Class: OpenTox::Algorithm::Similarity

Inherits:
Object
  • Object
show all
Defined in:
lib/similarity.rb

Class Method Summary collapse

Class Method Details

.cosine(scaled_properties) ⇒ Float

Get cosine similarity

http://stackoverflow.com/questions/1838806/euclidean-distance-vs-pearson-correlation-vs-cosine-similarity

Parameters:

Returns:



45
46
47
48
 
# File 'lib/similarity.rb', line 45

def self.cosine scaled_properties
  scaled_properties = remove_nils scaled_properties
  Algorithm::Vector.dot_product(scaled_properties[0], scaled_properties[1]) / (Algorithm::Vector.magnitude(scaled_properties[0]) * Algorithm::Vector.magnitude(scaled_properties[1]))
end

.euclid(scaled_properties) ⇒ Float

Get Euclidean distance

Parameters:

Returns:



36
37
38
39
 
# File 'lib/similarity.rb', line 36

def self.euclid scaled_properties
  sq = scaled_properties[0].zip(scaled_properties[1]).map{|a,b| (a - b) ** 2}
  Math.sqrt(sq.inject(0) {|s,c| s + c})
end

.remove_nils(scaled_properties) ⇒ Array<Array<Float>>

Remove nil values

Parameters:

Returns:



71
72
73
74
75
76
77
78
79
80
81
 
# File 'lib/similarity.rb', line 71

def self.remove_nils scaled_properties
  a =[]; b = []; w = []
  (0..scaled_properties.first.size-1).each do |i|
    if scaled_properties[0][i] and scaled_properties[1][i] and !scaled_properties[0][i].nan? and !scaled_properties[1][i].nan?
      a << scaled_properties[0][i]
      b << scaled_properties[1][i]
      w << scaled_properties[2][i]
    end
  end
  [a,b,w]
end

.tanimoto(fingerprints) ⇒ Float

Get Tanimoto similarity

Parameters:

Returns:



25
26
27
 
# File 'lib/similarity.rb', line 25

def self.tanimoto fingerprints
  ( fingerprints[0] & fingerprints[1]).size/(fingerprints[0]|fingerprints[1]).size.to_f
end

.weighted_cosine(scaled_properties) ⇒ Float

Get weighted cosine similarity

http://stackoverflow.com/questions/1838806/euclidean-distance-vs-pearson-correlation-vs-cosine-similarity

Parameters:

Returns:



54
55
56
57
58
59
60
61
62
63
64
65
66
 
# File 'lib/similarity.rb', line 54

def self.weighted_cosine scaled_properties 
  a,b,w = remove_nils scaled_properties
  return cosine(scaled_properties) if w.uniq.size == 1
  dot_product = 0
  magnitude_a = 0
  magnitude_b = 0
  (0..a.size-1).each do |i|
    dot_product += w[i].abs*a[i]*b[i]
    magnitude_a += w[i].abs*a[i]**2
    magnitude_b += w[i].abs*b[i]**2
  end
  dot_product/(Math.sqrt(magnitude_a)*Math.sqrt(magnitude_b))
end