public model validation, updated documentation

1 files changed, 17 insertions, 38 deletions

diff --git a/test/use_cases.rb b/test/use_cases.rb
index f39b3e2..51c3fef 100644
--- a/test/use_cases.rb
+++ b/test/use_cases.rb
@@ -3,59 +3,38 @@ require_relative "setup.rb"
 class UseCasesTest < MiniTest::Test
 
   def test_PA
-    # TODO add assertions
     skip "This test ist very time consuming, enable on demand."
-    kazius = Dataset.from_sdf_file "#{DATA_DIR}/cas_4337.sdf"
-    hansen = Dataset.from_csv_file "#{DATA_DIR}/hansen.csv"
-    efsa = Dataset.from_csv_file "#{DATA_DIR}/efsa.csv"
-    datasets = [kazius,hansen,efsa]
-    map = {"1" => "mutagen", "0" => "nonmutagen"}
-    #p "merging"
-    training_dataset = Dataset.merge datasets: datasets, features: datasets.collect{|d| d.bioactivity_features.first}, value_maps: [nil,map,map], keep_original_features: false, remove_duplicates: true
+    Download.mutagenicity
+    training_dataset = Dataset.from_csv_file File.join(Download::DATA,"Mutagenicity-Salmonella_typhimurium.csv")
     assert_equal 8281, training_dataset.compounds.size
-    #p training_dataset.features.size
-    #p training_dataset.id
-    #training_dataset = Dataset.find('5bd8ac8fca62695d767fca6b')
-    #training_dataset = Dataset.find('5bd8bbadca62695f69e7a33b')
-    #puts training_dataset.to_csv
-    #p "create model_validation"
-    model_validation = Model::Validation.from_dataset training_dataset: training_dataset, prediction_feature: training_dataset.merged_features.first, species: "Salmonella typhimurium", endpoint: "Mutagenicity"
-    #p model_validation.id
-    #model_validation = Model::Validation.find '5bd8df47ca6269604590ab38'
-    #p model_validation.crossvalidations.first.predictions.select{|cid,p| !p["warnings"].empty?}
-    #p "predict"
+    # TODO use Model::Validation.from_csv_file
+    model_validation = Model::Validation.from_csv_file File.join(Download::DATA,"Mutagenicity-Salmonella_typhimurium.csv")
     pa = Dataset.from_sdf_file "#{DATA_DIR}/PA.sdf"
     prediction_dataset = model_validation.predict pa
-    #p prediction_dataset.id
-    #prediction_dataset = Dataset.find('5bd98b88ca6269609aab79f4')
-    #puts prediction_dataset.to_csv
+    # TODO add assertions
   end
 
   def test_tox21
-    # TODO add assertions
     skip "This test ist very time consuming, enable on demand."
-    training_dataset = Dataset.from_pubchem_aid 743122
-    #p training_dataset.id
-    #'5bd9a1dbca626969d97fb421'
-    #File.open("AID743122.csv","w+"){|f| f.puts training_dataset.to_csv}
-    #model = Model::Lazar.create training_dataset: training_dataset
-    #p model.id
-    #p Model::Lazar.find('5bd9a70bca626969d97fc9df')
-    model_validation = Model::Validation.from_dataset training_dataset: training_dataset, prediction_feature: training_dataset.bioactivity_features.first, species: "Human HG2L7.5c1 cell line", endpoint: "aryl hydrocarbon receptor (AhR) signaling pathway activation"
-    #model_validation = Model::Validation.find '5bd9b210ca62696be39ab74d'
-    #model_validation.crossvalidations.each do |cv|
-      #p cv
-    #end
-    #p model_validation.crossvalidations.first.predictions.select{|cid,p| !p["warnings"].empty?}
+    csv_file = Download.pubchem_classification aid: 743122, species: "Human HG2L7.5c1 cell line", endpoint: "aryl hydrocarbon receptor (AhR) signaling pathway activation"
+    model_validation = Model::Validation.from_csv_file csv_file
+    assert_equal 5, model_validation.crossvalidations.size
   end
 
   def test_download_public_models
+    skip "This test will overwrite public data." 
     Download.public_data
+    assert_equal 11, Dir[File.join(File.dirname(__FILE__),"..","data","*csv")].size
+    assert_equal 11, Dir[File.join(File.dirname(__FILE__),"..","data","*json")].size
+    # TODO: check values
   end
 
   def test_import_public_models
-    skip
-    Import.public_data
+    skip "This test is very time consuming, enable on demand."
+    #$mongo.database.drop
+    #$gridfs = $mongo.database.fs # recreate GridFS indexes
+    validated_models = Import.public_data
+    assert_equal Dir[File.join(File.dirname(__FILE__),"..","data/*csv")].size, validated_models.size
   end
 
 end