lazar predictions and toxcreate are working

2 files changed, 74 insertions, 54 deletions

diff --git a/fminer.rb b/fminer.rb
index 06b4e67..3e39eda 100644
--- a/fminer.rb
+++ b/fminer.rb
@@ -11,7 +11,6 @@ get '/fminer/?' do
 end
 
 # Get RDF/XML representation of fminer bbrc algorithm
-#
 # @return [application/rdf+xml] OWL-DL representation of fminer bbrc algorithm
 get "/fminer/bbrc/?" do
 	response['Content-Type'] = 'application/rdf+xml'
@@ -23,14 +22,17 @@ get "/fminer/bbrc/?" do
     OT.isA => OTA.PatternMiningSupervised,
     OT.parameters => [
     { DC.description => "Dataset URI", OT.paramScope => "mandatory", DC.title => "dataset_uri" },
-    { DC.description => "Feature URI for dependent variable", OT.paramScope => "mandatory", DC.title => "prediction_feature" }
+    { DC.description => "Feature URI for dependent variable", OT.paramScope => "mandatory", DC.title => "prediction_feature" },
+    { DC.description => "Minimum frequency", OT.paramScope => "optional", DC.title => "minfreq" },
+    { DC.description => "Feature type, can be 'paths' or 'trees'", OT.paramScope => "optional", DC.title => "feature_type" },
+    { DC.description => "BBRC classes, pass 'false' to switch off mining for BBRC representatives.", OT.paramScope => "optional", DC.title => "backbone" },
+    { DC.description => "Significance threshold (between 0 and 1)", OT.paramScope => "optional", DC.title => "min_chisq_significance" },
     ]
   }
   algorithm.to_rdfxml
 end
 
 # Get RDF/XML representation of fminer last algorithm
-#
 # @return [application/rdf+xml] OWL-DL representation of fminer last algorithm
 get "/fminer/last/?" do
   algorithm = OpenTox::Algorithm::Generic.new(url_for('/fminer/last',:full))
@@ -41,7 +43,10 @@ get "/fminer/last/?" do
     OT.isA => OTA.PatternMiningSupervised,
     OT.parameters => [
     { DC.description => "Dataset URI", OT.paramScope => "mandatory", DC.title => "dataset_uri" },
-    { DC.description => "Feature URI for dependent variable", OT.paramScope => "mandatory", DC.title => "prediction_feature" }
+    { DC.description => "Feature URI for dependent variable", OT.paramScope => "mandatory", DC.title => "prediction_feature" },
+    { DC.description => "Minimum frequency", OT.paramScope => "optional", DC.title => "minfreq" },
+    { DC.description => "Feature type, can be 'paths' or 'trees'", OT.paramScope => "optional", DC.title => "feature_type" },
+    { DC.description => "Maximum number of hops", OT.paramScope => "optional", DC.title => "hops" },
     ]
   }
   algorithm.to_rdfxml
@@ -49,18 +54,23 @@ end
 
 # Run bbrc algorithm on dataset
 #
-# @param [URI] dataset_uri URI of the training dataset
-# @param [URI] prediction_feature URI of the prediction feature (i.e. dependent variable)
-# @param [optional, Integer] min_frequency minimum frequency (defaults to 5)
+# @param [String] dataset_uri URI of the training dataset
+# @param [String] prediction_feature URI of the prediction feature (i.e. dependent variable)
+# @param [optional] parameters BBRC parameters, accepted parameters are
+#   - minfreq  Minimum frequency (default 5)
+#   - feature_type Feature type, can be 'paths' or 'trees' (default "trees")
+#   - backbone BBRC classes, pass 'false' to switch off mining for BBRC representatives. (default "true")
+#   - min_chisq_significance Significance threshold (between 0 and 1)
 # @return [text/uri-list] Task URI
 post '/fminer/bbrc/?' do 
-#['/fminer/bbrc/?','/fminer/?'].each do |path| # AM LAST: set bbrc as default
-  #post path do
     
     # TODO: is this thread safe??
     @@fminer = Bbrc::Bbrc.new 
     minfreq = 5 unless minfreq = params[:min_frequency]
     @@fminer.SetMinfreq(minfreq)
+    @@fminer.SetType(1) if params[:feature_type] == "paths"
+    @@fminer.SetBackbone(params[:backbone]) if params[:backbone]
+    @@fminer.SetChisqSig(params[:min_chisq_significance]) if params[:min_chisq_significance]
     @@fminer.SetConsoleOut(false)
 
     halt 404, "Please submit a dataset_uri." unless params[:dataset_uri] and  !params[:dataset_uri].nil?
@@ -70,7 +80,7 @@ post '/fminer/bbrc/?' do
     training_dataset = OpenTox::Dataset.find "#{params[:dataset_uri]}"
     halt 404, "No feature #{params[:prediction_feature]} in dataset #{params[:dataset_uri]}" unless training_dataset.features and training_dataset.features.include?(params[:prediction_feature])
 
