tdigest 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.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: e55c5378cfd6bb3f02ff04c45e4a8303f2d983da
4
+ data.tar.gz: 860b7f13d3d16cef3fa4b351a5e44fb56d4c987a
5
+ SHA512:
6
+ metadata.gz: 1c4883e5bbcca571dc7215fa6b5884d03fce2850e06f0892653c6285eabfaa9af54a2d0c162a5dbdc7ba32c50314aa82c44ad98bf95391dedf0ad81fd8afbc8f
7
+ data.tar.gz: 7814344890f5b5d21012723f5291cb60ce0564f7792fb6e7ce0f7a9285097c636f90e0036d099ba79ac77b99346ad366f13176ee71aa6a5ad2160a5361c00949
@@ -0,0 +1,9 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /Gemfile.lock
4
+ /_yardoc/
5
+ /coverage/
6
+ /doc/
7
+ /pkg/
8
+ /spec/reports/
9
+ /tmp/
@@ -0,0 +1,4 @@
1
+ language: ruby
2
+ rvm:
3
+ - 2.2.3
4
+ before_install: gem install bundler -v 1.10.6
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # Specify your gem's dependencies in tdigest.gemspec
4
+ gemspec
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2015 Sebastian Wallin
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in
13
+ all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21
+ THE SOFTWARE.
@@ -0,0 +1,48 @@
1
+ # Tdigest
2
+
3
+ Ruby implementation of Ted Dunning's [t-digest](https://github.com/tdunning/t-digest) data structure.
4
+
5
+ Inspired by the [Javascript implementation](https://github.com/welch/tdigest) by [Will Welch](https://github.com/welch)
6
+
7
+ ## Installation
8
+
9
+ Add this line to your application's Gemfile:
10
+
11
+ ```ruby
12
+ gem 'tdigest'
13
+ ```
14
+
15
+ And then execute:
16
+
17
+ $ bundle
18
+
19
+ Or install it yourself as:
20
+
21
+ $ gem install tdigest
22
+
23
+ ## Usage
24
+
25
+ ```ruby
26
+ td = ::TDigest::TDigest.new
27
+ 1_000.times { td.push(rand) }
28
+ td.compress!
29
+
30
+ puts td.percentile(0.5)
31
+ puts td.p_rank(0.95)
32
+ ```
33
+
34
+ ## Development
35
+
36
+ After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
37
+
38
+ To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
39
+
40
+ ## Contributing
41
+
42
+ Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/tdigest. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](contributor-covenant.org) code of conduct.
43
+
44
+
45
+ ## License
46
+
47
+ The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
48
+
@@ -0,0 +1,10 @@
1
+ require "bundler/gem_tasks"
2
+ require "rake/testtask"
3
+
4
+ Rake::TestTask.new(:test) do |t|
5
+ t.libs << "test"
6
+ t.libs << "lib"
7
+ t.test_files = FileList['test/**/*_test.rb']
8
+ end
9
+
10
+ task :default => :test
@@ -0,0 +1,14 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "bundler/setup"
4
+ require "tdigest"
5
+
6
+ # You can add fixtures and/or initialization code here to make experimenting
7
+ # with your gem easier. You can also use a different console, if you like.
8
+
9
+ # (If you use this, don't forget to add pry to your Gemfile!)
10
+ # require "pry"
11
+ # Pry.start
12
+
13
+ require "irb"
14
+ IRB.start
@@ -0,0 +1,7 @@
1
+ #!/bin/bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+
5
+ bundle install
6
+
7
+ # Do any other automated setup that you need to do here
@@ -0,0 +1,6 @@
1
+ require "tdigest/version"
2
+ require "tdigest/tdigest"
3
+
4
+ module TDigest
5
+ # Your code goes here...
6
+ end
@@ -0,0 +1,10 @@
1
+ module TDigest
2
+ class Centroid
3
+ attr_accessor :mean, :n, :cumn, :mean_cumn
4
+ def initialize(params = {})
5
+ params.each do |p, value|
6
+ send("#{p}=", value)
7
+ end
8
+ end
9
+ end
10
+ end
@@ -0,0 +1,210 @@
1
+ require 'rbtree'
2
+ require 'tdigest/centroid'
3
+
4
+ module TDigest
5
+ class TDigest
6
+ def initialize(delta = 0.01, k = 25, cx = 1.1)
7
+ @delta = delta
8
+ @k = k
9
+ @cx = cx
10
+ @centroids = RBTree.new
11
+ @nreset = 0
12
+ reset!
