measurable 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 66337383a6c25685893bb39f7caf5c7f0b40bcff
-  data.tar.gz: 117a22bb28b1d36f14780d3a22bbad7211b279a0
+  metadata.gz: 8e94547914fc6532f23f86d4d8118100aad64398
+  data.tar.gz: f5eae04dfb5c5b2e041d59527921be80ba1b27bc
 SHA512:
-  metadata.gz: 0d7aff51213d2f0ca31472d1d5f43b3ce99d58255b9d3d53485b0983e953866a365927734c1852c7040f7c23149455712af6357679e03ff63bf247709ac7e124
-  data.tar.gz: 652066925d87d7d52656f87346c856d34296e4a98662e94a670d72e9612c568dd95bf758314c524501700b21b53484eaaf059e5b5fee315129fb1b0b90a170bd
+  metadata.gz: 8992dfff181353a0feb8d893f90c4705572f2706e158e6ee51f6d398c31ddd0b39f8f1153c123252eb064213984c11ec6d98cf720814065973a3d5a59884ebe7
+  data.tar.gz: 8643ac26d9471a6e1a78ca9b25c684196ad7fd61d7f930b0d2242b9d68d7b857ff7dd5c49da667517fd7a9ebf4593528947ebbb812ef9045026d381b5b76f978

data/Gemfile.lock

@@ -1,13 +1,13 @@
 PATH
   remote: .
   specs:
-    measurable (0.0.5)
+    measurable (0.0.6)
 
 GEM
   remote: http://rubygems.org/
   specs:
     diff-lcs (1.1.3)
-    rake (0.9.2.2)
+    rake (0.9.6)
     rspec (2.9.0)
       rspec-core (~> 2.9.0)
       rspec-expectations (~> 2.9.0)

data/README.md

@@ -27,13 +27,12 @@ The following are the similarity measures supported at the moment:
 - Jaccard distance
 - Tanimoto distance
 - Haversine distance
+- Minkowski (Cityblock or Manhattan) distance
+- Chebyshev distance
+- Hamming distance
 
 These still need to be implemented:
 
-- Cityblock distance
-- Chebyshev distance
-- Minkowski distance
-- Hamming distance
 - Correlation distance
 - Chi-square distance
 - Kullback-Leibler divergence
@@ -41,6 +40,8 @@ These still need to be implemented:
 - Mahalanobis distance
 - Squared Mahalanobis distance
 
+I plan to update the specs to reflect that each method is (or isn't) a mathematical metric, but I want to finish implementing them first. Any help is appreciated! :)
+
 ## How to use
 
 The API I intend to support is something like this:

data/lib/measurable.rb

@@ -2,11 +2,14 @@ require 'measurable/version'
 
 # Distance measures. The require order is important.
 require 'measurable/euclidean'
+require 'measurable/minkowski'
 require 'measurable/cosine'
 require 'measurable/jaccard'
 require 'measurable/tanimoto'
-require 'measurable/haversine'
+require 'measurable/chebyshev'
 require 'measurable/maxmin'
+require 'measurable/haversine'
+require 'measurable/hamming'
 
 module Measurable
   # PI / 180 degrees.

data/lib/measurable/chebyshev.rb

@@ -0,0 +1,23 @@
+module Measurable
+
+  # call-seq:
+  #     chebyshev(u, v) -> Float
+  #
+  #
+  #
+  # * *Arguments* :
+  #   - +u+ -> An array of Numeric objects.
+  #   - +v+ -> An array of Numeric objects.
+  # * *Returns* :
+  #   - The L-infinite distance between +u+ and +v+.
+  # * *Raises* :
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
+  #
+  def chebyshev(u, v)
+    # TODO: Change this to a more specific, custom-made exception.
+    raise ArgumentError if u.size != v.size
+
+    abs_differences = u.zip(v).map { |a| (a[0] - a[1]).abs }
+    abs_differences.max
+  end
+end

data/lib/measurable/cosine.rb

@@ -14,7 +14,7 @@ module Measurable
   #   - The normalized dot product of +u+ and +v+, that is, the angle between
   #     them in the n-dimensional space.
   # * *Raises* :
-  #   - +ArgumentError+ -> The sizes of +u+ and +v+ doesn't match.
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
   #
   def cosine(u, v)
     # TODO: Change this to a more specific, custom-made exception.

