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.

laborious/activities/mlflow.py

@@ -8,7 +8,7 @@ with workflow.unsafe.imports_passed_through():
     from typing import Any
     from logging import Logger
     from sientia_do.notifications.handlers import NotificationHandler
-    from laborious.utils.model_repository import ModelMonitoringRepository
+    from laborious.utils.repository.model_repository import MLFlowRepository
     from sientia_do.notifications.models import NotificationLevel
 
 
@@ -21,12 +21,22 @@ class MLFlow(BaseActivity):
         self.mlflow_username = mlflow_username
         self.mlflow_password = mlflow_password
 
-        self.model_monitoring_repository = ModelMonitoringRepository(
+        self.model_monitoring_repository = MLFlowRepository(
             f"{mlflow_host}:{mlflow_port}", mlflow_username, mlflow_password
         )
 
     @activity.defn(name="request_transform")
     async def request_transform(self, input_data: dict[str, Any]) -> tuple[dict[str, Any], str]:
+        """
+        Access MLFlow model to get the transformed data.
+        Args:
+            input_data (dict): The input data. Contains:
+                data (dict[str, Any]): The data to transform.
+                model_name (str): The name of the model.
+                model_retention (int): The retention of the model.
+        Returns:
+            tuple[dict[str, Any], str]: The transformed data and the latest timestamp of the data.
+        """
         self.logger.info('Transforming data...')
         data = DataFrame(input_data['data'])
         model_name = input_data['model_name']
@@ -50,6 +60,16 @@ class MLFlow(BaseActivity):
 
     @activity.defn(name="request_predict")
     async def request_predict(self, input_data: dict[str, Any]) -> tuple[dict[str, Any], str]:
+        """
+        Access MLFlow model to get the predicted data.
+        Args:
+            input_data (dict): The input data. Contains:
+                data (dict[str, Any]): The data to predict.
+                model_name (str): The name of the model.
+                model_retention (int): The retention of the model.
+        Returns:
+            tuple[dict[str, Any], str]: The predicted data and the latest timestamp of the data.
+        """
         self.logger.info('Predicting data...')
         data = DataFrame(input_data['data'])
         model_name = input_data['model_name']