ruby-svd 0.3.0 → 0.4.0

data/lib/lsa.rb

@@ -0,0 +1,37 @@
+require 'svd_matrix'
+
+class LSA
+  attr_accessor :u, :s, :v
+
+  def initialize(matrix)
+    @u, @s, @v = matrix.decompose(2)
+  end
+  
+  # Return a distance (cosine similarity) between a new vector,
+  # and all the clusters (columns) used in the original matrix.
+  # Returns a sorted list of indexes and distances,
+  def classify_vector(values)
+    raise "Unsupported vector length" unless values.size == @u.row_size
+    vector = Matrix.row_vector(values)
+    position = vector * @u * @s.inverse
+    puts position
+    x = position[0,0]
+    y = position[0,1]
+    results = []
+    
+    @v.row_size.times do |index|
+      results << [index, cosine_similarity(x, y, @v[index, 0], @v[index, 1])]
+    end
+    
+    results.sort {|a, b| b[1] <=> a[1]}
+  end
+  
+  # Determines the cosine similarity between two 2D points
+  def cosine_similarity(x1, y1, x2, y2)
+    dp = (x1 * x2) + (y1 * y2)
+    mag1 = Math.sqrt((x1 ** 2) + (y1 ** 2))
+    mag2 = Math.sqrt((x2 ** 2) + (y2 ** 2))
+    return 0 if mag1 == 0 || mag2 == 0
+    return (dp / (mag1 * mag2))
+  end
+end

data/lib/ruby-svd.rb

@@ -1,3 +1,3 @@
 require 'svd'
 require 'svd_matrix'
-
+require 'lsa'

data/lib/svd_matrix.rb

@@ -41,11 +41,11 @@ class SVDMatrix < Matrix
     
     # recompose U matrix
     u = SVDMatrix.new(row_size, reduce_dimensions_to || column_size)
-    row_size.times {|i| u.set_row(i, u_array.slice!(0, reduce_dimensions_to || column_size))}
+    row_size.times {|i| u.set_row(i, u_array.slice!(0, column_size)[0...reduce_dimensions_to])}
     
     # recompose V matric
     v = SVDMatrix.new(column_size, reduce_dimensions_to || column_size)
-    column_size.times {|i| v.set_row(i, v_array.slice!(0, reduce_dimensions_to || column_size))}
+    column_size.times {|i| v.set_row(i, v_array.slice!(0, column_size)[0...reduce_dimensions_to])}
     
     # diagonalise W array as a matrix
     if reduce_dimensions_to

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 0
-  - 3
+  - 4
   - 0
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors: 
 - Will Cannings
@@ -32,6 +32,7 @@ files:
 - ext/nrutil.h
 - ext/svd.c
 - ext/svd.h
+- lib/lsa.rb
 - lib/ruby-svd.rb
 - lib/svd_matrix.rb
 - LICENSE