ConfusionMatrixReport

class ConfusionMatrixReport

Calculate the confusion matrix of the model on the given dataset.

Parameters

normalize_displaybool , default: True:

boolean that determines whether to normalize the values of the matrix in the display.

n_samplesint , default: 1_000_000

number of samples to use for this check.

random_stateint, default: 42

random seed for all check internals.

__init__(normalize_display: bool = True, n_samples: int = 1000000, random_state: int = 42, **kwargs)

__new__(*args, **kwargs)

Methods

ConfusionMatrixReport.add_condition(name, ...)	Add new condition function to the check.
ConfusionMatrixReport.add_condition_misclassified_samples_lower_than_condition([...])	Add condition - Misclassified samples lower than threshold.
ConfusionMatrixReport.clean_conditions()	Remove all conditions from this check instance.
ConfusionMatrixReport.conditions_decision(result)	Run conditions on given result.
ConfusionMatrixReport.config([...])	Return check configuration (conditions' configuration not yet supported).
ConfusionMatrixReport.from_config(conf[, ...])	Return check object from a CheckConfig object.
ConfusionMatrixReport.from_json(conf[, ...])	Deserialize check instance from JSON string.
ConfusionMatrixReport.metadata([with_doc_link])	Return check metadata.
ConfusionMatrixReport.name()	Name of class in split camel case.
ConfusionMatrixReport.params([show_defaults])	Return parameters to show when printing the check.
ConfusionMatrixReport.remove_condition(index)	Remove given condition by index.
ConfusionMatrixReport.run(dataset[, model, ...])	Run check.
ConfusionMatrixReport.run_logic(context, ...)	Run check.
ConfusionMatrixReport.to_json([indent, ...])	Serialize check instance to JSON string.

Examples

Confusion Matrix Report

previous

CalibrationScore.to_json

next

ConfusionMatrixReport.add_condition