Class: CollaborativeFilter::SimpleSvd

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

Instance Method Summary collapse

Instance Method Details

#run(matrix, users, items, options) ⇒ Object 



17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
 
# File 'lib/correlators/simple_svd.rb', line 17

def run(matrix,users,items,options)
  qty = 0

  u,v,s = matrix.svd

  # we use the transpose of the V matrix
  xs,ys = [v.transpose.col(0).to_a, v.transpose.col(1).to_a]

  # precompute some of the terms from the cos. sim function. thanks pete!
  precomputes = []
  xs.each_index { |i| precomputes << Math.sqrt((xs[i] * xs[i]) + (ys[i] * ys[i])) }

  similar_users = {}
  # compute the similarities between each user and each other user currently this is O(n^2)... 
  # there is one major improvement that could be made to it... which is to cache the results
  xs.each_index do |user_idx|
    x1, y1 = xs[user_idx], ys[user_idx]
    sims = []
    xs.each_index do |target_idx|
      next if user_idx == target_idx
      x2, y2 = xs[target_idx], ys[target_idx]

      # compute the cosine similarity between user and target
      sim = ((x1 * x2) + (y1 * y2)) / (precomputes[user_idx] * precomputes[target_idx])

      sims << [target_idx, sim] if sim >= options[:cosine_similarity] 
    end

    x = sims.sort_by(&:last).reverse[0, (options[:max_similar_users] || sims.size)]
    qty += x.size
    similar_users[user_idx] = x
  end

  CollaborativeFilter.log "    Average sims per user: #{qty.to_f / similar_users.size}"
  similar_users
end