dataeval.metrics.bias.DiversityOutput ===================================== .. py:class:: dataeval.metrics.bias.DiversityOutput Output class for :func:`diversity` :term:`bias` metric .. attribute:: diversity_index :term:`Diversity` index for classes and factors :type: NDArray[np.double] .. attribute:: classwise Classwise diversity index [n_class x n_factor] :type: NDArray[np.double] .. attribute:: factor_names Names of each metadata factor :type: list[str] .. attribute:: class_list Class labels for each value in the dataset :type: NDArray[Any] .. py:method:: plot(row_labels = None, col_labels = None, plot_classwise = False) Plot a heatmap of diversity information :param row_labels: List/Array containing the labels for rows in the histogram :type row_labels: ArrayLike or None, default None :param col_labels: List/Array containing the labels for columns in the histogram :type col_labels: ArrayLike or None, default None :param plot_classwise: Whether to plot per-class balance instead of global balance :type plot_classwise: bool, default False