Merge branch 'development' into support

Conflicts:
	lib/algorithm.rb
	lib/model.rb

3 files changed, 77 insertions, 40 deletions

diff --git a/Rakefile b/Rakefile
index bd22c16..952affe 100644
--- a/Rakefile
+++ b/Rakefile
@@ -8,7 +8,7 @@ begin
     gem.summary = %Q{Ruby wrapper for the OpenTox REST API}
     gem.description = %Q{Ruby wrapper for the OpenTox REST API (http://www.opentox.org)}
     gem.email = "helma@in-silico.ch"
-    gem.homepage = "http://github.com/helma/opentox-ruby"
+    gem.homepage = "http://github.com/opentox/opentox-ruby"
     gem.authors = ["Christoph Helma, Martin Guetlein, Andreas Maunz, Micha Rautenberg, David Vorgrimmler"]
     # dependencies with versions
     gem.add_dependency "sinatra", "=1.2.6"
@@ -16,7 +16,7 @@ begin
     gem.add_dependency "sinatra-respond_to", "=0.7.0"
     gem.add_dependency "sinatra-static-assets", "=0.5.0"
     gem.add_dependency "rest-client", "=1.6.1"
-    gem.add_dependency "rack", "=1.3.0"
+    gem.add_dependency "rack", "=1.3.1"
     gem.add_dependency "rack-contrib", "=1.1.0"
     gem.add_dependency "rack-flash", "=0.1.1"
     gem.add_dependency "nokogiri", "=1.4.4"
@@ -44,6 +44,8 @@ begin
     gem.add_dependency "dm-sqlite-adapter", "=1.1.0"
     gem.add_dependency "ruby-plot", "=0.5.0"
     gem.add_dependency "gsl", "=1.14.7"
+    gem.add_dependency "statsample", "=1.1.0"
+    #gem.add_dependency "statsample-optimization", "=2.1.0"
 
     gem.add_development_dependency 'jeweler'
     gem.files =  FileList["[A-Z]*", "{bin,generators,lib,test}/**/*", 'lib/jeweler/templates/.gitignore']
diff --git a/lib/algorithm.rb b/lib/algorithm.rb
index 3170efb..528c426 100644
--- a/lib/algorithm.rb
+++ b/lib/algorithm.rb
@@ -230,21 +230,17 @@ module OpenTox
 
         raise "No neighbors found." unless params[:neighbors].size>0
         begin
-
           props = params[:prop_kernel] ? get_props(params) : nil
           acts = params[:neighbors].collect { |n| act = n[:activity].to_f }
           sims = params[:neighbors].collect { |n| Algorithm.gauss(n[:similarity]) }
-
           LOGGER.debug "Local MLR (Propositionalization / GSL)."
           prediction = mlr( {:n_prop => props[0], :q_prop => props[1], :sims => sims, :acts => acts} )
           transformer = eval "OpenTox::Algorithm::Transform::#{params[:transform]["class"]}.new ([#{prediction}], #{params[:transform]["offset"]})"
           prediction = transformer.values[0]
           LOGGER.debug "Prediction is: '" + prediction.to_s + "'."
-          sims = params[:neighbors].collect{ |n| Algorithm.gauss(n[:similarity]) } # similarity values btwn q and nbors
-          conf = sims.inject{|sum,x| sum + x }
-          confidence = conf/params[:neighbors].size if params[:neighbors].size > 0
+          params[:conf_stdev] = "false" if params[:conf_stdev].nil?
+          confidence = get_confidence({:sims => sims, :acts => acts, :neighbors => params[:neighbors], :conf_stdev => params[:conf_stdev]})
           {:prediction => prediction, :confidence => confidence}
-
         rescue Exception => e
           LOGGER.debug "#{e.class}: #{e.message}"
         end
@@ -351,8 +347,8 @@ module OpenTox
           transformer = eval "OpenTox::Algorithm::Transform::#{params[:transform]["class"]}.new ([#{prediction}], #{params[:transform]["offset"]})"
           prediction = transformer.values[0]
           LOGGER.debug "Prediction is: '" + prediction.to_s + "'."
-          conf = sims.inject{|sum,x| sum + x }
-          confidence = conf/params[:neighbors].size
+          params[:conf_stdev] = "false" if params[:conf_stdev].nil?
+          confidence = get_confidence({:sims => sims, :acts => acts, :neighbors => params[:neighbors], :conf_stdev => params[:conf_stdev]})
           {:prediction => prediction, :confidence => confidence}
         rescue Exception => e
           LOGGER.debug "#{e.class}: #{e.message}"
@@ -517,6 +513,29 @@ module OpenTox
           prediction
       end
 
+      # Get confidence for regression, with standard deviation of neighbor activity if conf_stdev is set.
+      # @param[Hash] Required keys: :sims, :acts, :neighbors, :conf_stdev
+      # @return[Float] Confidence
+      def self.get_confidence(params)
+        if params[:conf_stdev] == "true"
+          sim_median = Algorithm.median(params[:sims])
+          if sim_median.nil?
+            confidence = nil
+          else
+            standard_deviation = params[:acts].std_dev
+            confidence = (sim_median*Math.exp(-1*standard_deviation)).abs
+            if confidence.nan?
+              confidence = nil
+            end
+          end
+        else
+          conf = params[:sims].inject{|sum,x| sum + x }
+          confidence = conf/params[:neighbors].size
+        end
+        LOGGER.debug "Confidence is: '" + confidence.to_s + "'."
+        return confidence
+      end
+
       # Get X and Y size of a nested Array (Matrix)
       def self.get_sizes(matrix)
         begin
@@ -545,7 +564,7 @@ module OpenTox
             row = []
             params[:features].each do |f|
               if ! params[:fingerprints][n].nil? 
-                row << (params[:fingerprints][n].include?(f) ? 0.0 : params[:p_values][f])
+                row << (params[:fingerprints][n].include?(f) ? params[:p_values][f] : 0.0)
               else
                 row << 0.0
               end
@@ -778,9 +797,14 @@ module OpenTox
       Math.exp(-(d*d)/(2*sigma*sigma))
     end
 
