nano caret regression fixed

4 files changed, 79 insertions, 96 deletions

diff --git a/test/all.rb b/test/all.rb
index a10bcaa..eddf4e6 100644
--- a/test/all.rb
+++ b/test/all.rb
@@ -1,5 +1,5 @@
 # "./default_environment.rb" has to be executed separately
-exclude = ["./setup.rb","./all.rb", "./default_environment.rb","./nanoparticles.rb"]
+exclude = ["./setup.rb","./all.rb", "./default_environment.rb"]
 (Dir[File.join(File.dirname(__FILE__),"*.rb")]-exclude).each do |test|
   require_relative test
 end
diff --git a/test/model.rb b/test/model.rb
index 563d081..02b8e73 100644
--- a/test/model.rb
+++ b/test/model.rb
@@ -13,7 +13,7 @@ class ModelTest < MiniTest::Test
         :min => 0.1
       },
       :prediction => {
-        :method => "Algorithm::Regression.caret",
+        :method => "Algorithm::Caret.regression",
         :parameters => "pls",
       },
       :feature_selection => nil,
@@ -65,7 +65,7 @@ class ModelTest < MiniTest::Test
     training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.mini_log10.csv")
     model = Model::Lazar.create  training_dataset: training_dataset, algorithms: algorithms
     assert_kind_of Model::LazarRegression, model
-    assert_equal "Algorithm::Regression.caret", model.algorithms[:prediction][:method]
+    assert_equal "Algorithm::Caret.regression", model.algorithms[:prediction][:method]
     assert_equal "Algorithm::Similarity.weighted_cosine", model.algorithms[:similarity][:method]
     assert_equal 0.1, model.algorithms[:similarity][:min]
     assert_equal algorithms[:descriptors], model.algorithms[:descriptors]
@@ -78,7 +78,7 @@ class ModelTest < MiniTest::Test
       training_dataset = Dataset.where(name: "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
     end
     model = Model::Lazar.create  training_dataset: training_dataset
-    assert_equal "Algorithm::Regression.caret", model.algorithms[:prediction][:method]
+    assert_equal "Algorithm::Caret.regression", model.algorithms[:prediction][:method]
     assert_equal "rf", model.algorithms[:prediction][:parameters]
     assert_equal "Algorithm::Similarity.weighted_cosine", model.algorithms[:similarity][:method]
     prediction = model.predict training_dataset.substances[14]
@@ -87,6 +87,7 @@ class ModelTest < MiniTest::Test
   end
 
   def test_nanoparticle_parameters
+    skip
   end
 
   def test_regression_with_feature_selection
@@ -98,13 +99,14 @@ class ModelTest < MiniTest::Test
     training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.mini_log10.csv")
     model = Model::Lazar.create  training_dataset: training_dataset, algorithms: algorithms
     assert_kind_of Model::LazarRegression, model
-    assert_equal "Algorithm::Regression.caret", model.algorithms[:prediction][:method]
+    assert_equal "Algorithm::Caret.regression", model.algorithms[:prediction][:method]
     assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method]
     assert_equal 0.1, model.algorithms[:similarity][:min]
     assert_equal algorithms[:feature_selection][:method], model.algorithms[:feature_selection][:method]
   end
 
   def test_caret_parameters
+    skip
   end
 
   def test_default_classification
@@ -153,25 +155,4 @@ class ModelTest < MiniTest::Test
     assert_equal 4, prediction[:neighbors].size
   end
 
-=begin
-  def test_physchem_description
-    assert_equal 355, PhysChem.descriptors.size
-    assert_equal 15, PhysChem.openbabel_descriptors.size
-    assert_equal 295, PhysChem.cdk_descriptors.size
-    assert_equal 45, PhysChem.joelib_descriptors.size
-    assert_equal 310, PhysChem.unique_descriptors.size
-  end
-
-  def test_physchem
-    assert_equal 355, PhysChem.descriptors.size
-    c = Compound.from_smiles "CC(=O)CC(C)C"
-    logP = PhysChem.find_or_create_by :name => "Openbabel.logP"
-    assert_equal 1.6215, logP.calculate(c)
-    jlogP = PhysChem.find_or_create_by :name => "Joelib.LogP"
-    assert_equal 3.5951, jlogP.calculate(c)
-    alogP = PhysChem.find_or_create_by :name => "Cdk.ALOGP.ALogP"
-    assert_equal 0.35380000000000034, alogP.calculate(c)
-  end
-=end
-
 end
diff --git a/test/nanoparticles.rb b/test/nanoparticles.rb
index 23c09e7..9b2d2d9 100644
--- a/test/nanoparticles.rb
+++ b/test/nanoparticles.rb
@@ -5,29 +5,26 @@ class NanoparticleTest  < MiniTest::Test
   include OpenTox::Validation
 
