gitea_admin/sientia-dataops-laborious-legacy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SIENTIAPDE-1646

Browse Source 
Update README, requirements, and E2E tests for improved configuration and functionality

- Enhanced the README with updated model configuration examples, including the addition of an alias for production.
- Removed the `requirements-light.txt` file and updated `requirements-local.txt` and `requirements.txt` to replace `asyncua` with `opcua`.
- Refactored E2E test scenarios to utilize scenario input files for better maintainability and clarity.
- Improved test coverage for MinIO offload functionality and added new helper functions for loading scenario inputs.
- Updated `values.yaml` to reflect new global configurations and environment variables for the laborious worker.
This commit is contained in:
Vitor Pimentel dos Santos
2026-05-07 17:02:25 -03:00
parent aaf647efdf
commit e6018af23f
51 changed files with 4408 additions and 2660 deletions
Download Patch File Download Diff File Expand all files Collapse all files

168
tests/laborious/activities/test_mlflow.py
View File

@@ -1,9 +1,9 @@
from datetime import datetime
from unittest.mock import ANY, AsyncMock, MagicMock, patch
from unittest.mock import ANY, MagicMock, patch
import numpy as np
import pandas as pd
from pytest import fixture, mark, raises
from pytest import fixture, raises
from sientia_do.notifications.models import NotificationLevel
from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
@@ -22,7 +22,7 @@ def _passthrough_from_dict():
def test___init__(mock_minio_repository):
logger = MagicMock()
notification_handler = MagicMock()
metrics_controller = AsyncMock()
metrics_controller = MagicMock()
mlflow_repo = MagicMock()
plugin_store = MagicMock()
@@ -63,7 +63,7 @@ def test___init__(mock_minio_repository):
def mlflow(mock_minio_repository):
logger = MagicMock()
notification_handler = MagicMock()
metrics_controller = AsyncMock()
metrics_controller = MagicMock()
mlflow_repo = MagicMock()
plugin_store = MagicMock()
@@ -85,11 +85,10 @@ def mlflow(mock_minio_repository):
metrics_controller=metrics_controller,
)
mlflow.minio_repository = AsyncMock()
mlflow.minio_repository = MagicMock()
mlflow.send_notification = MagicMock()
mlflow.emit_metric = AsyncMock()
mlflow.send_notification_async = AsyncMock()
mlflow.emit_metric = MagicMock()
mlflow.error = MagicMock()
mlflow.debug = MagicMock()
mlflow.info = MagicMock()
@@ -150,12 +149,11 @@ def test_detect_and_parse_datetime_index_timestamp_with_tz_success(mlflow):
assert out.index[0].endswith('+0000')
@mark.asyncio
@patch(
'laborious.activities.mlflow.MinioDataFramePayload.from_dataframe',
new_callable=AsyncMock,
new_callable=MagicMock,
)
async def test_request_transform_success(mock_from_dataframe, mlflow):
def test_request_transform_success(mock_from_dataframe, mlflow):
ts = pd.Timestamp('2020-01-01', tz='UTC')
raw = pd.DataFrame(
{
@@ -180,8 +178,8 @@ async def test_request_transform_success(mock_from_dataframe, mlflow):
wrapper.transform.return_value = (out_df, {'meta': True})
mlflow.mlflow_repository.get_cached_model.return_value = wrapper
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw)
input_data = {
**metadata,
@@ -190,7 +188,7 @@ async def test_request_transform_success(mock_from_dataframe, mlflow):
'model_config': {},
}
response_data = await mlflow.request_transform(input_data)
response_data = mlflow.request_transform(input_data)
mlflow.mlflow_repository.get_cached_model.assert_called_once_with(
model_name='test_model',
@@ -202,12 +200,11 @@ async def test_request_transform_success(mock_from_dataframe, mlflow):
assert response_data == mock_from_dataframe.return_value
@mark.asyncio
