Deepchecks Hierarchy#

A Suite runs a collection of Checks with optional Conditions added to them.

Check#

Each check enables you to inspect a specific aspect of your data and models. They are the basic building block of the deepchecks package, covering all kinds of common issues, such as:

Each check can have two types of results:

  1. A visual result meant for display (e.g. a figure or a table).

  2. A return value that can be used for validating the expected check results (validations are typically done by adding a “Condition” to the check, as explained below).

See Also#

Condition#

A condition is a function that can be added to a Check, which returns a pass ✓, fail ✖ or warning ! result, intended for validating the Check’s return value. An example for adding a condition would be:

from deepchecks.tabular.checks import BoostingOverfit
BoostingOverfit().add_condition_test_score_percent_decline_not_greater_than(threshold=0.05)

Most checks come with pre-implemented conditions that can be added to the check, and their parameters can be tuned. Different conditions can be concatenated on the same check. Evaluation of these conditions will happen separately for each condition. Each condition has a ConditionCategory type, which indicates whether an unmet condition will be classified or as FAIL (✖) or as WARN (!).

See Also#

Suite#

An ordered collection of checks, that can have conditions added to them. The Suite enables displaying a concluding report for all of the Checks that ran. The existing suites include default conditions added for most of the checks. You can edit the preconfigured suites or build a suite of your own with a collection of checks and optional conditions.

See Also#

Deepchecks Diagram