SIENTIAPDE-994

Refactor activity methods and update requirements.txt to enhance functionality and remove deprecated filters. Added detailed docstrings for clarity and improved error handling in data processing workflows.

tests/laborious/activities/test_mlflow.py

@@ -0,0 +1,121 @@
+from unittest.mock import MagicMock, patch
+
+import numpy as np
+from pytest import fixture, mark
+from laborious.activities.mlflow import MLFlow
+
+
+@patch("laborious.activities.mlflow.MLFlowRepository")
+def test___init__(mock_mlflow_repository):
+    mlflow = MLFlow(
+        mlflow_host="http://localhost",
+        mlflow_port=5000,
+        mlflow_username="admin",
+        mlflow_password="admin",
+        logger=MagicMock(),
+        notification_handler=MagicMock()
+    )
+
+    assert mlflow.mlflow_host == "http://localhost"
+    assert mlflow.mlflow_port == 5000
+    assert mlflow.mlflow_username == "admin"
+    assert mlflow.mlflow_password == "admin"
+
+    mock_mlflow_repository.assert_called_once_with(
+        "http://localhost:5000", "admin", "admin"
+    )
+
+
+@fixture
+@patch("laborious.activities.mlflow.MLFlowRepository")
+def mlflow(mock_mlflow_repository):
+    return MLFlow(
+        mlflow_host="http://localhost:5000",
+        mlflow_port=5000,
+        mlflow_username="admin",
+        mlflow_password="admin",
+        logger=MagicMock(),
+        notification_handler=MagicMock()
+    )
+
+
+@mark.asyncio
+@patch("laborious.activities.mlflow.DataFrame")
+@patch("laborious.activities.mlflow.max")
+async def test_request_transform(mock_max, mock_dataframe, mlflow):
+    mock_max.return_value = '2024-01-02'
+    # Mock input data
+    input_data = {
+        '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}
+        ],
+        'model_name': 'test_model',
+        'model_retention': 30
+    }
+
+    # Mock the transform response
+    expected_response = {'prediction': [0.5, 0.6]}
+    mlflow.model_monitoring_repository.transform.return_value = expected_response
+
+    # Call the method
+    response_data, timestamp = await mlflow.request_transform(input_data)
+
+    # Verify the data was correctly transformed
+    mock_dataframe.assert_called_once_with(input_data['data'])
+    mock_dataframe.return_value.pivot.assert_called_once_with(
+        index='timestamp', columns='variable', values='value'
+    )
+    mock_dataframe = mock_dataframe.return_value.pivot.return_value
+    mock_dataframe.fillna.assert_called_once_with(np.nan, inplace=True)
+    mock_dataframe.reset_index.assert_called_once()
+    mock_dataframe.columns.name = None
+
+    # Verify the response
+    assert response_data == expected_response
+    assert timestamp == '2024-01-02'
+
+    # Verify the repository was called with correct arguments
+    mlflow.model_monitoring_repository.transform.assert_called_once_with(
+        'test_model', mock_dataframe, 30
+    )
+
+
+@mark.asyncio
+@patch("laborious.activities.mlflow.DataFrame")
+@patch("laborious.activities.mlflow.max")
+async def test_request_predict(mock_max, mock_dataframe, mlflow):
+    mock_max.return_value = '2024-01-02'
+    # Mock input data
+    input_data = {
+        '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}
+        ],
+        'model_name': 'test_model',
+        'model_retention': 30
+    }
+
+    # Mock the predict response
+    expected_response = {'prediction': [0.5, 0.6]}
+    mlflow.model_monitoring_repository.predict.return_value = expected_response
+
+    # Call the method
+    response_data = await mlflow.request_predict(input_data)
+
+    mock_dataframe.assert_called_once_with(input_data['data'])
+    mock_dataframe.return_value.replace.assert_called_once_with(
+        np.nan, None, inplace=True
+    )
+
+    # 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
+    )