tdigest 0.1.1 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 5aeae6aa49816daeea269ec499590c97075a3149
-  data.tar.gz: dd214c32109be62d1fb145743f52d1398feb13d4
+SHA256:
+  metadata.gz: e243d7b64e4a79cb7b3f0a5891602a3518179624eefebac431c71225092283cc
+  data.tar.gz: 53c8262286f8e6691add313ed1b13de00252bb3acd6415ebd3b1ca7ae6afb823
 SHA512:
-  metadata.gz: 9cc95403c4e428cf3ea0443e0cda972dd78b948779bff3fccf6265c155a50d47d83489965e93aa9ef6dbee316d543107d36a9fe76bbf5b8ea76f034d3f7332c4
-  data.tar.gz: 1325bf0d452da07415d9a12aabf8e014c76c7ade0ab21615cf95bfb4f582d9373b4b7ba70d6265a19d449ae9f88e45d6e1c52624c82d73e96f0f8bfaf4db5678
+  metadata.gz: fe0d0dbcf2e462b2d0b5431860b2c7883ef4d2754a215c98520afcb8d03b7a9def230a45c0a432589227c868ac5bbf089219f2f0681419a7da436e7189ab687a
+  data.tar.gz: 57917ef78aaa3335db1e7bfb9cfcf7ad5f5f5811508e11461676b296b7f4a49ffc4d17d32bb119829fa1418cf20db52179adfe9b65134aaddf42d3bc2209e6f5

data/.github/workflows/specs.yml

@@ -0,0 +1,22 @@
+name: CI
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby-version: [2.7, 3.1, 3.2]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Ruby ${{ matrix.ruby-version }}
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby-version }}
+    - name: Install dependencies
+      run: |
+        gem update --system
+        bundle install
+    - name: Run tests
+      run: bundle exec rake test

data/.ruby-version

@@ -1 +1 @@
-2.2.3
+3.2.2

data/Gemfile

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 source 'https://rubygems.org'
 
 # Specify your gem's dependencies in tdigest.gemspec

data/README.md

@@ -1,8 +1,7 @@
-# Tdigest
+# t-digest Ruby
 
+[![Ruby CI](https://github.com/castle/tdigest/actions/workflows/specs.yml/badge.svg?branch=master)](https://github.com/castle/tdigest/actions/workflows/specs.yml)
 [![Gem Version](https://badge.fury.io/rb/tdigest.svg)](https://badge.fury.io/rb/tdigest)
-[![Build Status](https://travis-ci.org/castle/tdigest.svg?branch=master)](https://travis-ci.org/castle/tdigest)
-[![Coverage Status](https://coveralls.io/repos/castle/tdigest/badge.svg?branch=master&service=github)](https://coveralls.io/github/castle/tdigest?branch=master)
 
 Ruby implementation of Ted Dunning's [t-digest](https://github.com/tdunning/t-digest) data structure.
 
@@ -37,12 +36,11 @@ puts td.p_rank(0.95)
 
 #### Serialization
 
-This gem offers the same serialization options as the original [Java implementation](https://github.com/tdunning/t-digest). You can read more about T-digest persistance in [Chapter 3 in the paper](https://github.com/tdunning/t-digest/blob/master/docs/t-digest-paper/histo.pdf).
+This gem offers the same serialization options as the original [Java implementation](https://github.com/tdunning/t-digest). You can read more about T-digest persistence in [Chapter 3 in the paper](https://github.com/tdunning/t-digest/blob/master/docs/t-digest-paper/histo.pdf).
 
 **Standard encoding**
 
-This encoding uses 8-byte Double for the means and a 4-byte integers for counts.
-Size per centroid is a fixed 12-bytes.
+This encoding uses 8-byte Double for the means and a 4-byte integer for counts. Size per centroid is a fixed 12-bytes.
 
 ```ruby
 bytes = tdigest.as_bytes
@@ -50,8 +48,7 @@ bytes = tdigest.as_bytes
 
 **Compressed encoding**
 
-This encoding uses delta encoding with 4-byte floats for the means and variable
-length encoding for the counts. Size per centroid is between 5-12 bytes.
+This encoding uses delta encoding with 4-byte floats for the means and variable length encoding for the counts. Size per centroid is between 5-12 bytes.
 
