Metric Functions

Functions used for Metrics

Overview Information Here: boa.metrics

boa.metrics.metric_funcs.normalized_root_mean_squared_error(y_true, y_pred, normalizer='iqr', **kwargs)

Normalized root mean squared error

Parameters:

• y_true (array_like) – With shape (n_samples,) or (n_samples, n_outputs) Ground truth (correct) target values.

• y_pred (array_like) – With shape (n_samples,) or (n_samples, n_outputs) Estimated target values.

• normalizer (str) – How to normalize the RMSE, options include iqr, std, mean, and range. (default iqr)

• **kwargs – see sklearn.metrics.mean_squared_error for additional options

Returns:

nrmse – A normalized version of RMSE

Return type:

float or numpy.ndarray[float]

boa.metrics.metric_funcs.setup_sklearn_metric(metric_to_eval, instantiate=True, **kw)

boa.metrics.metric_funcs.get_sklearn_func(metric_to_eval)