13
+ end
14
+
15
+ def bound_mean(x)
16
+ upper = @centroids.upper_bound(x)
17
+ lower = @centroids.lower_bound(x)
18
+ [lower[1], upper[1]]
19
+ end
20
+
21
+ def bound_mean_cumn(cumn)
22
+ last_c = nil
23
+ bounds = []
24
+ matches = @centroids.each do |k, v|
25
+ if v.mean_cumn == cumn
26
+ bounds << v
27
+ break
28
+ elsif v.mean_cumn > cumn
29
+ bounds << last_c
30
+ bounds << v
31
+ break
32
+ else
33
+ last_c = v
34
+ end
35
+ end
36
+ lower = bounds[0]
37
+ upper = bounds[1]
38
+
39
+ [lower, upper]
40
+ end
41
+
42
+ def compress!
43
+ points = to_a
44
+ reset!
45
+ while points.length > 0
46
+ push_centroid(points.delete_at(rand(points.length)))
47
+ end
48
+ _cumulate(true)
49
+ nil
50
+ end
51
+
52
+ def find_nearest(x)
53
+ return nil if size == 0
54
+
55
+ ceil = @centroids.upper_bound(x)
56
+ floor = @centroids.lower_bound(x)
57
+
58
+ return floor[1] if ceil.nil?
59
+ return ceil[1] if floor.nil?
60
+
61
+ ceil_key = ceil[0]
62
+ floor_key = floor[0]
63
+
64
+ if (floor_key - x).abs < (ceil_key - x).abs
65
+ floor[1]
66
+ else
67
+ ceil[1]
68
+ end
69
+ end
70
+
71
+ def p_rank(x)
72
+ is_array = x.is_a? Array
73
+ x = [x] unless is_array
74
+ x.map! do |item|
75
+ if size == 0
76
+ nil
77
+ elsif item < @centroids.min[1].mean
78
+ 0.0
79
+ elsif item > @centroids.max[1].mean
80
+ 1.0
81
+ else
82
+ _cumulate(true)
83
+ bound = bound_mean(item)
84
+ lower, upper = bound
85
+ mean_cumn = lower.mean_cumn
86
+ if lower != upper
87
+ mean_cumn += (item - lower.mean) * (upper.mean_cumn - lower.mean_cumn) / (upper.mean - lower.mean)
88
+ end
89
+ mean_cumn / @n
90
+ end
91
+ end
92
+ is_array ? x : x.first
93
+ end
94
+
95
+ def percentile(p)
96
+ is_array = p.is_a? Array
97
+ p = [p] unless is_array
98
+ p.map! do |item|
99
+ if size == 0
100
+ nil
101
+ else
102
+ _cumulate(true)
103
+ h = @n * item
104
+ lower, upper = bound_mean_cumn(h)
105
+ if upper == lower || lower.nil? || upper.nil?
106
+ (lower || upper).mean
107
+ elsif h == lower.mean_cumn
108
+ lower.mean
109
+ else
110
+ upper.mean
111
+ end
112
+ end
113
+ end
114
+ is_array ? p : p.first
115
+ end
116
+
117
+ def push(x, n = 1)
118
+ x = [x] unless x.is_a? Array
119
+ x.each { |value| _digest(value, n) }
120
+ end
121
+
122
+ def push_centroid(c)
123
+ c = [c] unless c.is_a? Array
124
+ c.each { |centroid| _digest(centroid.mean, centroid.n) }
125
+ end
126
+
127
+ def reset!
