nano caret regression fixed

4 files changed, 31 insertions, 259 deletions

diff --git a/lib/lazar.rb b/lib/lazar.rb
index d0f05c0..f251379 100644
--- a/lib/lazar.rb
+++ b/lib/lazar.rb
@@ -83,6 +83,7 @@ CLASSES = ["Feature","Substance","Dataset","LazarPrediction","CrossValidation","
   "model.rb",
   "classification.rb",
   "regression.rb",
+  "caret.rb",
   "validation-statistics.rb",
   "validation.rb",
   "train-test-validation.rb",
diff --git a/lib/model.rb b/lib/model.rb
index a272580..290309a 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -23,10 +23,12 @@ module OpenTox
         # explicit prediction algorithm
         if algorithms[:prediction] and algorithms[:prediction][:method]
           case algorithms[:prediction][:method]
-          when /Classifiction/
+          when /Classification/i
             model = LazarClassification.new
-          when /Regression/
+          when /Regression/i
             model = LazarRegression.new 
+          else
+            bad_request_error "Prediction method '#{algorithms[:prediction][:method]}' not implemented."
           end
 
         # guess model type
@@ -36,6 +38,10 @@ module OpenTox
           model = LazarClassification.new
         end
 
+        model.prediction_feature_id = prediction_feature.id
+        model.training_dataset_id = training_dataset.id
+        model.name = "#{training_dataset.name} #{prediction_feature.name}" 
+
         # set defaults
         substance_classes = training_dataset.substances.collect{|s| s.class.to_s}.uniq
         bad_request_error "Cannot create models for mixed substance classes '#{substance_classes.join ', '}'." unless substance_classes.size == 1
@@ -60,7 +66,7 @@ module OpenTox
             }
           elsif model.class == LazarRegression
             model.algorithms[:prediction] = {
-              :method => "Algorithm::Regression.caret",
+              :method => "Algorithm::Caret.regression",
               :parameters => "pls",
             }
           end
@@ -77,7 +83,7 @@ module OpenTox
               :min => 0.5
             },
             :prediction => {
-              :method => "Algorithm::Regression.caret",
+              :method => "Algorithm::Caret.regression",
               :parameters => "rf",
             },
             :feature_selection => {
@@ -100,10 +106,6 @@ module OpenTox
           end
         end
 
-        model.prediction_feature_id = prediction_feature.id
-        model.training_dataset_id = training_dataset.id
-        model.name = "#{training_dataset.name} #{prediction_feature.name}" 
-
         if model.algorithms[:feature_selection] and model.algorithms[:feature_selection][:method]
           model.relevant_features = Algorithm.run model.algorithms[:feature_selection][:method], dataset: training_dataset, prediction_feature: prediction_feature, types: model.algorithms[:descriptors][:types]
         end
@@ -151,8 +153,12 @@ module OpenTox
           else
             bad_request_error "Descriptor method '#{algorithms[:descriptors][:method]}' not available."
           end
-          params = algorithms[:prediction].merge({:descriptors => descriptors, :neighbors => neighbors})
-          params.delete :method
+          params = {
+            :method => algorithms[:prediction][:parameters],
+            :descriptors => descriptors,
+            :neighbors => neighbors,
+            :relevant_features => relevant_features
+          }
           result = Algorithm.run algorithms[:prediction][:method], params
           prediction.merge! result
           prediction[:neighbors] = neighbors
@@ -218,11 +224,9 @@ module OpenTox
     end
 
     class LazarClassification < Lazar
-
     end
 
     class LazarRegression < Lazar
-
     end
 
     class Prediction
@@ -240,7 +244,7 @@ module OpenTox
       field :leave_one_out_validation_id, type: BSON::ObjectId
 
       def predict object
-        Lazar.find(model_id).predict object
+        model.predict object
       end
 
       def training_dataset
@@ -251,6 +255,10 @@ module OpenTox
         Lazar.find model_id
       end
 