data/lib/measurable/euclidean.rb

@@ -17,7 +17,7 @@ module Measurable
   #   - The euclidean norm of +u+ or the euclidean distance between +u+ and
   #     +v+.
   # * *Raises* :
-  #   - +ArgumentError+ -> The sizes of +u+ and +v+ doesn't match.
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
   #
   def euclidean(u, v = nil)
     # If the second argument is nil, the method should return the norm of
@@ -57,7 +57,7 @@ module Measurable
   #   - The squared value of the euclidean norm of +u+ or of the euclidean
   #     distance between +u+ and +v+.
   # * *Raises* :
-  #   - +ArgumentError+ -> The sizes of +u+ and +v+ doesn't match.
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
   #
   def euclidean_squared(u, v = nil)
     # If the second argument is nil, the method should return the norm of

data/lib/measurable/hamming.rb

@@ -0,0 +1,27 @@
+module Measurable
+
+  # call-seq:
+  #     hamming(s1, s2) -> Integer
+  #
+  #
+  #
+  # See: http://en.wikipedia.org/wiki/Cosine_similarity
+  #
+  # * *Arguments* :
+  #   - +s1+ -> A String.
+  #   - +s2+ -> A String with the same size of +s1+.
+  # * *Returns* :
+  #   - The number of characters in which +s1+ and +s2+ differ.
+  # * *Raises* :
+  #   - +ArgumentError+ -> The sizes of +s1+ and +s2+ don't match.
+  #
+  def hamming(s1, s2)
+    # TODO: Change this to a more specific, custom-made exception.
+    raise ArgumentError if s1.size != s2.size
+
+    s1.chars.zip(s2.chars).reduce(0) do |acc, c|
+      acc += 1 if c[0] != c[1]
+      acc
+    end
+  end
+end

data/lib/measurable/maxmin.rb

@@ -17,7 +17,7 @@ module Measurable
   # * *Returns* :
   #   - Similarity between +u+ and +v+.
   # * *Raises* :
-  #   - +ArgumentError+ -> The sizes of +u+ and +v+ doesn't match.
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
   #
   def maxmin(u, v)
     # TODO: Change this to a more specific, custom-made exception.

data/lib/measurable/minkowski.rb

@@ -0,0 +1,28 @@
+module Measurable
+
+  # call-seq:
+  #     minkowski(u, v) -> Numeric
+  #
+  # Calculate the sum of the absolute value of the differences between each
+  # coordinate of +u+ and +v+.
+  #
+  # * *Arguments* :
+  #   - +u+ -> An array of Numeric objects.
+  #   - +v+ -> An array of Numeric objects.
+  # * *Returns* :
+  #   - The Minkowski (or L1) distance between +u+ and +v+.
+  # * *Raises* :
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
+  #
+  def minkowski(u, v)
+    # TODO: Change this to a more specific, custom-made exception.
+    raise ArgumentError if u.size != v.size
+
+    u.zip(v).reduce(0) do |acc, elem|
+      acc += (elem[0] - elem[1]).abs
+    end
+  end
+
+  alias :cityblock :minkowski
+  alias :manhattan :minkowski
+end

data/lib/measurable/tanimoto.rb

@@ -21,7 +21,7 @@ module Measurable
   # * *Returns* :
   #   - A measure of the similarity between +u+ and +v+.
   # * *Raises* :
-  #   - +ArgumentError+ -> The sizes of +u+ and +v+ doesn't match.
+  #   - +ArgumentError+ -> The sizes of +u+ and +v+ don't match.
   #
   def tanimoto(u, v)
     # TODO: Change this to a more specific, custom-made exception.

data/lib/measurable/version.rb

@@ -1,3 +1,3 @@
 module Measurable
-  VERSION = "0.0.5" # :nodoc:
+  VERSION = "0.0.6" # :nodoc:
 end

data/measurable.gemspec

@@ -4,12 +4,13 @@ require 'measurable/version'
 require 'date'
 
 Gem::Specification.new do |gem|
-  gem.name = "measurable"  
+  gem.name = "measurable"
   gem.version = Measurable::VERSION
   gem.date = Date.today.to_s
+  gem.license = "MIT"
   gem.summary = %Q{A Ruby gem with a lot of distance measures for your projects.}
   gem.description = %Q{A Ruby gem with a lot of distance measures for your projects.}
-  
+
   gem.authors = ["Carlos Agarie"]
   gem.email = "carlos.agarie@gmail.com"
   gem.homepage = "http://github.com/agarie/measurable"

data/spec/chebyshev_spec.rb

@@ -0,0 +1,29 @@
+describe "Chebyshev distance" do
+
+  before :all do
+    @u = [1.4, 2.5, 5.8]
+    @v = [2.2, 3.6, 2.7]
+    @w = [4.1, 5.7, 1.2]
+  end
+
+  it "accepts two arguments" do
+    expect { Measurable.chebyshev(@u, @v) }.to_not raise_error
+    expect { Measurable.chebyshev(@u, @v, @w) }.to raise_error(ArgumentError)
+  end
+
+  it "should be symmetric" do
+    x = Measurable.chebyshev(@u, @v)
+    y = Measurable.chebyshev(@v, @u)
+
+    x.should be_within(TOLERANCE).of(y)
+  end
+
+  it "should return the correct value" do
+    x = Measurable.chebyshev(@u, @v)
+    x.should be_within(TOLERANCE).of(3.1)
+  end
+
+  it "shouldn't work with vectors of different length" do
+    expect { Measurable.chebyshev(@u, [1, 3, 5, 7]) }.to raise_error(ArgumentError)
+  end
+end