@patch(
'laborious.activities.mlflow.MinioDataFramePayload.from_dataframe',
new_callable=AsyncMock,
new_callable=MagicMock,
)
async def test_request_transform_success_without_transform_meta(mock_from_dataframe, mlflow):
def test_request_transform_success_without_transform_meta(mock_from_dataframe, mlflow):
ts = pd.Timestamp('2020-01-01', tz='UTC')
raw = pd.DataFrame(
{
@@ -223,8 +220,8 @@ async def test_request_transform_success_without_transform_meta(mock_from_datafr
wrapper.transform.return_value = (out_df, {})
mlflow.mlflow_repository.get_cached_model.return_value = wrapper
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw)
input_data = {
**metadata,
@@ -233,21 +230,20 @@ async def test_request_transform_success_without_transform_meta(mock_from_datafr
'model_config': {},
}
await mlflow.request_transform(input_data)
mlflow.request_transform(input_data)
mock_from_dataframe.assert_called_once()
@mark.asyncio
@patch(
'laborious.activities.mlflow.MinioDataFramePayload.from_dataframe',
new_callable=AsyncMock,
new_callable=MagicMock,
)
async def test_request_transform_failure(mock_from_dataframe, mlflow):
def test_request_transform_failure(mock_from_dataframe, mlflow):
mlflow.mlflow_repository.get_cached_model.side_effect = RuntimeError('boom')
data_mock = MagicMock()
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=data_mock)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=data_mock)
input_data = {
**metadata,
@@ -260,7 +256,7 @@ async def test_request_transform_failure(mock_from_dataframe, mlflow):
data_mock.drop_duplicates.return_value = data_mock
data_mock.pivot.return_value = data_mock
await mlflow.request_transform(input_data)
mlflow.request_transform(input_data)
mock_from_dataframe.assert_called_once_with(
dataframe=None,
@@ -274,13 +270,12 @@ async def test_request_transform_failure(mock_from_dataframe, mlflow):
)
@mark.asyncio
@patch(
'laborious.activities.mlflow.MinioDataFramePayload.from_dataframe',
new_callable=AsyncMock,
new_callable=MagicMock,
)
@patch('laborious.activities.mlflow.to_datetime')
async def test_request_predict(mock_to_datetime, mock_from_dataframe, mlflow):
def test_request_predict(mock_to_datetime, mock_from_dataframe, mlflow):
wrapper = MagicMock()
pred_df = MagicMock()
wrapper.predict.return_value = (pred_df, {})
@@ -288,8 +283,8 @@ async def test_request_predict(mock_to_datetime, mock_from_dataframe, mlflow):
data_mock = MagicMock()
data_mock.index = pd.DatetimeIndex([pd.Timestamp('2020-01-01', tz='UTC')])
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=data_mock)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=data_mock)
input_data = {
**metadata,
@@ -301,7 +296,7 @@ async def test_request_predict(mock_to_datetime, mock_from_dataframe, mlflow):
pred_df.columns = MagicMock()
pred_df.__setitem__ = MagicMock()
response_data = await mlflow.request_predict(input_data)
response_data = mlflow.request_predict(input_data)
data_mock.replace.assert_called_once_with(np.nan, None, inplace=True)
mock_to_datetime.assert_called()
@@ -310,15 +305,12 @@ async def test_request_predict(mock_to_datetime, mock_from_dataframe, mlflow):
assert response_data == mock_from_dataframe.return_value
@mark.asyncio
@patch(
'laborious.activities.mlflow.MinioDataFramePayload.from_dataframe',
new_callable=AsyncMock,
new_callable=MagicMock,
)
@patch('laborious.activities.mlflow.to_datetime')
async def test_request_predict_success_dataframe_and_meta(
mock_to_datetime, mock_from_dataframe, mlflow
):
def test_request_predict_success_dataframe_and_meta(mock_to_datetime, mock_from_dataframe, mlflow):
wrapper = MagicMock()
pred_df = pd.DataFrame({'raw': [0.3]})
wrapper.predict.return_value = (pred_df, {'m': 1})
