63017754a8
Update coverage source in pyproject.toml, add testcontainers for PostgreSQL in requirements-dev.txt, increment image tag and adjust probe delays in values.yaml, and refine condition checks in format_and_export_prediction.py and mlflow.py. Additionally, enhance test coverage in test_gates.py.
416 lines
14 KiB
Python
416 lines
14 KiB
Python
"""
|
|
Pytest configuration and fixtures for E2E tests.
|
|
"""
|
|
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pandas as pd
|
|
import pytest
|
|
import pytest_asyncio
|
|
from sqlalchemy import create_engine, text
|
|
from testcontainers.postgres import PostgresContainer
|
|
from temporalio.testing import WorkflowEnvironment
|
|
from temporalio.worker import Worker
|
|
|
|
from laborious.activities.activities import Activities
|
|
from laborious.workflows.predictions_batch import PredictionsBatch
|
|
from laborious.workflows.sub_workflows.prediction_process import PredictionProcess
|
|
from laborious.workflows.sub_workflows.format_and_export_prediction import FormatAndExportPrediction
|
|
from sientia_do.notifications.handlers import CoreNotificationHandler
|
|
from sientia_do.observability.logger import Logger
|
|
from sientia_do.observability.metrics_controller import MetricsController
|
|
|
|
# Test constants
|
|
TEST_MONGODB_CONNECTION_STRING = 'mongodb://localhost:27017'
|
|
TEST_DATABASE_NAME = 'test_db'
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='session')
|
|
def postgres_container():
|
|
"""
|
|
Create a PostgreSQL container using testcontainers.
|
|
|
|
This fixture creates a real PostgreSQL database in a Docker container
|
|
that will be used for all tests in the session.
|
|
"""
|
|
postgres = PostgresContainer('postgres:15')
|
|
postgres.start()
|
|
yield postgres
|
|
postgres.stop()
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def postgres_engine(postgres_container):
|
|
"""
|
|
Create SQLAlchemy engine for PostgreSQL test database.
|
|
|
|
This fixture creates a connection to the PostgreSQL container
|
|
created by the postgres_container fixture.
|
|
"""
|
|
engine = create_engine(postgres_container.get_connection_url())
|
|
|
|
yield engine
|
|
|
|
engine.dispose()
|
|
|
|
|
|
def _create_schema_and_tables(engine):
|
|
"""
|
|
Helper function to create schema and tables in the given engine.
|
|
|
|
Creates predictions_schema with:
|
|
- laborious_data: Input data table for queries
|
|
- predictions: Output predictions table
|
|
- transformed_data: Output transformed data table
|
|
"""
|
|
# Use begin() to ensure transaction is properly committed
|
|
with engine.begin() as conn:
|
|
# Create predictions_schema
|
|
conn.execute(text("CREATE SCHEMA IF NOT EXISTS predictions_schema"))
|
|
|
|
# Create laborious_data table (input data from sensors)
|
|
create_laborious_data_sql = """
|
|
CREATE TABLE IF NOT EXISTS predictions_schema.laborious_data (
|
|
id SERIAL NOT NULL,
|
|
model_id int4 NOT NULL,
|
|
variable text NOT NULL,
|
|
value numeric NULL,
|
|
"timestamp" timestamptz NOT NULL,
|
|
created_at timestamptz NOT NULL,
|
|
PRIMARY KEY (id)
|
|
);
|
|
"""
|
|
conn.execute(text(create_laborious_data_sql))
|
|
|
|
# Create predictions table
|
|
create_predictions_sql = """
|
|
CREATE TABLE if not exists predictions_schema.predictions (
|
|
id SERIAL NOT NULL ,
|
|
model_id int4 NOT NULL,
|
|
prediction numeric NULL,
|
|
prediction_confidence numeric NOT NULL,
|
|
response_time numeric NOT NULL,
|
|
prediction_status text NOT NULL,
|
|
"timestamp" timestamptz NOT NULL,
|
|
created_at timestamptz DEFAULT CURRENT_TIMESTAMP NOT NULL,
|
|
"comments" text NULL,
|
|
PRIMARY KEY (id, created_at)
|
|
);
|
|
"""
|
|
conn.execute(text(create_predictions_sql))
|
|
|
|
# Create transformed_data table
|
|
create_transformed_sql = """
|
|
CREATE TABLE IF NOT EXISTS predictions_schema.transformed_data (
|
|
id SERIAL NOT NULL,
|
|
model_id int4 NOT NULL,
|
|
variable text NOT NULL,
|
|
value numeric NULL,
|
|
"timestamp" timestamptz NOT NULL,
|
|
created_at timestamptz DEFAULT CURRENT_TIMESTAMP NOT NULL,
|
|
PRIMARY KEY (id)
|
|
);
|
|
"""
|
|
conn.execute(text(create_transformed_sql))
|
|
|
|
|
|
@pytest_asyncio.fixture(autouse=True)
|
|
def setup_postgres_schema_and_tables(postgres_engine):
|
|
"""
|
|
Automatically create necessary schema and tables before each test.