-    task_uri = OpenTox::Task.as_task("Mining BBRC features", url_for('/fminer',:full)) do 
+    task = OpenTox::Task.create("Mining BBRC features", url_for('/fminer',:full)) do 
 
       feature_dataset = OpenTox::Dataset.new
       feature_dataset.add_metadata({
@@ -193,19 +203,26 @@ post '/fminer/bbrc/?' do
       feature_dataset.uri
     end
     response['Content-Type'] = 'text/uri-list'
-    halt 202,task_uri.to_s+"\n"
+    halt 202,task.uri.to_s+"\n"
   end
 #end
 
 # Run last algorithm on a dataset
 #
-# @param [URI] dataset_uri URI of the training dataset
-# @param [URI] prediction_feature URI of the prediction feature (i.e. dependent variable)
+# @param [String] dataset_uri URI of the training dataset
+# @param [String] prediction_feature URI of the prediction feature (i.e. dependent variable)
+# @param [optional] parameters LAST parameters, accepted parameters are
+#   - minfreq  Minimum frequency (default 5)
+#   - feature_type Feature type, can be 'paths' or 'trees' (default "trees")
+#   - hops Maximum number of hops
 # @return [text/uri-list] Task URI
 post '/fminer/last/?' do
 
   @@fminer = Last::Last.new 
-  @@fminer.SetMinfreq(5)
+  minfreq = 5 unless minfreq = params[:min_frequency]
+  @@fminer.SetMinfreq(minfreq)
+  @@fminer.SetType(1) if params[:feature_type] == "paths"
+  @@fminer.SetMaxHops(params[:hops]) if params[:hops]
   @@fminer.SetConsoleOut(false)
 
   halt 404, "Please submit a dataset_uri." unless params[:dataset_uri] and  !params[:dataset_uri].nil?
@@ -216,7 +233,7 @@ post '/fminer/last/?' do
   training_dataset.load_all
   halt 404, "No feature #{params[:prediction_feature]} in dataset #{params[:dataset_uri]}" unless training_dataset.features and training_dataset.features.include?(params[:prediction_feature])
 
-  task_uri = OpenTox::Task.as_task("Mining LAST features", url_for('/fminer',:full)) do 
+  task = OpenTox::Task.create("Mining LAST features", url_for('/fminer',:full)) do 
 
     feature_dataset = OpenTox::Dataset.new
     feature_dataset.add_metadata({
@@ -327,5 +344,5 @@ post '/fminer/last/?' do
     feature_dataset.uri
   end
   response['Content-Type'] = 'text/uri-list'
-  halt 202,task_uri.to_s+"\n"
+  halt 202,task.uri.to_s+"\n"
 end
diff --git a/lazar.rb b/lazar.rb
index e1b9846..c5a9259 100644
--- a/lazar.rb
+++ b/lazar.rb
@@ -1,7 +1,6 @@
 @@feature_generation_default = File.join(CONFIG[:services]["opentox-algorithm"],"fminer","bbrc")
 
 # Get RDF/XML representation of the lazar algorithm
-#
 # @return [application/rdf+xml] OWL-DL representation of the lazar algorithm
 get '/lazar/?' do
 	response['Content-Type'] = 'application/rdf+xml'
@@ -23,20 +22,18 @@ get '/lazar/?' do
 end
 
 # Create a lazar prediction model
-#
+# @param [String] dataset_uri Training dataset URI
+# @param [optional,String] prediction_feature URI of the feature to be predicted
+# @param [optional,String] feature_generation_uri URI of the feature generation algorithm 
+# @param [optional] - further parameters for the feature generation service 
 # @ return [text/uri-list] Task URI 
 post '/lazar/?' do 
 
-  LOGGER.debug params.inspect
   halt 404, "No dataset_uri parameter." unless params[:dataset_uri]
 	dataset_uri = params[:dataset_uri]
 