@@ -326,8 +318,8 @@ async def test_request_predict_success_dataframe_and_meta(
data_mock = MagicMock()
data_mock.index = pd.DatetimeIndex([pd.Timestamp('2020-01-01', tz='UTC')])
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=data_mock)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=data_mock)
input_data = {
**metadata,
@@ -336,25 +328,24 @@ async def test_request_predict_success_dataframe_and_meta(
'model_config': {},
}
await mlflow.request_predict(input_data)
mlflow.request_predict(input_data)
assert list(pred_df.columns) == ['prediction', 'response_time']
mlflow.info.assert_any_call("Wrapper predict metadata: {'m': 1}", metadata['metadata'])
mock_from_dataframe.assert_called_once()
@mark.asyncio
@patch(
'laborious.activities.mlflow.MinioDataFramePayload.from_dataframe',
new_callable=AsyncMock,
new_callable=MagicMock,
)
@patch('laborious.activities.mlflow.to_datetime')
async def test_request_predict_failure(mock_to_datetime, mock_from_dataframe, mlflow):
def test_request_predict_failure(mock_to_datetime, mock_from_dataframe, mlflow):
mlflow.mlflow_repository.get_cached_model.side_effect = RuntimeError('predict boom')
data_mock = MagicMock()
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=data_mock)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=data_mock)
input_data = {
**metadata,
@@ -363,7 +354,7 @@ async def test_request_predict_failure(mock_to_datetime, mock_from_dataframe, ml
'model_config': {},
}
await mlflow.request_predict(input_data)
mlflow.request_predict(input_data)
mock_from_dataframe.assert_called_once_with(
dataframe=None,
@@ -377,12 +368,11 @@ async def test_request_predict_failure(mock_to_datetime, mock_from_dataframe, ml
)
@mark.asyncio
@patch('laborious.activities.mlflow.mlflow.log_artifact')
@patch('laborious.activities.mlflow.tempfile.mkdtemp')
@patch('laborious.activities.mlflow.rmtree')
@patch('laborious.activities.mlflow.to_datetime')
async def test_retrain_model_success_data_success_retrain(
def test_retrain_model_success_data_success_retrain(
mock_to_datetime, mock_rmtree, mock_mkdtemp, mock_log_artifact, mlflow
):
mock_mkdtemp.return_value = 'tmp'
@@ -408,10 +398,10 @@ async def test_retrain_model_success_data_success_retrain(
}
)
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw_data)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw_data)
response = await mlflow.retrain_model(
response = mlflow.retrain_model(
{
**metadata,
'data': payload,
@@ -428,12 +418,11 @@ async def test_retrain_model_success_data_success_retrain(
assert response['experiment']['run_id'] == 'new-run'
@mark.asyncio
@patch('laborious.activities.mlflow.mlflow.log_artifact')
@patch('laborious.activities.mlflow.tempfile.mkdtemp')
@patch('laborious.activities.mlflow.rmtree')
@patch('laborious.activities.mlflow.to_datetime')
async def test_retrain_model_success_with_payload_data(
def test_retrain_model_success_with_payload_data(
mock_to_datetime, mock_rmtree, mock_mkdtemp, mock_log_artifact, mlflow
):
mock_mkdtemp.return_value = 'tmp'
@@ -448,8 +437,8 @@ async def test_retrain_model_success_with_payload_data(
raw_data = MagicMock(columns=['variable', 'timestamp', 'value', 'created_at'])
raw_data.__getitem__.return_value.max.return_value = 'ts'
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw_data)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw_data)
pivoted = MagicMock()
raw_data.sort_values.return_value = raw_data
@@ -460,7 +449,7 @@ async def test_retrain_model_success_with_payload_data(
pivoted.index = MagicMock()
pivoted.__setitem__ = MagicMock()
response = await mlflow.retrain_model(
response = mlflow.retrain_model(
{
**metadata,
'data': payload,
