ranking_distance 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 2bbbf46b3640915b503b8836f5509690f6c0f479f7d0d8e8b4fbeb71039e6bc4
+  data.tar.gz: e3b58bd3d424ae183c5f82633dd356e136e371b3fa0a716e50b9173b61557ceb
+SHA512:
+  metadata.gz: 57cf4109193102f0ad780e6ba1bb07d2ae8d5f4677daf6dd616c353d6110f5ed779faa9e2d2de4616cc96410d114f259e45c79d327e18280182e7b4b86d55266
+  data.tar.gz: 521c03eb613b6996a3d7266c1c3abbf5f1b928654897cbbde11a53808fb4c0117b357194dcdb1e758728689989a335a512a876a3286cab5ca0eb3221ddea13af

data/Gemfile

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in ranking_distance.gemspec
+gemspec
+
+group :development, :test do
+  gem "rake", "~> 13.0"
+  gem "rspec-core", "~> 3.12"
+end

data/Gemfile.lock

@@ -0,0 +1,23 @@
+PATH
+  remote: .
+  specs:
+    ranking_distance (0.1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    rake (13.0.6)
+    rspec-core (3.12.2)
+      rspec-support (~> 3.12.0)
+    rspec-support (3.12.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  rake (~> 13.0)
+  ranking_distance!
+  rspec-core (~> 3.12)
+
+BUNDLED WITH
+   2.3.5

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Mathieu Alexandre
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,60 @@
+# RankingDistance
+
+RankingDistance is a Ruby gem that provides a simple and efficient way to compute the distance between two rankings. Rankings are arrays of elements, and the distance is a positive number that is small when the rankings are similar and bigger when they are not.
+
+Unlike other edit distances, such as the Levenshtein distance, RankDistance weights more the insertions at the front of the rankings and gives less weight to insertions at the back of the rankings. This makes the distance computed by RankDistance more reflective of the percived similarity between the rankings.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ranking_distance'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install ranking_distance
+
+## Usage
+
+3 Methods are available:
+
+`RankingDistance.absolute_distance(arr1, arr2)`
+
+    Computes the absolute distance between two arrays.
+    The absolute distance is computed as follows:
+    - if the two arrays are equal, the distance is 0
+    - if the two arrays are different, the distance is the number of swaps and insertions needed to transform one array into the other
+    - Each swap cost is dependent on the distance between the two swapped elements
+    - Each insertion cost is dependent on the position of the inserted element (inserting at the end is cheaper than inserting at the start)
+    The absolute distance is thus always a positive integer.
+
+`RankingDistance.relative_distance(arr1, arr2)`
+
+    Computes the relative distance between two arrays.
+    The relative distance is computed by dividing the absolute distance by the maximum possible distance between the two arrays.
+    This means that the relative distance is always a float between 0 and 1.
+    0 if the two arrays are equal, 1 if the two arrays are built with completely different elements.
+
+`RankingDistance.relative_proximity(arr1, arr2)`
+
+    Computes the relative proximity between two arrays.
+    The relative proximity is computed by substracting the relative distance from 1.
+    This means that the relative proximity is always a float between 0 and 1.
+    1 if the two arrays are equal, 0 if the two arrays are built with completely different elements.
+
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. 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 the created tag, 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/almathie/ranking_distance.

data/Rakefile

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/lib/ranking_distance/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module RankingDistance
+  VERSION = "0.1.0"
+end

