jaccard 1.0.1 → 1.0.2

data/Gemfile

@@ -0,0 +1,9 @@
+source :rubygems
+
+gem "rake"
+gem "yard"
+gem "bluecloth" # yard dependency for Markdown formatting
+gem "rspec", "> 2"
+gem "autotest"
+gem "ruby-debug", :platform => :ruby_18
+gem "ruby-debug19", :platform => :ruby_19

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010 François Beausoleil
+
+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 +1,71 @@
+Jaccard
+=======
+
+The [Jaccard Coefficient Index][1] is a measure of how similar two sets are. This library makes calculating the coefficient very easy, and provides useful helpers.
+
+Examples
+========
+
+Calculate how similar two sets are:
+
+    a = ["likes:jeans", "likes:blue"]
+    b = ["likes:jeans", "likes:women", "likes:red"]
+    c = ["likes:women", "likes:red"]
+
+    # Determines how similar a pair of sets are
+    Jaccard.coefficient(a, b)
+    #=> 0.25
+
+    Jaccard.coefficient(a, c)
+    #=> 0.0
+
+    Jaccard.coefficient(b, c)
+    #=> 0.6666666666666666
+
+    # According to the input data, b and c have the most similar likes.
+
+We can also extract the distance quite easily:
+
+    Jaccard.distance(a, b)
+    #=> 0.75
+
+The Jaccard distance is the inverse relation of the coefficient: `1 - coefficient`.
+
+Find out which set is closest to a given set of attributes (return a value where the distance is the minimum):
+
+    Jaccard.closest_to(a, [b, c])
+    #=> ["likes:jeans", "likes:women", "likes:red"]
+
+    Jaccard.closest_to(b, [a, c])
+    #=> ["likes:women", "likes:red"]
+
+Finally, we can find the best pair in a set:
+
+    require "pp"
+    pp Jaccard.best_match([a, b, c])
+    # [["likes:jeans", "likes:women", "likes:red"],
+    #  ["likes:women", "likes:red"]]
+    #=> nil
+
+Notes on scalability
+====================
+
+This library wasn't designed to handle millions of entries. You'll have to benchmark and see if this library meets your needs.
+
+Note on Patches/Pull Requests
+=============================
+
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+Copyright
+=========
+
+Copyright (c) 2010 François Beausoleil. See LICENSE for details.
+
+  [1]: http://en.wikipedia.org/wiki/Jaccard_index