@@ -472,12 +461,11 @@ async def test_retrain_model_success_with_payload_data(
assert response['success'] is True
@mark.asyncio
@patch('laborious.activities.mlflow.mlflow.log_artifact')
@patch('laborious.activities.mlflow.tempfile.mkdtemp')
@patch('laborious.activities.mlflow.rmtree')
@patch('laborious.activities.mlflow.to_datetime')
async def test_retrain_model_always_uses_retrain_even_with_full_retrain_flag(
def test_retrain_model_always_uses_retrain_even_with_full_retrain_flag(
mock_to_datetime, mock_rmtree, mock_mkdtemp, mock_log_artifact, mlflow
):
mock_mkdtemp.return_value = 'tmp'
@@ -498,10 +486,10 @@ async def test_retrain_model_always_uses_retrain_even_with_full_retrain_flag(
'value': [1.0, 2.0, 3.0, 4.0],
}
)
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw_data)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw_data)
response = await mlflow.retrain_model(
response = mlflow.retrain_model(
{
**metadata,
'data': payload,
@@ -515,17 +503,16 @@ async def test_retrain_model_always_uses_retrain_even_with_full_retrain_flag(
assert response['success'] is True
@mark.asyncio
@patch('laborious.activities.mlflow.to_datetime')
async def test_retrain_model_success_data_fail_retrain(mock_to_datetime, mlflow):
def test_retrain_model_success_data_fail_retrain(mock_to_datetime, mlflow):
mv_alias = MagicMock(run_id='src')
mlflow.mlflow_repository._client.get_model_version_by_alias.return_value = mv_alias
mlflow.mlflow_repository.get_cached_model.side_effect = RuntimeError('retrain failed')
raw_data = MagicMock(columns=['variable', 'timestamp', 'value', 'created_at'])
raw_data.__getitem__.return_value.max.return_value = 'tsmax'
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw_data)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw_data)
pivoted = MagicMock()
raw_data.sort_values.return_value = raw_data
@@ -536,7 +523,7 @@ async def test_retrain_model_success_data_fail_retrain(mock_to_datetime, mlflow)
pivoted.index = MagicMock()
pivoted.__setitem__ = MagicMock()
response = await mlflow.retrain_model(
response = mlflow.retrain_model(
{
**metadata,
'data': payload,
@@ -549,9 +536,8 @@ async def test_retrain_model_success_data_fail_retrain(mock_to_datetime, mlflow)
assert 'retrain failed' in response['message']
@mark.asyncio
async def test_retrain_model_data_error(mlflow):
response = await mlflow.retrain_model(
def test_retrain_model_data_error(mlflow):
response = mlflow.retrain_model(
{
**metadata,
'model_name': 'test_model',
@@ -565,8 +551,7 @@ async def test_retrain_model_data_error(mlflow):
assert 'data' in response['message'].lower() or 'loading' in response['message'].lower()
@mark.asyncio
async def test_retrain_model_missing_target(mlflow):
def test_retrain_model_missing_target(mlflow):
ts = pd.Timestamp('2020-01-01', tz='UTC')
raw_data = pd.DataFrame(
{
@@ -575,10 +560,10 @@ async def test_retrain_model_missing_target(mlflow):
'value': [1.0, 2.0],
}
)
payload = AsyncMock()
payload.retrieve = AsyncMock(return_value=raw_data)
payload = MagicMock()
payload.retrieve = MagicMock(return_value=raw_data)
response = await mlflow.retrain_model(
response = mlflow.retrain_model(
{
**metadata,
'data': payload,
@@ -591,12 +576,11 @@ async def test_retrain_model_missing_target(mlflow):
assert 'target' in response['message']
@mark.asyncio
async def test_retrain_model_data_error_no_minio_repository(mlflow):
def test_retrain_model_data_error_no_minio_repository(mlflow):
mlflow.minio_repository = None
with raises(ValueError) as e:
await mlflow.retrain_model(
mlflow.retrain_model(
{
**metadata,
'object_key': 'test_object_key',
@@ -610,8 +594,7 @@ async def test_retrain_model_data_error_no_minio_repository(mlflow):
assert str(e.value) == 'Minio repository not initialized'