-	begin
-		training_activities = OpenTox::Dataset.new(dataset_uri)
-    training_activities.load_all
-	rescue => e
-		halt 404, "Dataset #{dataset_uri} not found (#{e.inspect})." 
-  end
+  halt 404, "Dataset #{dataset_uri} not found." unless training_activities = OpenTox::Dataset.new(dataset_uri)
+  training_activities.load_all
 
   prediction_feature = params[:prediction_feature]
   unless prediction_feature # try to read prediction_feature from dataset
@@ -51,23 +48,24 @@ post '/lazar/?' do
     training_activities.features.inspect+")" unless training_activities.features and training_activities.features.include?(prediction_feature)
 
   response['Content-Type'] = 'text/uri-list' 
-  task_uri = OpenTox::Task.as_task("Create lazar model",url_for('/lazar',:full)) do |task|
+  task = OpenTox::Task.create("Create lazar model",url_for('/lazar',:full)) do |task|
 
 		lazar = OpenTox::Model::Lazar.new
+    lazar.min_sim = params[:min_sim] if params[:min_sim] 
 
 		if params[:feature_dataset_uri]
       feature_dataset_uri = params[:feature_dataset_uri]
       training_features = OpenTox::Dataset.new(feature_dataset_uri)
       case training_features.feature_type
       when "classification"
-        lazar.similarity_algorithm = "weighted_tanimoto"
+        lazar.similarity_algorithm = "Similarity.tanimoto"
       when "regression"
-        lazar.similarity_algorithm = "weighted_euclid"
+        lazar.similarity_algorithm = "Similarity.euclid"
       end
     else # create features
       params[:feature_generation_uri] = feature_generation_uri
       if feature_generation_uri.match(/fminer/)
-        lazar.feature_calculation_algorithm = "substructure_match"
+        lazar.feature_calculation_algorithm = "Substructure.match"
       else
         halt 404, "External feature generation services not yet supported"
       end
@@ -82,11 +80,9 @@ post '/lazar/?' do
     lazar.features = training_features.features.sort if training_features.feature_type == "regression"
 
     training_features.data_entries.each do |compound,entry|
-			lazar.fingerprints[compound] = [] unless lazar.fingerprints[compound]
+      lazar.fingerprints[compound] = [] unless lazar.fingerprints[compound]
       entry.keys.each do |feature|
-        case training_features.feature_type
-        when "fminer"
-          # fingerprints are sets
+        if feature_generation_uri.match(/fminer/)
           smarts = training_features.features[feature][OT.smarts]
           lazar.fingerprints[compound] << smarts
           unless lazar.features.include? smarts
@@ -94,20 +90,23 @@ post '/lazar/?' do
             lazar.p_values[smarts] = training_features.features[feature][OT.p_value]
             lazar.effects[smarts] = training_features.features[feature][OT.effect]
           end
-        when "classification"
-          # fingerprints are sets
-          if entry[feature].flatten.size == 1
-            lazar.fingerprints[compound] << feature if entry[feature].flatten.first.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
-          else
-            LOGGER.warn "More than one entry (#{entry[feature].inspect}) for compound #{compound}, feature #{feature}"
+        else
+          case training_features.feature_type
+          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.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
+            else
+              LOGGER.warn "More than one entry (#{entry[feature].inspect}) for compound #{compound}, feature #{feature}"
+            end
           end
         end
       end
@@ -120,26 +119,30 @@ post '/lazar/?' do
 				when "false"
 					lazar.activities[compound] << false
 				else 
+          halt 404, "0 values not allowed in training dataset. log10 is calculated internally." if value.to_f == 0
 					lazar.activities[compound] << value.to_f
-          lazar.prediction_type = "regression"
+          lazar.prediction_algorithm = "Neighbors.local_svm_regression"
 				end
 			end
     end
 
+    lazar.metadata[DC.title] = "lazar model for #{URI.decode(File.basename(prediction_feature))}"
+    # TODO: fix dependentVariable
     lazar.metadata[OT.dependentVariables] = params[:prediction_feature]
     lazar.metadata[OT.trainingDataset] = dataset_uri
 		lazar.metadata[OT.featureDataset] = feature_dataset_uri
+    lazar.metadata[OT.isA] = OTA.ClassificationLazySingleTarget
 
-    lazar.parameters = {
-      "dataset_uri" => dataset_uri,
-      "prediction_feature" => prediction_feature,
-      "feature_generation_uri" => feature_generation_uri
-    }
+    lazar.metadata[OT.parameters] = [
+      {DC.title => "dataset_uri", OT.paramValue => dataset_uri},
+      {DC.title => "prediction_feature", OT.paramValue => prediction_feature},
+      {DC.title => "feature_generation_uri", OT.paramValue => feature_generation_uri}
+    ]
 		
 		model_uri = lazar.save
 		LOGGER.info model_uri + " created #{Time.now}"
     model_uri
 	end
-  halt 202,task_uri
+  halt 202,task.uri
 end