ClassPerformance

class ClassPerformance

Summarize given metrics on a dataset and model.

Parameters

scorers: Union[Dict[str, Union[Metric, Callable, str]], List[Any]], default: None

Scorers to override the default scorers (metrics), find more about the supported formats at https://docs.deepchecks.com/stable/user-guide/general/metrics_guide.html

alternative_metricsUnion[Dict[str, Union[Metric,str]], List[str]], default: None

Deprecated, please use scorers instead.

n_to_showint, default: 20

Number of classes to show in the report. If None, show all classes.

show_onlystr, default: ‘largest’

Specify which classes to show in the report. Can be one of the following: - ‘largest’: Show the largest classes. - ‘smallest’: Show the smallest classes. - ‘random’: Show random classes. - ‘best’: Show the classes with the highest score. - ‘worst’: Show the classes with the lowest score.

metric_to_show_bystr, default: None

Specify the metric to sort the results by. Relevant only when show_only is ‘best’ or ‘worst’. If None, sorting by the first metric in the default metrics list.

class_list_to_show: List[int], default: None

Specify the list of classes to show in the report. If specified, n_to_show, show_only and metric_to_show_by are ignored.

__init__(scorers: Optional[Union[Dict[str, Union[Metric, Callable, str]], List[Any]]] = None, alternative_metrics: Optional[Union[Dict[str, Union[Metric, str]], List[str]]] = None, n_to_show: int = 20, show_only: str = 'largest', metric_to_show_by: Optional[str] = None, class_list_to_show: Optional[List[int]] = None, **kwargs)

__new__(*args, **kwargs)

Methods

ClassPerformance.add_condition(name, ...)	Add new condition function to the check.
ClassPerformance.add_condition_class_performance_imbalance_ratio_less_than([...])	Add condition - relative ratio difference between highest-class and lowest-class is less than threshold.
ClassPerformance.add_condition_test_performance_greater_than(...)	Add condition - metric scores are greater than the threshold.
ClassPerformance.add_condition_train_test_relative_degradation_less_than([...])	Add condition - test performance is not degraded by more than given percentage in train.
ClassPerformance.clean_conditions()	Remove all conditions from this check instance.
ClassPerformance.compute(context)	Compute the metric result using the ignite metrics compute method and create display.
ClassPerformance.conditions_decision(result)	Run conditions on given result.
ClassPerformance.config([include_version])	Return check configuration (conditions' configuration not yet supported).
ClassPerformance.from_config(conf[, ...])	Return check object from a CheckConfig object.
ClassPerformance.from_json(conf[, ...])	Deserialize check instance from JSON string.
ClassPerformance.initialize_run(context)	Initialize run by creating the _state member with metrics for train and test.
ClassPerformance.metadata([with_doc_link])	Return check metadata.
ClassPerformance.name()	Name of class in split camel case.
ClassPerformance.params([show_defaults])	Return parameters to show when printing the check.
ClassPerformance.remove_condition(index)	Remove given condition by index.
ClassPerformance.run(train_dataset, test_dataset)	Run check.
ClassPerformance.to_json([indent])	Serialize check instance to JSON string.
ClassPerformance.update(context, batch, ...)	Update the metrics by passing the batch to ignite metric update method.

Examples

Class Performance

previous

TrainTestPredictionDrift.update

next

ClassPerformance.add_condition