|
|
|
|
This fixture runs automatically (autouse=True) and ensures
|
|
that the predictions_schema and tables exist with the correct structure.
|
|
"""
|
|
_create_schema_and_tables(postgres_engine)
|
|
yield
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_logger():
|
|
"""Mock logger for testing."""
|
|
def message(message):
|
|
print(f"[LOG] {message}")
|
|
def custom_message(message, _metadata={}):
|
|
print(f"[LOG] {message}")
|
|
logger = MagicMock()
|
|
logger.info = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.debug = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.error = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.warning = MagicMock(
|
|
side_effect=message
|
|
)
|
|
logger.custom_info = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
logger.custom_debug = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
logger.custom_error = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
logger.custom_warning = MagicMock(
|
|
side_effect=custom_message
|
|
)
|
|
return logger
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_mongo_client():
|
|
"""
|
|
Mock MongoDB client to avoid real connections.
|
|
|
|
This fixture mocks the pymongo.MongoClient used by CoreNotificationHandler,
|
|
allowing us to use a real NotificationHandler instance without connecting to MongoDB.
|
|
"""
|
|
mock_client = MagicMock()
|
|
mock_db = MagicMock()
|
|
mock_collection = MagicMock()
|
|
|
|
# Configure the mock chain: client[database] -> db[collection] -> collection
|
|
mock_client.__getitem__.return_value = mock_db
|
|
mock_db.__getitem__.return_value = mock_collection
|
|
|
|
# Mock server_info() to avoid connection attempts
|
|
mock_client.server_info = MagicMock()
|
|
|
|
# Mock insert_one for notifications
|
|
mock_collection.insert_one = MagicMock()
|
|
|
|
return mock_client
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def notification_handler(mock_logger, mock_mongo_client):
|
|
"""
|
|
Create a real NotificationHandler instance with mocked MongoDB client.
|
|
|
|
This fixture creates a real CoreNotificationHandler instance but mocks
|
|
the underlying MongoDB connection to avoid real database connections.
|
|
"""
|
|
# Patch MongoClient where it's imported in the handlers module
|
|
with patch('sientia_do.notifications.handlers.MongoClient', return_value=mock_mongo_client):
|
|
handler = CoreNotificationHandler(
|
|
connection_string=TEST_MONGODB_CONNECTION_STRING,
|
|
database=TEST_DATABASE_NAME,
|
|
logger=mock_logger,
|
|
project_name='laborious',
|
|
)
|
|
yield handler
|
|
handler.shutdown()
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def metrics_controller(mock_logger):
|
|
"""Create a real MetricsController instance."""
|
|
return MetricsController(logger=mock_logger)
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_minio_repository():
|
|
"""Mock MinIO repository for object storage operations."""
