feat: log regression metrics as parameters in Training class

- Added a method to persist computed regression metrics (MSE, MAE, R²) as MLflow parameters during model training, enhancing model evaluation and tracking.
- Updated the Training class to log the equation path if available, improving artifact management.

tests/utils/models/test_train_model_params.py

@@ -5,7 +5,10 @@ from unittest.mock import patch
 
 import pytest
 
-from model_manager.utils.models.train_model_params import TrainModelParams
+from model_manager.utils.models.train_model_params import (
+    TrainModelParams,
+    validate_frontend_date_format,
+)
 
 
 @pytest.fixture
@@ -262,3 +265,11 @@ def test_validate_model_param_all_schema_branches(valid_train_params_dict):
     p.model_kwargs = {}
     p.opt_params = {}
     p.validate_business_rules()
+
+
+def test_validate_frontend_date_format_whitespace_returns():
+    validate_frontend_date_format('   ')
+
+
+def test_validate_frontend_date_format_valid_returns():
+    validate_frontend_date_format('dd/MM/yyyy HH:mm:ss')

tests/utils/repository/test_data_manager_repository.py

@@ -100,10 +100,23 @@ def test_prepare_training_data_empty_after_load():
     p = TrainModelParams.from_dict(_minimal_dict_for_prepare())
     # empty csv with headers only
     csv_bytes = b'v1,t\n'
-    with pytest.raises(ValueError, match='Training data view is empty'):
+    with pytest.raises(ValueError, match='Index is not a DatetimeIndex'):
         repo.prepare_training_data(csv_bytes, None, p, {})
 
 
+def test_prepare_training_data_empty_after_transformation(monkeypatch):
+    repo = dmr.DataManagerRepository(MagicMock())
+    p = TrainModelParams.from_dict(_minimal_dict_for_prepare())
+    monkeypatch.setattr(
+        repo,
+        '_configure_datetime_index',
+        lambda *_args, **_kwargs: pd.DataFrame(columns=['v1', 't']),
+    )
+    monkeypatch.setattr(repo, '_set_timezone_on_index', lambda data, *_args, **_kwargs: data)
+    with pytest.raises(ValueError, match='Training data view is empty after transformation'):
+        repo.prepare_training_data(b'v1,t\n', None, p, {})
+
+
 def _minimal_dict_for_prepare():
     return {
         'variable_columns': ['v1'],
@@ -364,6 +377,8 @@ def test_generate_report_success(tmp_path):
         params=p,
         train_data=pd.DataFrame({'v1': [1.0, 2.0], 't': [1.0, 2.0]}),
         val_data=pd.DataFrame({'v1': [1.0, 2.0], 't': [1.0, 2.0]}),
+        y_train_pred=pd.DataFrame({'t': [1.0, 2.0]}),
+        y_pred=pd.DataFrame({'t': [1.0, 2.0]}),
         run_name='testrun',
     )
     tmr.equation = {'target_variable': 't'}
@@ -388,6 +403,8 @@ def test_generate_report_skips_equation_file_when_not_linear(tmp_path):
         params=p,
         train_data=pd.DataFrame({'v1': [1.0, 2.0], 't': [1.0, 2.0]}),
         val_data=pd.DataFrame({'v1': [1.0, 2.0], 't': [1.0, 2.0]}),
+        y_train_pred=pd.DataFrame({'t': [1.0, 2.0]}),
+        y_pred=pd.DataFrame({'t': [1.0, 2.0]}),
         run_name='testrun',
         equation={'k': 'v'},
     )
@@ -412,6 +429,21 @@ def test_generate_report_run_name_missing():
         repo.generate_report(tmr, {})
 
 
+def test_generate_report_requires_predictions():
+    repo = dmr.DataManagerRepository(MagicMock())
+    p = TrainModelParams.from_dict(_minimal_dict_for_prepare())
+    tmr = TrainModelResult(
+        params=p,
+        train_data=pd.DataFrame({'t': [1.0]}),
+        val_data=pd.DataFrame({'t': [1.0]}),
+        run_name='testrun',
+        y_train_pred=None,
+        y_pred=None,
+    )
+    with pytest.raises(ValueError, match='y_train_pred or y_pred is not set'):
+        repo.generate_report(tmr, {})
+
+
 def test_cleanup_run_directory_empty():
     repo = dmr.DataManagerRepository(MagicMock())
     repo.cleanup_run_directory('', {})