sciruby 0.1.0

data/lib/sciruby.rb

@@ -0,0 +1,31 @@
+# = sci_ruby.rb -
+# SciRuby - Ruby scientific visualization and computation.
+#
+# Copyright (C) 2011  SciRuby Development Team
+#  * John O. Woods
+#  * John T. Prince
+#  * Claudio Bustos
+#  * others
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+#
+# Specific notices will be placed where they are appropriate.
+#
+
+module SciRuby
+  VERSION = '0.1.0'
+
+  autoload(:Recommend, 'sciruby/recommend')
+end

data/lib/sciruby/recommend.rb

@@ -0,0 +1,66 @@
+require 'set'
+require 'distribution' # for Hypergeometric
+
+unless defined?(SortedSet) # Ruby 1.8
+  class SortedSet < Set
+  end
+end
+
+# Added by John O. Woods.
+#
+# Makes use of Distribution gem, formerly part of Statsample, by Claudio Bustos.
+
+module SciRuby
+  # Methods and classes for expert recommendation systems.
+  module Recommend
+    # Set Distance functions: determine distances between sets.
+    #
+    # These functions may be useful for k-nearest neighbors searches and expert recommendation systems.
+    #
+    # Sets are used for systems where vectors are binary. For example, if you have a matrix of customers and products, a
+    # zero means the customer has not bought the product, and a one means the customer has. There is no concept of
+    # degree.
+    #
+    # Pearson is probably the function most people will want to use.
+    class SetDistance
+
+      # Create a new recommendation-by-set-distance object. This requires as arguments two sets (+a+ and +b+) and a
+      # +total+ size which indicates the number of items from which the sets are drawn.
+      #
+      # It also takes an optional +distance_function+ (e.g., :hypergeometric or :pearson). If this is given, the distance
+      # will be calculated immediately. Otherwise, you can use the various distance functions to calculate distance by
+      # a variety of metrics (e.g., distance_hypergeometric, distance_pearson, and so on).
+      def initialize a, b, total, distance_function = nil
+        @a = a.is_a?(Set) ? a : SortedSet.new(a)
+        @b = b.is_a?(Set) ? b : SortedSet.new(b)
+        @total = total
+
+        unless distance_function.nil? # Calculate immediately if a distance function is given.
+          @distance_function = "distance_#{distance_function.to_s}".to_sym
+          @distance = self.send @distance_function
+        end
+      end
+
+      attr_reader :a, :b, :total, :distance
+
+      def m; a.size; end
+      def n; b.size; end
+      def ab; @ab ||= a.intersection(b); end
+      def k; ab.size; end
+      alias :a_dot_b :k
+
+      # Calculate distance as the hypergeometric probability of seeing an intersection of +k+ or greater between two sets
+      # +a+ and +b+. This is basically the complement of cdf(+k-1+, +m+, +n+, +total+).
+      def distance_hypergeometric
+        @distance_hypergeometric ||= 1.0 - Distribution::Hypergeometric.cdf(k-1, m, n, total)
+      end
+
+      # The generalization of Pearson correlation coefficient using binary vectors.
+      def distance_pearson
+        @distance_pearson ||= 1.0 - (total * a_dot_b - m*n).abs / Math.sqrt(  (total - m)*(total - n)*m*n    )
+      end
+      
+    end
+
+  end
+end

metadata

@@ -0,0 +1,63 @@
+--- !ruby/object:Gem::Specification
+name: sciruby
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- SciRuby
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-08-01 00:00:00.000000000 -04:00
+default_executable: 
+dependencies: []
+description: ! 'Ruby has for some time had no equivalent to the beautifully constructed
+  numpy, scipy, and matplotlib libraries for Python. We believe that the time for
+  a Ruby science and visualization package has come and gone. Sometimes when a solution
+  of sugar and water becomes super-saturated, from it precipitates a pure, delicious,
+  and diabetes-inducing crystal of sweetness, induced by no more than the tap of a
+  finger. So it is, we believe, with the need for numeric and visualization libraries
+  in Ruby.
+
+
+  We are not the first with this idea, but we are trying to bring it to life.
+
+
+  At this point, SciRuby has not much to offer. But if you install this gem, you''ll
+  get as dependencies all of the libraries that we plan to incorporate into SciRuby.
+
+'
+email: john.woods@marcottelab.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/sciruby.rb
+- lib/sciruby/recommend.rb
+has_rdoc: true
+homepage: http://www.github.com/SciRuby/sciruby
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: sciruby
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: Tools for scientific computation in Ruby
+test_files: []