nanoparticle crossvalidation technically working

3 files changed, 11 insertions, 11 deletions

diff --git a/lib/crossvalidation.rb b/lib/crossvalidation.rb
index 50afb6f..0ae36c4 100644
--- a/lib/crossvalidation.rb
+++ b/lib/crossvalidation.rb
@@ -44,7 +44,7 @@ module OpenTox
           $logger.debug "Dataset #{training_dataset.name}, Fold #{fold_nr}:  #{Time.now-t} seconds"
         #end
       end
-      Process.waitall
+      #Process.waitall
       cv.validation_ids = Validation.where(:crossvalidation_id => cv.id).distinct(:_id)
       cv.validations.each do |validation|
         nr_instances += validation.nr_instances
diff --git a/lib/regression.rb b/lib/regression.rb
index 5610a77..3a59c14 100644
--- a/lib/regression.rb
+++ b/lib/regression.rb
@@ -9,6 +9,7 @@ module OpenTox
         neighbors = params[:neighbors]
         neighbors.each do |row|
           sim = row["tanimoto"]
+          sim ||= 1 # TODO: sim f nanoparticles
           if row["toxicities"][params[:prediction_feature_id].to_s]
             row["toxicities"][params[:prediction_feature_id].to_s].each do |act|
               weighted_sum += sim*Math.log10(act)
@@ -120,7 +121,7 @@ module OpenTox
           result[:warning] = "No variables for regression model. Using weighted average of similar compounds."
           return result
         else
-          query_descriptors = pc_ids.collect{|i| compound.physchem_descriptors[i].for_R}
+          query_descriptors = pc_ids.collect{|i| compound.physchem_descriptors[i].for_R if compound.physchem_descriptors[i]}.compact
           remove_idx = []
           query_descriptors.each_with_index do |v,i|
             remove_idx << i if v == "NA"
@@ -172,13 +173,9 @@ rlib = File.expand_path(File.join(File.dirname(__FILE__),"..","R"))
         
         R.eval "data <- #{r_data_frame}"
         R.assign "features", training_features
-        R.eval "names(data) <- append(c('activities'),features)" #
-        #begin
+        begin
+          R.eval "names(data) <- append(c('activities'),features)" #
           R.eval "model <- train(activities ~ ., data = data, method = '#{method}', na.action = na.pass)"
-        #rescue 
-          #return nil
-        #end
-        p query_feature_values
         R.eval "fingerprint <- data.frame(rbind(c(#{query_feature_values.join ','})))"
         R.eval "names(fingerprint) <- features" 
         R.eval "prediction <- predict(model,fingerprint)"
@@ -187,6 +184,9 @@ rlib = File.expand_path(File.join(File.dirname(__FILE__),"..","R"))
           :rmse => R.eval("getTrainPerf(model)$TrainRMSE").to_f,
           :r_squared => R.eval("getTrainPerf(model)$TrainRsquared").to_f,
         }
+        rescue 
+          return nil
+        end
       end
 
     end
diff --git a/lib/validation.rb b/lib/validation.rb
index 6b515e4..68cb1a1 100644
--- a/lib/validation.rb
+++ b/lib/validation.rb
@@ -24,12 +24,12 @@ module OpenTox
 
     def self.create model, training_set, test_set, crossvalidation=nil
       
-      atts = model.attributes.dup # do not modify attributes from original model
+      atts = model.attributes.dup # do not modify attributes of the original model
       atts["_id"] = BSON::ObjectId.new
       atts[:training_dataset_id] = training_set.id
       validation_model = model.class.create model.prediction_feature, training_set, atts
       validation_model.save
-      predictions = validation_model.predict test_set.compounds
+      predictions = validation_model.predict test_set.substances
       predictions.each{|cid,p| p.delete(:neighbors)}
       nr_unpredicted = 0
       predictions.each do |cid,prediction|
@@ -43,7 +43,7 @@ module OpenTox
       validation = self.new(
         :model_id => validation_model.id,
         :test_dataset_id => test_set.id,
-        :nr_instances => test_set.compounds.size,
+        :nr_instances => test_set.substances.size,
         :nr_unpredicted => nr_unpredicted,
         :predictions => predictions#.sort{|a,b| p a; b[3] <=> a[3]} # sort according to confidence
       )