128
+ @centroids.clear
129
+ @n = 0
130
+ @nreset += 1
131
+ @last_cumulate = 0
132
+ end
133
+
134
+ def size
135
+ @centroids.count
136
+ end
137
+
138
+ def to_a
139
+ @centroids.map { |_, c| c }
140
+ end
141
+
142
+
143
+ private
144
+
145
+
146
+ def _add_weight(nearest, x, n)
147
+ unless x == nearest.mean
148
+ nearest.mean += n * (x - nearest.mean) / (nearest.n + n)
149
+ end
150
+
151
+ nearest.cumn += n
152
+ nearest.mean_cumn += n / 2
153
+ nearest.n += n
154
+ @n += n
155
+
156
+ nil
157
+ end
158
+
159
+ def _cumulate(exact = false)
160
+ factor = @last_cumulate == 0 ? Float::INFINITY : (@n / @last_cumulate)
161
+ if @n == @last_cumulate
162
+ return
163
+ end
164
+
165
+ cumn = 0
166
+ @centroids.each do |_, c|
167
+ c.mean_cumn = cumn + c.n / 2
168
+ cumn = c.cumn = cumn + c.n
169
+ end
170
+ @n = @last_cumulate = cumn
171
+ nil
172
+ end
173
+
174
+ def _digest(x, n)
175
+ min = @centroids.min
176
+ max = @centroids.max
177
+ min = min.nil? ? nil : min[1]
178
+ max = max.nil? ? nil : max[1]
179
+ nearest = find_nearest(x)
180
+
181
+ if nearest && nearest.mean == x
182
+ _add_weight(nearest, x, n)
183
+ elsif nearest == min
184
+ _new_centroid(x, n, 0)
185
+ elsif nearest == max
186
+ _new_centroid(x, n, @n)
187
+ else
188
+ p = nearest.mean_cumn.to_f / @n
189
+ max_n = (4 * @n * @delta * p * (1 - p)).floor
190
+ if (max_n - nearest.n >= n)
191
+ _add_weight(nearest, x, n)
192
+ else
193
+ _new_centroid(x, n, nearest.cumn)
194
+ end
195
+ end
196
+
197
+ _cumulate(false)
198
+
199
+ nil
200
+ end
201
+
202
+ def _new_centroid(x, n, cumn)
203
+ c = Centroid.new({ mean: x, n: n, cumn: cumn })
204
+ @centroids[x] = c
205
+ @n += n
206
+ c
207
+ end
208
+ end
209
+ end
210
+
@@ -0,0 +1,3 @@
1
+ module TDigest
2
+ VERSION = "0.0.1"
3
+ end
@@ -0,0 +1,27 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'tdigest/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = "tdigest"
8
+ spec.version = TDigest::VERSION
9
+ spec.authors = ["Sebastian Wallin"]
10
+ spec.email = ["sebastian.wallin@gmail.com"]
11
+
12
+ spec.summary = %q{Ruby implementation of Dunning's T-Digest for streaming quantile approximation}
13
+ spec.description = %q{Ruby implementation of Dunning's T-Digest for streaming quantile approximation}
14
+ spec.homepage = "https://github.com/castle/tdigest"
15
+ spec.license = "MIT"
16
+
17
+ spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
18
+ spec.bindir = "exe"
19
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
20
+ spec.require_paths = ["lib"]
21
+
22
+ spec.add_runtime_dependency 'rbtree', '~> 0.4.2'
23
+
24
+ spec.add_development_dependency "bundler", "~> 1.10"
25
+ spec.add_development_dependency "rake", "~> 10.0"
26
+ spec.add_development_dependency "minitest"
27
+ end
metadata ADDED
@@ -0,0 +1,113 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: tdigest
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Sebastian Wallin
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2015-11-11 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: rbtree
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: 0.4.2
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: 0.4.2
27
+ - !ruby/object:Gem::Dependency
28
+ name: bundler
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '1.10'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '1.10'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rake
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '10.0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '10.0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: minitest
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ description: Ruby implementation of Dunning's T-Digest for streaming quantile approximation
70
+ email:
71
+ - sebastian.wallin@gmail.com
72
+ executables: []
73
+ extensions: []
74
+ extra_rdoc_files: []
75
+ files:
76
+ - ".gitignore"
77
+ - ".travis.yml"
78
+ - Gemfile
79
+ - LICENSE.txt
80
+ - README.md
81
+ - Rakefile
82
+ - bin/console
83
+ - bin/setup
84
+ - lib/tdigest.rb
85
+ - lib/tdigest/centroid.rb
86
+ - lib/tdigest/tdigest.rb
87
+ - lib/tdigest/version.rb
88
+ - tdigest.gemspec
89
+ homepage: https://github.com/castle/tdigest
90
+ licenses:
91
+ - MIT
92
+ metadata: {}
93
+ post_install_message:
94
+ rdoc_options: []
95
+ require_paths:
96
+ - lib
97
+ required_ruby_version: !ruby/object:Gem::Requirement
98
+ requirements:
99
+ - - ">="
100
+ - !ruby/object:Gem::Version
101
+ version: '0'
102
+ required_rubygems_version: !ruby/object:Gem::Requirement
103
+ requirements:
104
+ - - ">="
105
+ - !ruby/object:Gem::Version
106
+ version: '0'
107
+ requirements: []
108
+ rubyforge_project:
109
+ rubygems_version: 2.4.5.1
110
+ signing_key:
111
+ specification_version: 4
112
+ summary: Ruby implementation of Dunning's T-Digest for streaming quantile approximation
113
+ test_files: []