benford 0.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.rspec +1 -0
- data/Gemfile +13 -0
- data/Gemfile.lock +28 -0
- data/LICENSE.txt +20 -0
- data/README.rdoc +5 -0
- data/Rakefile +49 -0
- data/VERSION +1 -0
- data/benford.gemspec +62 -0
- data/bin/benford +26 -0
- data/lib/benford.rb +63 -0
- data/spec/benford_spec.rb +65 -0
- data/spec/spec_helper.rb +12 -0
- metadata +139 -0
data/.document
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/Gemfile
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
source "http://rubygems.org"
|
2
|
+
# Add dependencies required to use your gem here.
|
3
|
+
# Example:
|
4
|
+
# gem "activesupport", ">= 2.3.5"
|
5
|
+
|
6
|
+
# Add dependencies to develop your gem here.
|
7
|
+
# Include everything needed to run rake, tests, features, etc.
|
8
|
+
group :development do
|
9
|
+
gem "rspec", "~> 2.3.0"
|
10
|
+
gem "bundler", "~> 1.0.0"
|
11
|
+
gem "jeweler", "~> 1.6.4"
|
12
|
+
gem "rcov", ">= 0"
|
13
|
+
end
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
GEM
|
2
|
+
remote: http://rubygems.org/
|
3
|
+
specs:
|
4
|
+
diff-lcs (1.1.3)
|
5
|
+
git (1.2.5)
|
6
|
+
jeweler (1.6.4)
|
7
|
+
bundler (~> 1.0)
|
8
|
+
git (>= 1.2.5)
|
9
|
+
rake
|
10
|
+
rake (0.9.2)
|
11
|
+
rcov (0.9.10)
|
12
|
+
rspec (2.3.0)
|
13
|
+
rspec-core (~> 2.3.0)
|
14
|
+
rspec-expectations (~> 2.3.0)
|
15
|
+
rspec-mocks (~> 2.3.0)
|
16
|
+
rspec-core (2.3.1)
|
17
|
+
rspec-expectations (2.3.0)
|
18
|
+
diff-lcs (~> 1.1.2)
|
19
|
+
rspec-mocks (2.3.0)
|
20
|
+
|
21
|
+
PLATFORMS
|
22
|
+
ruby
|
23
|
+
|
24
|
+
DEPENDENCIES
|
25
|
+
bundler (~> 1.0.0)
|
26
|
+
jeweler (~> 1.6.4)
|
27
|
+
rcov
|
28
|
+
rspec (~> 2.3.0)
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2011 Tijmen Brommet
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
data/Rakefile
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'rubygems'
|
4
|
+
require 'bundler'
|
5
|
+
begin
|
6
|
+
Bundler.setup(:default, :development)
|
7
|
+
rescue Bundler::BundlerError => e
|
8
|
+
$stderr.puts e.message
|
9
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
10
|
+
exit e.status_code
|
11
|
+
end
|
12
|
+
require 'rake'
|
13
|
+
|
14
|
+
require 'jeweler'
|
15
|
+
Jeweler::Tasks.new do |gem|
|
16
|
+
# gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
|
17
|
+
gem.name = "benford"
|
18
|
+
gem.homepage = "http://github.com/tijmenb/benford"
|
19
|
+
gem.license = "MIT"
|
20
|
+
gem.summary = %Q{Check the distribution if first digits in a dataset}
|
21
|
+
gem.description = %Q{Check if a dataset conforms to Benford's Law. More info: http://en.wikipedia.org/wiki/Benford's_law}
|
22
|
+
gem.email = "tijmen@gmail.com"
|
23
|
+
gem.authors = ["Tijmen Brommet"]
|
24
|
+
# dependencies defined in Gemfile
|
25
|
+
end
|
26
|
+
Jeweler::RubygemsDotOrgTasks.new
|
27
|
+
|
28
|
+
require 'rspec/core'
|
29
|
+
require 'rspec/core/rake_task'
|
30
|
+
RSpec::Core::RakeTask.new(:spec) do |spec|
|
31
|
+
spec.pattern = FileList['spec/**/*_spec.rb']
|
32
|
+
end
|
33
|
+
|
34
|
+
RSpec::Core::RakeTask.new(:rcov) do |spec|
|
35
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
36
|
+
spec.rcov = true
|
37
|
+
end
|
38
|
+
|
39
|
+
task :default => :spec
|
40
|
+
|
41
|
+
require 'rake/rdoctask'
|
42
|
+
Rake::RDocTask.new do |rdoc|
|
43
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
44
|
+
|
45
|
+
rdoc.rdoc_dir = 'rdoc'
|
46
|
+