 ```ruby
 bytes = tdigest.as_small_bytes
@@ -79,4 +76,3 @@ Bug reports and pull requests are welcome on GitHub at https://github.com/castle
 ## License
 
 The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
-

data/Rakefile

@@ -1,10 +1,12 @@
-require "bundler/gem_tasks"
-require "rake/testtask"
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rake/testtask'
 
 Rake::TestTask.new(:test) do |t|
-  t.libs << "test"
-  t.libs << "lib"
+  t.libs << 'test'
+  t.libs << 'lib'
   t.test_files = FileList['test/**/*_test.rb']
 end
 
-task :default => :test
+task default: :test

data/bin/console

@@ -1,7 +1,8 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
-require "bundler/setup"
-require "tdigest"
+require 'bundler/setup'
+require 'tdigest'
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.
@@ -10,5 +11,5 @@ require "tdigest"
 # require "pry"
 # Pry.start
 
-require "irb"
+require 'irb'
 IRB.start

data/lib/tdigest/centroid.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module TDigest
   class Centroid
     attr_accessor :mean, :n, :cumn, :mean_cumn

data/lib/tdigest/tdigest.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'rbtree'
 require 'tdigest/centroid'
 
@@ -20,10 +22,8 @@ module TDigest
     def +(other)
       # Uses delta, k and cx from the caller
       t = self.class.new(@delta, @k, @cx)
-      data = self.centroids.values + other.centroids.values
-      while data.length > 0
-        t.push_centroid(data.delete_at(rand(data.length)))
-      end
+      data = centroids.values + other.centroids.values
+      t.push_centroid(data.delete_at(rand(data.length))) until data.empty?
       t
     end
 
@@ -56,7 +56,7 @@ module TDigest
           arr << b
           n = n >> 7
           k += 1
-          fail 'Unreasonable large number' if k > 6
+          raise 'Unreasonable large number' if k > 6
         end
         arr << n
       end
@@ -77,7 +77,7 @@ module TDigest
     def bound_mean_cumn(cumn)
       last_c = nil
       bounds = []
-      matches = @centroids.each do |k, v|
+      @centroids.each do |_k, v|
         if v.mean_cumn == cumn
           bounds << v
           break
@@ -164,8 +164,9 @@ module TDigest
       p = [p] unless is_array
       p.map! do |item|
         unless (0..1).include? item
-          fail ArgumentError, "p should be in [0,1], got #{item}"
+          raise ArgumentError, "p should be in [0,1], got #{item}"
         end
+
         if size == 0
           nil
         else
@@ -219,7 +220,7 @@ module TDigest
       case format
       when VERBOSE_ENCODING
         array = bytes[start_idx..-1].unpack("d#{size}L#{size}")
-        means, counts = array.each_slice(size).to_a if array.size > 0
+        means, counts = array.each_slice(size).to_a unless array.empty?
       when SMALL_ENCODING
         means = bytes[start_idx..(start_idx + 4 * size)].unpack("f#{size}")
         # Decode delta encoding of means
@@ -237,7 +238,8 @@ module TDigest
           z = 0x7f & v
           shift = 7
           while (v & 0x80) != 0
-            fail 'Shift too large in decode' if shift > 28
+            raise 'Shift too large in decode' if shift > 28
+
             v = counts_bytes.shift || 0
             z += (v & 0x7f) << shift
             shift += 7
@@ -245,9 +247,9 @@ module TDigest
           counts << z
         end
         # This shouldn't happen
-        fail 'Mismatch' unless counts.size == means.size
+        raise 'Mismatch' unless counts.size == means.size
       else
-        fail 'Unknown compression format'
+        raise 'Unknown compression format'
       end
       if means && counts
         means.zip(counts).each { |val| tdigest.push(val[0], val[1]) }
@@ -281,11 +283,11 @@ module TDigest
     def _cumulate(exact = false, force = false)
       unless force
         factor = if @last_cumulate == 0
-          Float::INFINITY
-        else
-          (@n.to_f / @last_cumulate)
-        end
-        return if @n == @last_cumulate || (!exact && @cx && @cx > (factor))
+                   Float::INFINITY
+                 else
+                   (@n.to_f / @last_cumulate)
+                 end
+        return if @n == @last_cumulate || (!exact && @cx && @cx > factor)
       end
 
       cumn = 0
@@ -318,7 +320,7 @@ module TDigest
       else
         p = nearest.mean_cumn.to_f / @n
         max_n = (4 * @n * @delta * p * (1 - p)).floor
-        if (max_n - nearest.n >= n)
+        if max_n - nearest.n >= n
           _add_weight(nearest, x, n)
         else
           _new_centroid(x, n, nearest.cumn)
@@ -331,9 +333,7 @@ module TDigest
       # it may be due to values being inserted in sorted order.
       # We combat that by replaying the centroids in random order,
       # which is what compress! does
-      if @centroids.size > (@k / @delta)
-        compress!
-      end
+      compress! if @centroids.size > (@k / @delta)
 