+      def prediction_feature
+        model.prediction_feature
+      end
+
       def repeated_crossvalidation
         Validation::RepeatedCrossValidation.find repeated_crossvalidation_id
       end
@@ -276,15 +284,8 @@ module OpenTox
         bad_request_error "No metadata file #{metadata_file}" unless File.exist? metadata_file
         prediction_model = self.new JSON.parse(File.read(metadata_file))
         training_dataset = Dataset.from_csv_file file
-        prediction_feature = training_dataset.features.first
-        model = nil
-        if prediction_feature.nominal?
-          model = LazarClassification.create prediction_feature, training_dataset
-        elsif prediction_feature.numeric?
-          model = LazarRegression.create prediction_feature, training_dataset
-        end
+        model = Lazar.create training_dataset: training_dataset
         prediction_model[:model_id] = model.id
-        prediction_model[:prediction_feature_id] = prediction_feature.id
         prediction_model[:repeated_crossvalidation_id] = Validation::RepeatedCrossValidation.create(model).id
         #prediction_model[:leave_one_out_validation_id] = Validation::LeaveOneOut.create(model).id
         prediction_model.save
@@ -297,26 +298,19 @@ module OpenTox
 
       def self.from_json_dump dir, category
         Import::Enanomapper.import dir
-
+        training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
+        unless training_dataset
+          Import::Enanomapper.import File.join(File.dirname(__FILE__),"data","enm")
+          training_dataset = Dataset.where(name: "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
+        end
         prediction_model = self.new(
           :endpoint => "log2(Net cell association)",
           :source => "https://data.enanomapper.net/",
           :species => "A549 human lung epithelial carcinoma cells",
           :unit => "log2(ug/Mg)"
         )
-        params = {
-          :feature_selection_algorithm => :correlation_filter,
-          :feature_selection_algorithm_parameters => {:category => category},
-          :neighbor_algorithm => "physchem_neighbors",
-          :neighbor_algorithm_parameters => {:min_sim => 0.5},
-          :prediction_algorithm => "OpenTox::Algorithm::Regression.physchem_regression",
-          :prediction_algorithm_parameters => {:method => 'rf'}, # random forests
-          } 
-        training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
-        prediction_feature = Feature.find_or_create_by(name: "log2(Net cell association)", category: "TOX")
-        #prediction_feature = Feature.find("579621b84de73e267b414e55")
-        prediction_model[:prediction_feature_id] = prediction_feature.id
-        model = Model::LazarRegression.create(prediction_feature, training_dataset, params)
+        prediction_feature = Feature.where(name: "log2(Net cell association)", category: "TOX").first
+        model = Model::LazarRegression.create(prediction_feature: prediction_feature, training_dataset: training_dataset)
         prediction_model[:model_id] = model.id
         repeated_cv = Validation::RepeatedCrossValidation.create model
         prediction_model[:repeated_crossvalidation_id] = Validation::RepeatedCrossValidation.create(model).id
diff --git a/lib/regression.rb b/lib/regression.rb
index 396c9e4..cf6d9cb 100644
--- a/lib/regression.rb
+++ b/lib/regression.rb
@@ -19,226 +19,6 @@ module OpenTox
         {:value => prediction}
       end
 
