abacusai.api_class.monitor_alert

Classes

`AlertConditionConfig`	An abstract class for alert condition configs
`AccuracyBelowThresholdConditionConfig`	Accuracy Below Threshold Condition Config for Monitor Alerts
`FeatureDriftConditionConfig`	Feature Drift Condition Config for Monitor Alerts
`TargetDriftConditionConfig`	Target Drift Condition Config for Monitor Alerts
`HistoryLengthDriftConditionConfig`	History Length Drift Condition Config for Monitor Alerts
`DataIntegrityViolationConditionConfig`	Data Integrity Violation Condition Config for Monitor Alerts
`BiasViolationConditionConfig`	Bias Violation Condition Config for Monitor Alerts
`PredictionCountConditionConfig`	Deployment Prediction Condition Config for Deployment Alerts. By default we monitor if predictions made over a time window has reduced significantly.
`_AlertConditionConfigFactory`	Helper class that provides a standard way to create an ABC using
`AlertActionConfig`	An abstract class for alert action configs
`EmailActionConfig`	Email Action Config for Monitor Alerts
`_AlertActionConfigFactory`	Helper class that provides a standard way to create an ABC using
`MonitorThresholdConfig`	Monitor Threshold Config for Monitor Alerts

Module Contents

class abacusai.api_class.monitor_alert.AlertConditionConfig

Bases: abacusai.api_class.abstract.ApiClass

An abstract class for alert condition configs

alert_type: abacusai.api_class.enums.MonitorAlertType

classmethod _get_builder()

class abacusai.api_class.monitor_alert.AccuracyBelowThresholdConditionConfig

Bases: AlertConditionConfig

Accuracy Below Threshold Condition Config for Monitor Alerts

Parameters:: threshold (float) – Threshold for when to consider a column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.

threshold: float

__post_init__()

class abacusai.api_class.monitor_alert.FeatureDriftConditionConfig

Bases: AlertConditionConfig

Feature Drift Condition Config for Monitor Alerts

Parameters:

feature_drift_type (FeatureDriftType) – Feature drift type to apply the threshold on to determine whether a column has drifted significantly enough to be a violation.
threshold (float) – Threshold for when to consider a column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.
minimum_violations (int) – Number of columns that must exceed the specified threshold to trigger an alert.
feature_names (List[str]) – List of feature names to monitor for this alert.

feature_drift_type: abacusai.api_class.enums.FeatureDriftType

threshold: float

minimum_violations: int

feature_names: List[str]

__post_init__()

class abacusai.api_class.monitor_alert.TargetDriftConditionConfig

Bases: AlertConditionConfig

Target Drift Condition Config for Monitor Alerts

Parameters:

feature_drift_type (FeatureDriftType) – Target drift type to apply the threshold on to determine whether a column has drifted significantly enough to be a violation.
threshold (float) – Threshold for when to consider the target column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.

feature_drift_type: abacusai.api_class.enums.FeatureDriftType

threshold: float

__post_init__()

class abacusai.api_class.monitor_alert.HistoryLengthDriftConditionConfig

Bases: AlertConditionConfig

History Length Drift Condition Config for Monitor Alerts

Parameters:

feature_drift_type (FeatureDriftType) – History length drift type to apply the threshold on to determine whether the history length has drifted significantly enough to be a violation.
threshold (float) – Threshold for when to consider the history length to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.

feature_drift_type: abacusai.api_class.enums.FeatureDriftType

threshold: float

__post_init__()

class abacusai.api_class.monitor_alert.DataIntegrityViolationConditionConfig

Bases: AlertConditionConfig

Data Integrity Violation Condition Config for Monitor Alerts

Parameters:

data_integrity_type (DataIntegrityViolationType) – This option selects the data integrity violations to monitor for this alert.
minimum_violations (int) – Number of columns that must exceed the specified threshold to trigger an alert.

data_integrity_type: abacusai.api_class.enums.DataIntegrityViolationType

minimum_violations: int

__post_init__()

class abacusai.api_class.monitor_alert.BiasViolationConditionConfig

Bases: AlertConditionConfig

Bias Violation Condition Config for Monitor Alerts

Parameters:

bias_type (BiasType) – This option selects the bias metric to monitor for this alert.
threshold (float) – Threshold for when to consider a column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.
minimum_violations (int) – Number of columns that must exceed the specified threshold to trigger an alert.

bias_type: abacusai.api_class.enums.BiasType

threshold: float

minimum_violations: int

__post_init__()

class abacusai.api_class.monitor_alert.PredictionCountConditionConfig

Bases: AlertConditionConfig

Deployment Prediction Condition Config for Deployment Alerts. By default we monitor if predictions made over a time window has reduced significantly. :param threshold: Threshold for when to consider to be a violation. Negative means alert on reduction, positive means alert on increase. :type threshold: float :param aggregation_window: Time window to aggregate the predictions over, e.g. 1h, 10m. Only h(hour), m(minute) and s(second) are supported. :type aggregation_window: str :param aggregation_type: Aggregation type to use for the aggregation window, e.g. sum, avg. :type aggregation_type: str

threshold: float

aggregation_window: str

aggregation_type: str

__post_init__()

class abacusai.api_class.monitor_alert._AlertConditionConfigFactory

Bases: abacusai.api_class.abstract._ApiClassFactory

Helper class that provides a standard way to create an ABC using inheritance.

config_abstract_class

config_class_key = 'alert_type'

config_class_key_value_camel_case = True

config_class_map

class abacusai.api_class.monitor_alert.AlertActionConfig

Bases: abacusai.api_class.abstract.ApiClass

An abstract class for alert action configs

action_type: abacusai.api_class.enums.AlertActionType

classmethod _get_builder()

class abacusai.api_class.monitor_alert.EmailActionConfig

Bases: AlertActionConfig

Email Action Config for Monitor Alerts

Parameters:

email_recipients (List[str]) – List of email addresses to send the alert to.
email_body (str) – Body of the email to send.

email_recipients: List[str]

email_body: str

__post_init__()

class abacusai.api_class.monitor_alert._AlertActionConfigFactory

Bases: abacusai.api_class.abstract._ApiClassFactory

Helper class that provides a standard way to create an ABC using inheritance.

config_abstract_class

config_class_key = 'action_type'

config_class_map

class abacusai.api_class.monitor_alert.MonitorThresholdConfig

Bases: abacusai.api_class.abstract.ApiClass

Monitor Threshold Config for Monitor Alerts

Parameters:

drift_type (FeatureDriftType) – Feature drift type to apply the threshold on to determine whether a column has drifted significantly enough to be a violation.
threshold_config (ThresholdConfigs) – Thresholds for when to consider a column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.

drift_type: abacusai.api_class.enums.FeatureDriftType

at_risk_threshold: float

severely_drifting_threshold: float

to_dict(): Standardizes converting an ApiClass to dictionary. Keys of response dictionary are converted to camel case. This also validates the fields ( type, value, etc ) received in the dictionary.