@mark.asyncio
async def test_update_production_model(mlflow):
def test_update_production_model(mlflow):
mlflow.mlflow_repository._client.search_model_versions.return_value = [
MagicMock(version='3', run_id='run-x'),
MagicMock(version='2', run_id='run-x'),
@@ -626,7 +609,7 @@ async def test_update_production_model(mlflow):
'status': 'success',
}
response = await mlflow.update_production_model(input_data)
response = mlflow.update_production_model(input_data)
mlflow.mlflow_repository.promote_to_alias.assert_called_once_with(
model_name='test_model',
@@ -639,8 +622,7 @@ async def test_update_production_model(mlflow):
assert response['version'] == '3'
@mark.asyncio
async def test_update_production_model_error(mlflow):
def test_update_production_model_error(mlflow):
mlflow.mlflow_repository._client.search_model_versions.return_value = []
input_data = {
@@ -653,9 +635,9 @@ async def test_update_production_model_error(mlflow):
}
try:
await mlflow.update_production_model(input_data)
mlflow.update_production_model(input_data)
except Exception:
mlflow.send_notification_async.assert_called_once_with(
mlflow.send_notification.assert_called_once_with(
metadata=metadata['metadata'],
notification_id='UPDATE_PRODUCTION_MODEL_ERROR',
message=ANY,
@@ -667,9 +649,8 @@ async def test_update_production_model_error(mlflow):
raise AssertionError('Expected exception')
@mark.asyncio
@patch('laborious.activities.mlflow.to_datetime')
async def test_get_reference_data_success(mock_to_datetime, mlflow):
def test_get_reference_data_success(mock_to_datetime, mlflow):
input_data = {
**metadata,
'model_name': 'test_model',
@@ -690,14 +671,13 @@ async def test_get_reference_data_success(mock_to_datetime, mlflow):
with patch('laborious.activities.mlflow.rmtree'):
with patch('laborious.activities.mlflow.Path') as mp:
mp.return_value.rglob.return_value = [MagicMock()]
result = await mlflow.get_reference_data(input_data)
result = mlflow.get_reference_data(input_data)
mock_reference_data.to_dict.assert_called_once_with(orient='records')
assert result == mock_reference_data.to_dict.return_value
@mark.asyncio
async def test_get_reference_data_not_found(mlflow):
def test_get_reference_data_not_found(mlflow):
input_data = {
**metadata,
'model_name': 'test_model',
@@ -705,14 +685,13 @@ async def test_get_reference_data_not_found(mlflow):
mlflow.mlflow_repository._client.get_model_version_by_alias.side_effect = Exception('missing')
result = await mlflow.get_reference_data(input_data)
result = mlflow.get_reference_data(input_data)
mlflow.warning.assert_called()
assert result is None
@mark.asyncio
async def test_get_reference_data_missing_csv_file_returns_none(mlflow):
def test_get_reference_data_missing_csv_file_returns_none(mlflow):
input_data = {
**metadata,
'model_name': 'test_model',
@@ -724,13 +703,12 @@ async def test_get_reference_data_missing_csv_file_returns_none(mlflow):
with patch('laborious.activities.mlflow.rmtree'):
with patch('laborious.activities.mlflow.Path') as mp:
mp.return_value.rglob.return_value = []
result = await mlflow.get_reference_data(input_data)
result = mlflow.get_reference_data(input_data)
assert result is None
@mark.asyncio
async def test_get_reference_data_exception(mlflow):
def test_get_reference_data_exception(mlflow):
input_data = {
**metadata,
'model_name': 'test_model',
@@ -740,6 +718,6 @@ async def test_get_reference_data_exception(mlflow):
mlflow.mlflow_repository._client.get_model_version_by_alias.return_value = mv
mlflow.mlflow_repository.download_artifacts.side_effect = Exception('dl fail')
result = await mlflow.get_reference_data(input_data)
result = mlflow.get_reference_data(input_data)
assert result is None