bootstrap_statistic#

cinnabar.stats.bootstrap_statistic(y_true: ndarray, y_pred: ndarray, dy_true: ndarray | None = None, dy_pred: ndarray | None = None, ci: float = 0.95, statistic: str = 'RMSE', nbootstrap: int = 1000, plot_type: str = 'dG', include_true_uncertainty: bool = False, include_pred_uncertainty: bool = False) → dict[source]#

Compute mean and confidence intervals of specified statistic.

Parameters:

  • y_true (ndarray with shape (N,)) – True values

  • y_pred (ndarray with shape (N,)) – Predicted values

  • dy_true (ndarray with shape (N,) or None) – Errors of true values. If None, the values are assumed to have no errors

  • dy_pred (ndarray with shape (N,) or None) – Errors of predicted values. If None, the values are assumed to have no errors

  • ci (float, optional, default=0.95) – Interval for confidence interval (CI)

  • statistic (str) – Statistic, one of [‘RMSE’, ‘MUE’, ‘R2’, ‘rho’,’KTAU’,’RAE’]

  • nbootstrap (int, optional, default=1000) – Number of bootstrap samples

  • plot_type (str, optional, default=’dG’) – ‘dG’ or ‘ddG’

  • include_true_uncertainty (bool, default False) – whether to account for the uncertainty in y_true when bootstrapping

  • include_pred_uncertainty (bool, default False) – whether to account for the uncertainty in y_pred when bootstrapping

Returns:

rmse_stats – ‘mean’ : mean RMSE ‘stderr’ : standard error ‘low’ : low end of CI ‘high’ : high end of CI

Return type:

dict of float