data/lib/ranking_distance.rb

@@ -0,0 +1,87 @@
+# frozen_string_literal: true
+
+require_relative "ranking_distance/version"
+
+module RankingDistance
+  class Error < StandardError; end
+
+  # A class used to represent a unique element in an array.
+  # This class is used to fill arrays with a unique element so that the arrays can be compared.
+  # This class is used internally by the RankingDistance module and should not be used directly.
+  class UniqueElement
+    def ==(_)
+      false
+    end
+  end
+
+  #
+  # Computes the absolute distance between two arrays.
+  # The absolute distance is computed as follows:
+  # - if the two arrays are equal, the distance is 0
+  # - if the two arrays are different, the distance is the number of swaps and insertions needed to transform one array into the other
+  # - Each swap cost is dependent on the distance between the two swapped elements
+  # - Each insertion cost is dependent on the position of the inserted element (inserting at the end is cheaper than inserting at the start)
+  # The absolute distance is thus always a positive integer.
+  #
+  # @param arr1 [Array] the first array
+  # @param arr2 [Array] the second array
+  # @return [Integer] the absolute distance between the two arrays
+  #
+  def self.absolute_distance(arr1, arr2)
+    return 0 if arr1 == arr2
+
+    shortest_arr, longest_arr = [arr1.dup, arr2.dup].sort_by(&:length)
+    shortest_arr << UniqueElement.new until shortest_arr.length == longest_arr.length
+
+    edit_distance = 0
+    start_index = 0
+    while start_index < longest_arr.length
+      if longest_arr[start_index] != shortest_arr[start_index]
+        element = longest_arr[start_index]
+        element_index_in_truncated_short_array = shortest_arr.drop(start_index).index(element)
+        if element_index_in_truncated_short_array # Element found -> swap
+          edit_distance += element_index_in_truncated_short_array
+          shortest_arr.insert(start_index, shortest_arr.delete_at(element_index_in_truncated_short_array + start_index))
+        else # Element not found -> insert
+          edit_distance += (longest_arr.length - start_index)
+          shortest_arr.insert(start_index, element)
+        end
+      end
+      start_index += 1
+    end
+
+    return edit_distance
+  end
+
+  #
+  # Computes the relative distance between two arrays.
+  # The relative distance is computed by dividing the absolute distance by the maximum possible distance between the two arrays.
+  # This means that the relative distance is always a float between 0 and 1.
+  # 0 if the two arrays are equal, 1 if the two arrays are built with completely different elements.
+  #
+  # @param arr1 [Array] the first array
+  # @param arr2 [Array] the second array
+  # @return [Float] the relative distance between the two arrays
+  #
+  def self.relative_distance(arr1, arr2)
+    return 0 if arr1.empty? && arr2.empty?
+
+    _, longest_arr = [arr1, arr2].sort_by(&:length)
+    max_distance = longest_arr.length * (longest_arr.length + 1) / 2
+    return absolute_distance(arr1, arr2).to_f / max_distance
+  end
+
+  #
+  # Computes the relative proximity between two arrays.
+  # The relative proximity is computed by substracting the relative distance from 1.
+  # This means that the relative proximity is always a float between 0 and 1.
+  # 1 if the two arrays are equal, 0 if the two arrays are built with completely different elements.
+  #
+  # @param arr1 [Array] the first array
+  # @param arr2 [Array] the second array
+  # @return [Float] the relative proximity between the two arrays
+  #
+  def self.relative_proximity(arr1, arr2)
+    return 1 - relative_distance(arr1, arr2)
+  end
+end

data/sig/ranking_distance.rbs

@@ -0,0 +1,4 @@
+module RankingDistance
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,53 @@
+--- !ruby/object:Gem::Specification
+name: ranking_distance
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Alexandre Mathieu
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2023-06-02 00:00:00.000000000 Z
+dependencies: []
+description: Helps determine how closely related two rankings are
+email:
+- almathie@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- lib/ranking_distance.rb
+- lib/ranking_distance/version.rb
+- sig/ranking_distance.rbs
+homepage: https://github.com/almathie/ranking_distance
+licenses: []
+metadata:
+  homepage_uri: https://github.com/almathie/ranking_distance
+  source_code_uri: https://github.com/almathie/ranking_distance
+  changelog_uri: https://github.com/almathie/ranking_distance
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.26
+signing_key:
+specification_version: 4
+summary: Compute a distance between two arrays
+test_files: []