weighted_sampler 0.0.1 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b82cc1aeea5268c4d1fd689deee743e64bf338d334b552c5600f4cbd46f0b3bb
-  data.tar.gz: 5e509683f24970d4659e2daf970127996f48bca2205be4367f3853add61111f8
+  metadata.gz: d03c4329b1bc66f6c6ae1008c7f50b466f990f77bb46faa9850b8812d777dc9a
+  data.tar.gz: 13b517ea952b2f9c532601b57dbe6cbd8a6263b9f1f8cc29a2c6829caf88d7d0
 SHA512:
-  metadata.gz: 10c649840d4332437671074e1114e81a2d5665bf3b4d6c8f33c85faef7387f9438da0af346eb40c7fbb0966a0ad0ae498c48a1a678184230572959734cf90d86
-  data.tar.gz: cae656dc33e4f08da8609dd19294d4ba01825b1a803e6d02727cb4837f5d0d19a6232b852ac16456d970f15ecb717f45dbe38a2b391d3bcd42c61e3a8dd1c174
+  metadata.gz: b09dc165fcd8f11ddc6aa34a894ad315d256f1b8450ee86e8c8fc7639a162622996250db77b9e6e3a32bc0c552487f21a306eb5e7155ec598e6cf9a8c5d39486
+  data.tar.gz: 247ad644e8d31e944aaba67bb5230c49464c7f5b0607bba4a57e566222441ca9cd8783f8bd9a3c33371062534441055ea637f52523a7f85046a3a6d58452366b

data/.gitignore

@@ -9,3 +9,5 @@
 
 # rspec failure tracking
 .rspec_status
+
+*.gem

data/.gitlab-ci.yml

@@ -0,0 +1,23 @@
+image: ruby
+
+stages:
+  - test
+
+before_script:
+  - bundle install
+
+ruby2.3:
+  image: ruby:2.3
+  script: rspec
+
+ruby2.4:
+  image: ruby:2.4
+  script: rspec
+
+ruby2.5:
+  image: ruby:2.5
+  script: rspec
+
+ruby2.6-rc:
+  image: ruby:2.6-rc
+  script: rspec

data/.rspec

@@ -1,3 +1,3 @@
---format documentation
+--format progress
 --color
 --require spec_helper

data/.rubocop.yml

@@ -0,0 +1,60 @@
+AllCops:
+  Exclude:
+    - tmp/**/*
+
+Rails:
+  Enabled: true
+
+# We prefer having assignments inside if-s
+Lint/AssignmentInCondition:
+  Enabled: false
+
+# Longer lines is awesome
+Metrics/LineLength:
+  Max: 160
+
+# Having every class documented is too much
+Style/Documentation:
+  Enabled: false
+
+# We do love empty lines
+Layout/EmptyLines:
+  Enabled: false
+
+Layout/EmptyLinesAroundArguments:
+  Enabled: false
+
+Layout/EmptyLinesAroundClassBody:
+  Enabled: false
+
+Layout/EmptyLinesAroundBlockBody:
+  Enabled: false
+
+Layout/EmptyLinesAroundModuleBody:
+  Enabled: false
+
+# We do love complex code
+Metrics/AbcSize:
+  Enabled: false
+
+Metrics/CyclomaticComplexity:
+  Enabled: false
+
+Metrics/ClassLength:
+  Enabled: false
+
+Metrics/MethodLength:
+  Enabled: false
+
+Metrics/PerceivedComplexity:
+  Enabled: false
+
+Metrics/BlockLength:
+  Enabled: false
+
+# This is AR-only cop
+Rails/FindEach:
+  Enabled: false
+
+Rails/CreateTableWithTimestamps:
+  Enabled: false

data/.travis.yml

@@ -2,4 +2,4 @@ sudo: false
 language: ruby
 rvm:
   - 2.5.1
-before_install: gem install bundler -v 1.16.1
+before_install: gem install bundler

data/Gemfile

@@ -1,6 +1,11 @@
-source "https://rubygems.org"
+# frozen_string_literal: true
 
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+gem 'pry-byebug'
+gem 'simplecov'
 
