Merge branch 'new_pc_dv' into pc_new_1

1 files changed, 62 insertions, 82 deletions

diff --git a/lazar.rb b/lazar.rb
index 9aac0d8..f69495c 100644
--- a/lazar.rb
+++ b/lazar.rb
@@ -45,45 +45,76 @@ post '/lazar/?' do
 
   task = OpenTox::Task.create("Create lazar model",url_for('/lazar',:full)) do |task|
 
+
+    # # # Dataset present, prediction feature present?
     raise OpenTox::NotFoundError.new "Dataset #{dataset_uri} not found." unless training_activities = OpenTox::Dataset.new(dataset_uri)
     training_activities.load_all(@subjectid)
 
+    # Prediction Feature
     prediction_feature = OpenTox::Feature.find(params[:prediction_feature],@subjectid)
     unless params[:prediction_feature] # try to read prediction_feature from dataset
     raise OpenTox::NotFoundError.new "#{training_activities.features.size} features in dataset #{dataset_uri}. Please provide a  prediction_feature parameter." unless training_activities.features.size == 1
       prediction_feature = OpenTox::Feature.find(training_activities.features.keys.first,@subjectid)
       params[:prediction_feature] = prediction_feature.uri # pass to feature mining service
     end
+    raise OpenTox::NotFoundError.new "No feature #{prediction_feature.uri} in dataset #{params[:dataset_uri]}. (features: "+ training_activities.features.inspect+")" unless training_activities.features and training_activities.features.include?(prediction_feature.uri)
     
-    feature_generation_uri = @@feature_generation_default unless feature_generation_uri = params[:feature_generation_uri]
-
-    raise OpenTox::NotFoundError.new "No feature #{prediction_feature.uri} in dataset #{params[:dataset_uri]}. (features: "+
-      training_activities.features.inspect+")" unless training_activities.features and training_activities.features.include?(prediction_feature.uri)
+    # Feature Generation URI
+    feature_generation_uri = @@feature_generation_default unless ( (feature_generation_uri = params[:feature_generation_uri]) || (params[:feature_dataset_uri]) )
 
+    # Create instance
 		lazar = OpenTox::Model::Lazar.new
-    lazar.min_sim = params[:min_sim].to_f if params[:min_sim]
     
 
 
 
-    # AM: Manage endpoint related variables.
+    # # # ENDPOINT RELATED
+    
+    # Default Values
+    # Classification: Weighted Majority, Substructure.match
     if prediction_feature.feature_type == "classification"
       @training_classes = training_activities.accept_values(prediction_feature.uri).sort
       @training_classes.each_with_index { |c,i|
         lazar.value_map[i+1] = c # don't use '0': we must take the weighted mean later.
         params[:value_map] = lazar.value_map
       }
+    # Regression: SVM, Substructure.match_hits
     elsif  prediction_feature.feature_type == "regression"
-      lazar.nr_hits = true
+      #lazar.nr_hits = true # AM: Brauchen wir die Variable noch? Kann man an feature_calculation_algorithm auch ablesen (nĂchste Zeile)
+      lazar.feature_calculation_algorithm = "Substructure.match_hits" 
       lazar.prediction_algorithm = "Neighbors.local_svm_regression" 
     end
 
+
+
+
+    # # # USER VALUES
+    
+    # Min Sim
+    lazar.min_sim = params[:min_sim].to_f if params[:min_sim]
+
+    # Nr Hits
     if params[:nr_hits] == "false" # if nr_hits is set optional to true/false it will return as String (but should be True/FalseClass)
-      lazar.nr_hits = false
+      #lazar.nr_hits = false
+      lazar.feature_calculation_algorithm = "Substructure.match"
     elsif params[:nr_hits] == "true"
-      lazar.nr_hits = true
+      #lazar.nr_hits = true
+      lazar.feature_calculation_algorithm = "Substructure.match_hits"
     end
-    params[:nr_hits] = "true" if lazar.nr_hits
+    params[:nr_hits] = "true" if lazar.feature_calculation_algorithm == "Substructure.match_hits" #not sure if this line in needed 
+
+    # Algorithm
+    lazar.prediction_algorithm = "Neighbors.#{params[:prediction_algorithm]}" unless params[:prediction_algorithm].nil?
+
+    # Propositionalization
+    lazar.prop_kernel = true if (params[:local_svm_kernel] == "propositionalized" || params[:prediction_algorithm] == "local_mlr_prop")
+   
+    # PC type
+    lazar.pc_type = params[:pc_type] unless params[:pc_type].nil?
+
+    # Conf_stdev
+    lazar.conf_stdev = ( (params[:conf_stdev] == "true") ? true : false ) 
+ 
 
 
 
@@ -96,29 +127,20 @@ post '/lazar/?' do
 
 
 
