def run_pipeline_from_automl(train_file_path: str,
test_file_path: str,
max_run_time: timedelta = timedelta(minutes=10)):
""" Function run pipeline with Auto ML models in nodes
:param train_file_path: path to the csv file with data for train
:param test_file_path: path to the csv file with data for validation
:param max_run_time: maximum running time for customization of the "tpot" model
:return roc_auc_value: ROC AUC metric for pipeline
"""
train_data = InputData.from_csv(train_file_path)
test_data = InputData.from_csv(test_file_path)
testing_target = test_data.target
node_scaling = PrimaryNode('scaling')
node_tpot = PrimaryNode('tpot')
node_tpot.operation.params = {'max_run_time_sec': max_run_time.seconds}
node_lda = SecondaryNode('lda', nodes_from=[node_scaling])
node_rf = SecondaryNode('rf', nodes_from=[node_tpot, node_lda])
OperationTypesRepository.assign_repo('model', 'automl_repository.json')
pipeline = Pipeline(node_rf)
pipeline.fit(train_data)
results = pipeline.predict(test_data)
roc_auc_value = roc_auc(y_true=testing_target, y_score=results.predict)
print(roc_auc_value)
return roc_auc_value
def test_pipeline_from_automl_example():
project_root_path = str(fedot_project_root())
with OperationTypesRepository().assign_repo('model', 'model_repository_with_automl.json') as _:
file_path_train = os.path.join(project_root_path, 'test/data/simple_classification.csv')
file_path_test = file_path_train
auc = run_pipeline_from_automl(file_path_train, file_path_test, max_run_time=timedelta(seconds=1))
OperationTypesRepository.assign_repo('model', 'model_repository.json')
assert auc > 0.5