descriptive-statistics 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.
- data/.gitignore +17 -0
- data/.travis.yml +3 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +38 -0
- data/Rakefile +6 -0
- data/descriptive-statistics.gemspec +23 -0
- data/lib/descriptive-statistics.rb +13 -0
- data/lib/descriptive-statistics/central-tendency.rb +46 -0
- data/lib/descriptive-statistics/version.rb +5 -0
- data/spec/lib/descriptive-statistics/central_tendency_spec.rb +51 -0
- data/spec/spec_helper.rb +2 -0
- metadata +98 -0
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Julian Tescher
|
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 +1,38 @@
|
|
1
|
+
# DescriptiveStatistics
|
2
|
+
|
3
|
+
This gem calculates measures of central tendency (e.g. mean, median mode), dispersion (e.g. range, and quartiles), and
|
4
|
+
spread (e.g variance and standard deviation)
|
5
|
+
|
6
|
+
[]
|
7
|
+
(http://travis-ci.org/jtescher/descriptive-statistics)
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
gem 'descriptive-statistics'
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install descriptive-statistics
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
### Central Tendency:
|
25
|
+
```ruby
|
26
|
+
stats = DescriptiveStatistics.new([1,1,2,3,10])
|
27
|
+
stats.mean #=> 3.4
|
28
|
+
stats.median #=> 2
|
29
|
+
stats.mode #=> 1
|
30
|
+
```
|
31
|
+
|
32
|
+
## Contributing
|
33
|
+
|
34
|
+
1. Fork it
|
35
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
36
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
37
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
38
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'descriptive-statistics/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "descriptive-statistics"
|
8
|
+
gem.version = Descriptive::Statistics::VERSION
|
9
|
+
gem.authors = ["Julian Tescher"]
|
10
|
+
gem.email = ["virulent@gmail.com"]
|
11
|
+
gem.description = %q{Descriptive Statistics Calculator}
|
12
|
+
gem.summary = %q{Simply calculate measures of central tendency (e.g. mean, median mode), dispersion (e.g. range
|
13
|
+
and quartiles), and spread (e.g variance and standard deviation)}
|
14
|
+
gem.homepage = "https://github.com/jtescher/descriptive-stats"
|
15
|
+
|
16
|
+
gem.files = `git ls-files`.split($/)
|
17
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
18
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
19
|
+
gem.require_paths = ["lib"]
|
20
|
+
|
21
|
+
gem.add_development_dependency "rspec"
|
22
|
+
gem.add_development_dependency "rake"
|
23
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
require "descriptive-statistics/version"
|
2
|
+
require 'descriptive-statistics/central-tendency'
|
3
|
+
|
4
|
+
class DescriptiveStatistics
|
5
|
+
extend Forwardable
|
6
|
+
include CentralTendency
|
7
|
+
|
8
|
+
def initialize(data)
|
9
|
+
@data = data
|
10
|
+
end
|
11
|
+
|
12
|
+
def_delegators :@data, :length, :inject, :sort, :each_with_object
|
13
|
+
end
|
@@ -0,0 +1,46 @@
|
|
1
|
+
class DescriptiveStatistics
|
2
|
+
module CentralTendency
|
3
|
+
def sum
|
4
|
+
inject(0, :+)
|
5
|
+
end
|
6
|
+
|
7
|
+
def mean
|
8
|
+
return if length < 1
|
9
|
+
sum / length.to_f
|
10
|
+
end
|
11
|
+
|
12
|
+
def median
|
13
|
+
return if length < 1
|
14
|
+
sorted = self.sort
|
15
|
+
|
16
|
+
if length % 2 == 0
|
17
|
+
(sorted[(length/2) -1 ] + sorted[length / 2]) / 2.0
|
18
|
+
else
|
19
|
+
sorted[length / 2]
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def mode
|
24
|
+
return if length < 1
|
25
|
+
frequency_distribution = each_with_object(Hash.new(0)) { |value, hash| hash[value] += 1 }
|
26
|
+
top_2 = frequency_distribution.sort { |a,b| b[1] <=> a[1] } .take(2)
|
27
|
+
if top_2.length == 1
|
28
|
+
top_2.first.first # Only one value in distribution, so it's the mode.
|
29
|
+
elsif top_2.first.last == top_2.last.last
|
30
|
+
nil # Equal frequency, no mode.
|
31
|
+
else
|
32
|
+
top_2.first.first # Most frequent is mode.
