nimbus 0.10 → 1.0

data/spec/forest_spec.rb

@@ -0,0 +1,57 @@
+# encoding: UTF-8
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe Nimbus::Forest do
+  before(:each) do
+    @config = Nimbus::Configuration.new
+    @config.load fixture_file('regression_config.yml')
+    @config.load_training_data
+    @forest = ::Nimbus::Forest.new @config
+  end
+  
+  it 'grows a forest of N trees' do
+    @forest.trees.should == []
+    @config.forest_size.should == 3
+    @forest.grow
+    @forest.trees.size.should == @config.forest_size
+    @forest.trees.each{|t| t.should be_kind_of Hash}
+  end
+  
+  it 'creates averaged predictions for individuals in the training set' do
+    @forest.predictions.should == {}
+    @forest.grow
+    (@forest.predictions.keys - (1..800).to_a ).should == []
+    @forest.predictions.values.each{|v| v.should be_kind_of Numeric}
+  end
+  
+  it 'computes averaged SNP importances for every SNP' do
+    @forest.snp_importances.should == {}
+    @forest.grow
+    @forest.snp_importances.keys.sort.should == (1..200).to_a
+    @forest.snp_importances.values.each{|v| v.should be_kind_of Numeric}
+  end
+  
+  it 'traverses a set of testing individuals through every tree in the forest and return predictions' do
+    @forest = @config.load_forest
+    @forest.predictions.should == {}
+    
+    tree_structure = YAML.load(File.open fixture_file('regression_random_forest.yml'))
+    expected_predictions = {}
+    @config.read_testing_data{|individual|
+      individual_prediction = 0.0
+      tree_structure.each do |t|
+        individual_prediction = (individual_prediction + Nimbus::Tree.traverse(t, individual.snp_list)).round(5)
+      end
+      expected_predictions[individual.id] = (individual_prediction / 3).round(5)
+    }
+    
+    @forest.traverse
+    @forest.predictions.should == expected_predictions    
+  end
+  
+  it 'can output forest structure in YAML format' do
+    @forest = @config.load_forest
+    YAML.load(File.open fixture_file('regression_random_forest.yml')) == YAML.load(@forest.to_yaml)
+  end
+  
+end

data/spec/individual_spec.rb

@@ -0,0 +1,13 @@
+# encoding: UTF-8
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe Nimbus::Individual do
+  
+  it "stores id, fenotype and SNPs information for an individual" do
+    @individual = Nimbus::Individual.new(11, 33.275, [1,0,2,1])
+    @individual.id.should       == 11
+    @individual.fenotype.should == 33.275
+    @individual.snp_list.should == [1,0,2,1]
+  end
+  
+end

data/spec/nimbus_spec.rb

@@ -1,2 +1,18 @@
 # encoding: UTF-8
-require File.dirname(__FILE__) + '/spec_helper'
+require File.dirname(__FILE__) + '/spec_helper'
+
+
+describe 'Nimbus module' do
+  
+  it "manages a Nimbus::Application object" do
+    app = Nimbus.application
+    app.should be_kind_of Nimbus::Application
+  end
+  
+  it "accepts setting an external Nimbus::Application" do
+    app = Nimbus::Application.new 
+    Nimbus.application = app
+    Nimbus.application.should == app
+  end
+    
+end

data/spec/spec_helper.rb

@@ -1,2 +1,8 @@
 # encoding: UTF-8
-require File.dirname(__FILE__) + '/../lib/nimbus'
+require File.dirname(__FILE__) + '/../lib/nimbus'
+$fixtures_path = File.dirname(__FILE__) + '/fixtures'
+ENV['nimbus_test'] = 'running_nimbus_tests'
+
+def fixture_file(filename) #:nodoc:
+  return "#{$fixtures_path}/#{filename}"
+end

