SIENTIAPDE-1241: Refactor: Remove redundant logging and fix duplicate logs

This commit removes redundant logging statements from training and experiment tracking activities, preventing duplicate log entries. It also introduces a logger helper to disable log propagation, further addressing the duplicate logs issue. Additionally, the Makefile, run_coverage.sh, setup_port_forwards.sh, and simulator/Dockerfile files were removed as they are no longer needed.

model_manager/utils/logger_helper.py

@@ -0,0 +1,27 @@
+"""
+Logger helper to prevent duplicate logs caused by propagation.
+
+This module provides a wrapper around sientia_do Logger to disable
+log propagation and prevent duplicate log entries in the Model Manager.
+"""
+
+from sientia_do.observability.logger import Logger as SientiaLogger
+
+
+def get_logger(name: str) -> SientiaLogger:
+    """
+    Create a Logger instance with propagation disabled.
+
+    This prevents duplicate logs caused by hierarchical propagation
+    in Python's logging system.
+
+    Args:
+        name: Logger name (typically __name__ of the calling module).
+
+    Returns:
+        Logger: Configured logger instance with propagation disabled.
+    """
+    logger = SientiaLogger(name)
+    # Disable propagation to prevent duplicate logs
+    logger.base_logger.propagate = False
+    return logger

model_manager/utils/repository/model_repository.py

@@ -55,25 +55,14 @@ class ModelRepository:
             Exception: If model saving fails (after sending notification)
         """
         experiment_name = train_result.params.experiment_name
-        self.logger.info(f'Starting model save for experiment: {experiment_name}')
-
-        # Step 1: Generate next run name
-        self.logger.info('Generating run name')
         train_result.run_name = self._get_next_run_name(experiment_name)
-        self.logger.info(f'Generated run name: {train_result.run_name}')
-
-        # Step 2: Generate artifacts (reports, CSV files)
-        self.logger.info('Generating artifacts')
         train_result = self._generate_artifacts(train_result)
-        self.logger.info('Artifacts generated successfully')
-
-        # Step 3: Save run to MLflow
-        self.logger.info('Saving run to MLflow')
         self._save_run(train_result)
 
         self.logger.info(
-            f'Model saved successfully - Run: {train_result.run_name}, '
-            f'Experiment: {experiment_name}'
+            f'Model saved successfully - experiment run id: {train_result.params.experiment_run_id}, '
+            f'experiment name: {experiment_name}, '
+            f'run name: {train_result.run_name}'
         )
 
         return train_result
@@ -93,8 +82,6 @@ class ModelRepository:
             self.logger.info('No run directory specified, skipping cleanup')
             return
 
-        self.logger.info(f'Cleaning up run directory: {run_dir}')
-
         if os.path.exists(run_dir):
             shutil.rmtree(run_dir)
             self.logger.info(f'Run directory deleted successfully: {run_dir}')

model_manager/utils/repository/storage_repository.py

@@ -102,7 +102,6 @@ class StorageRepository:
         Raises:
             OSError: If the download fails (network, permissions, missing key, etc.).
         """
-        self.logger.info(f'Fetching file from MinIO: {bucket_name}/{file_name}')
         response = self.minio_client.get_object(Bucket=bucket_name, Key=file_name)
 
         with response['Body'] as body:
@@ -124,6 +123,5 @@ class StorageRepository:
             bucket_name: Bucket that contains the object.
             file_name: Object key to delete.
         """
-        self.logger.info(f'Deleting file from MinIO: {bucket_name}/{file_name}')
         self.minio_client.delete_object(Bucket=bucket_name, Key=file_name)
         self.logger.info(f'File deleted successfully: {bucket_name}/{file_name}')

model_manager/utils/repository/training_repository.py

@@ -66,9 +66,7 @@ class TrainingRepository:
             ValueError: If transformed data is empty
             Exception: If data loading, preprocessing, or training fails
         """
-        self.logger.info('Loading data from BytesIO file')
         data = load_data(uploaded_file, params.line_separator, params.decimal_separator)
-        self.logger.info('Initializing and fitting data preprocessor')
         process_data = self._init_data_preprocessor(params)
         process_data.fit(data)
         data_view = process_data.transform(data)
@@ -76,7 +74,6 @@ class TrainingRepository:
         if len(data_view) <= 0:
             raise ValueError('Data view is empty after transformation')
 
