Skip to content

Feature Monitoring Result#

You can retrieve feature monitoring results by calling FeatureMonitoringConfig.get_history.

FeatureMonitoringResult #

config_id property #

config_id: int

Id of the feature monitoring configuration containing this result.

detection_statistics property #

detection_statistics: FeatureDescriptiveStatistics | None

Feature descriptive statistics computed on the detection window.

detection_statistics_id property #

detection_statistics_id: int | None

Id of the feature descriptive statistics computed on the detection window.

difference property #

difference: float | None

Difference between detection and reference values. It can be relative or absolute difference, depending on the statistics comparison configuration provided in relative parameter passed to compare_on() when enabling feature monitoring.

empty_detection_window property #

empty_detection_window: bool

Whether or not the detection window was empty in this feature monitoring run.

empty_reference_window property #

empty_reference_window: bool

Whether or not the reference window was empty in this feature monitoring run.

execution_id property #

execution_id: int | None

Execution id of the feature monitoring job.

feature_name property #

feature_name: str

Name of the feature being monitored.

feature_store_id property #

feature_store_id: int

Id of the Feature Store.

id property #

id: int | None

Id of the feature monitoring result.

monitoring_time property #

monitoring_time: int

Time at which this feature monitoring result was created.

reference_statistics property #

reference_statistics: FeatureDescriptiveStatistics | None

Feature descriptive statistics computed on the reference window.

reference_statistics_id property #

reference_statistics_id: int | None

Id of the feature descriptive statistics computed on the reference window.

shift_detected property #

shift_detected: bool

Whether or not shift was detected in the detection window based on the computed statistics and the threshold provided in compare_on() when enabling feature monitoring.

specific_value property #

specific_value: float | None

Specific value used as reference in the statistics comparison.