+    # For symbolic features
+    # @param [Array] Array to test, must indicate non-occurrence with 0.
+    # @return [Boolean] Whether the feature is singular or non-occurring or present everywhere.
     def self.isnull_or_singular?(array)
       nr_zeroes = array.count(0)
-      return ((nr_zeroes == array.size) || (nr_zeroes == 0) || (nr_zeroes == 1) || (nr_zeroes == array.size-1) )
+      return (nr_zeroes == array.size) ||    # remove non-occurring feature
+             (nr_zeroes == array.size-1) ||  # remove singular feature
+             (nr_zeroes == 0)                # also remove feature present everywhere
     end
     
     # Median of an array
@@ -865,6 +889,24 @@ module OpenTox
       p_sum 
     end
                 
+    # Adds variance, mean and standard deviation calculation to Array class
+    module Variance
+      def sum(&blk)
+        map(&blk).inject { |sum, element| sum + element }
+      end
+      def mean
+        (sum.to_f / size.to_f)
+      end
+      def variance
+        m = mean
+        sum { |i| ( i - m )**2 } / (size-1).to_f
+      end
+      def std_dev
+        Math.sqrt(variance)
+      end
+    end
+    Array.send :include, Variance
+
   end
 end
 
diff --git a/lib/validation.rb b/lib/validation.rb
index 3e8367c..646b076 100644
--- a/lib/validation.rb
+++ b/lib/validation.rb
@@ -85,34 +85,27 @@ module OpenTox
       @metadata = YAML.load(OpenTox::RestClientWrapper.get(uri,{:subjectid => subjectid, :accept => "application/x-yaml"}))
     end
     
-    # PENDING: creates summary as used for ToxCreate
-    def summary
-      if @metadata[OT.classificationStatistics]
-        res = {
-          :nr_predictions => @metadata[OT.numInstances].to_i - @metadata[OT.numUnpredicted].to_i,
-          :correct_predictions => @metadata[OT.classificationStatistics][OT.percentCorrect],
-          :weighted_area_under_roc => @metadata[OT.classificationStatistics][OT.weightedAreaUnderRoc],
-        }
-        @metadata[OT.classificationStatistics][OT.classValueStatistics].each do |s|
-          if s[OT.classValue].to_s=="true"
-            res[:true_positives] = s[OT.numTruePositives]
-            res[:false_positives] = s[OT.numFalsePositives]
-            res[:true_negatives] = s[OT.numTrueNegatives]
-            res[:false_negatives] = s[OT.numFalseNegatives]
-            res[:sensitivity] = s[OT.truePositiveRate]
-            res[:specificity] = s[OT.trueNegativeRate]
-            break
+    # returns confusion matrix as array, predicted values are in rows
+    # example:
+    # [[nil,"active","moderate","inactive"],["active",1,3,99],["moderate",4,2,8],["inactive",3,8,6]]
+    # -> 99 inactive compounds have been predicted as active 
+    def confusion_matrix
+      raise "no classification statistics, probably a regression valdiation" unless @metadata[OT.classificationStatistics]
+      matrix =  @metadata[OT.classificationStatistics][OT.confusionMatrix][OT.confusionMatrixCell]
+      values = matrix.collect{|cell| cell[OT.confusionMatrixPredicted]}.uniq
+      table = [[nil]+values]
+      values.each do |c|
+        table << [c]
+        values.each do |r|
+          matrix.each do |cell|
+            if cell[OT.confusionMatrixPredicted]==c and cell[OT.confusionMatrixActual]==r
+              table[-1] << cell[OT.confusionMatrixValue].to_f
+              break
+            end
           end
         end
-        res
-      elsif @metadata[OT.regressionStatistics]
-        {
-          :nr_predictions => @metadata[OT.numInstances].to_i - @metadata[OT.numUnpredicted].to_i,
-          :r_square => @metadata[OT.regressionStatistics][OT.rSquare],
-          :root_mean_squared_error => @metadata[OT.regressionStatistics][OT.rootMeanSquaredError],
-          :mean_absolute_error => @metadata[OT.regressionStatistics][OT.meanAbsoluteError],
-        }
       end
+      table
     end
   end
   
@@ -171,9 +164,9 @@ module OpenTox
       @metadata = YAML.load(OpenTox::RestClientWrapper.get(uri,{:subjectid => subjectid, :accept => "application/x-yaml"}))
     end
     
-    # PENDING: creates summary as used for ToxCreate
-    def summary( subjectid=nil )
-      Validation.from_cv_statistics( @uri, subjectid ).summary
+    # returns a Validation object containing the statistics of the crossavlidation
+    def statistics( subjectid=nil )
+      Validation.from_cv_statistics( @uri, subjectid )
     end
   end