-      def self.caret descriptors:, neighbors:, method: "pls", parameters:nil
-        values = []
-        descriptors = {}
-        weights = []
-        descriptor_ids = neighbors.collect{|n| n["descriptors"]}.flatten.uniq.sort
-
-        neighbors.each do |n|
-          activities = n["measurements"]
-          activities.each do |act|
-            values << act
-            weights << n["similarity"]
-            descriptor_ids.each do |id|
-              descriptors[id] ||= []
-              descriptors[id] << n["descriptors"].include?(id) 
-            end
-          end if activities
-        end
-
-        variables = []
-        data_frame = [values]
-
-        descriptors.each do |k,v| 
-          unless v.uniq.size == 1
-            data_frame << v.collect{|m| m ? "T" : "F"}
-            variables << k
-          end
-        end
-
-        if variables.empty?
-          prediction = weighted_average(descriptors: descriptors, neighbors: neighbors)
-          prediction[:warning] = "No variables for regression model. Using weighted average of similar substances."
-          prediction
-        else
-          substance_features = variables.collect{|f| descriptors.include?(f) ? "T" : "F"} 
-          #puts data_frame.to_yaml
-          prediction = r_model_prediction method, data_frame, variables, weights, substance_features
-          if prediction.nil? or prediction[:value].nil?
-            prediction = weighted_average(descriptors: descriptors, neighbors: neighbors)
-            prediction[:warning] = "Could not create local caret model. Using weighted average of similar substances."
-            prediction
-          else
-            prediction[:prediction_interval] = [prediction[:value]-1.96*prediction[:rmse], prediction[:value]+1.96*prediction[:rmse]]
-            prediction[:value] = prediction[:value]
-            prediction[:rmse] = prediction[:rmse]
-            prediction
-          end
-        end
-      
-      end
-
-      def self.fingerprint_regression substance:, neighbors:, method: "pls" #, method_params="sigma=0.05"
-        values = []
-        fingerprints = {}
-        weights = []
-        fingerprint_ids = neighbors.collect{|n| Compound.find(n["_id"]).fingerprint}.flatten.uniq.sort
-
-        neighbors.each do |n|
-          fingerprint = Substance.find(n["_id"]).fingerprint
-          activities = n["measurements"]
-          activities.each do |act|
-            values << act
-            weights << n["similarity"]
-            fingerprint_ids.each do |id|
-              fingerprints[id] ||= []
-              fingerprints[id] << fingerprint.include?(id) 
-            end
-          end if activities
-        end
-
-        variables = []
-        data_frame = [values]
-
-        fingerprints.each do |k,v| 
-          unless v.uniq.size == 1
-            data_frame << v.collect{|m| m ? "T" : "F"}
-            variables << k
-          end
-        end
-
-        if variables.empty?
-          prediction = weighted_average(substance: substance, neighbors: neighbors)
-          prediction[:warning] = "No variables for regression model. Using weighted average of similar substances."
-          prediction
-        else
-          substance_features = variables.collect{|f| substance.fingerprint.include?(f) ? "T" : "F"} 
-          prediction = r_model_prediction method, data_frame, variables, weights, substance_features
-          if prediction.nil? or prediction[:value].nil?
-            prediction = weighted_average(substance: substance, neighbors: neighbors)
-            prediction[:warning] = "Could not create local PLS model. Using weighted average of similar substances."
-            prediction
-          else
-            prediction[:prediction_interval] = [prediction[:value]-1.96*prediction[:rmse], prediction[:value]+1.96*prediction[:rmse]]
-            prediction[:value] = prediction[:value]
-            prediction[:rmse] = prediction[:rmse]
-            prediction
-          end
-        end
-      
-      end
-
-=begin
-      def self.physchem_regression substance:, neighbors:, method: "pls"
-
-        activities = []
-        weights = []
-        pc_ids = neighbors.collect{|n| n["common_descriptors"].collect{|d| d[:id]}}.flatten.uniq.sort
-        data_frame = []
-        data_frame[0] = []
-        
-        neighbors.each_with_index do |n,i|
-          activities = n["measurements"]
-          activities.each do |act|
-            data_frame[0][i] = act
-            weights << n["similarity"]
-            n["common_descriptors"].each do |d| 
-              j = pc_ids.index(d[:id])+1
-              data_frame[j] ||= []
-              data_frame[j][i] = d[:scaled_value]
-            end
-          end if activities
