dataeval.outputs.BalanceOutput¶

class dataeval.outputs.BalanceOutput¶

Output class for balance() bias metric.

balance¶

Estimate of mutual information between metadata factors and class label

Type:¶

NDArray[np.float64]

factors¶

Estimate of inter/intra-factor mutual information

Type:¶

NDArray[np.float64]

classwise¶

Estimate of mutual information between metadata factors and individual class labels

Type:¶

NDArray[np.float64]

factor_names¶

Names of each metadata factor

Type:¶

Sequence[str]

class_names¶

List of the class labels present in the dataset

Type:¶

Sequence[str]

data()¶

The output data as a dictionary.

Return type:¶

dict[str, Any]

meta()¶

Metadata about the execution of the function or method for the Output class.

Return type:¶

ExecutionMetadata

plot(row_labels=None, col_labels=None, plot_classwise=False)¶

Plot a heatmap of balance information.

Parameters:¶

row_labels : ArrayLike or None, default None¶

List/Array containing the labels for rows in the histogram

col_labels : ArrayLike or None, default None¶

List/Array containing the labels for columns in the histogram

plot_classwise : bool, default False¶

Whether to plot per-class balance instead of global balance

Return type:¶

matplotlib.figure.Figure

Notes

This method requires matplotlib to be installed.