
12
|
+
interval = WilsonScore.interval(1, 2, 0.95, true)
|
13
|
+
assert_in_delta 0.0267, interval.first
|
14
|
+
assert_in_delta 0.9733, interval.last
|
15
|
+
end
|
16
|
+
|
17
|
+
def test_rating
|
18
|
+
interval = WilsonScore.rating_interval(5, 1, 1..5, 0.95)
|
19
|
+
assert_in_delta 1.8262, interval.first
|
20
|
+
assert_in_delta 5, interval.last
|
21
|
+
end
|
22
|
+
|
23
|
+
def test_rating_advanced
|
24
|
+
interval = WilsonScore.rating_interval(3.7, 10, 1..5, 0.95)
|
25
|
+
assert_in_delta 2.4998, interval.first
|
26
|
+
assert_in_delta 4.5117, interval.last
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'wilson_score/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "wilson_score"
|
8
|
+
spec.version = WilsonScore::VERSION
|
9
|
+
spec.authors = ["Andrew Kane"]
|
10
|
+
spec.email = ["andrew@chartkick.com"]
|
11
|
+
spec.description = %q{Simple, dependency-free Wilson score}
|
12
|
+
spec.summary = %q{Simple, dependency-free Wilson score}
|
13
|
+
spec.homepage = "https://github.com/instacart/wilson_score"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "minitest"
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,98 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: wilson_score
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Andrew Kane
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-09-28 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: minitest
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description: Simple, dependency-free Wilson score
|
56
|
+
email:
|
57
|
+
- andrew@chartkick.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- .gitignore
|
63
|
+
- Gemfile
|
64
|
+
- LICENSE.txt
|
65
|
+
- README.md
|
66
|
+
- Rakefile
|
67
|
+
- lib/wilson_score.rb
|
68
|
+
- lib/wilson_score/version.rb
|
69
|
+
- test/test_helper.rb
|
70
|
+
- test/wilson_score_test.rb
|
71
|
+
- wilson_score.gemspec
|
72
|
+
homepage: https://github.com/instacart/wilson_score
|
73
|
+
licenses:
|
74
|
+
- MIT
|
75
|
+
metadata: {}
|
76
|
+
post_install_message:
|
77
|
+
rdoc_options: []
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - '>='
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
requirements: []
|
91
|
+
rubyforge_project:
|
92
|
+
rubygems_version: 2.0.0
|
93
|
+
signing_key:
|
94
|
+
specification_version: 4
|
95
|
+
summary: Simple, dependency-free Wilson score
|
96
|
+
test_files:
|
97
|
+
- test/test_helper.rb
|
98
|
+
- test/wilson_score_test.rb
|