metrics#

Utils module containing utilities for checks working with metrics.

Functions

task_type_check(model, dataset)

Check task type (regression, binary, multiclass) according to model object and label column.

get_gain(base_score, score, perfect_score, ...)

Get gain between base score and score compared to the distance from the perfect score.

init_validate_scorers(scorers, model, dataset)

Initialize scorers and return all of them as deepchecks scorers.

get_default_scorers(model_type[, class_avg])

Get default scorers based on model type.

Classes

ModelType

Enum containing supported task types.

DeepcheckScorer

Encapsulate scorer function with extra methods.