1 files changed, 56 insertions, 0 deletions
diff --git a/lib/feature-selection.rb b/lib/feature-selection.rb
new file mode 100644
index 0000000..8601737
--- /dev/null
+++ b/lib/feature-selection.rb
@@ -0,0 +1,56 @@
+module OpenTox
+  module Algorithm
+    
+    # Feature selection algorithms
+    module FeatureSelection
+
+      class Supervised
+
+        # Select features correlated to the models prediction feature
+        # @param [OpenTox::Model::Lazar]
+        def self.correlation_filter model
+          relevant_features = {}
+          R.assign "dependent", model.dependent_variables.collect{|v| to_r(v)}
+          model.descriptor_weights = []
+          selected_variables = [] 
+          selected_descriptor_ids = []
+          model.independent_variables.each_with_index do |v,i|
+            v.collect!{|n| to_r(n)}
+            R.assign "independent", v
+            begin
+              R.eval "cor <- cor.test(dependent,independent,method = 'pearson',use='pairwise')"
+              pvalue = R.eval("cor$p.value").to_ruby
+              if pvalue <= 0.05
+                model.descriptor_weights << R.eval("cor$estimate").to_ruby**2
+                selected_variables << v
+                selected_descriptor_ids << model.descriptor_ids[i]
+              end
+            rescue
+              warn "Correlation of '#{model.prediction_feature.name}' (#{model.dependent_variables}) with (#{v}) failed."
+            end
+          end
+
+          model.independent_variables = selected_variables
+          model.descriptor_ids = selected_descriptor_ids
+          model
+        end
+
+        def self.to_r v
+          return 0 if v == false
+          return 1 if v == true
+          v
+        end
+
+      end
+
+      class Unsupervised
+        # Select features correlated to the models prediction feature
+        # @param [OpenTox::Model::Lazar]
+        def self.nonredundant independent_variables
+        end
+      end
+
+    end
+
+  end
+end