SIENTIAPDE-1253: Implement business rule validation for training parameters. Adds a validate_business_rules method to the TrainModelParams class to enforce constraints on training parameters, improving data integrity and preventing errors. Also updates tests to include target variable in variable columns and adds tests for business rule validations.

tests/utils/models/test_train_model_params.py

@@ -297,3 +297,201 @@ def test_train_model_params_check_type_method():
     # Test that _check_type is a private method
     assert hasattr(params, '_check_type')
     assert callable(params._check_type)
+
+
+# ============================================================================
+# Tests for validate_business_rules method
+# ============================================================================
+
+
+def test_validate_business_rules_success(valid_params_dict):
+    """Test that valid params pass business rules validation."""
+    # Ensure target_variable is in variable_columns
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    # Should not raise any exception
+    params.validate_business_rules()
+
+
+def test_validate_business_rules_train_size_too_low(valid_params_dict):
+    """Test that train_size < 1 raises ValueError."""
+    valid_params_dict['train_size'] = 0
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='train_size must be between 1 and 99'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_train_size_too_high(valid_params_dict):
+    """Test that train_size > 99 raises ValueError."""
+    valid_params_dict['train_size'] = 100
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='train_size must be between 1 and 99'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_empty_variable_columns(valid_params_dict):
+    """Test that empty variable_columns raises ValueError."""
+    valid_params_dict['variable_columns'] = []
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='variable_columns cannot be empty'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_lag_train_zero(valid_params_dict):
+    """Test that lag_train = 0 raises ValueError."""
+    valid_params_dict['lag_train'] = 0
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='lag_train must be positive'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_lag_train_negative(valid_params_dict):
+    """Test that lag_train < 0 raises ValueError."""
+    valid_params_dict['lag_train'] = -1
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='lag_train must be positive'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_lag_val_zero(valid_params_dict):
+    """Test that lag_val = 0 raises ValueError."""
+    valid_params_dict['lag_val'] = 0
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='lag_val must be positive'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_window_zero(valid_params_dict):
+    """Test that window = 0 raises ValueError."""
+    valid_params_dict['window'] = 0
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='window must be positive'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_low_lim_upp_lim_keys_mismatch(valid_params_dict):
+    """Test that mismatched keys in low_lim and upp_lim raises ValueError."""
+    valid_params_dict['low_lim'] = {'var1': 0.0, 'var2': 0.0}
+    valid_params_dict['upp_lim'] = {'var1': 100.0, 'var3': 100.0}  # var3 instead of var2
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='low_lim and upp_lim must have the same keys'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_low_lim_greater_than_upp_lim(valid_params_dict):
+    """Test that low_lim >= upp_lim raises ValueError."""
+    valid_params_dict['low_lim'] = {'var1': 100.0, 'var2': 0.0, 'var3': 0.0}
+    valid_params_dict['upp_lim'] = {'var1': 50.0, 'var2': 100.0, 'var3': 100.0}
+    valid_params_dict['target_variable'] = 'var2'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='low_lim must be less than upp_lim for variable "var1"'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_low_lim_equal_to_upp_lim(valid_params_dict):
+    """Test that low_lim == upp_lim raises ValueError."""
+    valid_params_dict['low_lim'] = {'var1': 50.0, 'var2': 0.0, 'var3': 0.0}
+    valid_params_dict['upp_lim'] = {'var1': 50.0, 'var2': 100.0, 'var3': 100.0}
+    valid_params_dict['target_variable'] = 'var2'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='low_lim must be less than upp_lim for variable "var1"'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_target_not_in_variable_columns(valid_params_dict):
+    """Test that target_variable not in variable_columns raises ValueError."""
+    valid_params_dict['target_variable'] = 'nonexistent_var'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(
+        ValueError, match='target_variable "nonexistent_var" must be in variable_columns'
+    ):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_empty_bucket_name(valid_params_dict):
+    """Test that empty bucket_name raises ValueError."""
+    valid_params_dict['bucket_name'] = '   '
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='bucket_name cannot be empty or whitespace'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_empty_file_name(valid_params_dict):
+    """Test that empty file_name raises ValueError."""
+    valid_params_dict['file_name'] = ''
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='file_name cannot be empty or whitespace'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_empty_experiment_name(valid_params_dict):
+    """Test that empty experiment_name raises ValueError."""
+    valid_params_dict['experiment_name'] = '   '
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    with pytest.raises(ValueError, match='experiment_name cannot be empty or whitespace'):
+        params.validate_business_rules()
+
+
+def test_validate_business_rules_all_valid_edge_cases(valid_params_dict):
+    """Test that edge case valid values pass validation."""
+    valid_params_dict['train_size'] = 1  # Minimum valid
+    valid_params_dict['lag_train'] = 1  # Minimum valid
+    valid_params_dict['lag_val'] = 1  # Minimum valid
+    valid_params_dict['window'] = 1  # Minimum valid
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    # Should not raise any exception
+    params.validate_business_rules()
+
+
+def test_validate_business_rules_train_size_99(valid_params_dict):
+    """Test that train_size = 99 (maximum valid) passes validation."""
+    valid_params_dict['train_size'] = 99
+    valid_params_dict['target_variable'] = 'var1'
+
+    params = TrainModelParams.from_dict(valid_params_dict)
+
+    # Should not raise any exception
+    params.validate_business_rules()