data/spec/training_set_spec.rb

@@ -0,0 +1,25 @@
+# encoding: UTF-8
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe Nimbus::TrainingSet do
+  
+  it "stores individuals list and fenotype data for them" do
+    i1 = Nimbus::Individual.new 1, 11.0, [1,0,2,1]
+    i2 = Nimbus::Individual.new 2, 22.0, [2,1,2,2]
+    i3 = Nimbus::Individual.new 3, 33.0, [0,2,1,0]
+    @training_set = Nimbus::TrainingSet.new [i1, i3], {i1.id => 11.0, i3.id => 33.0}
+    
+    @training_set.individuals.should   == [i1, i3]
+    @training_set.ids_fenotypes.should == {i1.id => 11.0, i3.id => 33.0}
+  end
+  
+  it "keeps track of ids of all individuals in the training set" do
+    i1 = Nimbus::Individual.new 1, 11.0, [1,0,2,1]
+    i2 = Nimbus::Individual.new 2, 22.0, [2,1,2,2]
+    i3 = Nimbus::Individual.new 3, 33.0, [0,2,1,0]
+    @training_set = Nimbus::TrainingSet.new [i1, i3], {i1.id => 11.0, i3.id => 33.0}
+    
+    @training_set.all_ids.should == [1,3]
+  end
+  
+end

data/spec/tree_spec.rb

@@ -0,0 +1,130 @@
+# encoding: UTF-8
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe Nimbus::Tree do
+  
+  before(:each) do
+    @config = Nimbus::Configuration.new
+    @config.load fixture_file('regression_config.yml')
+    
+    @tree = Nimbus::Tree.new @config.tree
+  end
+  
+  it "is initialized with tree config info" do
+    @tree.snp_total_count.should == 200
+    @tree.snp_sample_size.should == 60
+    @tree.node_min_size.should   == 5
+  end
+  
+  it "creates a tree structure when seeded with training data" do
+    @config.load_training_data
+    @tree.structure.should be_nil
+    @tree.seed(@config.training_set.individuals, @config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    @tree.structure.should_not be_nil
+    @tree.structure.should be_kind_of Hash
+    
+    @tree.structure.keys.first.should == @tree.used_snps.last
+    @tree.used_snps.should_not be_empty
+  end
+  
+  it "split node in three when building a node and finds a suitable split" do
+    @config.load_training_data
+    @tree.stub!(:snps_random_sample).and_return((141..200).to_a) #189 is best split
+    
+    @tree.individuals = @config.training_set.individuals
+    @tree.id_to_fenotype = @config.training_set.ids_fenotypes
+    @tree.used_snps = []
+    @tree.predictions = {}
+    
+    branch = @tree.build_node @config.training_set.all_ids, Nimbus::LossFunctions.average(@config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    branch.keys.size.should == 1
+    branch.keys.first.should == 189
+    branch[189].size.should == 3
+    branch[189][0].should be_kind_of Hash
+    branch[189][1].should be_kind_of Hash
+    branch[189][2].should be_kind_of Hash
+  end
+  
+  it "keeps track of all SNPs used for the tree" do
+    @config.load_training_data
+    snps = (131..190).to_a
+    @tree.stub!(:snps_random_sample).and_return(snps)
+    @tree.used_snps.should be_nil
+    @tree.seed(@config.training_set.individuals, @config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    @tree.used_snps.size.should > 4
+    @tree.used_snps.each{|snp|
+      snps.include?(snp).should be_true
+    }
+  end
+  
+  it "labels node when building a node and there is not a suitable split" do
+    @config.load_training_data
+    @tree.stub!(:snps_random_sample).and_return([33])
+    
+    @tree.individuals = @config.training_set.individuals
+    @tree.id_to_fenotype = @config.training_set.ids_fenotypes
+    @tree.used_snps = []
+    @tree.predictions = {}
+    
+    branch = @tree.build_node @config.training_set.all_ids, Nimbus::LossFunctions.average(@config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    branch[33][0].should be_kind_of Numeric
+    branch[33][1].should be_kind_of Numeric
+    branch[33][2].should be_kind_of Numeric
+  end
+  
+  it "labels node when building a node with less individuals than the minimum node size" do
+    @config.load_training_data
+    
+    @tree.individuals = @config.training_set.individuals
+    @tree.id_to_fenotype = @config.training_set.ids_fenotypes
+    @tree.used_snps = []
+    @tree.predictions = {}
+    
+    label = @tree.build_node [1, 10, 33], Nimbus::LossFunctions.average(@config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    label.should be_kind_of Numeric
+    
+    label = @tree.build_node [2, 10], Nimbus::LossFunctions.average(@config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    label.should be_kind_of Numeric
+    
+    label = @tree.build_node [1, 10, 33], Nimbus::LossFunctions.average(@config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    label.should be_kind_of Numeric
+    
+    label = @tree.build_node [108, 22, 10, 33], Nimbus::LossFunctions.average(@config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    label.should be_kind_of Numeric
+  end
+  
+  it 'computes generalization error for the tree' do
+    @config.load_training_data
+    @tree.seed(@config.training_set.individuals, @config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    @tree.generalization_error.should be_nil
+    @tree.generalization_error_from_oob((2..200).to_a)
+    @tree.generalization_error.should be_kind_of Numeric
+    @tree.generalization_error.should > 0.0
+    @tree.generalization_error.should < 100.0
+  end
+  
+  it 'estimates importance for all SNPs' do
+    @config.load_training_data
+    @tree.seed(@config.training_set.individuals, @config.training_set.all_ids, @config.training_set.ids_fenotypes)
+    @tree.importances.should be_nil
+    @tree.estimate_importances((300..533).to_a)
+    @tree.importances.should be_kind_of Hash
+    @tree.importances.keys.should_not be_empty
+    (@tree.importances.keys - (1..200).to_a).should be_empty
+  end
+  
+  it 'get prediction for an individual pushing it down a tree structure' do
+    tree_structure = YAML.load(File.open fixture_file('regression_random_forest.yml')).first
+    individual_data = [0]*200
+    prediction = Nimbus::Tree.traverse tree_structure, individual_data
+    prediction.should == 0.25043
+    
+    individual_data[189-1] = 1
+    individual_data[4-1] = 1
+    individual_data[62-1] = 2
+    individual_data[146-1] = 2
+    prediction = Nimbus::Tree.traverse tree_structure, individual_data
+    prediction.should == -0.9854
+  end
+  
+end