|
|
mock_repo = MagicMock()
|
|
|
|
# Mock repository methods
|
|
mock_repo.put_parquet_from_dataframe = AsyncMock(return_value='test-object-key')
|
|
mock_repo.get_parquet_as_dataframe = AsyncMock(return_value=pd.DataFrame())
|
|
mock_repo.minio_bucket = 'test-bucket'
|
|
|
|
return mock_repo
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def patch_create_engine(postgres_engine):
|
|
"""Patch create_engine to return test postgres_engine."""
|
|
with patch('sientia_do.temporal.activities.postgres.create_engine', return_value=postgres_engine):
|
|
yield
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def patch_minio_repository(mock_minio_repository):
|
|
"""Patch MinioRepository to return mock."""
|
|
with patch('laborious.utils.repository.minio_repository.MinioRepository', return_value=mock_minio_repository):
|
|
yield
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def mock_mlflow_models():
|
|
"""Create mock models for MLflow load_model methods."""
|
|
# Mock transform model - returns DataFrame with same index as input
|
|
mock_transform_model = MagicMock()
|
|
def mock_transform_predict(data):
|
|
num_rows = max(len(data), 1) if hasattr(data, '__len__') else 1
|
|
print(data.to_csv())
|
|
print(data.index)
|
|
result = pd.DataFrame({
|
|
'feature_1': [0.234] * num_rows,
|
|
'feature_2': [0.783] * num_rows,
|
|
})
|
|
result.index = data.index
|
|
return result
|
|
mock_transform_model.predict = MagicMock(side_effect=mock_transform_predict)
|
|
|
|
# Mock predict model - returns array/list of predictions
|
|
mock_predict_model = MagicMock()
|
|
def mock_predict_predict(data):
|
|
num_rows = max(len(data), 1) if hasattr(data, '__len__') else 1
|
|
return [0.5] * num_rows
|
|
mock_predict_model.predict = MagicMock(side_effect=mock_predict_predict)
|
|
|
|
# Mock PyFuncModel for compressed models
|
|
mock_pyfunc_model = MagicMock()
|
|
mock_pyfunc_model._model_impl = MagicMock()
|
|
mock_pyfunc_model._model_impl.python_model = mock_transform_model
|
|
|
|
return {
|
|
'transform_model': mock_transform_model,
|
|
'predict_model': mock_predict_model,
|
|
'pyfunc_model': mock_pyfunc_model,
|
|
}
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
def patch_mlflow(mock_mlflow_models):
|
|
"""Patch mlflow module in repository with load_model mocks."""
|
|
mock_mlflow = MagicMock()
|
|
|
|
# Mock sklearn.load_model
|
|
def mock_sklearn_load_model(model_uri):
|
|
if 'data_model' in model_uri or 'transform' in model_uri.lower():
|
|
return mock_mlflow_models['transform_model']
|
|
return mock_mlflow_models['predict_model']
|
|
mock_mlflow.sklearn = MagicMock()
|
|
mock_mlflow.sklearn.load_model = MagicMock(side_effect=mock_sklearn_load_model)
|
|
|
|
# Mock pyfunc.load_model
|
|
def mock_pyfunc_load_model(model_uri):
|
|
if 'artifacts' in model_uri or 'tmp' in model_uri:
|
|
return mock_mlflow_models['pyfunc_model']
|
|
if 'data_model' in model_uri or 'transform' in model_uri.lower():
|
|
return mock_mlflow_models['transform_model']
|
|
return mock_mlflow_models['predict_model']
|
|
mock_mlflow.pyfunc = MagicMock()
|
|
mock_mlflow.pyfunc.load_model = MagicMock(side_effect=mock_pyfunc_load_model)
|
|
|
|
# Mock pytorch.load_model
|
|
mock_mlflow.pytorch = MagicMock()
|
|
mock_mlflow.pytorch.load_model = MagicMock(return_value=mock_mlflow_models['predict_model'])
|
|
|
|
# Mock other mlflow methods that might be called
|
|
mock_mlflow.set_tracking_uri = MagicMock()
|
|
mock_mlflow.get_run = MagicMock(return_value=MagicMock(info=MagicMock(artifact_uri='mlflow-artifacts:/test_run_id')))
|
|
mock_mlflow.tracking = MagicMock()
|
|
mock_mlflow.tracking.MlflowClient = MagicMock(return_value=MagicMock(
|
|
search_registered_models=MagicMock(return_value=[MagicMock(name='test_model')]),
|
|
search_model_versions=MagicMock(return_value=[MagicMock(
|
|
current_stage='Production',
|
|
version='1',
|
|
source='runs:/artifacts/test_run_id'
|
|
)])
|
|
))
|
|
|
|
with patch('laborious.utils.repository.model_repository.mlflow', new=mock_mlflow):
|
|
yield mock_mlflow
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def test_activities(
|
|
postgres_engine,
|
|
postgres_container,
|
|
mock_logger,
|
|
notification_handler,
|
|
metrics_controller,
|
|
mock_minio_repository,
|
|
patch_create_engine,
|
|
patch_minio_repository,
|
|
patch_mlflow,
|
|
):
|
|
"""
|
|
Create Activities instance with test dependencies.
