feat: enhance training and regression metrics logging

- Added debug logging for data preparation, transformation, and prediction steps in the Training class to improve traceability.
- Updated compute_regression_metrics method to include metadata for better debugging and validation of index alignment between true and predicted values.

model_manager/activities/training.py

@@ -13,6 +13,7 @@ with workflow.unsafe.imports_passed_through():
     from typing import Any
 
     import mlflow
+    import pandas as pd
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.notifications.models import NotificationLevel
     from sientia_do.observability.logger import Logger
@@ -231,6 +232,12 @@ class Training(SientiaMonitoring):
             train_data = train_result.train_data
             val_data = train_result.val_data
 
+            self.debug(
+                f'train_model prepared data (head 10):\ntrain:\n{train_data.head(10).to_string()}'
+                f'\nval:\n{val_data.head(10).to_string()}',
+                metadata,
+            )
+
             wrapper.train(
                 train_data=train_data,
                 val_data=val_data,
@@ -245,9 +252,21 @@ class Training(SientiaMonitoring):
             transformed_train, _ = wrapper.transform(train_data)
             transformed_val, _ = wrapper.transform(val_data)
 
+            self.debug(
+                f'train_model transform (head 10):\ntrain:\n{transformed_train.head(10).to_string()}'
+                f'\nval:\n{transformed_val.head(10).to_string()}',
+                metadata,
+            )
+
             y_train_pred_df, _ = wrapper.predict({}, transformed_train)
             y_val_pred_df, _ = wrapper.predict({}, transformed_val)
 
+            self.debug(
+                f'train_model predict (head 10):\ntrain:\n{y_train_pred_df.head(10).to_string()}'
+                f'\nval:\n{y_val_pred_df.head(10).to_string()}',
+                metadata,
+            )
+
             y_train_pred_df.sort_index(inplace=True, ascending=False)
             y_val_pred_df.sort_index(inplace=True, ascending=False)
 
@@ -258,6 +277,7 @@ class Training(SientiaMonitoring):
             train_result = self.data_manager_repository.compute_regression_metrics(
                 train_result,
                 wrapper,
+                metadata=metadata,
             )
 
             self.info(f'Starting MLflow run for {train_params.model_type}', metadata)

model_manager/utils/repository/data_manager_repository.py

@@ -273,6 +273,7 @@ class DataManagerRepository(SientiaMonitoring):
         self,
         tmr: TrainModelResult,
         wrapper: SientiaModel,
+        metadata: dict[str, Any] | None = None,
     ) -> TrainModelResult:
         """
         Compute regression metrics for training results.
@@ -286,9 +287,11 @@ class DataManagerRepository(SientiaMonitoring):
             tmr: Training result containing:
                 - train_data/val_data DataFrames with a target column
                 - y_train_pred/y_pred populated (model predictions for train/val)
+            wrapper: Trained model wrapper (used for linear equation extraction).
+            metadata: Optional workflow metadata for debug logging.
 
         Return:
-            Updated TrainModelResult with mse_val, mae_val and r2_val fields populated.
+            TrainModelResult: Same object with mse_val, mae_val and r2_val set.
         """
         if tmr.y_pred is None:
             raise ValueError('y_pred must be set before computing regression metrics')
@@ -304,12 +307,28 @@ class DataManagerRepository(SientiaMonitoring):
 
         # Align by index to avoid metric calculation errors if ordering differs.
         common_index = y_true_val.index.intersection(y_pred_val.index)
+        head = min(5, len(y_true_val), len(y_pred_val))
+        self.debug(
+            'compute_regression_metrics index alignment: '
+            f'val_n={len(y_true_val)} pred_n={len(y_pred_val)} common_n={len(common_index)}; '
+            f'val_index_dtype={y_true_val.index.dtype} '
+            f'pred_index_dtype={y_pred_val.index.dtype}; '
+            f'val_index_sample={list(y_true_val.index[:head])} '
+            f'pred_index_sample={list(y_pred_val.index[:head])}',
+            metadata,
+        )
+
+        if len(common_index) == 0:
+            raise ValueError(
+                'No overlapping indices between val_data and y_pred. '
+                f'val_n={len(y_true_val)} pred_n={len(y_pred_val)} '
+                f'val_index_sample={list(y_true_val.index[:head])} '
+                f'pred_index_sample={list(y_pred_val.index[:head])}'
+            )
+
         y_true_val = y_true_val.loc[common_index]
         y_pred_val = y_pred_val.loc[common_index]
 
-        if len(y_true_val) == 0:
-            raise ValueError('No overlapping indices between val_data and y_pred')
-
         # Metrics helpers already round to 2 decimals.
         tmr.mse_val = mse(y_true_val, y_pred_val)
         tmr.mae_val = mae(y_true_val, y_pred_val)