 # Specify your gem's dependencies in weighted_sampler.gemspec
 gemspec

data/Gemfile.lock

@@ -0,0 +1,53 @@
+PATH
+  remote: .
+  specs:
+    weighted_sampler (1.0.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    byebug (10.0.2)
+    coderay (1.1.2)
+    diff-lcs (1.3)
+    docile (1.3.1)
+    json (2.1.0)
+    method_source (0.9.0)
+    pry (0.11.3)
+      coderay (~> 1.1.0)
+      method_source (~> 0.9.0)
+    pry-byebug (3.6.0)
+      byebug (~> 10.0)
+      pry (~> 0.10)
+    rake (10.5.0)
+    rspec (3.7.0)
+      rspec-core (~> 3.7.0)
+      rspec-expectations (~> 3.7.0)
+      rspec-mocks (~> 3.7.0)
+    rspec-core (3.7.1)
+      rspec-support (~> 3.7.0)
+    rspec-expectations (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-mocks (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-support (3.7.1)
+    simplecov (0.16.1)
+      docile (~> 1.1)
+      json (>= 1.8, < 3)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.16)
+  pry-byebug
+  rake (~> 10.0)
+  rspec (~> 3.0)
+  simplecov
+  weighted_sampler!
+
+BUNDLED WITH
+   1.16.1

data/README.md

@@ -22,17 +22,100 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+Module or sampler instance modes available
+
+### Module
+
+```ruby
+>> WeightedSampler.sample([P0, P1, ...])
+=> INDEX
+>> WeightedSampler.sample({K0 => P0, K1 => P1, ...})
+=> Ki
+```
+
+#### Input as an Array
+
+You can provide `Array` of probabilities in a form of weights for each option.
+
+Equal probabilities: `[50, 50]` or `[1, 1]` or `[0.5, 0.5]`
+
+Different probabilities: `[99, 1]`, or `[0.001, 0.1]` (index 1 is 100x times more likely to be chosen than 0)
+
+If your input probabilies are not normalized `WeightedSampler` will do it for you
+
+`OUTPUT` will be an index of selected value, so that you can match it to your more complex data structure
+
+#### Input as an Hash
+
+To simplify dome workflows you can provide `Hash` structure in a way
+
+```ruby
+{ K0 => P0, ...}
+{ a: 1, b: 1, c: 2} # c has 0.5, a and b - 0.25
+{ 0 => 50, 150 => 1} # 105 key is 50 times less probable to be picked
+```
+
+where `values` are probabilities with requirements similar to `Array` approach
+
+`OUTPUT` in this case will be picked `key`
+
+### Class (`::Base`)
+
+Class is the *recommended* way to use of sampler becuase it's performance is ~10x better than Module
+
+You need to initialize sampler:
+
+```ruby
+sampler = WeightedSampler::Base.new([P0, P1, ...])
+# OR
+sampler = WeightedSampler::Base.new({K0 => P0, K1 => P1, ...})
+```
+
+after that you can get samples via
+
+`sampler.sample # => index (for Array) or key (for Hash)`
+
+Input parameter to initialization of an instance are similar to Module use case.
+
+Plus, you can you `seed` option for repeatable results
+
+### Options
+
+#### `skip_normalization`
+**You do not have to normalize input probabilities**
+
+But for some reason you may want to normalize yourself, for this
+you have an option `skip_normalization`
+
+```ruby
+WeightedSampler.sample([...], skip_normalization: true)
+WeightedSampler.sample({...}, skip_normalization: true)
+```
+
+if we will not be able to sum provided probabilities into `1` you'll get `RuntimeError` exception with some information about this
+
+#### `seed` (¡ Class use case only !)
+
+If you need to get repeatable sequence of samples you can initialize sampler with seed Integer (similar to ruby`s [Random](https://ruby-doc.org/core/Random.html#method-c-new)
+
+```ruby
+WeightedSampler::Base.new([...], seed: SEED)
+WeightedSampler::Base.new([...], seed: SEED)
+```
+
+Please, note that if `seed` is not provided, sampler will use generic `rand` functionality without any seed initialization
+
+### Performance
 