   def setup
-    # TODO: multiple runs create duplicates
-    #$mongo.database.drop
-    #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
     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_create_model
-    skip
-    @training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
-    feature = Feature.find_or_create_by(name: "Net cell association", category: "TOX", unit: "mL/ug(Mg)")
-    model = Model::LazarRegression.create(feature, @training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average", :neighbor_algorithm => "physchem_neighbors"})
+    model = Model::Lazar.create training_dataset: @training_dataset
     nanoparticle = @training_dataset.nanoparticles[-34]
     prediction = model.predict nanoparticle
+    p prediction
     refute_nil prediction[:value]
     assert_includes nanoparticle.dataset_ids, @training_dataset.id
     model.delete
   end
 
   def test_inspect_cv
+    skip
     cv = CrossValidation.all.sort_by{|cv| cv.created_at}.last
     #p cv
     #p cv.id
@@ -45,6 +42,7 @@ class NanoparticleTest  < MiniTest::Test
     end
   end
   def test_inspect_worst_prediction
+    skip
   
     cv = CrossValidation.all.sort_by{|cv| cv.created_at}.last
     worst_predictions = cv.worst_predictions(n: 3,show_neigbors: false)
@@ -64,10 +62,8 @@ class NanoparticleTest  < MiniTest::Test
   end
 
   def test_validate_model
-    #feature = Feature.find_or_create_by(name: "Net cell association", category: "TOX", unit: "mL/ug(Mg)")
-    feature = Feature.find_or_create_by(name: "Log2 transformed", category: "TOX")
-    
-    model = Model::LazarRegression.create(feature, @training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average", :feature_selection_algorithm => :correlation_filter, :neighbor_algorithm => "physchem_neighbors", :neighbor_algorithm_parameters => {:min_sim => 0.5}})
+    algorithms = { :prediction => {:method => "Algorithm::Regression.weighted_average" } }
+    model = Model::Lazar.create training_dataset: @training_dataset
     cv = RegressionCrossValidation.create model
     p cv.rmse
     p cv.r_squared
@@ -77,17 +73,14 @@ class NanoparticleTest  < MiniTest::Test
   end
 
   def test_validate_pls_model
-    feature = Feature.find_or_create_by(name: "Log2 transformed", category: "TOX")
-    
-    model = Model::LazarRegression.create(feature, @training_dataset, {
-      :prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression",
-      :feature_selection_algorithm => :correlation_filter,
-      :prediction_algorithm_parameters => {:method => 'pls'},
-      #:feature_selection_algorithm_parameters => {:category => "P-CHEM"},
-      #:feature_selection_algorithm_parameters => {:category => "Proteomics"},
-      :neighbor_algorithm => "physchem_neighbors",
-      :neighbor_algorithm_parameters => {:min_sim => 0.5}
-    })
+    algorithms = {
+      :descriptors => {
+        :method => "properties",
+        :types => ["P-CHEM"]
+      },
+      :prediction => {:method => "Algorithm::Caret.regression", :parameters => 'pls' },
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = RegressionCrossValidation.create model
     p cv.rmse
     p cv.r_squared
@@ -96,17 +89,14 @@ class NanoparticleTest  < MiniTest::Test
   end
 
