default_model_config

abstract property RegressionModelBuilder.default_model_config: dict

Return a class default configuration dictionary.

For model builder if no model_config is provided on class initialization Useful for understanding structure of required model_config to allow its customization by users

Returns:

model_configdict

A set of default parameters for predictor distributions that allow to save and recreate the model.

Examples

@classmethod
def default_model_config(self):
    Return {
        'a' : {
            'loc': 7,
            'scale' : 3
        },
        'b' : {
            'loc': 3,
            'scale': 5
        },
         'obs_error': 2
    }