diff options
author | Christoph Helma <helma@in-silico.ch> | 2019-08-24 15:06:53 +0200 |
---|---|---|
committer | Christoph Helma <helma@in-silico.ch> | 2019-08-24 15:06:53 +0200 |
commit | 8e1e8b94539dbdd74bd4ac28295cbfd1b84036ab (patch) | |
tree | 28528e19dc6ed4cca7ed824e939dedd6c4acc94c /test/validation-classification.rb | |
parent | 1ee7de09c969e16fd11522d22179224e694b0161 (diff) | |
parent | 488ce9fe6d4b715680675861105b8c52a7535140 (diff) |
Merge remote-tracking branch 'origin/development'
Diffstat (limited to 'test/validation-classification.rb')
-rw-r--r-- | test/validation-classification.rb | 67 |
1 files changed, 0 insertions, 67 deletions
diff --git a/test/validation-classification.rb b/test/validation-classification.rb deleted file mode 100644 index ce06063..0000000 --- a/test/validation-classification.rb +++ /dev/null @@ -1,67 +0,0 @@ -require_relative "setup.rb" - -class ValidationClassificationTest < MiniTest::Test - include OpenTox::Validation - - # defaults - - def test_default_classification_crossvalidation - dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv" - 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})." - File.open("/tmp/tmp.pdf","w+"){|f| f.puts cv.probability_plot(format:"pdf")} - p `file -b /tmp/tmp.pdf` - File.open("/tmp/tmp.png","w+"){|f| f.puts cv.probability_plot(format:"png")} - p `file -b /tmp/tmp.png` - end - - # parameters - - def test_classification_crossvalidation_parameters - dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv" - algorithms = { - :similarity => { :min => 0.3, }, - :descriptors => { :type => "FP3" } - } - model = Model::Lazar.create training_dataset: dataset, algorithms: algorithms - cv = ClassificationCrossValidation.create model - 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.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 - end - end - - # LOO - - def test_classification_loo_validation - dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv" - model = Model::Lazar.create training_dataset: dataset - loo = ClassificationLeaveOneOut.create model - assert_equal 24, 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 - - # repeated CV - - def test_repeated_crossvalidation - dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv" - 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" - end - end - -end |