SIENTIAPDE-1430: Refactor DataPreprocessor date filtering, make rce_train radius optional, and introduce constants for model names.

model_manager/utils/models/train_model_params.py

@@ -1,6 +1,10 @@
 from dataclasses import dataclass
 from typing import Any
 
+# Model name constants
+MODEL_LINEAR_REGRESSION = 'Linear Regression'
+MODEL_POLYNOMIAL_REGRESSION = 'Polynomial Regression'
+
 
 @dataclass
 class TrainModelParams:
@@ -239,23 +243,23 @@ class TrainModelParams:
         if self.scaler_name not in valid_scalers:
             raise ValueError(f'scaler_name must be one of {valid_scalers}, got {self.scaler_name}')
 
-        valid_models = ['Linear Regression', 'Polynomial Regression']
+        valid_models = [MODEL_LINEAR_REGRESSION, MODEL_POLYNOMIAL_REGRESSION]
         if self.model_name not in valid_models:
             raise ValueError(f'model_name must be one of {valid_models}, got {self.model_name}')
 
-        if self.model_name == 'Polynomial Regression' and self.degree < 2:
+        if self.model_name == MODEL_POLYNOMIAL_REGRESSION and self.degree < 2:
             raise ValueError(
-                f'degree must be at least 2 for Polynomial Regression, got {self.degree}'
+                f'degree must be at least 2 for {MODEL_POLYNOMIAL_REGRESSION}, got {self.degree}'
             )
 
-        if self.model_name == 'Polynomial Regression' and self.scaler_name == 'None':
+        if self.model_name == MODEL_POLYNOMIAL_REGRESSION and self.scaler_name == 'None':
             raise ValueError(
-                'scaler_name must be set (e.g., "Standard Scaler") for Polynomial Regression '
+                f'scaler_name must be set (e.g., "Standard Scaler") for {MODEL_POLYNOMIAL_REGRESSION} '
                 'to avoid numerical overflow with large feature values'
             )
 
-        if self.model_name == 'Linear Regression' and self.degree != 1:
-            raise ValueError(f'degree must be 1 for Linear Regression, got {self.degree}')
+        if self.model_name == MODEL_LINEAR_REGRESSION and self.degree != 1:
+            raise ValueError(f'degree must be 1 for {MODEL_LINEAR_REGRESSION}, got {self.degree}')
 
     def _validate_intervals_and_dates(self) -> None:
         """Validate removed_intervals format and date parameters."""