Universal Timber Slab: Disciplinary Surrogate Models

Model Artifacts Each surrogate is saved as a .joblib file which stores: { 'model': <trained sklearn model>, # Trained model 'scaler': <StandardScaler or None>, # Feature scaler 'feature_names': List[str], # 31 feature names 'model_name': str, # e.g., 'Extra Trees' 'target': str, # Target variable 'discipline': str, # Discipline 'metrics': { 'test_r2': float, 'test_rmse': float, 'test_mae': float, } } Demo Python script The Python script predict_bays.py demonstrates how to extract the relevant features from the UTS BHoM data schema and use the trained models to predict the performance of each bay in a slab.

To run the CLI script, (cd) to the directory containing predict_bays.py. By default, the trained models should be located in a models subdirectory within this directory. Alternatively, a custom models directory can be specified using the --models-dir option.