data/spec/cosine_spec.rb

@@ -1,16 +1,16 @@
 describe "Cosine distance" do
-  
+
   before :all do
     @u = [1, 2]
     @v = [2, 3]
     @w = [4, 5]
   end
-  
+
   it "accepts two arguments" do
     expect { Measurable.cosine(@u, @v) }.to_not raise_error
     expect { Measurable.cosine(@u, @v, @w) }.to raise_error(ArgumentError)
   end
-  
+
   it "should be symmetric" do
     x = Measurable.cosine(@u, @v)
     y = Measurable.cosine(@v, @u)
@@ -24,6 +24,6 @@ describe "Cosine distance" do
   end
 
   it "shouldn't work with vectors of different length" do
-    expect { Measurable.cosine(@u, [1, 3, 5, 7]) }.to raise_error
+    expect { Measurable.cosine(@u, [1, 3, 5, 7]) }.to raise_error(ArgumentError)
   end
 end

data/spec/euclidean_spec.rb

@@ -1,22 +1,22 @@
 describe "Euclidean" do
-  
+
   before :all do
     @u = [1, 3, 16]
     @v = [1, 4, 16]
     @w = [4, 5, 6]
   end
-  
+
   context "Distance" do
     it "accepts two arguments" do
       expect { Measurable.euclidean(@u, @v) }.to_not raise_error
       expect { Measurable.euclidean(@u, @v, @w) }.to raise_error(ArgumentError)
     end
-  
+
     it "accepts one argument and returns the vector's norm" do
       # Remember that 3^2 + 4^2 = 5^2.
       Measurable.euclidean([3, 4]).should == 5
     end
-          
+
     it "should be symmetric" do
       Measurable.euclidean(@u, @v).should == Measurable.euclidean(@v, @u)
     end
@@ -25,27 +25,27 @@ describe "Euclidean" do
       Measurable.euclidean(@u, @u).should == 0
       Measurable.euclidean(@u, @v).should == 1
     end
-  
+
     it "shouldn't work with vectors of different length" do
-      expect { Measurable.euclidean(@u, [2, 2, 2, 2]) }.to raise_error
+      expect { Measurable.euclidean(@u, [2, 2, 2, 2]) }.to raise_error(ArgumentError)
     end
   end
-  
+
   context "Squared Distance" do
     it "accepts two arguments" do
       expect { Measurable.euclidean_squared(@u, @v) }.to_not raise_error
       expect { Measurable.euclidean_squared(@u, @v, @w) }.to raise_error(ArgumentError)
     end
-  
+
     it "accepts one argument and returns the vector's norm" do
       # Remember that 3^2 + 4^2 = 5^2.
       Measurable.euclidean_squared([3, 4]).should == 25
     end
-          
+
     it "should be symmetric" do
       x = Measurable.euclidean_squared(@u, @v)
       y = Measurable.euclidean_squared(@v, @u)
-      
+
       x.should == y
     end
 
@@ -53,9 +53,9 @@ describe "Euclidean" do
       Measurable.euclidean_squared(@u, @u).should == 0
       Measurable.euclidean_squared(@u, @v).should == 1
     end
-  
+
     it "shouldn't work with vectors of different length" do
-      expect { Measurable.euclidean_squared(@u, [2, 2, 2, 2]) }.to raise_error
-    end    
+      expect { Measurable.euclidean_squared(@u, [2, 2, 2, 2]) }.to raise_error(ArgumentError)
+    end
   end
 end

data/spec/hamming_spec.rb

@@ -0,0 +1,30 @@
+describe "Hamming distance" do
+
+  before :all do
+    @u = "Hi, I'm a test string!"
+    @v = "Hello, not a test omg."
+    @w = "Hey there, a test wtf!"
+  end
+
+  it "accepts two arguments" do
+    expect { Measurable.hamming(@u, @v) }.to_not raise_error
+    expect { Measurable.hamming(@u, @v, @w) }.to raise_error(ArgumentError)
+  end
+
+  it "should be symmetric" do
+    x = Measurable.hamming(@u, @v)
+    y = Measurable.hamming(@v, @u)
+
+    x.should be(y)
+  end
+
+  it "should return the correct value" do
+    x = Measurable.hamming(@u, @v)
+    x.should be(17)
+  end
+
+  it "shouldn't work with strings of different length" do
+    expect { Measurable.hamming(@u, "smallstring") }.to raise_error(ArgumentError)
+    expect { Measurable.hamming(@u, "largestring" * 20) }.to raise_error(ArgumentError)
+  end
+end

