refactor(metrics): warn with the remaining count and document NaN pairs (SIENTIAPDE-2215)

model_manager/utils/repository/data_manager_repository.py

@@ -357,7 +357,8 @@ class DataManagerRepository(SientiaMonitoring):
         This helper mirrors the previous TrainingRepository.after_train_calculation
         behavior, assuming that predictions (y_pred/y_train_pred) are already on the
         correct scale for metric calculation (any scaling is handled inside the
-        model wrapper).
+        model wrapper). Pairs with a NaN target or a NaN prediction are left out of
+        mse/mae/r2.
 
         Args:
             tmr: Training result containing:
@@ -368,6 +369,10 @@ class DataManagerRepository(SientiaMonitoring):
 
         Return:
             TrainModelResult: Same object with mse_val, mae_val and r2_val set.
+
+        Raises:
+            ValueError: If y_pred is not set, val_data and y_pred share no indices,
+                or no pair has both a valid target and a valid prediction.
         """
         if tmr.y_pred is None:
             raise ValueError('y_pred must be set before computing regression metrics')
@@ -414,9 +419,10 @@ class DataManagerRepository(SientiaMonitoring):
                 f'{len(valid)} overlapping rows have NaN'
             )
         if not valid.all():
-            self.info(
+            n_valid = int(valid.sum())
-                f'Ignoring {int((~valid).sum())} validation row(s) with NaN target or prediction '
+            self.warning(
-                'in the regression metrics',
+                f'Ignoring {len(valid) - n_valid} of {len(valid)} validation row(s) with NaN '
+                f'target or prediction; regression metrics use the remaining {n_valid}',
                 metadata,
             )
         y_true_val = y_true_val[valid]

tests/utils/repository/test_data_manager_repository.py

@@ -323,10 +323,14 @@ def test_compute_regression_metrics_ignores_nan_pairs():
 
     wrapper = MagicMock()
     wrapper.model = object()  # no sklearn .regr -> equation extraction is skipped
-    out = repo.compute_regression_metrics(tmr, wrapper)
+    with patch.object(repo, 'warning') as warn:
+        out = repo.compute_regression_metrics(tmr, wrapper)
 
     assert out.mse_val == 0.0
     assert out.mae_val == 0.0
+    assert out.r2_val == 1.0
+    warn.assert_called_once()
+    assert 'Ignoring 2 of 4' in warn.call_args.args[0]
 
 
 def test_compute_regression_metrics_all_nan_pairs_raises():