-    # 
-    # AM: features
-    # 
-    # 
-    # 
+    # # # Features
 
-    # READ OR CREATE
+    # Read Features
     if params[:feature_dataset_uri]
+      lazar.feature_calculation_algorithm = "Substructure.lookup"
       feature_dataset_uri = params[:feature_dataset_uri]
       training_features = OpenTox::Dataset.new(feature_dataset_uri)
-      case training_features.feature_type(@subjectid)
-      when "classification"
-        lazar.similarity_algorithm = "Similarity.tanimoto"
-      when "regression"
-        lazar.similarity_algorithm = "Similarity.euclid"
+      if training_features.feature_type(@subjectid) == "regression"
+        lazar.similarity_algorithm = "Similarity.cosine"
       end
-    else # create features
+
+    # Create Features
+    else 
       params[:feature_generation_uri] = feature_generation_uri
-      if feature_generation_uri.match(/fminer/)
-        lazar.feature_calculation_algorithm = "Substructure.match"
-      else
-        raise OpenTox::NotFoundError.new "External feature generation services not yet supported"
-      end
       params[:subjectid] = @subjectid
       prediction_feature = OpenTox::Feature.find params[:prediction_feature], @subjectid
       if prediction_feature.feature_type == "regression" && feature_generation_uri.match(/fminer/) 
@@ -130,27 +152,23 @@ post '/lazar/?' do
 
 
 
-    # WRITE IN MODEL
+    # # # Write fingerprints
     training_features.load_all(@subjectid)
 		raise OpenTox::NotFoundError.new "Dataset #{feature_dataset_uri} not found." if training_features.nil?
 
-    # sorted features for index lookups
-
-    lazar.features = training_features.features.sort if prediction_feature.feature_type == "regression" and lazar.feature_calculation_algorithm != "Substructure.match"
-
     training_features.data_entries.each do |compound,entry|
       lazar.fingerprints[compound] = {} unless lazar.fingerprints[compound]
       entry.keys.each do |feature|
 
         # CASE 1: Substructure
-        if lazar.feature_calculation_algorithm == "Substructure.match"
+        if lazar.feature_calculation_algorithm == "Substructure.match" || lazar.feature_calculation_algorithm == "Substructure.match_hits"
           if training_features.features[feature]
             smarts = training_features.features[feature][OT.smarts]
             #lazar.fingerprints[compound] << smarts
-            if params[:nr_hits]
-              lazar.fingerprints[compound][smarts] = entry[feature].flatten.first
+            if lazar.feature_calculation_algorithm == "Substructure.match_hits"
+              lazar.fingerprints[compound][smarts] = entry[feature].flatten.first * training_features.features[feature][OT.pValue]
             else
-              lazar.fingerprints[compound][smarts] = 1
+              lazar.fingerprints[compound][smarts] = 1 * training_features.features[feature][OT.pValue]
             end
             unless lazar.features.include? smarts
               lazar.features << smarts
@@ -160,26 +178,11 @@ post '/lazar/?' do
           end
 
         # CASE 2: Others
+        elsif entry[feature].flatten.size == 1
+          lazar.fingerprints[compound][feature] = entry[feature].flatten.first
+          lazar.features << feature unless lazar.features.include? feature
         else
-          case training_features.feature_type(@subjectid)
-          when "classification"
-            # fingerprints are sets
-            if entry[feature].flatten.size == 1
-              #lazar.fingerprints[compound] << feature if entry[feature].flatten.first.to_s.match(TRUE_REGEXP)
-              lazar.fingerprints[compound][feature] = entry[feature].flatten.first if entry[feature].flatten.first.to_s.match(TRUE_REGEXP)
-              lazar.features << feature unless lazar.features.include? feature
-            else
-              LOGGER.warn "More than one entry (#{entry[feature].inspect}) for compound #{compound}, feature #{feature}"
-            end
-          when "regression"
-            # fingerprints are arrays
-            if entry[feature].flatten.size == 1
-              lazar.fingerprints[compound][lazar.features.index(feature)] = entry[feature].flatten.first
-              #lazar.fingerprints[compound][feature] = entry[feature].flatten.first
-            else
-              LOGGER.warn "More than one entry (#{entry[feature].inspect}) for compound #{compound}, feature #{feature}"
-            end
-          end
+          LOGGER.warn "More than one entry (#{entry[feature].inspect}) for compound #{compound}, feature #{feature}"
         end
       end
     end
@@ -188,28 +191,8 @@ post '/lazar/?' do
 
 
 
-
-    # 
-    # AM: SETTINGS
-    # 
-    # 
-    # 
-
-    # AM: allow settings override by user
-    lazar.prediction_algorithm = "Neighbors.#{params[:prediction_algorithm]}" unless params[:prediction_algorithm].nil?
-    lazar.prop_kernel = true if (params[:local_svm_kernel] == "propositionalized" || params[:prediction_algorithm] == "local_mlr_prop")
-    lazar.conf_stdev = false
-    lazar.conf_stdev = true if params[:conf_stdev] == "true"
-
-
-
-
-
-    # 
-    # AM: Feed data
-    # 
-    # 
-    # 
+    
+    # # # Activities
   
     if prediction_feature.feature_type == "regression"
       training_activities.data_entries.each do |compound,entry| 
@@ -235,11 +218,7 @@ post '/lazar/?' do
 
 
 
-    # 
-    # AM: Metadata
-    # 
-    # 
-    # 
+    # Metadata
 
     lazar.metadata[DC.title] = "lazar model for #{URI.decode(File.basename(prediction_feature.uri))}"
     lazar.metadata[OT.dependentVariables] = prediction_feature.uri
@@ -261,6 +240,7 @@ post '/lazar/?' do
 		model_uri = lazar.save(@subjectid)
 		LOGGER.info model_uri + " created #{Time.now}"
     model_uri
+
 	end
   response['Content-Type'] = 'text/uri-list' 
   raise OpenTox::ServiceUnavailableError.newtask.uri+"\n" if task.status == "Cancelled"