rdoc.title = "benford #{version}"
|
47
|
+
rdoc.rdoc_files.include('README*')
|
48
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
49
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.0
|
data/benford.gemspec
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{benford}
|
8
|
+
s.version = "0.0.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = [%q{Tijmen Brommet}]
|
12
|
+
s.date = %q{2011-09-20}
|
13
|
+
s.description = %q{Check if a dataset conforms to Benford's Law. More info: http://en.wikipedia.org/wiki/Benford's_law}
|
14
|
+
s.email = %q{tijmen@gmail.com}
|
15
|
+
s.executables = [%q{benford}]
|
16
|
+
s.extra_rdoc_files = [
|
17
|
+
"LICENSE.txt",
|
18
|
+
"README.rdoc"
|
19
|
+
]
|
20
|
+
s.files = [
|
21
|
+
".document",
|
22
|
+
".rspec",
|
23
|
+
"Gemfile",
|
24
|
+
"Gemfile.lock",
|
25
|
+
"LICENSE.txt",
|
26
|
+
"README.rdoc",
|
27
|
+
"Rakefile",
|
28
|
+
"VERSION",
|
29
|
+
"benford.gemspec",
|
30
|
+
"bin/benford",
|
31
|
+
"lib/benford.rb",
|
32
|
+
"spec/benford_spec.rb",
|
33
|
+
"spec/spec_helper.rb"
|
34
|
+
]
|
35
|
+
s.homepage = %q{http://github.com/tijmenb/benford}
|
36
|
+
s.licenses = [%q{MIT}]
|
37
|
+
s.require_paths = [%q{lib}]
|
38
|
+
s.rubygems_version = %q{1.8.5}
|
39
|
+
s.summary = %q{Check the distribution if first digits in a dataset}
|
40
|
+
|
41
|
+
if s.respond_to? :specification_version then
|
42
|
+
s.specification_version = 3
|
43
|
+
|
44
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
45
|
+
s.add_development_dependency(%q<rspec>, ["~> 2.3.0"])
|
46
|
+
s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
|
47
|
+
s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
|
48
|
+
s.add_development_dependency(%q<rcov>, [">= 0"])
|
49
|
+
else
|
50
|
+
s.add_dependency(%q<rspec>, ["~> 2.3.0"])
|
51
|
+
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
52
|
+
s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
|
53
|
+
s.add_dependency(%q<rcov>, [">= 0"])
|
54
|
+
end
|
55
|
+
else
|
56
|
+
s.add_dependency(%q<rspec>, ["~> 2.3.0"])
|
57
|
+
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
58
|
+
s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
|
59
|
+
s.add_dependency(%q<rcov>, [">= 0"])
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
data/bin/benford
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
|
3
|
+
require 'pp'
|
4
|
+
require 'lib/benford'
|
5
|
+
|
6
|
+
class Float
|
7
|
+
def perc
|
8
|
+
"%.1f%" % (self * 100)
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
beginning = Time.now
|
13
|
+
|
14
|
+
file = File.open(ARGV[0], "rb")
|
15
|
+
b = Benford.new
|
16
|
+
data = file.read.gsub(',', '').scan(/\w+/) # remove , for correct parsing of '123,456,78'
|
17
|
+
b.load! data
|
18
|
+
|
19
|
+
puts ["digit", "count", "sample", "benford", "deviation"].join("\t\t")
|
20
|
+
|
21
|
+
(1..9).each do |d|
|
22
|
+
d = d.to_s # the digits are string
|
23
|
+
puts [d, b.counts[d], b.distribution[d].perc , b.law[d].perc, b.deviation[d].perc ].join("\t\t")
|
24
|
+
end
|
25
|
+
|
26
|
+
puts "-> Analysis of #{b.numbers.count} samples in #{Time.now - beginning} seconds"
|
data/lib/benford.rb
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
class Benford
|
2
|
+
|
3
|
+
def load!(nums)
|
4
|
+
@numbers = []
|
5
|
+
nums.each do |num|
|
6
|
+
num.gsub!(".", "")
|
7
|
+
num.gsub!(",", "")
|
8
|
+
@numbers << num.to_s if num.is_numeric?
