SIENTIAPDE-1241: Added remaining trainig_repository tests and some model_repository tests
This commit is contained in:
Kou-Kinoshita
@@ -199,3 +199,291 @@ def test_get_reports_directory(mock_model_serving_class, mock_logger):
|
||||
|
||||
assert result.endswith(os.path.join('model_manager', 'reports'))
|
||||
assert os.path.isabs(result)
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
def test_init_artifacts_data_success(mock_model_serving_class, mock_logger, mock_train_result):
|
||||
"""Test _init_artifacts_data successfully prepares data."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
reference_data, current_data = repo._init_artifacts_data(mock_train_result)
|
||||
|
||||
# Check reference data
|
||||
assert 'target' in reference_data.columns
|
||||
assert 'prediction' in reference_data.columns
|
||||
assert len(reference_data) == 3
|
||||
|
||||
# Check current data
|
||||
assert 'target' in current_data.columns
|
||||
assert 'prediction' in current_data.columns
|
||||
assert len(current_data) == 3
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
def test_init_artifacts_data_empty_x_train(mock_model_serving_class, mock_logger, mock_train_result):
|
||||
"""Test _init_artifacts_data raises ValueError when x_train is empty."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
mock_train_result.x_train = pd.DataFrame()
|
||||
|
||||
with pytest.raises(ValueError, match='Training features .* are empty'):
|
||||
repo._init_artifacts_data(mock_train_result)
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
def test_init_artifacts_data_empty_y_train(mock_model_serving_class, mock_logger, mock_train_result):
|
||||
"""Test _init_artifacts_data raises ValueError when y_train is empty."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
mock_train_result.y_train = pd.Series(dtype=float)
|
||||
|
||||
with pytest.raises(ValueError, match='Training target .* is empty'):
|
||||
repo._init_artifacts_data(mock_train_result)
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
def test_init_artifacts_data_none_y_pred(mock_model_serving_class, mock_logger, mock_train_result):
|
||||
"""Test _init_artifacts_data raises ValueError when y_pred is None."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
mock_train_result.y_pred = None
|
||||
|
||||
with pytest.raises(ValueError, match='Test predictions .* are None'):
|
||||
repo._init_artifacts_data(mock_train_result)
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.datetime')
|
||||
@patch('model_manager.utils.repository.model_repository.makedirs')
|
||||
def test_create_run_directory_success(
|
||||
mock_makedirs, mock_datetime, mock_model_serving_class, mock_logger
|
||||
):
|
||||
"""Test _create_run_directory creates directory successfully."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
mock_datetime.now.return_value.strftime.return_value = '20240101_120000_123456'
|
||||
|
||||
result = repo._create_run_directory('/tmp/reports', 'test_run') # noqa: S108
|
||||
|
||||
expected_path = os.path.join('/tmp/reports', 'test_run_20240101_120000_123456') # noqa: S108
|
||||
assert result == expected_path
|
||||
mock_makedirs.assert_called_once_with(expected_path, exist_ok=True)
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.makedirs')
|
||||
def test_create_run_directory_permission_error(
|
||||
mock_makedirs, mock_model_serving_class, mock_logger
|
||||
):
|
||||
"""Test _create_run_directory raises PermissionError."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
mock_makedirs.side_effect = PermissionError('Permission denied')
|
||||
|
||||
with pytest.raises(PermissionError, match='Permission denied when creating directory'):
|
||||
repo._create_run_directory('/tmp/reports', 'test_run') # noqa: S108
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.shutil.copy')
|
||||
@patch('builtins.open', create=True)
|
||||
def test_setup_run_directory_success(mock_open, mock_copy, mock_model_serving_class, mock_logger):
|
||||
"""Test _setup_run_directory creates files successfully."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
repo._setup_run_directory('/tmp/test_run', '/tmp/header.html') # noqa: S108
|
||||
|
||||
# Check that empty files were created
|
||||
assert mock_open.call_count == 3
|
||||
mock_copy.assert_called_once()
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.json.dump')
|
||||
@patch('model_manager.utils.repository.model_repository.Reports')
|
||||
@patch('builtins.open', create=True)
|
||||
def test_generate_report_with_equation(
|
||||
mock_open, mock_reports_class, mock_json_dump, mock_model_serving_class, mock_logger, mock_train_result
|
||||
):
|
||||
"""Test _generate_report creates equation JSON artifact."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
# Add equation to train result
|
||||
mock_train_result.equation = {
|
||||
'target_variable': 'target',
|
||||
'coefficients': {'var1': 1.5, 'var2': -0.75},
|
||||
'intercept': 10.5,
|
||||
'equation_string': 'target = 10.5 + 1.5 * var1 + -0.75 * var2',
|
||||
'latex_equation': 'target = 10.5 + 1.5 \\cdot var1 + -0.75 \\cdot var2',
|
||||
'model_type': 'Linear Regression',
|
||||
}
|
||||
|
||||
reference_data = pd.DataFrame({'var1': [1, 2], 'var2': [3, 4], 'target': [5, 6]})
|
||||
current_data = pd.DataFrame({'var1': [7, 8], 'var2': [9, 10], 'target': [11, 12]})
|
||||
|
||||
# Mock DataFrame.to_csv to avoid file I/O
|
||||
with patch.object(pd.DataFrame, 'to_csv'):
|
||||
result = repo._generate_report(reference_data, current_data, mock_train_result)
|
||||
|
||||
# Verify equation path was set
|
||||
assert result.equation_path == os.path.join(mock_train_result.run_dir, 'model_equation.json')
|
||||
|
||||
# Verify JSON was written
|
||||
mock_json_dump.assert_called()
|
||||
call_args = mock_json_dump.call_args
|
||||
assert call_args[0][0] == mock_train_result.equation
|
||||
assert call_args[1]['indent'] == 2
|
||||
assert call_args[1]['ensure_ascii'] is False
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.Reports')
|
||||
@patch('builtins.open', create=True)
|
||||
def test_generate_report_without_equation(
|
||||
mock_open, mock_reports_class, mock_model_serving_class, mock_logger, mock_train_result
|
||||
):
|
||||
"""Test _generate_report works without equation."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
# No equation
|
||||
mock_train_result.equation = None
|
||||
|
||||
reference_data = pd.DataFrame({'var1': [1, 2], 'var2': [3, 4], 'target': [5, 6]})
|
||||
current_data = pd.DataFrame({'var1': [7, 8], 'var2': [9, 10], 'target': [11, 12]})
|
||||
|
||||
# Mock DataFrame.to_csv to avoid file I/O
|
||||
with patch.object(pd.DataFrame, 'to_csv'):
|
||||
result = repo._generate_report(reference_data, current_data, mock_train_result)
|
||||
|
||||
# Verify equation path was not set
|
||||
assert not hasattr(result, 'equation_path') or result.equation_path is None
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.path.exists')
|
||||
def test_save_run_with_equation(
|
||||
mock_exists, mock_model_serving_class, mock_logger, mock_train_result
|
||||
):
|
||||
"""Test _save_run logs equation artifact."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
mock_model_serving_instance = MagicMock()
|
||||
mock_model_serving_class.return_value = mock_model_serving_instance
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
# Set equation path
|
||||
mock_train_result.equation_path = '/tmp/test_run/model_equation.json' # noqa: S108
|
||||
|
||||
# Mock all path.exists calls to return True
|
||||
mock_exists.return_value = True
|
||||
|
||||
repo._save_run(mock_train_result)
|
||||
|
||||
# Verify equation artifact was logged
|
||||
logged_artifacts = [
|
||||
call[0][0] for call in mock_model_serving_instance.log_artifact.call_args_list
|
||||
]
|
||||
assert '/tmp/test_run/model_equation.json' in logged_artifacts # noqa: S108
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.path.exists')
|
||||
def test_save_run_without_equation(
|
||||
mock_exists, mock_model_serving_class, mock_logger, mock_train_result
|
||||
):
|
||||
"""Test _save_run works without equation."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
mock_model_serving_instance = MagicMock()
|
||||
mock_model_serving_class.return_value = mock_model_serving_instance
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
# No equation
|
||||
mock_train_result.equation_path = None
|
||||
|
||||
# Mock path.exists to return True for required artifacts
|
||||
mock_exists.return_value = True
|
||||
|
||||
repo._save_run(mock_train_result)
|
||||
|
||||
# Verify only 3 artifacts were logged (report, train_data, test_data)
|
||||
assert mock_model_serving_instance.log_artifact.call_count == 3
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
@patch('model_manager.utils.repository.model_repository.path.exists')
|
||||
def test_save_run_missing_report(
|
||||
mock_exists, mock_model_serving_class, mock_logger, mock_train_result
|
||||
):
|
||||
"""Test _save_run raises ValueError when report is missing."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
# Mock report doesn't exist
|
||||
def exists_side_effect(path):
|
||||
return not path.endswith('report.html')
|
||||
|
||||
mock_exists.side_effect = exists_side_effect
|
||||
|
||||
with pytest.raises(ValueError, match='Report file does not exist'):
|
||||
repo._save_run(mock_train_result)
|
||||
|
||||
|
||||
@patch('model_manager.utils.repository.model_repository.ModelServing')
|
||||
def test_save_run_none_metrics(mock_model_serving_class, mock_logger, mock_train_result):
|
||||
"""Test _save_run raises ValueError when metrics are None."""
|
||||
from model_manager.utils.repository.model_repository import ModelRepository
|
||||
|
||||
repo = ModelRepository(
|
||||
url='http://mlflow.test', username='user', password='pass', logger=mock_logger
|
||||
)
|
||||
|
||||
mock_train_result.mse_val = None
|
||||
|
||||
with pytest.raises(ValueError, match='One or more metrics .* are None'):
|
||||
repo._save_run(mock_train_result)
|
||||
|
||||
Reference in New Issue
Block a user