def test_scenario4(self): """ Scenario: Successfully building feature selection from filtered dataset setting objective: 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 filter out field "<field>" from dataset and log to "<output_dir>" And I check that the new dataset has been created And I create BigML feature selection <kfold>-fold cross-validations for "<objective>" 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> Examples: | data | field | objective |output | output_dir | kfold | metric | selection | metric_value | | ../data/iris_2fd.csv | sepal length | species |./scenario_a_6/evaluation |./scenario_a_6 | 2 | recall | petal width | 100.00% | """ print self.test_scenario4.__doc__ examples = [ ['data/iris_2fd.csv', 'sepal length', 'species', 'scenario_a_6/evaluation', 'scenario_a_6', '2', 'recall', 'petal width', '100.00%']] for example in examples: print "\nTesting with:\n", example test_pred.i_create_dataset(self, data=example[0], output=example[3]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self) dataset.i_filter_field_from_dataset(self, field=example[1], output_dir=example[4]) test_pred.i_check_create_new_dataset(self) test_pred.i_create_kfold_cross_validation_objective(self, k_folds=example[5], objective=example[2], metric=example[6]) test_pred.i_check_create_kfold_datasets(self, example[5]) test_pred.i_check_create_kfold_models(self, example[5]) test_pred.i_check_create_all_kfold_cross_validations(self, example[5]) test_pred.i_check_feature_selection(self, example[7], example[6], example[8])
def test_scenario3(self): """ Scenario: Successfully building feature selection from dataset setting objective: 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 for "<objective>" 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> Examples: | data | objective |output | kfold | metric | selection | metric_value | | ../data/iris_2f.csv | 0 |./scenario_a_5/evaluation | 2 | r_squared| species | 0.352845 | | ../data/iris_2f.csv | 0 |./scenario_a_8/evaluation | 2 | mean_squared_error| species | 0.475200 | """ print self.test_scenario3.__doc__ examples = [ ['data/iris_2f.csv', '0', 'scenario_a_5/evaluation', '2', 'r_squared', 'species', '0.352845'], ['data/iris_2f.csv', '0', 'scenario_a_8/evaluation', '2', 'mean_squared_error', 'species', '0.475200']] for example in examples: print "\nTesting with:\n", example test_pred.i_create_dataset(self, data=example[0], output=example[2]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self) test_pred.i_create_kfold_cross_validation_objective(self, k_folds=example[3], objective=example[1], metric=example[4]) test_pred.i_check_create_kfold_datasets(self, example[3]) test_pred.i_check_create_kfold_models(self, example[3]) test_pred.i_check_create_all_kfold_cross_validations(self, example[3]) test_pred.i_check_feature_selection(self, example[5], example[4], example[6])