|
|
|
|
This fixture creates a real Activities instance with:
|
|
- PostgreSQL database (via testcontainers)
|
|
- Mocked MinIO client
|
|
- Real NotificationHandler and MetricsController (with mocked underlying services)
|
|
"""
|
|
activities = Activities(
|
|
postgres_config={
|
|
'host': 'localhost',
|
|
'port': postgres_container.get_exposed_port(5432),
|
|
'user': 'test',
|
|
'password': 'test',
|
|
'dbname': 'test',
|
|
'min_connections': 1,
|
|
'max_connections': 5,
|
|
},
|
|
mlflow_config={
|
|
'host': 'http://localhost',
|
|
'port': '5000',
|
|
'username': 'test',
|
|
'password': 'test',
|
|
},
|
|
minio_config={
|
|
'endpoint_url': 'http://localhost:9000',
|
|
'access_key': 'test',
|
|
'secret_key': 'test',
|
|
'region_name': 'us-east-1',
|
|
'default_bucket': 'test-bucket',
|
|
},
|
|
opc_config={},
|
|
pi_web_api_config={
|
|
'base_url': 'http://localhost:8080',
|
|
'auth_type': 'bearer',
|
|
'auth_token': 'test_token',
|
|
},
|
|
logger=mock_logger,
|
|
notification_handler=notification_handler,
|
|
)
|
|
|
|
try:
|
|
yield activities
|
|
finally:
|
|
# Cleanup - ALWAYS runs, even if test fails
|
|
await activities.shutdown()
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def temporal_test_env():
|
|
"""Create Temporal test environment."""
|
|
env = await WorkflowEnvironment.start_time_skipping()
|
|
async with env:
|
|
yield env
|
|
|
|
|
|
@pytest_asyncio.fixture(scope='function')
|
|
async def temporal_worker(temporal_test_env, test_activities):
|
|
"""Create Temporal worker with test activities."""
|
|
async with Worker(
|
|
temporal_test_env.client,
|
|
task_queue='test-queue',
|
|
workflows=[PredictionsBatch, PredictionProcess, FormatAndExportPrediction],
|
|
activities=[
|
|
test_activities.load_custom_query,
|
|
test_activities.get_last_timestamp,
|
|
test_activities.input_gate,
|
|
test_activities.request_transform,
|
|
test_activities.mlflow_response_gate,
|
|
test_activities.mlflow_content_gate,
|
|
test_activities.request_predict,
|
|
test_activities.repeat_last_prediction,
|
|
test_activities.format_prediction,
|
|
test_activities.format_transformed_data,
|
|
test_activities.format_default_prediction,
|
|
test_activities.write_pi_web_api_data,
|
|
test_activities.write_opc_data,
|
|
test_activities.export_data_to_postgres,
|
|
test_activities.write_metrics,
|
|
],
|
|
) as worker:
|
|
yield worker
|