-        self.logger.info('Splitting data into train/test sets')
         x_train, x_test, y_train, y_test = split_train_test(
             data_view[params.variable_columns],
             data_view[params.target_variable],
@@ -85,17 +82,18 @@ class TrainingRepository:
             random_state=42,
         )
 
-        self.logger.info('Preparing training data')
         data_train = pd.concat([x_train, y_train], axis=1)
         scaler_dict = self._init_scaler_dict(process_data, params)
 
-        self.logger.info('Training linear regression model')
         regr = LinearRegressionModel(
             target_variable=params.target_variable,
             variable_columns=params.variable_columns,
         )
 
         regr.fit(data_train)
+        self.logger.info(
+            f'Model trained successfully - experiment run id: {params.experiment_run_id}'
+        )
 
         return TrainModelResult(
             params=params,
@@ -128,12 +126,10 @@ class TrainingRepository:
             TrainModelResult: Updated result with predictions, denormalized data,
                             and metrics (mse_val, mae_val, r2_val)
         """
-        self.logger.info('Making predictions on test set')
         y_pred_array = tmr.regr.predict(tmr.x_test)
 
         if params.use_scaler:
             scaler = tmr.process_data.get_scaler()
-            self.logger.info('Denormalizing features')
 
             # If using custom scaler with denormalize_* helpers
             if hasattr(scaler, 'denormalize_single_input'):
@@ -141,7 +137,6 @@ class TrainingRepository:
                     tmr.x_train[col] = scaler.denormalize_single_input(tmr.x_train[col], col)
                     tmr.x_test[col] = scaler.denormalize_single_input(tmr.x_test[col], col)
 
-                self.logger.info('Denormalizing target variable')
                 tmr.y_train = scaler.denormalize_single_input(tmr.y_train, params.target_variable)
                 tmr.y_test = scaler.denormalize_single_input(tmr.y_test, params.target_variable)
                 y_pred_array = scaler.denormalize_predictions(y_pred_array, params.target_variable)
@@ -158,18 +153,15 @@ class TrainingRepository:
                 tmr.x_test[feature_cols] = scaler.inverse_transform(x_test_features)
                 # Target was not scaled with StandardScaler in preprocessing; leave y as-is
 
-        self.logger.info('Adding index to predictions')
         tmr.y_pred = pd.Series(y_pred_array, index=tmr.y_test.index)
         tmr.y_pred.name = f'{params.target_variable}_pred'
 
-        self.logger.info('Reordering all data by index')
         tmr.x_train = tmr.x_train.sort_index()
         tmr.x_test = tmr.x_test.sort_index()
         tmr.y_train = tmr.y_train.sort_index()
         tmr.y_test = tmr.y_test.sort_index()
         tmr.y_pred = tmr.y_pred.sort_index()
 
-        self.logger.info('Calculating evaluation metrics')
         assert tmr.y_pred is not None, 'y_pred should be set at this point'
 
         tmr.mse_val = round(
@@ -183,6 +175,9 @@ class TrainingRepository:
         )
 
         tmr.r2_val = round(r2(tmr.y_test.astype(np.float64), tmr.y_pred.astype(np.float64)), 2)
+        self.logger.info(
+            f'Model metrics calculated successfully - experiment run id: {params.experiment_run_id}'
+        )
         return tmr
 
     def _init_scaler_dict(self, process_data: DataPreprocessor, params: TrainModelParams) -> dict: