From db38c345fdc119edd8a892a5b0ba2c2a4b1cbe1f Mon Sep 17 00:00:00 2001
From: gebele <gebele@in-silico.ch>
Date: Fri, 31 Mar 2017 15:07:28 +0000
Subject: set default min sim to 0.1 for classification and 0.5 for regression

---
 lib/model.rb                      | 12 ++++++++----
 test/model-classification.rb      | 22 +++++++++++-----------
 test/validation-classification.rb |  4 ++--
 3 files changed, 21 insertions(+), 17 deletions(-)

diff --git a/lib/model.rb b/lib/model.rb
index 7cc6765..80affd5 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -68,10 +68,6 @@ module OpenTox
               :method => "fingerprint",
               :type => "MP2D",
             },
-            :similarity => {
-              :method => "Algorithm::Similarity.tanimoto",
-              :min => 0.5,
-            },
             :feature_selection => nil
           }
 
@@ -79,10 +75,18 @@ module OpenTox
             model.algorithms[:prediction] = {
                 :method => "Algorithm::Classification.weighted_majority_vote",
             }
+            model.algorithms[:similarity] = {
+              :method => "Algorithm::Similarity.tanimoto",
+              :min => 0.1,
+            }
           elsif model.class == LazarRegression
             model.algorithms[:prediction] = {
               :method => "Algorithm::Caret.rf",
             }
+            model.algorithms[:similarity] = {
+              :method => "Algorithm::Similarity.tanimoto",
+              :min => 0.5,
+            }
           end
 
         elsif substance_classes.first == "OpenTox::Nanoparticle"
diff --git a/test/model-classification.rb b/test/model-classification.rb
index 0bb3e83..1424f6a 100644
--- a/test/model-classification.rb
+++ b/test/model-classification.rb
@@ -10,35 +10,35 @@ class LazarClassificationTest < MiniTest::Test
       },
       :similarity => {
         :method => "Algorithm::Similarity.tanimoto",
-        :min => 0.5
+        :min => 0.1
       },
-      :feature_selection => nil,
       :prediction => {
         :method => "Algorithm::Classification.weighted_majority_vote",
       },
+      :feature_selection => nil,
     }
     training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"hamster_carcinogenicity.csv")
     model = Model::Lazar.create  training_dataset: training_dataset
     assert_kind_of Model::LazarClassification, model
     assert_equal algorithms, model.algorithms
-    substance = training_dataset.substances[49]
+    substance = training_dataset.substances[10]
     prediction = model.predict substance
     assert_equal "false", prediction[:value]
     [ {
-      :compound => OpenTox::Compound.from_inchi("InChI=1S/C6H14N2O4/c1-5(10)2-8(7-12)3-6(11)4-9/h5-6,9-11H,2-4H2,1H3"),
+      :compound => OpenTox::Compound.from_inchi("InChI=1S/C6H6/c1-2-4-6-5-3-1/h1-6H"),
       :prediction => "false",
     },{
-      :compound => OpenTox::Compound.from_smiles("OCC(CN(CC(O)C)N=O)O"),
+      :compound => OpenTox::Compound.from_smiles("c1ccccc1NN"),
       :prediction => "false",
     } ].each do |example|
       prediction = model.predict example[:compound]
       assert_equal example[:prediction], prediction[:value]
     end
 
-    compound = Compound.from_smiles "O=NN1CCC1"
+    compound = Compound.from_smiles "CCO"
     prediction = model.predict compound
     assert_equal "true", prediction[:value]
-    #assert_equal ["false"], prediction[:measurements]
+    assert_equal ["false"], prediction[:measurements]
 
     # make a dataset prediction
     compound_dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.mini_log10.csv")
@@ -46,12 +46,12 @@ class LazarClassificationTest < MiniTest::Test
     assert_equal compound_dataset.compounds, prediction_dataset.compounds
 
     cid = prediction_dataset.compounds[7].id.to_s
-    assert_equal "Could not find similar substances with experimental data in the training dataset.", prediction_dataset.predictions[cid][:warnings][0]
+    assert_equal "Could not find similar substances with experimental data in the training dataset.", prediction_dataset.predictions[cid][:warning]
     prediction_dataset.predictions.each do |cid,pred|
-      assert_equal "Could not find similar substances with experimental data in the training dataset.", pred[:warnings][0] if pred[:value].nil?
+      assert_equal "Could not find similar substances with experimental data in the training dataset.", pred[:warning] if pred[:value].nil?
     end
     cid = Compound.from_smiles("CCOC(=O)N").id.to_s
-    assert_match "excluded", prediction_dataset.predictions[cid][:info]
+    assert_match "excluded", prediction_dataset.predictions[cid][:warning]
     # cleanup
     [training_dataset,model,compound_dataset,prediction_dataset].each{|o| o.delete}
   end
@@ -85,7 +85,7 @@ class LazarClassificationTest < MiniTest::Test
     model = Model::Lazar.create training_dataset: training_dataset
     t = Time.now
     2.times do
-      compound = Compound.from_smiles("OCC(CN(CC(O)C)N=O)O")
+      compound = Compound.from_smiles("Clc1ccccc1NN")
       prediction = model.predict compound
       assert_equal "1", prediction[:value]
     end
diff --git a/test/validation-classification.rb b/test/validation-classification.rb
index ac25b29..fb4c3e7 100644
--- a/test/validation-classification.rb
+++ b/test/validation-classification.rb
@@ -47,9 +47,9 @@ class ValidationClassificationTest < MiniTest::Test
     dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
     model = Model::Lazar.create training_dataset: dataset
     loo = ClassificationLeaveOneOut.create model
-    assert_equal 77, loo.nr_unpredicted
+    assert_equal 14, loo.nr_unpredicted
     refute_empty loo.confusion_matrix
-    assert loo.accuracy > 0.74
+    assert loo.accuracy > 0.77
     assert loo.weighted_accuracy > loo.accuracy, "Weighted accuracy (#{loo.weighted_accuracy}) should be larger than accuracy (#{loo.accuracy})."
   end
 
-- 
cgit v1.2.3