syndi.task_evaluator

Task Evaluator

Task_Evaluator(task[, preprocess_fn])
Task_Evaluator.evaluate_task([metrics])	Run benchmark testing on a task.
Task_Evaluator.get_sampler_logs()
Task_Evaluator._get_scores(ground_truth, …)
Task_Evaluator._get_classification_scores(…)
Task_Evaluator._get_regression_scores(…)

previous

syndi.sampler.Sampler._sample_baseline

next

syndi.task_evaluator.Task_Evaluator