data/spec/haversine_spec.rb

@@ -32,6 +32,6 @@ describe "Haversine distance" do
   end
 
   it "should only work with [lat, long] vectors" do
-    expect { Measurable.haversine([2, 4], [1, 3, 5, 7]) }.to raise_error
+    expect { Measurable.haversine([2, 4], [1, 3, 5, 7]) }.to raise_error(ArgumentError)
   end
 end

data/spec/jaccard_spec.rb

@@ -26,7 +26,7 @@ describe "Jaccard" do
     end
 
     it "shouldn't work with vectors of different length" do
-      expect { Measurable.jaccard_index(@u, [1, 2, 3, 4]) }.to raise_error
+      expect { Measurable.jaccard_index(@u, [1, 2, 3, 4]) }.to raise_error(ArgumentError)
     end
   end
 
@@ -56,7 +56,7 @@ describe "Jaccard" do
     end
 
     it "shouldn't work with vectors of different length" do
-      expect { Measurable.jaccard(@u, [1, 2, 3, 4]) }.to raise_error
+      expect { Measurable.jaccard(@u, [1, 2, 3, 4]) }.to raise_error(ArgumentError)
     end
   end
 end

data/spec/maxmin_spec.rb

@@ -25,6 +25,6 @@ describe "Max-min distance" do
   end
 
   it "shouldn't work with vectors of different length" do
-    expect { Measurable.maxmin(@u, [1, 3, 5, 7]) }.to raise_error
+    expect { Measurable.maxmin(@u, [1, 3, 5, 7]) }.to raise_error(ArgumentError)
   end
 end

data/spec/minkowski_spec.rb

@@ -0,0 +1,28 @@
+describe "Minkowski" do
+
+  before :all do
+    @u = [1, 3, 6]
+    @v = [1, 4, 7]
+    @w = [4, 5, 6]
+  end
+
+  context "Distance" do
+    it "accepts two arguments" do
+      expect { Measurable.minkowski(@u, @v) }.to_not raise_error
+      expect { Measurable.minkowski(@u, @v, @w) }.to raise_error(ArgumentError)
+    end
+
+    it "should be symmetric" do
+      Measurable.minkowski(@u, @v).should == Measurable.minkowski(@v, @u)
+    end
+
+    it "should return the correct value" do
+      Measurable.minkowski(@u, @u).should == 0
+      Measurable.minkowski(@u, @v).should == 2
+    end
+
+    it "shouldn't work with vectors of different length" do
+      expect { Measurable.minkowski(@u, [2, 2, 2, 2]) }.to raise_error(ArgumentError)
+    end
+  end
+end

data/spec/tanimoto_spec.rb

@@ -25,6 +25,6 @@ describe "Tanimoto distance" do
   end
 
   it "shouldn't work with vectors of different length" do
-    expect { Measurable.tanimoto(@u, [1, 3, 5, 7]) }.to raise_error
+    expect { Measurable.tanimoto(@u, [1, 3, 5, 7]) }.to raise_error(ArgumentError)
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: measurable
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Carlos Agarie
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-24 00:00:00.000000000 Z
+date: 2013-08-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -66,23 +66,30 @@ files:
 - README.md
 - Rakefile
 - lib/measurable.rb
+- lib/measurable/chebyshev.rb
 - lib/measurable/cosine.rb
 - lib/measurable/euclidean.rb
+- lib/measurable/hamming.rb
 - lib/measurable/haversine.rb
 - lib/measurable/jaccard.rb
 - lib/measurable/maxmin.rb
+- lib/measurable/minkowski.rb
 - lib/measurable/tanimoto.rb
 - lib/measurable/version.rb
 - measurable.gemspec
+- spec/chebyshev_spec.rb
 - spec/cosine_spec.rb
 - spec/euclidean_spec.rb
+- spec/hamming_spec.rb
 - spec/haversine_spec.rb
 - spec/jaccard_spec.rb
 - spec/maxmin_spec.rb
+- spec/minkowski_spec.rb
 - spec/spec_helper.rb
 - spec/tanimoto_spec.rb
 homepage: http://github.com/agarie/measurable
-licenses: []
+licenses:
+- MIT
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -100,15 +107,18 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.3
+rubygems_version: 2.0.6
 signing_key: 
 specification_version: 4
 summary: A Ruby gem with a lot of distance measures for your projects.
 test_files:
+- spec/chebyshev_spec.rb
 - spec/cosine_spec.rb
 - spec/euclidean_spec.rb
+- spec/hamming_spec.rb
 - spec/haversine_spec.rb
 - spec/jaccard_spec.rb
 - spec/maxmin_spec.rb
+- spec/minkowski_spec.rb
 - spec/spec_helper.rb
 - spec/tanimoto_spec.rb