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
def sample_variance
|
37
|
+
sum = self.inject(0) {|accumulator, value| accumulator + (value - mean) ** 2 }
|
38
|
+
sum / (length.to_f - 1)
|
39
|
+
end
|
40
|
+
|
41
|
+
def standard_deviation
|
42
|
+
return if length < 2
|
43
|
+
Math.sqrt(sample_variance)
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
@@ -0,0 +1,51 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe DescriptiveStatistics::CentralTendency do
|
4
|
+
describe '#sum' do
|
5
|
+
it 'returns the amount attained by adding all numbers in the array' do
|
6
|
+
DescriptiveStatistics.new([1,2,6]).sum.should == 9
|
7
|
+
end
|
8
|
+
|
9
|
+
it 'returns 0 if empty' do
|
10
|
+
DescriptiveStatistics.new([]).sum.should == 0
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
describe '#mean' do
|
15
|
+
it 'returns the sum of the values over the count of the values' do
|
16
|
+
DescriptiveStatistics.new([1,2,6]).mean.should == 3
|
17
|
+
end
|
18
|
+
|
19
|
+
it 'returns nil if empty' do
|
20
|
+
DescriptiveStatistics.new([]).mean.should be_nil
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
describe '#median' do
|
25
|
+
it 'returns the value lying at the midpoint of the array' do
|
26
|
+
DescriptiveStatistics.new([1,2,6]).median.should == 2
|
27
|
+
end
|
28
|
+
|
29
|
+
it 'returns the mean of the two midpoint values if the array length is even' do
|
30
|
+
DescriptiveStatistics.new([1,2,3,6]).median.should == 2.5
|
31
|
+
end
|
32
|
+
|
33
|
+
it 'returns nil if empty' do
|
34
|
+
DescriptiveStatistics.new([]).median.should be_nil
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
describe '#mode' do
|
39
|
+
it 'returns the most frequent value' do
|
40
|
+
DescriptiveStatistics.new([1,1,2,46]).mode.should == 1
|
41
|
+
end
|
42
|
+
|
43
|
+
it 'returns nil if there is no most frequent value' do
|
44
|
+
DescriptiveStatistics.new([1,2,3]).mode.should be_nil
|
45
|
+
end
|
46
|
+
|
47
|
+
it 'returns nil if empty' do
|
48
|
+
DescriptiveStatistics.new([]).mode.should be_nil
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,98 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: descriptive-statistics
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Julian Tescher
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-09-29 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
description: Descriptive Statistics Calculator
|
47
|
+
email:
|
48
|
+
- virulent@gmail.com
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- .gitignore
|
54
|
+
- .travis.yml
|
55
|
+
- Gemfile
|
56
|
+
- LICENSE.txt
|
57
|
+
- README.md
|
58
|
+
- Rakefile
|
59
|
+
- descriptive-statistics.gemspec
|
60
|
+
- lib/descriptive-statistics.rb
|
61
|
+
- lib/descriptive-statistics/central-tendency.rb
|
62
|
+
- lib/descriptive-statistics/version.rb
|
63
|
+
- spec/lib/descriptive-statistics/central_tendency_spec.rb
|
64
|
+
- spec/spec_helper.rb
|
65
|
+
homepage: https://github.com/jtescher/descriptive-stats
|
66
|
+
licenses: []
|
67
|
+
post_install_message:
|
68
|
+
rdoc_options: []
|
69
|
+
require_paths:
|
70
|
+
- lib
|
71
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
72
|
+
none: false
|
73
|
+
requirements:
|
74
|
+
- - ! '>='
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '0'
|
77
|
+
segments:
|
78
|
+
- 0
|
79
|
+
hash: 2378606324476284759
|
80
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
86
|
+
segments:
|
87
|
+
- 0
|
88
|
+
hash: 2378606324476284759
|
89
|
+
requirements: []
|
90
|
+
rubyforge_project:
|
91
|
+
rubygems_version: 1.8.24
|
92
|
+
signing_key:
|
93
|
+
specification_version: 3
|
94
|
+
summary: Simply calculate measures of central tendency (e.g. mean, median mode), dispersion
|
95
|
+
(e.g. range and quartiles), and spread (e.g variance and standard deviation)
|
96
|
+
test_files:
|
97
|
+
- spec/lib/descriptive-statistics/central_tendency_spec.rb
|
98
|
+
- spec/spec_helper.rb
|