From faccda14c0f98333bf7623d4caef00eea7bb1933 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Mon, 19 Aug 2019 20:53:53 +0200
Subject: temporary commit before branching - Dataset.from_descriptor_csv_file
 is broken

---
 lib/dataset.rb | 35 +++++++++++++----------------------
 1 file changed, 13 insertions(+), 22 deletions(-)

(limited to 'lib/dataset.rb')

diff --git a/lib/dataset.rb b/lib/dataset.rb
index 9e9fdd5..1d6b56c 100644
--- a/lib/dataset.rb
+++ b/lib/dataset.rb
@@ -167,13 +167,15 @@ module OpenTox
     #   - bioactivity column (last column): header with bioactivity name, bioactivity values (i.e. dependent variable)
     # @param [String] Descriptor type
     # @return [OpenTox::Dataset]
-    def self.from_descriptor_csv_file file, type
+    def self.from_descriptor_csv_file file, category
       md5 = Digest::MD5.hexdigest(File.read(file)) # use hash to identify identical files
       dataset = self.find_by(:md5 => md5)
+      #dataset = nil
       if dataset
         $logger.debug "Found #{file} in the database (id: #{dataset.id}, md5: #{dataset.md5}), skipping import."
       else
         $logger.debug "Parsing #{file}."
+        p "Parsing #{file}."
         table = nil
         sep = ","
         ["\t",";"].each do |s| # guess alternative CSV separator
@@ -189,26 +191,17 @@ module OpenTox
         # features
         feature_names = table.shift.collect{|f| f.strip}
         raise ArgumentError, "Duplicated features in table header." unless feature_names.size == feature_names.uniq.size
+
         original_id = OriginalId.find_or_create_by(:dataset_id => dataset.id,:name => feature_names.shift)
 
-        numeric = []
-        features = []
-
-        feature_names.each_with_index do |f,i|
-          values = table.collect{|row| val=row[i+1].to_s.strip; val.blank? ? nil : val }.uniq.compact
-          types = values.collect{|v| v.numeric? ? true : false}.uniq
-          feature = nil
-          if values.size == 0 # empty feature
-          elsif  values.size > 5 and types.size == 1 and types.first == true # 5 max classes
-            numeric[i] = true
-            i == feature_names.size-1 ?  feature = NumericBioActivity.find_or_create_by(:name => f) : feature = NumericSubstanceProperty.find_or_create_by(:name => f)
-          else
-            numeric[i] = false
-            i == feature_names.size-1 ?  feature = NominalBioActivity.find_or_create_by(:name => f, :accept_values => values.sort) : feature = NominalSubstanceProperty.find_or_create_by(:name => f, :accept_values => values.sort)
-          end
-          features << feature if feature
+        bioactivity_feature_name = feature_names.pop
+        values = table.collect{|row| val=row.last.to_s.strip; val.blank? ? nil : val }.uniq.compact
+        types = values.collect{|v| v.numeric? ? true : false}.uniq
+        if  values.size > 5 and types.size == 1 and types.first == true # 5 max classes
+          bioactivity_feature = NumericBioActivity.find_or_create_by(:name => bioactivity_feature_name)
+        else
+          bioactivity_feature = NominalBioActivity.find_or_create_by(:name => bioactivity_feature_name, :accept_values => values.sort)
         end
-        bioactivity_feature = features.pop
         
         # substances and values
 
@@ -223,12 +216,10 @@ module OpenTox
             if v.blank?
               warnings << "Empty value for compound '#{identifier}' (#{original_id_value}) and feature '#{feature_names[j]}'."
               next
-            elsif numeric[j]
-              v = v.to_f
             else
-              v = v.strip
+              property = NumericSubstanceProperty.find_or_create_by(:name => feature_names[j],:category => category)
+              substance.properties[property.id.to_s] = v.to_f
             end
-            substance.properties[features[j].id.to_s] = [v]
           end
           substance.save
           dataset.add substance, bioactivity_feature, bioactivity_value
-- 
cgit v1.2.3