Merge branch 'development' into reg_conf

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

4 files changed, 67 insertions, 160 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 43845fb..cfca069 100644
--- a/lib/algorithm.rb
+++ b/lib/algorithm.rb
@@ -205,21 +205,17 @@ 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
@@ -326,19 +322,9 @@ 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 + "'."
-          sim_median = Algorithm.median(sims)
-          if sim_median.nil?
-            confidence = nil
-            LOGGER.debug "dv ------------ sim_median is nil"
-          else
-            standard_deviation = acts.std_dev
-            confidence = (sim_median*Math.exp(-1*standard_deviation)).abs
-            if confidence.nan?
-              confidence = nil
-            end
-          end
-          LOGGER.debug "Confidence is: '" + confidence.to_s + "'."
-          return {:prediction => prediction, :confidence => confidence}
+          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}"
           LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
@@ -502,6 +488,29 @@ 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
@@ -840,7 +849,7 @@ module OpenTox
       end
       def variance
         m = mean
-        sum { |i| ( i - m )**2 } / size
+        sum { |i| ( i - m )**2 } / (size-1).to_f
       end
       def std_dev
         Math.sqrt(variance)
diff --git a/lib/model.rb b/lib/model.rb
index 825f697..13212ee 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -91,7 +91,7 @@ module OpenTox
       include Algorithm
       include Model
 
-      attr_accessor :compound, :prediction_dataset, :features, :effects, :activities, :p_values, :fingerprints, :feature_calculation_algorithm, :similarity_algorithm, :prediction_algorithm, :min_sim, :subjectid, :prop_kernel, :value_map, :balanced
+      attr_accessor :compound, :prediction_dataset, :features, :effects, :activities, :p_values, :fingerprints, :feature_calculation_algorithm, :similarity_algorithm, :prediction_algorithm, :min_sim, :subjectid, :prop_kernel, :value_map, :transform
 
       def initialize(uri=nil)
 
@@ -116,7 +116,7 @@ module OpenTox
 
         @min_sim = 0.3
         @prop_kernel = false
-        @balanced = false
+        @transform = { "class" => "NOP"  }
 
       end
 
@@ -212,78 +212,17 @@ module OpenTox
 
         unless database_activity(subjectid) # adds database activity to @prediction_dataset
 
-          if @balanced && OpenTox::Feature.find(metadata[OT.dependentVariables]).feature_type == "classification"
-            # AM: Balancing, see http://www.maunz.de/wordpress/opentox/2011/balanced-lazar
-            l = Array.new # larger 
-            s = Array.new # smaller fraction
+          neighbors
+          prediction = eval("#{@prediction_algorithm} ( { :neighbors => @neighbors, 
+                                                          :compound => @compound,
+                                                          :features => @features, 
+                                                          :p_values => @p_values, 
+                                                          :fingerprints => @fingerprints,
+                                                          :similarity_algorithm => @similarity_algorithm, 
+                                                          :prop_kernel => @prop_kernel,
+                                                          :value_map => @value_map, 
+                                                          :transform => @transform } ) ")
 
-            raise "no fingerprints in model" if @fingerprints.size==0
-
-            @fingerprints.each do |training_compound,training_features|
-              @activities[training_compound].each do |act|
-                case act.to_s
-                when "0" 
-                  l << training_compound
-                when "1"  
-                  s << training_compound
-                else
-                  LOGGER.warn "BLAZAR: Activity #{act.to_s} should not be reached (supports only two classes)."
-                end
-              end
-            end
-            if s.size > l.size then 
-              l,s = s,l # happy swapping
-              LOGGER.info "BLAZAR: |s|=#{s.size}, |l|=#{l.size}."
-            end
-            # determine ratio
-            modulo = l.size.divmod(s.size)# modulo[0]=ratio, modulo[1]=rest
-            LOGGER.info "BLAZAR: Balance: #{modulo[0]}, rest #{modulo[1]}."
-
-            # AM: Balanced predictions
-            addon = (modulo[1].to_f/modulo[0]).ceil # what will be added in each round 
-            slack = (addon!=0 ? modulo[1].divmod(addon)[1] : 0) # what remains for the last round
-            position = 0
-            predictions = Array.new
-
-            prediction_best=nil
-            neighbors_best=nil
-
-            begin
-              for i in 1..modulo[0] do
-                (i == modulo[0]) && (slack>0) ? lr_size = s.size + slack : lr_size = s.size + addon  # determine fraction
-                LOGGER.info "BLAZAR: Neighbors round #{i}: #{position} + #{lr_size}."
-                neighbors_balanced(s, l, position, lr_size) # get ratio fraction of larger part
-                if @prop_kernel && ( @prediction_algorithm.include?("svm") || @prediction_algorithm.include?("local_mlr_prop") )
-                  props = get_props 
-                else
-                  props = nil
-                end
-                prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values, :value_map => @value_map}, props)")
-                if prediction_best.nil? || prediction[:confidence].abs > prediction_best[:confidence].abs 
-                  prediction_best=prediction 
-                  neighbors_best=@neighbors
-                end
-                position = position + lr_size
-              end
-            rescue Exception => e
-              LOGGER.error "BLAZAR failed in prediction: "+e.class.to_s+": "+e.message
-            end
-
-            prediction=prediction_best
-            @neighbors=neighbors_best
-            ### END AM balanced predictions
-
-          else # AM: no balancing or regression
-            LOGGER.info "LAZAR: Unbalanced."
-            neighbors
-            if @prop_kernel && ( @prediction_algorithm.include?("svm") || @prediction_algorithm.include?("local_mlr_prop") )
-             props = get_props 
-            else
-             props = nil
-            end
-            prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values, :value_map => @value_map}, props)")
-          end
-          
           value_feature_uri = File.join( @uri, "predicted", "value")
           confidence_feature_uri = File.join( @uri, "predicted", "confidence")
 
@@ -356,43 +295,7 @@ module OpenTox
         @prediction_dataset
       end
 
-      # Calculate the propositionalization matrix aka instantiation matrix (0/1 entries for features)
-      # Same for the vector describing the query compound
-      def get_props
-        matrix = Array.new
-        begin 
-          @neighbors.each do |n|
-            n = n[:compound]
-            row = []
-            @features.each do |f|
-              if ! @fingerprints[n].nil? 
-                row << (@fingerprints[n].include?(f) ? 0.0 : @p_values[f])
-              else
-                row << 0.0
-              end
-            end
-            matrix << row
-          end
-          row = []
-          @features.each do |f|
-            row << (@compound.match([f]).size == 0 ? 0.0 : @p_values[f])
-          end
-        rescue Exception => e
-          LOGGER.debug "get_props failed with '" + $! + "'"
-        end
-        [ matrix, row ]
-      end
-
-      # Find neighbors and store them as object variable, access only a subset of compounds for that.
-      def neighbors_balanced(s, l, start, offset)
-        @compound_features = eval("#{@feature_calculation_algorithm}(@compound,@features)") if @feature_calculation_algorithm
-        @neighbors = []
-        [ l[start, offset ] , s ].flatten.each do |training_compound| # AM: access only a balanced subset
-          training_features = @fingerprints[training_compound]
-          add_neighbor training_features, training_compound
-        end
-
-      end
+      
 
       # Find neighbors and store them as object variable, access all compounds for that.
       def neighbors
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