enm import fixed

6 files changed, 23 insertions, 28 deletions

diff --git a/test/descriptor.rb b/test/descriptor.rb
index 6eb4316..563cdce 100644
--- a/test/descriptor.rb
+++ b/test/descriptor.rb
@@ -6,7 +6,6 @@ class DescriptorTest < MiniTest::Test
     # check available descriptors
     assert_equal 15,PhysChem.openbabel_descriptors.size,"incorrect number of Openbabel descriptors"
     assert_equal 45,PhysChem.joelib_descriptors.size,"incorrect number of Joelib descriptors"
-    p PhysChem.cdk_descriptors
     assert_equal 286,PhysChem.cdk_descriptors.size,"incorrect number of Cdk descriptors"
     assert_equal 346,PhysChem.descriptors.size,"incorrect number of physchem descriptors"
   end
diff --git a/test/model-nanoparticle.rb b/test/model-nanoparticle.rb
index c5f3223..7fb944e 100644
--- a/test/model-nanoparticle.rb
+++ b/test/model-nanoparticle.rb
@@ -108,7 +108,6 @@ class NanoparticleModelTest  < MiniTest::Test
       },
     }
     model = Model::Lazar.create training_dataset: @training_dataset, prediction_feature: @prediction_feature, algorithms: algorithms
-    p model
     refute_empty model.dependent_variables
     refute_empty model.descriptor_ids
     refute_empty model.independent_variables
diff --git a/test/nanomaterial-prediction-models.rb b/test/nanomaterial-prediction-models.rb
index b0c05f3..f90a822 100644
--- a/test/nanomaterial-prediction-models.rb
+++ b/test/nanomaterial-prediction-models.rb
@@ -13,7 +13,6 @@ class NanomaterialPredictionModelTest < MiniTest::Test
 
   def test_default_nanomaterial_prediction_model
     prediction_model = Model::NanoPrediction.create
-    p prediction_model
     [:endpoint,:species,:source].each do |p|
       refute_empty prediction_model[p]
     end
diff --git a/test/setup.rb b/test/setup.rb
index 6c97282..63b59fb 100644
--- a/test/setup.rb
+++ b/test/setup.rb
@@ -5,5 +5,9 @@ require_relative '../lib/lazar.rb'
 include OpenTox
 TEST_DIR ||= File.expand_path(File.dirname(__FILE__))
 DATA_DIR ||= File.join(TEST_DIR,"data")
+training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
+unless training_dataset
+  Import::Enanomapper.import File.join(File.dirname(__FILE__),"data","enm")
+end
 #$mongo.database.drop
 #$gridfs = $mongo.database.fs
diff --git a/test/validation-nanoparticle.rb b/test/validation-nanoparticle.rb
index 5ed70f2..9351e1b 100644
--- a/test/validation-nanoparticle.rb
+++ b/test/validation-nanoparticle.rb
@@ -5,74 +5,72 @@ class NanoparticleValidationTest  < MiniTest::Test
 
   def setup
     @training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
-    unless @training_dataset
-      Import::Enanomapper.import File.join(File.dirname(__FILE__),"data","enm")
-      @training_dataset = Dataset.where(name: "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
-    end
     @prediction_feature = @training_dataset.features.select{|f| f["name"] == 'log2(Net cell association)'}.first
   end
 
   def test_validate_default_nanoparticle_model
     model = Model::Lazar.create training_dataset: @training_dataset, prediction_feature: @prediction_feature
     cv = CrossValidation.create model
-    p cv
-    p cv.rmse
-    p cv.r_squared
     #File.open("tmp.pdf","w+"){|f| f.puts cv.correlation_plot}
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
 
-  def test_validate_pls_nanoparticle_model
+  def test_validate_pls_pchem_model
     algorithms = {
       :descriptors => {
         :method => "properties",
         :categories => ["P-CHEM"]
       },
       :prediction => {:method => 'Algorithm::Caret.pls' },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
     }
     model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     assert_equal "Algorithm::Caret.pls", model.algorithms[:prediction][:method]
     cv = CrossValidation.create model
-    p cv.rmse
-    p cv.r_squared
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
 
-  def test_validate_proteomics_pls_nanoparticle_model
+=begin
+  def test_validate_proteomics_pls_pchem_model
     algorithms = {
       :descriptors => {
         :method => "properties",
         :categories => ["Proteomics"]
       },
       :prediction => {:method => 'Algorithm::Caret.pls' },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
     }
     model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     assert_equal "Algorithm::Caret.pls", model.algorithms[:prediction][:method]
     cv = CrossValidation.create model
-    p cv.rmse
-    p cv.r_squared
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
+=end
 
-  def test_validate_all_default_nanoparticle_model
+  def test_validate_proteomics_pchem_default_model
     algorithms = {
       :descriptors => {
         :method => "properties",
         :categories => ["Proteomics","P-CHEM"]
       },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
     }
     model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = CrossValidation.create model
-    p cv.rmse
-    p cv.r_squared
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
 
-  def test_nanoparticle_fingerprint_model
+  def test_nanoparticle_fingerprint_model_without_feature_selection
     algorithms = {
       :descriptors => {
         :method => "fingerprint",
@@ -86,13 +84,11 @@ class NanoparticleValidationTest  < MiniTest::Test
     }
     model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = CrossValidation.create model
-    p cv.rmse
-    p cv.r_squared
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
 
-  def test_nanoparticle_fingerprint_weighted_average_model
+  def test_nanoparticle_fingerprint_weighted_average_model_without_feature_selection
     algorithms = {
       :descriptors => {
         :method => "fingerprint",
@@ -107,8 +103,6 @@ class NanoparticleValidationTest  < MiniTest::Test
     }
     model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = CrossValidation.create model
-    p cv.rmse
-    p cv.r_squared
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
@@ -123,11 +117,12 @@ class NanoparticleValidationTest  < MiniTest::Test
         :method => "Algorithm::Similarity.tanimoto",
         :min => 0.1
       },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
     }
     model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = CrossValidation.create model
-    p cv.rmse
-    p cv.r_squared
     refute_nil cv.r_squared
     refute_nil cv.rmse
   end
diff --git a/test/validation-regression.rb b/test/validation-regression.rb
index a0895f9..7630521 100644
--- a/test/validation-regression.rb
+++ b/test/validation-regression.rb
@@ -86,7 +86,6 @@ class ValidationRegressionTest < MiniTest::Test
       #assert cv.r_squared > 0.34, "R^2 (#{cv.r_squared}) should be larger than 0.034"
       #assert_operator cv.accuracy, :>, 0.7, "model accuracy < 0.7, this may happen by chance due to an unfavorable training/test set split"
     end
-    p repeated_cv
     File.open("tmp.png","w+"){|f| f.puts repeated_cv.correlation_plot}
   end