first nanomaterial prediction

3 files changed, 40 insertions, 6 deletions

diff --git a/test/nanoparticles.rb b/test/nanoparticles.rb
index 46073a9..31bb903 100644
--- a/test/nanoparticles.rb
+++ b/test/nanoparticles.rb
@@ -11,9 +11,38 @@ class NanoparticleTest  < MiniTest::Test
     p dataset_ids.collect{|d| {d => Dataset.find(d).name}}
     dataset_ids.collect do |d|
       d = Dataset.find(d)
-      p d.name
-      puts d.to_csv
+      #p d.name
+      #puts d.to_csv
+    end
+  end
+
+  def test_summaries
+    features = Feature.all.to_a
+    #p features.collect do |f|
+      #f if f.category == "TOX"
+    #end.to_a.flatten.size
+    toxcounts = {}
+    pccounts = {}
+    Nanoparticle.all.each do |np|
+      np.toxicities.each do |t,v|
+        toxcounts[t] ||= 0
+        toxcounts[t] += 1#v.uniq.size
+      end
+      np.physchem_descriptors.each do |t,v|
+        pccounts[t] ||= 0
+        pccounts[t] += 1#v.uniq.size
+      end
     end
+    #puts counts.keys.collect{|i| Feature.find(i)}.to_yaml
+    #pccounts.each{|e,n| p Feature.find(e),n if n > 100}
+    #p toxcounts.collect{|e,n| Feature.find(e).name if n > 1}.uniq
+    toxcounts.each{|e,n| p Feature.find(e),n if n > 100}
+  end
+
+
+  def test_import_ld
+    skip
+    dataset_ids = Import::Enanomapper.import_ld
   end
 
   def test_export
@@ -24,11 +53,14 @@ class NanoparticleTest  < MiniTest::Test
 
   def test_create_model
     training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
-    model = Model::LazarRegression.create(training_dataset, :prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression", :neighbor_algorithm => "nanoparticle_neighbors")
+    feature = Feature.find_or_create_by(name: "7.99 Toxicity (other) ICP-AES", category: "TOX", unit: "mL/ug(Mg)")
+    model = Model::LazarRegression.create(feature, training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression", :neighbor_algorithm => "nanoparticle_neighbors"})
     nanoparticle = training_dataset.nanoparticles[-34]
+    #p nanoparticle.neighbors
     prediction = model.predict nanoparticle
     p prediction
-    refute_nil prediction[:value]
+    #p prediction
+    #refute_nil prediction[:value]
   end
 
 end
diff --git a/test/setup.rb b/test/setup.rb
index e7c32b4..6c97282 100644
--- a/test/setup.rb
+++ b/test/setup.rb
@@ -5,5 +5,5 @@ require_relative '../lib/lazar.rb'
 include OpenTox
 TEST_DIR ||= File.expand_path(File.dirname(__FILE__))
 DATA_DIR ||= File.join(TEST_DIR,"data")
-$mongo.database.drop
-$gridfs = $mongo.database.fs
+#$mongo.database.drop
+#$gridfs = $mongo.database.fs
diff --git a/test/validation.rb b/test/validation.rb
index baee2d1..cbc7d09 100644
--- a/test/validation.rb
+++ b/test/validation.rb
@@ -9,6 +9,7 @@ class ValidationTest < MiniTest::Test
     model = Model::LazarClassification.create dataset.features.first, 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})."
   end
 
   def test_default_regression_crossvalidation
@@ -85,6 +86,7 @@ class ValidationTest < MiniTest::Test
     assert_equal 14, loo.nr_unpredicted
     refute_empty loo.confusion_matrix
     assert loo.accuracy > 0.77
+    assert loo.weighted_accuracy > loo.accuracy, "Weighted accuracy (#{loo.weighted_accuracy}) should be larger than accuracy (#{loo.accuracy})."
   end
 
   def test_regression_loo_validation