   def test_validate_random_forest_model
-    feature = Feature.find_or_create_by(name: "Log2 transformed", category: "TOX")
-    
-    model = Model::LazarRegression.create(feature, @training_dataset, {
-      :prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression",
-      :prediction_algorithm_parameters => {:method => 'rf'},
-      :feature_selection_algorithm => :correlation_filter,
-      #:feature_selection_algorithm_parameters => {:category => "P-CHEM"},
-      #:feature_selection_algorithm_parameters => {:category => "Proteomics"},
-      :neighbor_algorithm => "physchem_neighbors",
-      :neighbor_algorithm_parameters => {:min_sim => 0.5}
-    })
+    algorithms = {
+      :descriptors => {
+        :method => "properties",
+        :types => ["P-CHEM"]
+      },
+      :prediction => {:method => "Algorithm::Caret.regression", :parameters => 'rf' }
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = RegressionCrossValidation.create model
     p cv.rmse
     p cv.r_squared
@@ -115,9 +105,28 @@ class NanoparticleTest  < MiniTest::Test
   end
 
   def test_validate_proteomics_pls_model
-    feature = Feature.find_or_create_by(name: "Log2 transformed", category: "TOX")
-    
-    model = Model::LazarRegression.create(feature, @training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression", :neighbor_algorithm => "proteomics_neighbors", :neighbor_algorithm_parameters => {:min_sim => 0.5}})
+    algorithms = {
+      :descriptors => {
+        :method => "properties",
+        :types => ["Proteomics"]
+      },
+      :prediction => {:method => "Algorithm::Caret.regression", :parameters => 'rf' }
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    cv = RegressionCrossValidation.create model
+    p cv.rmse
+    p cv.r_squared
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+  def test_validate_all_default_model
+    algorithms = {
+      :descriptors => {
+        :types => ["Proteomics","P-CHEM"]
+      },
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
     cv = RegressionCrossValidation.create model
     p cv.rmse
     p cv.r_squared
diff --git a/test/validation.rb b/test/validation.rb
index b4f5a92..03adf69 100644
--- a/test/validation.rb
+++ b/test/validation.rb
@@ -7,7 +7,7 @@ class ValidationTest < MiniTest::Test
   
   def test_default_classification_crossvalidation
     dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
-    model = Model::LazarClassification.create dataset.features.first, dataset
+    model = Model::Lazar.create training_dataset: dataset
     cv = ClassificationCrossValidation.create model
     assert cv.accuracy > 0.7, "Accuracy (#{cv.accuracy}) should be larger than 0.7, this may occur due to an unfavorable training/test set split"
     assert cv.weighted_accuracy > cv.accuracy, "Weighted accuracy (#{cv.weighted_accuracy}) should be larger than accuracy (#{cv.accuracy})."
@@ -15,9 +15,9 @@ class ValidationTest < MiniTest::Test
 
   def test_default_regression_crossvalidation
     dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv"
-    model = Model::LazarRegression.create dataset.features.first, dataset
+    model = Model::Lazar.create training_dataset: dataset
     cv = RegressionCrossValidation.create model
-    assert cv.rmse < 1.5, "RMSE #{cv.rmse} should be larger than 1.5, this may occur due to an unfavorable training/test set split"
+    assert cv.rmse < 1.5, "RMSE #{cv.rmse} should be smaller than 1.5, this may occur due to an unfavorable training/test set split"
     assert cv.mae < 1, "MAE #{cv.mae} should be smaller than 1, this may occur due to an unfavorable training/test set split"
   end
 
@@ -25,23 +25,20 @@ class ValidationTest < MiniTest::Test
 
   def test_classification_crossvalidation_parameters
     dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
-    params = {
-      :neighbor_algorithm_parameters => {
-        :min_sim => 0.3,
-        :type => "FP3"
-      }
+    algorithms = {
+      :similarity => { :min => 0.3, },
+      :descriptors => { :type => "FP3" }
     }
-    model = Model::LazarClassification.create dataset.features.first, dataset, params
-    model.save
+    model = Model::Lazar.create training_dataset: dataset, algorithms: algorithms
     cv = ClassificationCrossValidation.create model
-    params = model.neighbor_algorithm_parameters
+    params = model.algorithms
     params = Hash[params.map{ |k, v| [k.to_s, v] }] # convert symbols to string
-
+    
     cv.validations.each do |validation|
-      validation_params = validation.model.neighbor_algorithm_parameters
-      refute_nil params["dataset_id"]
-      refute_nil validation_params[:dataset_id]
-      refute_equal params["dataset_id"], validation_params[:dataset_id]
+      validation_params = validation.model.algorithms
+      refute_nil model.training_dataset_id
+      refute_nil validation.model.training_dataset_id
+      refute_equal model.training_dataset_id, validation.model.training_dataset_id
       ["min_sim","type","prediction_feature_id"].each do |k|
         assert_equal params[k], validation_params[k]
       end
@@ -50,24 +47,20 @@ class ValidationTest < MiniTest::Test
   