-          (0..pc_ids.size).each do |j| # for R: fill empty values with NA
-            data_frame[j] ||= []
-            data_frame[j][i] ||= "NA"
-          end
-        end
-
-        data_frame = data_frame.each_with_index.collect do |r,i|
-          if r.uniq.size == 1 # remove properties with a single value 
-            r = nil
-            pc_ids[i-1] = nil # data_frame frame has additional activity entry
-          end
-          r
-        end
-        data_frame.compact!
-        pc_ids.compact!
-
-        if pc_ids.empty?
-          prediction = weighted_average(substance: substance, neighbors: neighbors)
-          prediction[:warning] = "No relevant variables for regression model. Using weighted average of similar substances."
-          prediction
-        else
-          query_descriptors = pc_ids.collect { |i| substance.scaled_values[i] }
-          query_descriptors = query_descriptors.each_with_index.collect do |v,i|
-            unless v
-              v = nil
-              data_frame[i] = nil
-              pc_ids[i] = nil
-            end
-            v
-          end
-          query_descriptors.compact!
-          data_frame.compact!
-          pc_ids.compact!
-          prediction = r_model_prediction method, data_frame, pc_ids.collect{|i| "\"#{i}\""}, weights, query_descriptors
-          if prediction.nil?
-            prediction = weighted_average(substance: substance, neighbors: neighbors)
-            prediction[:warning] = "Could not create local PLS model. Using weighted average of similar substances."
-          end
-          p prediction
-          prediction
-        end
-      
-      end
-=end
-
-      def self.r_model_prediction method, training_data, training_features, training_weights, query_feature_values
-        R.assign "weights", training_weights
-        r_data_frame = "data.frame(#{training_data.collect{|r| "c(#{r.join(',')})"}.join(', ')})"
-=begin
-rlib = File.expand_path(File.join(File.dirname(__FILE__),"..","R"))
-        File.open("tmp.R","w+"){|f|
-          f.puts "suppressPackageStartupMessages({
-  library(iterators,lib=\"#{rlib}\")
-  library(foreach,lib=\"#{rlib}\")
-  library(ggplot2,lib=\"#{rlib}\")
-  library(grid,lib=\"#{rlib}\")
-  library(gridExtra,lib=\"#{rlib}\")
-  library(pls,lib=\"#{rlib}\")
-  library(caret,lib=\"#{rlib}\")
-  library(doMC,lib=\"#{rlib}\")
-  registerDoMC(#{NR_CORES})
-})"
-
-          f.puts "data <- #{r_data_frame}\n"
-          f.puts "weights <- c(#{training_weights.join(', ')})"
-          f.puts "features <- c(#{training_features.join(', ')})"
-          f.puts "names(data) <- append(c('activities'),features)" #
-          f.puts "ctrl <- rfeControl(functions = #{method}, method = 'repeatedcv', repeats = 5, verbose = T)"
-          f.puts "lmProfile <- rfe(activities ~ ., data = data, rfeControl = ctrl)"
-
-          f.puts "model <- train(activities ~ ., data = data, method = '#{method}')"
-          f.puts "fingerprint <- data.frame(rbind(c(#{query_feature_values.join ','})))"
-          f.puts "names(fingerprint) <- features" 
-          f.puts "prediction <- predict(model,fingerprint)"
-        }
-=end
-        
-        R.eval "data <- #{r_data_frame}"
-        R.assign "features", training_features
-        begin
-          R.eval "names(data) <- append(c('activities'),features)" #
-          R.eval "model <- train(activities ~ ., data = data, method = '#{method}', na.action = na.pass, allowParallel=TRUE)"
-          R.eval "fingerprint <- data.frame(rbind(c(#{query_feature_values.join ','})))"
-          R.eval "names(fingerprint) <- features" 
-          R.eval "prediction <- predict(model,fingerprint)"
-          value = R.eval("prediction").to_f
-          rmse = R.eval("getTrainPerf(model)$TrainRMSE").to_f
-          r_squared = R.eval("getTrainPerf(model)$TrainRsquared").to_f
-          prediction_interval = value-1.96*rmse, value+1.96*rmse
-          {
-            :value => value,
-            :rmse => rmse,
-            :r_squared => r_squared,
-            :prediction_interval => prediction_interval
-          }
-        rescue 
-          return nil
-        end
-      end
-
     end
   end
 end
diff --git a/lib/train-test-validation.rb b/lib/train-test-validation.rb
index 286614a..e3f5905 100644
--- a/lib/train-test-validation.rb
+++ b/lib/train-test-validation.rb
@@ -9,10 +9,7 @@ module OpenTox
 
       def self.create model, training_set, test_set
         
-        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 = model.class.create prediction_feature: model.prediction_feature, training_dataset: training_set, algorithms: model.algorithms
         validation_model.save
         predictions = validation_model.predict test_set.substances
         nr_unpredicted = 0