temporary commit before branching - Dataset.from_descriptor_csv_file is broken

1 files changed, 25 insertions, 5 deletions

diff --git a/lib/model.rb b/lib/model.rb
index d7b2df6..07759c5 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -109,8 +109,25 @@ module OpenTox
               :method => "Algorithm::FeatureSelection.correlation_filter",
             },
           }
+        elsif substance_classes.first == "OpenTox::Substance" and algorithms[:descriptors][:method] == "properties" and algorithms[:descriptors][:categories]
+          model.algorithms = {
+            :feature_selection => nil,
+            :similarity => { # similarity algorithm
+              :method => "Algorithm::Similarity.weighted_cosine",
+              :min => [0.5,0.2]
+            },
+          }
+          if model.class == LazarClassification
+            model.algorithms[:prediction] = {
+                :method => "Algorithm::Classification.weighted_majority_vote",
+            }
+          elsif model.class == LazarRegression
+            model.algorithms[:prediction] = {
+              :method => "Algorithm::Caret.rf",
+            }
+          end
         else
-          raise ArgumentError, "Cannot create models for #{substance_classes.first}."
+          raise ArgumentError, "Cannot create models for #{substance_classes.first} #{algorithms.to_json}."
         end
         
         # overwrite defaults with explicit parameters
@@ -165,14 +182,17 @@ module OpenTox
           end
         # parse independent_variables
         when "properties"
-          categories = model.algorithms[:descriptors][:categories]
           feature_ids = []
-          categories.each do |category|
+          model.algorithms[:descriptors][:categories].each do |category|
+            p category
             Feature.where(category:category).each{|f| feature_ids << f.id.to_s}
           end
-          properties = model.substances.collect { |s| s.properties  }
-          property_ids = properties.collect{|p| p.keys}.flatten.uniq
+          p feature_ids
+          property_ids = model.substances.collect { |s| s.properties.keys  }.flatten.uniq
+          p property_ids
           model.descriptor_ids = feature_ids & property_ids
+          p model.descriptor_ids
+          exit
           model.independent_variables = model.descriptor_ids.collect{|i| properties.collect{|p| p[i] ? p[i].median : nil}}
         else
           raise ArgumentError, "Descriptor method '#{descriptor_method}' not implemented."