def test_scenario2(self): """ Scenario: Successfully building feature selection from dataset: Given I create BigML dataset uploading train "<data>" file in "<output>" And I check that the source has been created And I check that the dataset has been created And I create BigML feature selection <kfold>-fold cross-validations improving "<metric>" And I check that the <kfold>-datasets have been created And I check that the <kfold>-models have been created And I check that all the <kfold>-fold cross-validations have been created Then the best feature selection is "<selection>", with "<metric>" of <metric_value> And I generate a report from the output directory And a symlink file is generated in the reports directory Examples: | data | output | kfold | metric | selection | metric_value | ../data/iris_2f.csv | ./scenario_a_2/evaluation | 2 | accuracy | petal width | 100.00% | ../data/iris_2f.csv | ./scenario_a_3/evaluation | 2 | phi | petal width | 1 """ print self.test_scenario2.__doc__ examples = [ ['data/iris_2f.csv', 'scenario_a_2/evaluation', '2', 'accuracy', 'petal width', '100.00%'], ['data/iris_2f.csv', 'scenario_a_3/evaluation', '2', 'phi', 'petal width', '1']] for example in examples: print "\nTesting with:\n", example test_pred.i_create_dataset(self, data=example[0], output=example[1]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self) test_pred.i_create_kfold_cross_validation_metric(self, k_folds=example[2], metric=example[3]) test_pred.i_check_create_kfold_datasets(self, example[2]) test_pred.i_check_create_kfold_models(self, example[2]) test_pred.i_check_create_all_kfold_cross_validations(self, example[2]) test_pred.i_check_feature_selection(self, example[4], example[3], example[5]) test_pred.i_generate_report(self) test_pred.is_symlink(self)