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
# P(d) = log10(1 + 1/d)
|
13
|
+
def law
|
14
|
+
return @benford unless @benford.nil?
|
15
|
+
benford = {}
|
16
|
+
(1..9).each { |d| benford[d.to_s] = Math.log10( 1 + 1 / d.to_f) }
|
17
|
+
@benford = benford
|
18
|
+
end
|
19
|
+
|
20
|
+
def counts
|
21
|
+
return @digit_counts unless @digit_counts.nil?
|
22
|
+
digit_counts = Hash.new(0)
|
23
|
+
numbers.each do |v|
|
24
|
+
digit_counts[v.first] += 1
|
25
|
+
end
|
26
|
+
@digit_counts = digit_counts
|
27
|
+
end
|
28
|
+
|
29
|
+
def distribution
|
30
|
+
return @dist unless @dist.nil?
|
31
|
+
dist = Hash.new(0.0)
|
32
|
+
counts.each do |k, v|
|
33
|
+
dist[k] = v.to_f / numbers.count
|
34
|
+
end
|
35
|
+
@dist = dist
|
36
|
+
end
|
37
|
+
|
38
|
+
def numbers
|
39
|
+
@numbers
|
40
|
+
end
|
41
|
+
|
42
|
+
def deviation
|
43
|
+
return @variants unless @variants.nil?
|
44
|
+
variants = Hash.new(0.0)
|
45
|
+
law.each do |digit, occurence|
|
46
|
+
variants[digit] = distribution[digit] - occurence
|
47
|
+
end
|
48
|
+
@variants = variants
|
49
|
+
end
|
50
|
+
|
51
|
+
end
|
52
|
+
|
53
|
+
|
54
|
+
class String
|
55
|
+
|
56
|
+
def first
|
57
|
+
self.to_i.to_s[0,1]
|
58
|
+
end
|
59
|
+
|
60
|
+
def is_numeric?
|
61
|
+
self.to_s.match(/\A[+-]?\d+?(\.\d+)?\Z/) == nil ? false : true
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
|
3
|
+
describe Benford do
|
4
|
+
|
5
|
+
describe "after loading" do
|
6
|
+
|
7
|
+
before(:each) do
|
8
|
+
@b = Benford.new
|
9
|
+
end
|
10
|
+
|
11
|
+
it "counts the correct numbers" do
|
12
|
+
@b.load! ["6712", "1232"]
|
13
|
+
@b.numbers.count.should == 2
|
14
|
+
end
|
15
|
+
|
16
|
+
it "counts floats" do
|
17
|
+
@b.load! ["6712", "65123.1", "1232"]
|
18
|
+
@b.numbers.count.should == 3
|
19
|
+
end
|
20
|
+
|
21
|
+
it "strips strings" do
|
22
|
+
@b.load! ["6712345", "kjaadish", "2713678"]
|
23
|
+
@b.numbers.count.should == 2
|
24
|
+
end
|
25
|
+
|
26
|
+
it "converts a 1 < float into an integer" do
|
27
|
+
@b.load! ["0.123"]
|
28
|
+
@b.numbers.first.first.should == "1" # first.first is confusing, but alas
|
29
|
+
end
|
30
|
+
|
31
|
+
it "does not skip commas in numbers" do
|
32
|
+
@b.load! ["123,212.1"]
|
33
|
+
@b.numbers.count.should == 1
|
34
|
+
end
|
35
|
+
|
36
|
+
it "get the counts per number right" do
|
37
|
+
@b.load! ["18213", "2187356", "2131234", "2131234"]
|
38
|
+
@b.counts["1"].should == 1
|
39
|
+
@b.counts["2"].should == 3
|
40
|
+
end
|
41
|
+
|
42
|
+
it "gets the right distribution" do
|
43
|
+
@b.load! ["18213", "1187356", "2131234", "2131234"]
|
44
|
+
@b.distribution["1"].should == 0.5
|
45
|
+
@b.distribution["2"].should == 0.5
|
46
|
+
end
|
47
|
+
|
48
|
+
it "also get another distribution" do
|
49
|
+
@b.load! ["111", "111", "111", "222"]
|
50
|
+
@b.distribution["1"].should == 0.75
|
51
|
+
@b.distribution["2"].should == 0.25
|
52
|
+
end
|
53
|
+
|
54
|
+
it "and another distribution" do
|
55
|
+
@b.load! ["1"]
|
56
|
+
@b.distribution["1"].should == 1
|
57
|
+
end
|
58
|
+
|
59
|
+
it "gets the correct variant from the distribution" do
|
60
|
+
@b.load! ["111", "111", "222", "222"]
|
61
|
+
@b.deviation["1"].should be_between 0.19, 0.2
|
62
|
+
@b.deviation["2"].should be_between 0.32, 0.33
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,12 @@
|
|
1
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
2
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
3
|
+
require 'rspec'
|
4
|
+
require 'benford'
