nimbus 0.7 → 0.8

data/lib/nimbus/application.rb

@@ -31,6 +31,7 @@ module Nimbus
           output_random_forest_file(@forest)
           output_tree_errors_file(@forest)
           output_training_file_predictions(@forest)
+          output_snp_importances_file(@forest)
         end
         
         if @config.do_testing
@@ -102,7 +103,7 @@ module Nimbus
         }
       }
       Nimbus.message "* Predictions for the training sample saved to:"
-      Nimbus.message "*   Output forest file: #{@config.output_training_file}"
+      Nimbus.message "*   Output from training file: #{@config.output_training_file}"
       Nimbus.message "*" * 50
     end
     
@@ -113,7 +114,18 @@ module Nimbus
         }
       }
       Nimbus.message "* Predictions for the testing set saved to:"
-      Nimbus.message "*   Output forest file: #{@config.output_testing_file}"
+      Nimbus.message "*   Output from testing file: #{@config.output_testing_file}"
+      Nimbus.message "*" * 50
+    end
+    
+    def output_snp_importances_file(forest)
+      File.open(@config.output_snp_importances_file , 'w') {|f|
+        forest.snp_importances.sort.each{|p|
+          f.write("SNP ##{p[0]}: #{p[1].round(5)}\n")
+        }
+      }
+      Nimbus.message "* SNP importances for the forest saved to:"
+      Nimbus.message "*   Output snp importance file: #{@config.output_snp_importances_file}"
       Nimbus.message "*" * 50
     end
     

data/lib/nimbus/configuration.rb

@@ -17,7 +17,8 @@ module Nimbus
       :output_forest_file,
       :output_training_file,
       :output_testing_file,
-      :output_tree_errors_file
+      :output_tree_errors_file,
+      :output_snp_importances_file
     )
     
     DEFAULTS = {
@@ -37,7 +38,8 @@ module Nimbus
       :output_forest_file   => 'random_forest.yml',
       :output_training_file => 'training_file_predictions.txt',
       :output_testing_file  => 'testing_file_predictions.txt',
-      :output_tree_errors_file => 'generalization_errors.txt'
+      :output_tree_errors_file => 'generalization_errors.txt',
+      :output_snp_importances_file => 'snp_importances.txt'
     }
     
     
@@ -56,6 +58,7 @@ module Nimbus
       @output_training_file = File.expand_path(DEFAULTS[:output_training_file], Dir.pwd)
       @output_testing_file  = File.expand_path(DEFAULTS[:output_testing_file], Dir.pwd)
       @output_tree_errors_file  = File.expand_path(DEFAULTS[:output_tree_errors_file], Dir.pwd)
+      @output_snp_importances_file = File.expand_path(DEFAULTS[:output_snp_importances_file], Dir.pwd)
     end
     
     def tree

data/lib/nimbus/forest.rb

@@ -1,7 +1,7 @@
 module Nimbus
   
   class Forest
-    attr_accessor :size, :trees, :bag, :predictions, :tree_errors
+    attr_accessor :size, :trees, :bag, :predictions, :tree_errors, :snp_importances
     attr_accessor :options
     
     def initialize(config)
@@ -10,7 +10,9 @@ module Nimbus
       @options = config
       @size = config.forest_size
       @predictions = {}
-      @times_predicted =[]
+      @times_predicted = []
+      @snp_importances = {}
+      @tree_snp_importances = []
       raise Nimbus::ForestError, "Forest size parameter (#{@size}) is invalid. You need at least one tree." if @size < 1
     end
     
@@ -22,9 +24,11 @@ module Nimbus
         tree = Tree.new @options.tree
         @trees << tree.seed(@options.training_set.individuals, tree_individuals_bag, @options.training_set.ids_fenotypes)
         @tree_errors << tree.generalization_error_from_oob(tree_out_of_bag)
+        @tree_snp_importances << tree.estimate_importances(tree_out_of_bag)        
         acumulate_predictions tree.predictions
         Nimbus.clear_line!
       end
+      average_snp_importances
       average_predictions
     end
     
