fix(metrics): ignore NaN target/prediction pairs in validation metrics (SIENTIAPDE-2215)

model_manager/utils/repository/data_manager_repository.py

@@ -405,6 +405,23 @@ class DataManagerRepository(SientiaMonitoring):
         y_true_val = y_true_val.loc[common_index]
         y_pred_val = y_pred_val.loc[common_index]
 
+        # NaN target, or NaN prediction for rows with NaN features, carries no error signal
+        # (SIENTIAPDE-2215).
+        valid = y_true_val.notna() & y_pred_val.notna()
+        if not valid.any():
+            raise ValueError(
+                'No validation rows with both target and prediction: all '
+                f'{len(valid)} overlapping rows have NaN'
+            )
+        if not valid.all():
+            self.info(
+                f'Ignoring {int((~valid).sum())} validation row(s) with NaN target or prediction '
+                'in the regression metrics',
+                metadata,
+            )
+        y_true_val = y_true_val[valid]
+        y_pred_val = y_pred_val[valid]
+
         # 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)

tests/utils/repository/test_data_manager_repository.py

@@ -309,6 +309,41 @@ def test_compute_regression_metrics_no_overlap():
         repo.compute_regression_metrics(tmr, MagicMock())
 
 
+def test_compute_regression_metrics_ignores_nan_pairs():
+    """NaN target or NaN prediction rows are left out of mse/mae/r2 (SIENTIAPDE-2215)."""
+    repo = dmr.DataManagerRepository(MagicMock())
+    p = TrainModelParams.from_dict(_minimal_dict_for_prepare())
+    idx = pd.Index([0, 1, 2, 3])
+    tmr = TrainModelResult(
+        params=p,
+        train_data=pd.DataFrame({'t': [1.0, 2.0, 3.0, 4.0]}, index=idx),
+        val_data=pd.DataFrame({'t': [1.0, np.nan, 3.0, 4.0]}, index=idx),
+        y_pred=pd.DataFrame({'p': [1.0, 2.0, np.nan, 4.0]}, index=idx),
+    )
+
+    wrapper = MagicMock()
+    wrapper.model = object()  # no sklearn .regr -> equation extraction is skipped
+    out = repo.compute_regression_metrics(tmr, wrapper)
+
+    assert out.mse_val == 0.0
+    assert out.mae_val == 0.0
+
+
+def test_compute_regression_metrics_all_nan_pairs_raises():
+    repo = dmr.DataManagerRepository(MagicMock())
+    p = TrainModelParams.from_dict(_minimal_dict_for_prepare())
+    idx = pd.Index([0, 1])
+    tmr = TrainModelResult(
+        params=p,
+        train_data=pd.DataFrame({'t': [1.0, 2.0]}, index=idx),
+        val_data=pd.DataFrame({'t': [1.0, 2.0]}, index=idx),
+        y_pred=pd.DataFrame({'p': [np.nan, np.nan]}, index=idx),
+    )
+
+    with pytest.raises(ValueError, match='No validation rows with both target and prediction'):
+        repo.compute_regression_metrics(tmr, MagicMock())
+
+
 def test_compute_regression_metrics_linear_equation():
     repo = dmr.DataManagerRepository(MagicMock())
     p = TrainModelParams.from_dict(_minimal_dict_for_prepare())