|
5
|
+
|
6
|
+
# Requires supporting files with custom matchers and macros, etc,
|
7
|
+
# in ./support/ and its subdirectories.
|
8
|
+
Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
|
9
|
+
|
10
|
+
RSpec.configure do |config|
|
11
|
+
|
12
|
+
end
|
metadata
ADDED
@@ -0,0 +1,139 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: benford
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 31
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 0
|
10
|
+
version: 0.0.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Tijmen Brommet
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-09-20 00:00:00 Z
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
type: :development
|
22
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
23
|
+
none: false
|
24
|
+
requirements:
|
25
|
+
- - ~>
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
hash: 3
|
28
|
+
segments:
|
29
|
+
- 2
|
30
|
+
- 3
|
31
|
+
- 0
|
32
|
+
version: 2.3.0
|
33
|
+
prerelease: false
|
34
|
+
name: rspec
|
35
|
+
version_requirements: *id001
|
36
|
+
- !ruby/object:Gem::Dependency
|
37
|
+
type: :development
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ~>
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
hash: 23
|
44
|
+
segments:
|
45
|
+
- 1
|
46
|
+
- 0
|
47
|
+
- 0
|
48
|
+
version: 1.0.0
|
49
|
+
prerelease: false
|
50
|
+
name: bundler
|
51
|
+
version_requirements: *id002
|
52
|
+
- !ruby/object:Gem::Dependency
|
53
|
+
type: :development
|
54
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
55
|
+
none: false
|
56
|
+
requirements:
|
57
|
+
- - ~>
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
hash: 7
|
60
|
+
segments:
|
61
|
+
- 1
|
62
|
+
- 6
|
63
|
+
- 4
|
64
|
+
version: 1.6.4
|
65
|
+
prerelease: false
|
66
|
+
name: jeweler
|
67
|
+
version_requirements: *id003
|
68
|
+
- !ruby/object:Gem::Dependency
|
69
|
+
type: :development
|
70
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
71
|
+
none: false
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
hash: 3
|
76
|
+
segments:
|
77
|
+
- 0
|
78
|
+
version: "0"
|
79
|
+
prerelease: false
|
80
|
+
name: rcov
|
81
|
+
version_requirements: *id004
|
82
|
+
description: "Check if a dataset conforms to Benford's Law. More info: http://en.wikipedia.org/wiki/Benford's_law"
|
83
|
+
email: tijmen@gmail.com
|
84
|
+
executables:
|
85
|
+
- benford
|
86
|
+
extensions: []
|
87
|
+
|
88
|
+
extra_rdoc_files:
|
89
|
+
- LICENSE.txt
|
90
|
+
- README.rdoc
|
91
|
+
files:
|
92
|
+
- .document
|
93
|
+
- .rspec
|
94
|
+
- Gemfile
|
95
|
+
- Gemfile.lock
|
96
|
+
- LICENSE.txt
|
97
|
+
- README.rdoc
|
98
|
+
- Rakefile
|
99
|
+
- VERSION
|
100
|
+
- benford.gemspec
|
101
|
+
- bin/benford
|
102
|
+
- lib/benford.rb
|
103
|
+
- spec/benford_spec.rb
|
104
|
+
- spec/spec_helper.rb
|
105
|
+
homepage: http://github.com/tijmenb/benford
|
106
|
+
licenses:
|
107
|
+
- MIT
|
108
|
+
post_install_message:
|
109
|
+
rdoc_options: []
|
110
|
+
|
111
|
+
require_paths:
|
112
|
+
- lib
|
113
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
114
|
+
none: false
|
115
|
+
requirements:
|
116
|
+
- - ">="
|
117
|
+
- !ruby/object:Gem::Version
|
118
|
+
hash: 3
|
119
|
+
segments:
|
120
|
+
- 0
|
121
|
+
version: "0"
|
122
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
123
|
+
none: false
|
124
|
+
requirements:
|
125
|
+
- - ">="
|
126
|
+
- !ruby/object:Gem::Version
|
127
|
+
hash: 3
|
128
|
+
segments:
|
129
|
+
- 0
|
130
|
+
version: "0"
|
131
|
+
requirements: []
|
132
|
+
|
133
|
+
rubyforge_project:
|
134
|
+
rubygems_version: 1.8.5
|
135
|
+
signing_key:
|
136
|
+
specification_version: 3
|
137
|
+
summary: Check the distribution if first digits in a dataset
|
138
|
+
test_files: []
|
139
|
+
|