fairlens.metrics.bootstrap_binned_statistic#

bootstrap_binned_statistic(h_x, h_y, statistic, n_samples=1000)[source]#

Compute the samples of a binned statistic estimate using the bootstrap method.

Parameters
  • h_x (pd.Series) – First histogram.

  • h_y (pd.Series) – Second histogram.

  • statistic (Callable[[pd.Series, pd.Series], float]) – Function that computes the statistic.

  • n_samples (int, optional) – Number of bootstrap samples to perform.

Returns

The bootstrap samples.

Return type

np.ndarray