SIENTIAPDE-1273

SIENTIAPDE-1273
Enhance security analysis and SQL injection handling

- Added skip for potential SQL injection false positives in Bandit configuration.
- Updated validate.sh to use the pyproject.toml configuration for Bandit security analysis.
- Refactored code to replace ensure_dataframe utility with direct DataFrame usage in multiple activities, improving clarity and reducing dependencies.
- Removed the deprecated dataframe_utils module to streamline the codebase.

laborious/activities/mlflow.py

@@ -1,4 +1,3 @@
-from typing import Hashable
 from temporalio import activity, workflow
 
 with workflow.unsafe.imports_passed_through():
@@ -20,7 +19,6 @@ with workflow.unsafe.imports_passed_through():
         now,
     )
 
-    from laborious.utils.dataframe_utils import ensure_dataframe
     from laborious.utils.repository.minio_repository import MinioRepository
     from laborious.utils.repository.model_repository import MLFlowRepository
 
@@ -140,7 +138,7 @@ class MLFlow(SientiaMonitoring):
         """
         metadata = input_data['metadata']
         self.info('Transforming data...', metadata)
-        data = ensure_dataframe(input_data['data'])
+        data = DataFrame(input_data['data'])
         model_name = input_data['model_name']
         model_config = input_data.get('model_config', {})
 
@@ -212,7 +210,7 @@ class MLFlow(SientiaMonitoring):
         """
         metadata = input_data['metadata']
         self.info('Predicting data...', metadata)
-        data = ensure_dataframe(input_data['data'])
+        data = DataFrame(input_data['data'])
         model_name = input_data['model_name']
         model_config = input_data.get('model_config', {})
 
@@ -421,7 +419,6 @@ class MLFlow(SientiaMonitoring):
             self.error(trace, metadata=metadata)
             raise e
 
-
     @activity.defn(name='get_reference_data')
     async def get_reference_data(self, input_data: dict[str, Any]) -> list[dict] | None:
         """
@@ -439,7 +436,7 @@ class MLFlow(SientiaMonitoring):
 
         metadata = input_data['metadata']
         model_name = input_data['model_name']
-        artifact = "evaluation_data.csv"
+        artifact = 'evaluation_data.csv'
 
         reference_data = await self.model_monitoring_repository.load_artifact_dataframe(
             model_name=model_name, artifact_path=artifact, metadata=metadata
@@ -452,4 +449,4 @@ class MLFlow(SientiaMonitoring):
         reference_data['timestamp'] = to_datetime(reference_data['timestamp'])
         reference_data['timestamp'] = reference_data['timestamp'].dt.strftime(DATETIME_FORMAT)
 
-        return reference_data.to_dict(orient='records')
+        return reference_data.to_dict(orient='records')