class SimString::DiceMeasure

Public Instance Methods

max_feature_size(db, query_size, alpha) click to toggle source
# File lib/simstring_pure.rb, line 89
def max_feature_size(db, query_size, alpha)
  (((2 - alpha).to_f / alpha) * query_size).floor.to_i
end
min_feature_size(db, query_size, alpha) click to toggle source
# File lib/simstring_pure.rb, line 85
def min_feature_size(db, query_size, alpha)
  ((alpha.to_f / (2 - alpha)) * query_size).ceil.to_i
end
minimum_common_feature_count(query_size, y_size, alpha) click to toggle source
# File lib/simstring_pure.rb, line 93
def minimum_common_feature_count(query_size, y_size, alpha)
  (0.5 * alpha * (query_size * y_size)).ceil.to_i
end
similarity(x_feature_set, y_feature_set) click to toggle source
# File lib/simstring_pure.rb, line 97
def similarity(x_feature_set, y_feature_set)
  (2 * (x_feature_set & y_feature_set).size).to_f / (x_feature_set.size + y_feature_set.size)
end