tfma.view.render_slicing_metrics

View source on GitHub

Renders the slicing metrics view as widget.

tfma.view.render_slicing_metrics(
    result: tfma.EvalResult,
    slicing_column: Optional[Text] = None,
    slicing_spec: Optional[Union[slicer.SingleSliceSpec, tfma.SlicingSpec]] = None,
    weighted_example_column: Text = None,
    event_handlers: Optional[Callable[[Dict[Text, Union[Text, float]]], None]] = None
) -> Optional[visualization.SlicingMetricsViewer]

Used in the notebooks

Used in the tutorials

result An tfma.EvalResult.
slicing_column The column to slice on.
slicing_spec The tfma.SlicingSpec to filter results. If neither column nor spec is set, show overall.
weighted_example_column Override for the weighted example column. This can be used when different weights are applied in different aprts of the model (eg: multi-head).
event_handlers The event handlers

A SlicingMetricsViewer object if in Jupyter notebook; None if in Colab.