def test_scenario2(self): """ Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with proportional missing strategy and log predictions in "<output>" And I check that the source has been created And I check that the dataset has been created And I check that the model has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch prediction has been created And I check that the predictions are ready Then the local prediction file is like "<predictions_file>" Examples: | data | test | output |predictions_file | | ../data/iris.csv | ../data/test_iris_nulls.csv | ./scenario_mis_2/predictions.csv | ./check_files/predictions_iris_nulls.csv """ print self.test_scenario2.__doc__ examples = [ ['data/iris.csv', 'data/test_iris_nulls.csv', 'scenario_mis_2/predictions.csv', 'check_files/predictions_iris_nulls.csv']] for example in examples: print "\nTesting with:\n", example test_pred.i_create_all_resources_remote_proportional(self, data=example[0], test=example[1], output=example[2]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self, suffix=None) test_pred.i_check_create_model(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) test_pred.i_check_create_batch_prediction(self) test_pred.i_check_create_predictions(self) test_pred.i_check_predictions(self, example[3])
def test_scenario2(self): """ Scenario: Successfully building test predictions from scratch: Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with a missing-splits model and log predictions in "<output>" And I check that the source has been created And I check that the dataset has been created And I check that the model has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch prediction has been created And I check that the predictions are ready Then the local prediction file is like "<predictions_file>" Examples: | data | test | output |predictions_file | | ../data/iris_missing.csv | ../data/test_iris_missing.csv | ./scenario_mspl_2/predictions.csv | ./check_files/predictions_iris_missing.csv """ print self.test_scenario2.__doc__ examples = [[ 'data/iris_missing.csv', 'data/test_iris_missing.csv', 'scenario_mspl_2/predictions.csv', 'check_files/predictions_iris_missing.csv' ]] for example in examples: print "\nTesting with:\n", example test_pred.i_create_all_resources_remote_missing_splits( self, data=example[0], test=example[1], output=example[2]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self, suffix=None) test_pred.i_check_create_model(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) test_pred.i_check_create_batch_prediction(self) test_pred.i_check_create_predictions(self) test_pred.i_check_predictions(self, example[3])
def test_scenario1(self): """ Scenario: Successfully building test centroid predictions from scratch: Given I create BigML resources uploading train "<data>" file to find centroids for "<test>" remotely with mapping file "<fields_map>" and log predictions in "<output>" And I check that the source has been created And I check that the dataset has been created And I check that the cluster has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch centroid prediction has been created And I check that the centroids are ready Then the local centroids file is like "<predictions_file>" Examples: | data | test | fields_map | output |predictions_file | | ../data/grades.csv | ../data/grades_perm.csv | ../data/grades_fields_map_perm.csv | ./scenario_cb_1_r/centroids.csv | ./check_files/centroids_grades.csv | """ print self.test_scenario1.__doc__ examples = [ ['data/grades.csv', 'data/grades_perm.csv', 'data/grades_fields_map_perm.csv', 'scenario_cb_1_r/centroids.csv', 'check_files/centroids_grades.csv']] for example in examples: print "\nTesting with:\n", example test_cluster.i_create_all_cluster_resources_with_mapping(self, data=example[0], test=example[1], fields_map=example[2], output=example[3]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self, suffix=None) test_pred.i_check_create_cluster(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) batch_pred.i_check_create_batch_centroid(self) test_cluster.i_check_create_centroids(self) test_pred.i_check_predictions(self, example[4])
def test_scenario2(self): """ Scenario: Successfully building remote test centroid predictions from scratch to dataset: Given I create BigML resources uploading train "<data>" file to find centroids for "<test>" remotely to dataset with no CSV and log resources in "<output_dir>" And I check that the source has been created And I check that the dataset has been created And I check that the cluster has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch centroid prediction has been created Then I check that the batch centroids dataset exists And no local CSV file is created Examples: | data | test | output_dir | | ../data/grades.csv | ../data/test_grades.csv | ./scenario_cb_2 | """ print self.test_scenario2.__doc__ examples = [ ['data/grades.csv', 'data/test_grades.csv', 'scenario_cb_2']] for example in examples: print "\nTesting with:\n", example test_cluster.i_create_all_cluster_resources_to_dataset(self, data=example[0], test=example[1], output_dir=example[2]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self, suffix=None) test_pred.i_check_create_cluster(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) batch_pred.i_check_create_batch_centroid(self) batch_pred.i_check_create_batch_centroids_dataset(self) test_anomaly.i_check_no_local_CSV(self)