metadata

@@ -2,7 +2,7 @@
 name: nimbus
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: "0.10"
+  version: "1.0"
 platform: ruby
 authors: 
 - "Juanjo Baz\xC3\xA1n"
@@ -11,7 +11,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-08-24 00:00:00 Z
+date: 2011-08-25 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: rspec
@@ -35,7 +35,6 @@ extra_rdoc_files: []
 
 files: 
 - MIT-LICENSE.txt
-- README.rdoc
 - lib/nimbus/application.rb
 - lib/nimbus/configuration.rb
 - lib/nimbus/exceptions.rb
@@ -45,13 +44,22 @@ files:
 - lib/nimbus/training_set.rb
 - lib/nimbus/tree.rb
 - lib/nimbus.rb
-- spec/fixtures/config.yml
-- spec/fixtures/testing_regression.data
-- spec/fixtures/training_regression.data
+- spec/configuration_spec.rb
+- spec/fixtures/regression_config.yml
+- spec/fixtures/regression_random_forest.yml
+- spec/fixtures/regression_snp_importances.txt
+- spec/fixtures/regression_testing.data
+- spec/fixtures/regression_testing_file_predictions.txt
+- spec/fixtures/regression_training.data
+- spec/fixtures/regression_training_file_predictions.txt
+- spec/forest_spec.rb
+- spec/individual_spec.rb
 - spec/nimbus_spec.rb
 - spec/spec_helper.rb
+- spec/training_set_spec.rb
+- spec/tree_spec.rb
 - bin/nimbus
-homepage: http://github.com/xuanxu/nimbus
+homepage: http://nimbusgem.org
 licenses: []
 
 post_install_message: 
@@ -81,8 +89,17 @@ signing_key:
 specification_version: 3
 summary: Random Forest algorithm for Genomics
 test_files: 
-- spec/fixtures/config.yml
-- spec/fixtures/testing_regression.data
-- spec/fixtures/training_regression.data
+- spec/configuration_spec.rb
+- spec/fixtures/regression_config.yml
+- spec/fixtures/regression_random_forest.yml
+- spec/fixtures/regression_snp_importances.txt
+- spec/fixtures/regression_testing.data
+- spec/fixtures/regression_testing_file_predictions.txt
+- spec/fixtures/regression_training.data
+- spec/fixtures/regression_training_file_predictions.txt
+- spec/forest_spec.rb
+- spec/individual_spec.rb
 - spec/nimbus_spec.rb
 - spec/spec_helper.rb
+- spec/training_set_spec.rb
+- spec/tree_spec.rb

data/README.rdoc

@@ -1 +0,0 @@
-= Nimbus

data/spec/fixtures/config.yml

@@ -1,11 +0,0 @@
-#Input files
-input:
-  training: training_regression.data
-  testing:  testing_regression.data
-
-#Forest parameters
-forest:
-  forest_size: 10 #how many trees
-  SNP_sample_size_mtry: 60 #mtry
-  SNP_total_count: 200
-  node_min_size: 5