 ## Development
 
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rspec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
 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).
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/weighted_sampler. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+Bug reports and pull requests are welcome on GitHub at https://gitlab.com/[USERNAME]/weighted_sampler. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
 
 ## License
 

data/Rakefile

@@ -1,6 +1,8 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+task default: :spec

data/bin/console

@@ -1,7 +1,8 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
-require "bundler/setup"
-require "weighted_sampler"
+require 'bundler/setup'
+require 'weighted_sampler'
 
 # 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 "weighted_sampler"
 # require "pry"
 # Pry.start
 
-require "irb"
+require 'irb'
 IRB.start(__FILE__)

data/lib/weighted_sampler/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module WeightedSampler
-  VERSION = '0.0.1'.freeze
+  VERSION = '1.0.0'.freeze
 end

data/lib/weighted_sampler.rb

@@ -1,5 +1,7 @@
-require 'weighted_sampler/version'
+# frozen_string_literal: true
 
+require 'weighted_sampler/version'
+require 'pry'
 module WeightedSampler
 
   # sum of floats are never stable enough to guarantee exact equality to 1
@@ -16,16 +18,17 @@ module WeightedSampler
       elsif enum.is_a?(Array)
         @p_ranges = normalized_ranges(enum, skip_normalization)
         @keys = [*0...enum.size]
-      else
-        raise ArgumentError, 'input structure must be a Hash or an Array'
       end
+
+      return unless @p_ranges.nil? || @keys.nil? || @keys.empty?
+      raise ArgumentError, 'input structure must be a non-empty Hash or Array'
     end
 
     def sample
       pick = @random ? @random.rand : rand
 
       idx = @p_ranges.index { |range| range.include? pick }
-      @keys[idx]
+      @keys[idx] if idx
     end
 
     private
@@ -40,23 +43,28 @@ module WeightedSampler
     end
 
     def normalize_probabilities(array)
-      sum = array.inject(&:+)
+      sum = array.inject(&:+).to_f
 
       array.map { |el| el / sum }
     end
 
     def array_to_ranges(array)
       start = 0.0
-      ranges = array.map { |v| p_start = start; start += v; (p_start...v + p_start) }
+      ranges = array.map do |v|
+        p_start = start
+        start += v
+
+        (p_start...v + p_start)
+      end
 
-      raise 'normalized probabilities total is not 1' if start - 1.0 > ERROR_ALLOWANCE
+      raise 'normalized probabilities total is not 1' if (start - 1.0).abs > ERROR_ALLOWANCE
 
       ranges
     end
 
   end
 
-  def self.sample(enum, seed: nil, skip_normalization: false)
-    Base.new(enum, seed: seed, skip_normalization: skip_normalization).sample
+  def self.sample(enum, skip_normalization: false)
+    Base.new(enum, skip_normalization: skip_normalization).sample
   end
 end

data/weighted_sampler.gemspec

@@ -1,4 +1,6 @@
 
+# frozen_string_literal: true
+
 lib = File.expand_path('lib', __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'weighted_sampler/version'
@@ -18,15 +20,6 @@ Gem::Specification.new do |spec|
   spec.homepage      = 'https://gitlab.com/alexey_b/weighted_sampler'
   spec.license       = 'MIT'
 
-  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
-  # to allow pushing to a single host or delete this section to allow pushing to any host.
-  # if spec.respond_to?(:metadata)
-  #   spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
-  # else
-  #   raise 'RubyGems 2.0 or newer is required to protect against ' \
-  #     'public gem pushes.'
-  # end
-
   spec.files = `git ls-files -z`.split("\x0").reject do |f|
     f.match(%r{^(test|spec|features)/})
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: weighted_sampler
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Oleksiy Babich
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-06-01 00:00:00.000000000 Z
+date: 2018-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -62,10 +62,13 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".gitlab-ci.yml"
 - ".rspec"
+- ".rubocop.yml"
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
 - Gemfile
+- Gemfile.lock
 - LICENSE.txt
 - README.md
 - Rakefile