From d6eced29e104b9bc1923b2ac89b2700a48adf07a Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Fri, 8 Jan 2016 11:00:20 +0100
Subject: mg-mmol conversion fixed

---
 lib/compound.rb        | 20 ++------------------
 lib/crossvalidation.rb |  2 --
 lib/dataset.rb         | 17 ++++++++++++++---
 3 files changed, 16 insertions(+), 23 deletions(-)

diff --git a/lib/compound.rb b/lib/compound.rb
index d5a4cbb..040fd6f 100644
--- a/lib/compound.rb
+++ b/lib/compound.rb
@@ -337,30 +337,15 @@ module OpenTox
         
     end
     
-    # Get mg from logmmol (for nch LOAEL/pTD50 data)
-    # @return [Float] value in mg
-    def logmmol_to_mg(value, mw)
-      mg = (10**(-1.0*value.to_f)*(mw.to_f*1000))
-      return mg
-    end
-
     # Get mg from mmol
     # @return [Float] value in mg
-    def mmol_to_mg(value, mw)
-      mg = (value.to_f)*(mw.to_f)
-      return mg
+    def mmol_to_mg mmol
+      mmol.to_f*molecular_weight
     end
 
     def mg_to_mmol mg
       mg.to_f/molecular_weight
     end
-
-    # Get mg from logmg
-    # @return [Float] value in mg
-    def logmg_to_mg(value)
-      mg = 10**value.to_f
-      return mg
-    end
     
     # Calculate molecular weight of Compound with OB and store it in object
     # @return [Float] molecular weight
@@ -371,7 +356,6 @@ module OpenTox
       self["molecular_weight"].to_f
     end
 
-
     private
 
     def self.obconversion(identifier,input_format,output_format,option=nil)
diff --git a/lib/crossvalidation.rb b/lib/crossvalidation.rb
index 3127351..9b5c4e2 100644
--- a/lib/crossvalidation.rb
+++ b/lib/crossvalidation.rb
@@ -175,8 +175,6 @@ module OpenTox
       weighted_rse = 0
       mae = 0
       weighted_mae = 0
-      rae = 0
-      weighted_rae = 0
       confidence_sum = 0
       predictions.each do |pred|
         compound_id,activity,prediction,confidence = pred
diff --git a/lib/dataset.rb b/lib/dataset.rb
index 366c79f..55cde63 100644
--- a/lib/dataset.rb
+++ b/lib/dataset.rb
@@ -126,6 +126,17 @@ module OpenTox
     end
 
     # Diagnostics
+    
+    def duplicates feature=self.features.first
+      col = feature_ids.index feature.id
+      dups = {}
+      compound_ids.each_with_index do |cid,i|
+        rows = compound_ids.each_index.select{|r| compound_ids[r] == cid }
+        values = rows.collect{|row| data_entries[row][col]}
+        dups[cid] = values if values.size > 1
+      end
+      dups
+    end
 
     def correlation_plot training_dataset
       # TODO: create/store svg
@@ -162,10 +173,10 @@ module OpenTox
     # TODO
     #def self.from_sdf_file
     #end
-
+    
     # Create a dataset from CSV file
     # TODO: document structure
-    def self.from_csv_file file, source=nil, bioassay=true
+    def self.from_csv_file file, source=nil, bioassay=true#, layout={}
       source ||= file
       name = File.basename(file,".*")
       dataset = self.find_by(:source => source, :name => name)
@@ -175,7 +186,7 @@ module OpenTox
         $logger.debug "Parsing #{file}."
         table = CSV.read file, :skip_blanks => true, :encoding => 'windows-1251:utf-8'
         dataset = self.new(:source => source, :name => name)
-        dataset.parse_table table, bioassay
+        dataset.parse_table table, bioassay#, layout
       end
       dataset
     end
-- 
cgit v1.2.3