@@ -76,6 +80,16 @@ module Nimbus
       }
     end
     
+    def average_snp_importances
+      1.upto(@options.tree_SNP_total_count) {|snp|
+        @snp_importances[snp] = 0.0
+        @tree_snp_importances.each{|tree_snp_importance|
+          @snp_importances[snp] += tree_snp_importance[snp] unless tree_snp_importance[snp].nil?
+        }
+        @snp_importances[snp] = @snp_importances[snp] / @size
+      }
+    end
+    
   end
   
 end

data/lib/nimbus/tree.rb

@@ -1,7 +1,7 @@
 module Nimbus
   
   class Tree
-    attr_accessor :snp_sample_size, :snp_total_count, :node_min_size, :structure, :generalization_error, :predictions
+    attr_accessor :snp_sample_size, :snp_total_count, :node_min_size, :used_snps, :structure, :generalization_error, :predictions, :importances
     attr_accessor :individuals, :id_to_fenotype
     
     def initialize(options)
@@ -14,19 +14,10 @@ module Nimbus
       @individuals = all_individuals
       @id_to_fenotype = ids_fenotypes
       @predictions = {}
+      @used_snps = []
       
       @structure = build_node individuals_sample, Nimbus::LossFunctions.average(individuals_sample, @id_to_fenotype)
     end
-    
-    def generalization_error_from_oob(oob_ids)
-      return nil if (@structure.nil? || @individuals.nil? || @id_to_fenotype.nil?)
-      oob_y_hat = Nimbus::LossFunctions.average(oob_ids, @id_to_fenotype)
-      oob_predictions = {}
-      oob_ids.each do |oobi|
-        oob_predictions[oobi] = Tree.traverse @structure, individuals[oobi].snp_list
-      end
-      @generalization_error = Nimbus::LossFunctions.quadratic_loss oob_ids, oob_predictions, oob_y_hat
-    end
 
     def build_node(individuals_ids, y_hat)
       # General loss function value for the node
@@ -60,8 +51,35 @@ module Nimbus
       node_1 = split[1].size == 0 ? label_node(parent_y_hat, []) : build_node(split[1], y_hats[1])
       node_2 = split[2].size == 0 ? label_node(parent_y_hat, []) : build_node(split[2], y_hats[2])
       
+      split_by_snp(snp)
       return { snp => [node_0, node_1, node_2] }
     end
+
+    def generalization_error_from_oob(oob_ids)
+      return nil if (@structure.nil? || @individuals.nil? || @id_to_fenotype.nil?)
+      oob_y_hat = Nimbus::LossFunctions.average(oob_ids, @id_to_fenotype)
+      oob_predictions = {}
+      oob_ids.each do |oobi|
+        oob_predictions[oobi] = Tree.traverse @structure, individuals[oobi].snp_list
+      end
+      @generalization_error = Nimbus::LossFunctions.quadratic_loss oob_ids, oob_predictions, oob_y_hat
+    end
+
+    def estimate_importances(oob_ids)
+      return nil if (@generalization_error.nil? && generalization_error_from_oob(oob_ids))
+      oob_individuals_count = oob_ids.size
+      @importances = {}
+      @used_snps.uniq.each do |current_snp|
+        shuffled_ids = oob_ids.shuffle
+        permutated_snp_error = 0.0
+        oob_ids.each_with_index {|oobi, index|
+          permutated_prediction = traverse_with_permutation @structure, individuals[oobi].snp_list, current_snp, individuals[shuffled_ids[index]].snp_list
+          permutated_snp_error += Nimbus::LossFunctions.mean_squared_error [oobi], @id_to_fenotype, permutated_prediction
+        }
+        @importances[current_snp] = ((permutated_snp_error / oob_individuals_count) - @generalization_error).round(5)
+      end
+      @importances
+    end
     
     def self.traverse(tree_structure, data)
       return tree_structure if tree_structure.is_a? Numeric
@@ -69,6 +87,12 @@ module Nimbus
       return self.traverse( tree_structure.values.first[ data[tree_structure.keys.first - 1].to_i], data)
     end
     
+    def traverse_with_permutation(tree_structure, data, snp_to_permute, individual_to_permute)
+      return tree_structure if tree_structure.is_a? Numeric
+      individual_data = (tree_structure.keys.first == snp_to_permute ? individual_to_permute : data)
+      return traverse_with_permutation( tree_structure.values.first[ individual_data[tree_structure.keys.first - 1].to_i], data, snp_to_permute, individual_to_permute)
+    end
+    
     
     private
     
@@ -92,6 +116,10 @@ module Nimbus
       raise Nimbus::TreeError, "Values for SNPs columns must be in [0, 1, 2]"
     end
     
+    def split_by_snp(x)
+      @used_snps << x
+    end
+    
   end
   
 end

metadata

@@ -2,7 +2,7 @@
 name: nimbus
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: "0.7"
+  version: "0.8"
 platform: ruby
 authors: 
 - "Juanjo Baz\xC3\xA1n"
@@ -11,7 +11,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-08-22 00:00:00 Z
+date: 2011-08-23 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: rspec