data/lib/jaccard.rb

@@ -0,0 +1,114 @@
+require "set"
+
+# Helpers to calculate the Jaccard Coefficient Index and related metrics easily.
+#
+# (from Wikipedia): The Jaccard coefficient measures similarity between sample sets, and is defined
+# as the size of the intersection divided by the size of the union of the sample sets.
+#
+# The closer to 1.0 this number is, the more similar two items are.
+module Jaccard
+  # Calculates the Jaccard Coefficient Index.
+  #
+  # +a+ must implement the set intersection and set union operators: <code>#&</code> and <code>#+</code>. Array and Set
+  # both implement these methods natively. It is expected that the results of <code>+</code> will either return a
+  # unique set or that it returns an object that responds to +#uniq!+. The results of +#coefficient+ will be
+  # wrong if the union contains duplicate elements.
+  #
+  # Also note that the individual items in +a+ and +b+ must implement a sane #eql? method.
+  # ActiveRecord::Base, String, Fixnum (but not Float), Array and Hash instances all implement
+  # a correct notion of equality. Other instances might have to be checked to ensure correct
+  # behavior.
+  #
+  # @param [#&, #+] a A set of items
+  # @param [#&, #+] b A second set of items
+  #
+  # @return [Float] The Jaccard Coefficient Index between +a+ and +b+.
+  #
+  # @example
+  #
+  #   a = [1, 2, 3, 4]
+  #   b = [1, 3, 4]
+  #   Jaccard.coefficient(a, b) #=> 0.75
+  #
+  # @see http://en.wikipedia.org/wiki/Jaccard_index Jaccard Coefficient Index on Wikipedia.
+  def self.coefficient(a, b)
+    raise ArgumentError, "#{a.inspect} does not implement #&" unless a.respond_to?(:&)
+    raise ArgumentError, "#{a.inspect} does not implement #+" unless a.respond_to?(:+)
+
+    intersection = a & b
+    union        = a + b
+
+    # Set does not implement #uniq or #uniq! since elements are
+    # always guaranteed to be present only once. That's the only
+    # reason we need to guard against that here.
+    union.uniq! if union.respond_to?(:uniq!)
+
+    intersection.length.to_f / union.length.to_f
+  end
+
+  # Calculates the inverse of the Jaccard coefficient.
+  #
+  # The closer to 0.0 the distance is, the more similar two items are.
+  #
+  # @return [Float] <code>1.0 - #coefficient(a, b)</code>
+  #
+  # @see Jaccard#coefficient for parameter calling convention and caveats about Array vs Set vs other object types.
+  def self.distance(a, b)
+    1.0 - coefficient(a, b)
+  end
+
+  # Determines which member of +others+ has the smallest distance vs +a+.
+  #
+  # Because of the implementation, if multiple items from +others+ have
+  # the same distance, the last one will be returned. If this is undesirable,
+  # reverse +others+ before calling #closest_to.
+  #
+  # @param [#&, #+] a A set of attributes
+  # @param [#inject] others A collection of set of attributes
+  #
+  # @return The item from +others+ with the distance minimized to 0.0.
+  #
+  # @example
+  #
+  #   a = [1, 2, 3]
+  #   b = [1, 3]
+  #   c = [1, 2, 3]
+  #   Jaccard.closest_to(b, [a, c]) #=> [1, 2, 3]
+  #   # Note that the actual instance returned will be c
+  def self.closest_to(a, others)
+    others.inject([2.0, nil]) do |memo, other|
+      dist = distance(a, other)
+      next memo if memo.first < dist
+
+      [dist, other]
+    end.last
+  end
+
+  # Returns the pair of items whose distance is minimized.
+  #
+  # @param [#each] items A collection of attributes.
+  #
+  # @return [Array<a, b>] A pair of set of attributes whose Jaccard distance is the minimal, given the input set.
+  #
+  # @example
+  #
+  #   a = [1, 2, 3]
+  #   b = [1, 2]
+  #   c = [1, 3]
+  #   Jaccard.best_match([a, b, c]) #=> [[1, 2, 3], [1, 2]]
+  def self.best_match(items)
+    seen = Set.new
+    matches = []
+
+    items.each do |row|
+      items.each do |col|
+        next if row == col
+        next if seen.include?([row, col]) || seen.include?([col, row])
+        seen << [row, col]
+        matches << [distance(row, col), [row, col]]
+      end
+    end
+
+    matches.sort.first.last
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jaccard
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -13,7 +13,7 @@ date: 2012-02-24 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2153795880 !ruby/object:Gem::Requirement
+  requirement: &2153317540 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: 1.2.9
   type: :development
   prerelease: false
-  version_requirements: *2153795880
+  version_requirements: *2153317540
 - !ruby/object:Gem::Dependency
   name: yard
-  requirement: &2153795400 !ruby/object:Gem::Requirement
+  requirement: &2153317060 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,14 +32,18 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153795400
+  version_requirements: *2153317060
 description: The Jaccard Coefficient Index is a measure of how similar two sets are.
   This library makes calculating the coefficient very easy, and provides useful helpers.
 email: francois@teksol.info
 executables: []
 extensions: []
 extra_rdoc_files: []
-files: []
+files:
+- lib/jaccard.rb
+- README.md
+- LICENSE
+- Gemfile
 homepage: http://github.com/francois/jaccard
 licenses: []
 post_install_message: 
@@ -60,7 +64,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.6
+rubygems_version: 1.8.17
 signing_key: 
 specification_version: 3
 summary: A library to make calculating the Jaccard Coefficient Index a snap