SIENTIAPDE-1430: Implement advanced model training capabilities and enhanced data preprocessing. This includes support for Polynomial Regression with configurable degree and interaction terms, flexible per-variable lag configurations, and new data filtering options by date range and removed intervals. Comprehensive business validations are now enforced for all parameters, and MLflow logging has been extended to capture these detailed configurations. Additionally, Reduced Coulomb Energy (RCE) metrics are added for drift detection, with a new changelog documenting all pipeline parameter updates.

tests/utils/models/test_train_model_params.py

@@ -8,8 +8,8 @@ def valid_train_params_dict():
     """Create a valid dictionary for TrainModelParams."""
     return {
         'variable_columns': ['var1', 'var2'],
-        'lag_train': 5,
-        'lag_val': 3,
+        'lag_train': {'var1': 5, 'var2': 5},
+        'lag_val': {'var1': 3, 'var2': 3},
         'target_variable': 'target',
         'rem_static_win': True,
         'low_lim': {'var1': 0.0, 'var2': 1.0},
@@ -26,6 +26,14 @@ def valid_train_params_dict():
         'experiment_run_id': 1,
         'experiment_name': 'test_experiment',
         'removed_intervals': [],
+        'model_name': 'Linear Regression',
+        'degree': 1,
+        'interaction_only': False,
+        'nan_treatment': 'drop',
+        'start_date': None,
+        'end_date': None,
+        'scaler_name': 'Standard Scaler',
+        'support_filters': {},
     }
 
 
@@ -36,8 +44,8 @@ def test_train_model_params_from_dict_success(valid_train_params_dict):
     params = TrainModelParams.from_dict(valid_train_params_dict)
 
     assert params.variable_columns == ['var1', 'var2']
-    assert params.lag_train == 5
-    assert params.lag_val == 3
+    assert params.lag_train == {'var1': 5, 'var2': 5}
+    assert params.lag_val == {'var1': 3, 'var2': 3}
     assert params.target_variable == 'target'
     assert params.rem_static_win is True
     assert params.low_lim == {'var1': 0.0, 'var2': 1.0}
@@ -118,9 +126,9 @@ def test_train_model_params_from_dict_wrong_type(valid_train_params_dict):
     """Test from_dict raises TypeError when field has wrong type."""
     from model_manager.utils.models.train_model_params import TrainModelParams
 
-    valid_train_params_dict['lag_train'] = 'not_an_int'
+    valid_train_params_dict['lag_train'] = 'not_a_dict'
 
-    with pytest.raises(TypeError, match='lag_train must be of type int, but got str'):
+    with pytest.raises(TypeError, match='lag_train must be of type dict, but got str'):
         TrainModelParams.from_dict(valid_train_params_dict)
 
 
@@ -179,10 +187,10 @@ def test_validate_business_rules_negative_lag_train(valid_train_params_dict):
     """Test validate_business_rules raises error when lag_train is negative."""
     from model_manager.utils.models.train_model_params import TrainModelParams
 
-    valid_train_params_dict['lag_train'] = -1
+    valid_train_params_dict['lag_train'] = {'var1': -1, 'var2': 5}
     params = TrainModelParams.from_dict(valid_train_params_dict)
 
-    with pytest.raises(ValueError, match='lag_train must be positive, got -1'):
+    with pytest.raises(ValueError, match='lag_train for var1 must be non-negative, got -1'):
         params.validate_business_rules()
 
 
@@ -190,10 +198,10 @@ def test_validate_business_rules_negative_lag_val(valid_train_params_dict):
     """Test validate_business_rules raises error when lag_val is negative."""
     from model_manager.utils.models.train_model_params import TrainModelParams
 
-    valid_train_params_dict['lag_val'] = -2
+    valid_train_params_dict['lag_val'] = {'var1': 3, 'var2': -2}
     params = TrainModelParams.from_dict(valid_train_params_dict)
 
-    with pytest.raises(ValueError, match='lag_val must be positive, got -2'):
+    with pytest.raises(ValueError, match='lag_val for var2 must be non-negative, got -2'):
         params.validate_business_rules()
 
 
@@ -204,7 +212,7 @@ def test_validate_business_rules_negative_window(valid_train_params_dict):
     valid_train_params_dict['window'] = -5
     params = TrainModelParams.from_dict(valid_train_params_dict)
 
-    with pytest.raises(ValueError, match='window must be positive, got -5'):
+    with pytest.raises(ValueError, match='window must be non-negative, got -5'):
         params.validate_business_rules()
 
 
@@ -334,7 +342,7 @@ def test_validate_business_rules_zero_lag_train(valid_train_params_dict):
     """Test validate_business_rules accepts lag_train = 0."""
     from model_manager.utils.models.train_model_params import TrainModelParams
 
-    valid_train_params_dict['lag_train'] = 0
+    valid_train_params_dict['lag_train'] = {'var1': 0, 'var2': 0}
     params = TrainModelParams.from_dict(valid_train_params_dict)
 
     params.validate_business_rules()  # Should not raise
@@ -344,7 +352,7 @@ def test_validate_business_rules_zero_lag_val(valid_train_params_dict):
     """Test validate_business_rules accepts lag_val = 0."""
     from model_manager.utils.models.train_model_params import TrainModelParams
 
-    valid_train_params_dict['lag_val'] = 0
+    valid_train_params_dict['lag_val'] = {'var1': 0, 'var2': 0}
     params = TrainModelParams.from_dict(valid_train_params_dict)
 
     params.validate_business_rules()  # Should not raise