       nil
     end

data/lib/tdigest/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module TDigest
-  VERSION = "0.1.1"
+  VERSION = '0.2.1'
 end

data/lib/tdigest.rb

@@ -1,6 +1,6 @@
-require "tdigest/version"
-require "tdigest/tdigest"
+# frozen_string_literal: true
 
 module TDigest
-  # Your code goes here...
+  require 'tdigest/version'
+  require 'tdigest/tdigest'
 end

data/tdigest.gemspec

@@ -1,29 +1,37 @@
-# coding: utf-8
-lib = File.expand_path('../lib', __FILE__)
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'tdigest/version'
 
+java = (ENV['RUBY_PLATFORM'] == 'java')
+
 Gem::Specification.new do |spec|
-  spec.name          = "tdigest"
+  spec.name          = 'tdigest'
   spec.version       = TDigest::VERSION
-  spec.authors       = ["Sebastian Wallin"]
-  spec.email         = ["sebastian.wallin@gmail.com"]
+  spec.authors       = ['Sebastian Wallin']
+  spec.email         = ['sebastian.wallin@gmail.com']
 
-  spec.summary       = %q{Ruby implementation of Dunning's T-Digest for streaming quantile approximation}
-  spec.description   = %q{Ruby implementation of Dunning's T-Digest for streaming quantile approximation}
-  spec.homepage      = "https://github.com/castle/tdigest"
-  spec.license       = "MIT"
+  spec.summary       = 'TDigest for Ruby'
+  spec.description   = "Ruby implementation of Dunning's T-Digest for streaming quantile approximation"
+  spec.homepage      = 'https://github.com/castle/tdigest'
+  spec.license       = 'MIT'
 
   spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
-  spec.bindir        = "exe"
+  spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
+  spec.require_paths = ['lib']
+  spec.platform      = java ? 'java' : 'ruby'
 
-  spec.add_runtime_dependency 'rbtree', '~> 0.4.2'
+  if java
+    spec.add_runtime_dependency 'rbtree-jruby', '~> 0.2.1'
+  else
+    spec.add_runtime_dependency 'rbtree3', '~> 0.7.1'
+  end
 
-  spec.add_development_dependency 'bundler', '~> 1.10'
-  spec.add_development_dependency 'rake', '~> 10.0'
-  spec.add_development_dependency 'minitest', '~> 5.8.3'
+  spec.add_development_dependency 'bundler', '~> 2.1'
   spec.add_development_dependency 'coveralls', '~> 0.8.10'
-  spec.add_development_dependency 'simplecov', '~> 0.11.1'
+  spec.add_development_dependency 'minitest', '~> 5.8'
+  spec.add_development_dependency 'rake', '>= 12.3.3'
+  spec.add_development_dependency 'simplecov', '~> 0.16.0'
 end

metadata

@@ -1,99 +1,99 @@
 --- !ruby/object:Gem::Specification
 name: tdigest
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.1
 platform: ruby
 authors:
 - Sebastian Wallin
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2016-10-07 00:00:00.000000000 Z
+date: 2023-08-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: rbtree
+  name: rbtree3
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.2
+        version: 0.7.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.2
+        version: 0.7.1
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '2.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '2.1'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: 0.8.10
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: 0.8.10
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.8.3
+        version: '5.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.8.3
+        version: '5.8'
 - !ruby/object:Gem::Dependency
-  name: coveralls
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.8.10
+        version: 12.3.3
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.8.10
+        version: 12.3.3
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.11.1
+        version: 0.16.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.11.1
+        version: 0.16.0
 description: Ruby implementation of Dunning's T-Digest for streaming quantile approximation
 email:
 - sebastian.wallin@gmail.com
@@ -101,9 +101,9 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/specs.yml"
 - ".gitignore"
 - ".ruby-version"
-- ".travis.yml"
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -119,7 +119,7 @@ homepage: https://github.com/castle/tdigest
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -134,9 +134,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.1
-signing_key: 
+rubygems_version: 3.4.19
+signing_key:
 specification_version: 4
-summary: Ruby implementation of Dunning's T-Digest for streaming quantile approximation
+summary: TDigest for Ruby
 test_files: []

data/.travis.yml

@@ -1,7 +0,0 @@
-language: ruby
-rvm:
-  - 2.0.0
-  - 2.1.0
-  - 2.2.4
-  - 2.3.1
-before_install: gem install bundler -v 1.10.6