nimbus 0.6.1 → 0.7

data/lib/nimbus/application.rb

@@ -29,6 +29,7 @@ module Nimbus
           @forest = ::Nimbus::Forest.new @config
           @forest.grow
           output_random_forest_file(@forest)
+          output_tree_errors_file(@forest)
           output_training_file_predictions(@forest)
         end
         
@@ -83,6 +84,17 @@ module Nimbus
       Nimbus.message "*" * 50
     end
     
+    def output_tree_errors_file(forest)
+      File.open(@config.output_tree_errors_file , 'w') {|f| 
+        1.upto(forest.tree_errors.size) do |te|
+          f.write("generalization error for tree ##{te}: #{forest.tree_errors[te-1].round(5)}\n")
+        end
+      }
+      Nimbus.message "* Generalization errors for every tree saved to:"
+      Nimbus.message "*   Output tree errors file: #{@config.output_tree_errors_file}"
+      Nimbus.message "*" * 50
+    end
+    
     def output_training_file_predictions(forest)
       File.open(@config.output_training_file , 'w') {|f|
         forest.predictions.sort.each{|p|

data/lib/nimbus/configuration.rb

@@ -16,7 +16,8 @@ module Nimbus
       :training_set,
       :output_forest_file,
       :output_training_file,
-      :output_testing_file
+      :output_testing_file,
+      :output_tree_errors_file
     )
     
     DEFAULTS = {
@@ -35,7 +36,8 @@ module Nimbus
       
       :output_forest_file   => 'random_forest.yml',
       :output_training_file => 'training_file_predictions.txt',
-      :output_testing_file  => 'testing_file_predictions.txt'
+      :output_testing_file  => 'testing_file_predictions.txt',
+      :output_tree_errors_file => 'generalization_errors.txt'
     }
     
     
@@ -53,6 +55,7 @@ module Nimbus
       @output_forest_file   = File.expand_path(DEFAULTS[:output_forest_file], Dir.pwd)
       @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)
     end
     
     def tree

data/lib/nimbus/forest.rb

@@ -1,11 +1,12 @@
 module Nimbus
   
   class Forest
-    attr_accessor :size, :trees, :bag, :predictions
+    attr_accessor :size, :trees, :bag, :predictions, :tree_errors
     attr_accessor :options
     
     def initialize(config)
       @trees = []
+      @tree_errors = []
       @options = config
       @size = config.forest_size
       @predictions = {}
@@ -20,6 +21,7 @@ module Nimbus
         tree_out_of_bag = oob tree_individuals_bag
         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)
         acumulate_predictions tree.predictions
         Nimbus.clear_line!
       end
@@ -30,7 +32,7 @@ module Nimbus
       @predictions = {}
       prediction_count = trees.size
       @options.read_testing_data{|individual|
-        individual_prediction=0.0
+        individual_prediction = 0.0
         trees.each do |t|
           individual_prediction = (individual_prediction + Nimbus::Tree.traverse(t, individual.snp_list)).round(5)
         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, :predictions
+    attr_accessor :snp_sample_size, :snp_total_count, :node_min_size, :structure, :generalization_error, :predictions
     attr_accessor :individuals, :id_to_fenotype
     
     def initialize(options)
@@ -17,6 +17,16 @@ module Nimbus
       
       @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
@@ -26,7 +36,7 @@ module Nimbus
       
       # Finding the SNP that minimizes loss function
       snps = snps_random_sample
-      min_loss, min_SNP, split, means  = node_loss_function, nil, nil, nil
+      min_loss, min_SNP, split, means = node_loss_function, nil, nil, nil
 
       snps.each do |snp|
         individuals_split_by_snp_value = split_by_snp_value individuals_ids, snp

metadata

@@ -2,7 +2,7 @@
 name: nimbus
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.6.1
+  version: "0.7"
 platform: ruby
 authors: 
 - "Juanjo Baz\xC3\xA1n"