Generate Performance Dashboard

This section presents how to generate a Performance Dashboard from the Python API Client.

expai.ExpaiModelPerformance

To initialise this class, it is required to get a ModelFairness object using expai.ExpaiProject.get_model_performance(). More info here.

expai.ExpaiModelFairness.launch_performance_dashboard

Create a new model within the project.

expai.ExpaiModelFairness.launch_performance_dashboard(self, sample_name: str = None, sample_id: str = None, subset_indexes: list = None, protected_columns: list = None)

Attribute	Description	Required
sample_name	Exact name of the sample that will be used to measure fairness in the model.	Yes, if sample_id is not provided
sample_id	Unique identifier of the sample that will be used to measure fairness in the model.	Yes, if sample_name is not provided

fairness_explainer.launch_performance_dashboard(sample_name="Dataset")

This method returns an URL from which you will be able to access the dashboard in your browser. You can also create an IFrame wherever you need it.