SIENTIAPDE-1222

Refactor model configuration handling in MLFlow and workflows

- Replaced 'model_retention' with 'model_config' to encapsulate retention settings and improve consistency across various components.
- Updated test cases to reflect changes in argument structure, ensuring compatibility with the new model configuration format.
- Added 'prediction_store_policy' to input data handling in workflows for enhanced configuration management.

tests/laborious/activities/test_mlflow.py

@@ -4,6 +4,7 @@ from unittest.mock import ANY, MagicMock, patch
 import numpy as np
 from pandas import DataFrame, Timestamp
 from pytest import fixture, mark, raises
+from sientia_do.temporal.constants import DATETIME_FORMAT, DATETIME_FORMAT_WITH_TZ
 from laborious.activities.mlflow import MLFlow
 from sientia_do.notifications.models import NotificationLevel
 
@@ -79,7 +80,7 @@ async def test_request_transform_success(mock_max, mock_dataframe, mlflow):
                 'value': 1.0, 'created_at': '2024-01-01 12:00:00'}
         ],
         'model_name': 'test_model',
-        'model_retention': 30
+        'model_config': {}
     }
 
     # Mock the transform response
@@ -108,26 +109,35 @@ async def test_request_transform_success(mock_max, mock_dataframe, mlflow):
 
     # Verify the repository was called with correct arguments
     mlflow.model_monitoring_repository.transform.assert_called_once_with(
-        'test_model', mock_dataframe, 30
+        'test_model', mock_dataframe, {}, metadata['metadata']
     )
 
 
 @mark.asyncio
 @patch("laborious.activities.mlflow.DataFrame")
+@patch("laborious.activities.mlflow.to_datetime")
 @patch("laborious.activities.mlflow.max")
-async def test_request_predict(mock_max, mock_dataframe, mlflow):
+async def test_request_predict(mock_max, mock_to_datetime, mock_dataframe, mlflow):
     mock_max.return_value = '2024-01-02'
     # Mock input data
     input_data = {
         **metadata,
-        'data': [
-            {'timestamp': '2024-01-01', 'variable': 'var1', 'value': 1.0},
-            {'timestamp': '2024-01-01', 'variable': 'var2', 'value': 2.0},
-            {'timestamp': '2024-01-02', 'variable': 'var1', 'value': 3.0},
-            {'timestamp': '2024-01-02', 'variable': 'var2', 'value': 4.0}
-        ],
+        'data': {
+            "variable": {
+                "2024-01-01": "var1",
+                "2024-01-02": "var2",
+                "2024-01-03": "var1",
+                "2024-01-04": "var2"
+            },
+            "value": {
+                "2024-01-01": 1.0,
+                "2024-01-02": 2.0,
+                "2024-01-03": 3.0,
+                "2024-01-04": 4.0
+            }
+        },
         'model_name': 'test_model',
-        'model_retention': 30
+        'model_config': {}
     }
 
     # Mock the predict response
@@ -141,13 +151,26 @@ async def test_request_predict(mock_max, mock_dataframe, mlflow):
     mock_dataframe.return_value.replace.assert_called_once_with(
         np.nan, None, inplace=True
     )
+    mock_dataframe.return_value.__setitem__.assert_any_call(
+        'timestamp', mock_to_datetime.return_value.dt.strftime.return_value
+    )
+    mock_dataframe.return_value.__setitem__.assert_any_call(
+        'timestamp', mock_to_datetime.return_value.dt.strftime.return_value
+    )
+
+    mock_to_datetime.assert_called_once_with(
+        mock_dataframe.return_value.__getitem__.return_value, format=DATETIME_FORMAT_WITH_TZ
+    )
+    mock_to_datetime.return_value.dt.strftime.assert_called_once_with(
+        DATETIME_FORMAT
+    )
 
     # Verify the response
     assert response_data == expected_response
 
     # Verify the repository was called with correct arguments
     mlflow.model_monitoring_repository.predict.assert_called_once_with(
-        'test_model', mock_dataframe.return_value, 30
+        'test_model', mock_dataframe.return_value, {}, metadata['metadata']
     )