def test_scenario2(self): """ Scenario: Successfully building remote test centroid predictions from scratch to dataset: Given I create BigML resources uploading train "<data>" file to find centroids for "<test>" remotely to dataset with no CSV and log resources in "<output_dir>" And I check that the source has been created And I check that the dataset has been created And I check that the cluster has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch centroid prediction has been created Then I check that the batch centroids dataset exists And no local CSV file is created Examples: | data | test | output_dir | | ../data/grades.csv | ../data/test_grades.csv | ./scenario_cb_2 | """ print self.test_scenario2.__doc__ examples = [[ 'data/grades.csv', 'data/test_grades.csv', 'scenario_cb_2' ]] for example in examples: print "\nTesting with:\n", example test_cluster.i_create_all_cluster_resources_to_dataset( self, data=example[0], test=example[1], output_dir=example[2]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self, suffix=None) test_pred.i_check_create_cluster(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) batch_pred.i_check_create_batch_centroid(self) batch_pred.i_check_create_batch_centroids_dataset(self) test_anomaly.i_check_no_local_CSV(self)
def test_scenario1(self): """ Scenario: Successfully building test anomaly score predictions from scratch: Given I create BigML resources uploading train "<data>" file to find anomaly scores for "<test>" remotely with mapping file "<fields_map>" and log predictions in "<output>" And I check that the source has been created And I check that the dataset has been created And I check that the anomaly detector has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch anomaly scores prediction has been created And I check that the anomaly scores are ready Then the local anomaly scores file is like "<predictions_file>" Examples: | data | test | fields_map | output |predictions_file | | ../data/grades.csv | ../data/grades_perm.csv | ../data/grades_fields_map_perm.csv | ./scenario_ab_1_r/anomalies.csv | ./check_files/anomaly_scores_grades.csv | """ print self.test_scenario1.__doc__ examples = [ ['data/grades.csv', 'data/grades_perm.csv', 'data/grades_fields_map_perm.csv', 'scenario_ab_1_r/anomalies.csv', 'check_files/anomaly_scores_grades.csv']] for example in examples: print "\nTesting with:\n", example test_anomaly.i_create_all_anomaly_resources_with_mapping(self, data=example[0], test=example[1], fields_map=example[2], output=example[3]) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self) test_anomaly.i_check_create_anomaly(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) test_batch.i_check_create_batch_anomaly_scores(self) test_anomaly.i_check_create_anomaly_scores(self) test_anomaly.i_check_anomaly_scores(self, example[4])
def test_scenario2(self): """ Scenario: Successfully building test predictions from scratch: Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with a missing-splits model and log predictions in "<output>" And I check that the source has been created And I check that the dataset has been created And I check that the model has been created And I check that the source has been created from the test file And I check that the dataset has been created from the test file And I check that the batch prediction has been created And I check that the predictions are ready Then the local prediction file is like "<predictions_file>" Examples: | data | test | output |predictions_file | | ../data/iris_missing.csv | ../data/test_iris_missing.csv | ./scenario_mspl_2/predictions.csv | ./check_files/predictions_iris_missing.csv """ print self.test_scenario2.__doc__ examples = [ [ "data/iris_missing.csv", "data/test_iris_missing.csv", "scenario_mspl_2/predictions.csv", "check_files/predictions_iris_missing.csv", ] ] for example in examples: print "\nTesting with:\n", example test_pred.i_create_all_resources_remote_missing_splits( self, data=example[0], test=example[1], output=example[2] ) test_pred.i_check_create_source(self) test_pred.i_check_create_dataset(self, suffix=None) test_pred.i_check_create_model(self) test_pred.i_check_create_test_source(self) test_pred.i_check_create_test_dataset(self) test_pred.i_check_create_batch_prediction(self) test_pred.i_check_create_predictions(self) test_pred.i_check_predictions(self, example[3])