   def test_regression_crossvalidation_params
     dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv"
-    params = {
-      :prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average",
-      :neighbor_algorithm => "fingerprint_neighbors",
-      :neighbor_algorithm_parameters => {
-        :type => "MACCS",
-        :min_sim => 0.7,
-      }
+    algorithms = {
+      :prediction => { :method => "OpenTox::Algorithm::Regression.weighted_average" },
+      :descriptors => { :type => "MACCS", },
+      :similarity => {:min => 0.7}
     }
-    model = Model::LazarRegression.create dataset.features.first, dataset, params
-    assert_equal params[:neighbor_algorithm_parameters][:type], model[:neighbor_algorithm_parameters][:type]
+    model = Model::Lazar.create training_dataset: dataset, algorithms: algorithms
+    assert_equal algorithms[:descriptors][:type], model.algorithms[:descriptors][:type]
     cv = RegressionCrossValidation.create model
     cv.validation_ids.each do |vid|
       model = Model::Lazar.find(Validation.find(vid).model_id)
-      assert_equal params[:neighbor_algorithm_parameters][:type], model[:neighbor_algorithm_parameters][:type]
-      assert_equal params[:neighbor_algorithm_parameters][:min_sim], model[:neighbor_algorithm_parameters][:min_sim]
-      refute_nil model[:neighbor_algorithm_parameters][:dataset_id]
-      refute_equal dataset.id, model[:neighbor_algorithm_parameters][:dataset_id]
-      assert_equal model.training_dataset_id, model[:neighbor_algorithm_parameters][:dataset_id]
+      assert_equal algorithms[:descriptors][:type], model.algorithms[:descriptors][:type]
+      assert_equal algorithms[:similarity][:min], model.algorithms[:similarity][:min]
+      refute_nil model.training_dataset_id
+      refute_equal dataset.id, model.training_dataset_id
     end
 
     refute_nil cv.rmse
@@ -77,7 +70,7 @@ class ValidationTest < MiniTest::Test
   def test_physchem_regression_crossvalidation
     skip # TODO: fix
     training_dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
-    model = Model::LazarRegression.create(training_dataset.features.first, training_dataset, :prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression")
+    model = Model::Lazar.create(training_dataset.features.first, training_dataset, :prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression")
     cv = RegressionCrossValidation.create model
     refute_nil cv.rmse
     refute_nil cv.mae 
@@ -87,7 +80,7 @@ class ValidationTest < MiniTest::Test
 
   def test_classification_loo_validation
     dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
-    model = Model::LazarClassification.create dataset.features.first, dataset
+    model = Model::Lazar.create training_dataset: dataset
     loo = ClassificationLeaveOneOut.create model
     assert_equal 14, loo.nr_unpredicted
     refute_empty loo.confusion_matrix
@@ -97,7 +90,7 @@ class ValidationTest < MiniTest::Test
 
   def test_regression_loo_validation
     dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
-    model = Model::LazarRegression.create dataset.features.first, dataset
+    model = Model::Lazar.create training_dataset: dataset
     loo = RegressionLeaveOneOut.create model
     assert loo.r_squared > 0.34, "R^2 (#{loo.r_squared}) should be larger than 0.034"
   end
@@ -106,7 +99,7 @@ class ValidationTest < MiniTest::Test
 
   def test_repeated_crossvalidation
     dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
-    model = Model::LazarClassification.create dataset.features.first, dataset
+    model = Model::Lazar.create training_dataset: dataset
     repeated_cv = RepeatedCrossValidation.create model
     repeated_cv.crossvalidations.each do |cv|
       assert_operator cv.accuracy, :>, 0.7, "model accuracy < 0.7, this may happen by chance due to an unfavorable training/test set split"