From 1f789133d961c29d3babfaf69cdde3d675288537 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Sat, 24 Aug 2019 14:44:52 +0200
Subject: initial refactored version for mutagenicity paper

---
 lib/classification.rb | 43 ++++++++++++++++++-------------------------
 1 file changed, 18 insertions(+), 25 deletions(-)

(limited to 'lib/classification.rb')

diff --git a/lib/classification.rb b/lib/classification.rb
index 638492b..5796ce2 100644
--- a/lib/classification.rb
+++ b/lib/classification.rb
@@ -1,29 +1,22 @@
-module OpenTox
-  module Algorithm
+module Lazar
     
-    # Classification algorithms
-    class Classification
-
-      # Weighted majority vote
-      # @param [Array<TrueClass,FalseClass>] dependent_variables
-      # @param [Array<Float>] weights
-      # @return [Hash]
-      def self.weighted_majority_vote dependent_variables:, independent_variables:nil, weights:, query_variables:nil
-        class_weights = {}
-        dependent_variables.each_with_index do |v,i|
-          class_weights[v] ||= []
-          class_weights[v] << weights[i] unless v.nil?
-        end
-        probabilities = {}
-        class_weights.each do |a,w|
-          probabilities[a] = w.sum/weights.sum
-        end
-        probabilities = probabilities.collect{|a,p| [a,weights.max*p]}.to_h
-        p_max = probabilities.collect{|a,p| p}.max
-        prediction = probabilities.key(p_max)
-        {:value => prediction,:probabilities => probabilities}
-      end
-
+  # Classification algorithms
+  class Classification
+    
+    # Weighted majority vote
+    # @param [Array<0,1>] dependent_variables
+    # @param [Array<Float>] weights
+    # @return [Hash]
+    def self.weighted_majority_vote dependent_variables:, weights:
+      w = []
+      w[0] = weights.each_index.select{|i| dependent_variables[i] == 0}.collect{|i| weights[i]}
+      w[1] = weights.each_index.select{|i| dependent_variables[i] == 1}.collect{|i| weights[i]}
+      weights_sum = weights.sum.to_f
+      weights_max = weights.max.to_f
+      probabilities = []
+      probabilities[0] = weights_max*w[0].sum/weights_sum
+      probabilities[1] = weights_max*w[1].sum/weights_sum
+      probabilities
     end
 
   end
-- 
cgit v1.2.3