From 9d17895ab9e8cd31e0f32e8e622e13612ea5ff77 Mon Sep 17 00:00:00 2001 From: "helma@in-silico.ch" Date: Fri, 12 Oct 2018 21:58:36 +0200 Subject: validation statistic fixes --- test/regression-model.rb | 171 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 171 insertions(+) create mode 100644 test/regression-model.rb (limited to 'test/regression-model.rb') diff --git a/test/regression-model.rb b/test/regression-model.rb new file mode 100644 index 0000000..5903e88 --- /dev/null +++ b/test/regression-model.rb @@ -0,0 +1,171 @@ +require_relative "setup.rb" + +class LazarRegressionTest < MiniTest::Test + + def test_default_regression + algorithms = { + :descriptors => { + :method => "fingerprint", + :type => "MP2D" + }, + :similarity => { + :method => "Algorithm::Similarity.tanimoto", + :min => 0.5 + }, + :prediction => { + :method => "Algorithm::Caret.rf", + }, + :feature_selection => nil, + } + training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM_log10.csv") + model = Model::Lazar.create training_dataset: training_dataset + assert_kind_of Model::LazarRegression, model + assert_equal algorithms, model.algorithms + substance = training_dataset.substances[145] + prediction = model.predict substance + assert_includes prediction[:prediction_interval][0]..prediction[:prediction_interval][1], prediction[:measurements].median, "This assertion assures that measured values are within the prediction interval. It may fail in 5% of the predictions." + substance = Compound.from_smiles "c1ccc(cc1)Oc1ccccc1" + prediction = model.predict substance + refute_nil prediction[:value] + refute_nil prediction[:prediction_interval] + refute_empty prediction[:neighbors] + end + + def test_weighted_average + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" + algorithms = { + :similarity => { + :min => 0 + }, + :prediction => { + :method => "Algorithm::Regression.weighted_average", + }, + } + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + compound = Compound.from_smiles "CC(C)(C)CN" + prediction = model.predict compound + assert_equal -0.86, prediction[:value].round(2) + assert_equal model.substance_ids.size, prediction[:neighbors].size + end + + def test_mpd_fingerprints + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" + algorithms = { + :descriptors => { + :method => "fingerprint", + :type => "MP2D" + }, + } + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + compound = Compound.from_smiles "CCCSCCSCC" + prediction = model.predict compound + assert_equal 3, prediction[:neighbors].size + assert prediction[:value].round(2) > 1.37, "Prediction value (#{prediction[:value].round(2)}) should be larger than 1.37." + end + + def test_local_physchem_regression + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" + algorithms = { + :descriptors => { + :method => "calculate_properties", + :features => PhysChem.openbabel_descriptors, + }, + :similarity => { + :method => "Algorithm::Similarity.weighted_cosine", + :min => 0.5 + }, + } + model = Model::Lazar.create(training_dataset:training_dataset, algorithms:algorithms) + compound = Compound.from_smiles "NC(=O)OCCC" + prediction = model.predict compound + refute_nil prediction[:value] + end + + def test_local_physchem_regression_with_feature_selection + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" + algorithms = { + :descriptors => { + :method => "calculate_properties", + :features => PhysChem.openbabel_descriptors, + }, + :similarity => { + :method => "Algorithm::Similarity.weighted_cosine", + :min => 0.5 + }, + :feature_selection => { + :method => "Algorithm::FeatureSelection.correlation_filter", + }, + } + model = Model::Lazar.create(training_dataset:training_dataset, algorithms:algorithms) + compound = Compound.from_smiles "NC(=O)OCCC" + prediction = model.predict compound + refute_nil prediction[:value] + end + + def test_unweighted_cosine_physchem_regression + algorithms = { + :descriptors => { + :method => "calculate_properties", + :features => PhysChem.openbabel_descriptors, + }, + :similarity => { + :method => "Algorithm::Similarity.cosine", + } + } + training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv") + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + assert_kind_of Model::LazarRegression, model + assert_equal "Algorithm::Caret.rf", model.algorithms[:prediction][:method] + assert_equal "Algorithm::Similarity.cosine", model.algorithms[:similarity][:method] + assert_equal 0.5, model.algorithms[:similarity][:min] + algorithms[:descriptors].delete :features + assert_equal algorithms[:descriptors], model.algorithms[:descriptors] + prediction = model.predict training_dataset.substances[10] + refute_nil prediction[:value] + end + + def test_regression_with_feature_selection + algorithms = { + :feature_selection => { + :method => "Algorithm::FeatureSelection.correlation_filter", + }, + } + training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM_log10.csv") + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + assert_kind_of Model::LazarRegression, model + assert_equal "Algorithm::Caret.rf", model.algorithms[:prediction][:method] + assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method] + assert_equal 0.5, model.algorithms[:similarity][:min] + assert_equal algorithms[:feature_selection][:method], model.algorithms[:feature_selection][:method] + prediction = model.predict training_dataset.substances[145] + refute_nil prediction[:value] + end + + def test_regression_parameters + algorithms = { + :descriptors => { + :method => "fingerprint", + :type => "MP2D" + }, + :similarity => { + :method => "Algorithm::Similarity.tanimoto", + :min => 0.3 + }, + :prediction => { + :method => "Algorithm::Regression.weighted_average", + }, + :feature_selection => nil, + } + training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv") + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + assert_kind_of Model::LazarRegression, model + assert_equal "Algorithm::Regression.weighted_average", model.algorithms[:prediction][:method] + assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method] + assert_equal algorithms[:similarity][:min], model.algorithms[:similarity][:min] + assert_equal algorithms[:prediction][:parameters], model.algorithms[:prediction][:parameters] + substance = training_dataset.substances[10] + prediction = model.predict substance + assert_equal 0.83, prediction[:value].round(2) + end + +end -- cgit v1.2.3