Skip to content

LabelSchema

Source code in docs_src/capo_frauddetector/types/label_schema.py 
12
13
14
15
16
17
18
class LabelSchema(TypedDict, closed=True):
    label_mapper: NotRequired["capo_frauddetector.types.label_mapper.labelMapper"]
    """<p>The label mapper maps the Amazon Fraud Detector supported model classification labels (<code>FRAUD</code>, <code>LEGIT</code>) to the appropriate event type labels. For example, if "<code>FRAUD</code>" and "<code>LEGIT</code>" are Amazon Fraud Detector supported labels, this mapper could be: <code>{"FRAUD" => ["0"]</code>, <code>"LEGIT" => ["1"]}</code> or <code>{"FRAUD" => ["false"]</code>, <code>"LEGIT" => ["true"]}</code> or <code>{"FRAUD" => ["fraud", "abuse"]</code>, <code>"LEGIT" => ["legit", "safe"]}</code>. The value part of the mapper is a list, because you may have multiple label variants from your event type for a single Amazon Fraud Detector label. </p>"""
    unlabeled_events_treatment: NotRequired[
        "capo_frauddetector.types.unlabeled_events_treatment.UnlabeledEventsTreatment"
    ]
    """<p>The action to take for unlabeled events.</p> <ul> <li> <p>Use <code>IGNORE</code> if you want the unlabeled events to be ignored. This is recommended when the majority of the events in the dataset are labeled.</p> </li> <li> <p>Use <code>FRAUD</code> if you want to categorize all unlabeled events as “Fraud”. This is recommended when most of the events in your dataset are fraudulent.</p> </li> <li> <p>Use <code>LEGIT</code> if you want to categorize all unlabeled events as “Legit”. This is recommended when most of the events in your dataset are legitimate.</p> </li> <li> <p>Use <code>AUTO</code> if you want Amazon Fraud Detector to decide how to use the unlabeled data. This is recommended when there is significant unlabeled events in the dataset.</p> </li> </ul> <p>By default, Amazon Fraud Detector ignores the unlabeled data.</p>"""

label_mapper instance-attribute 

label_mapper: NotRequired[labelMapper]

The label mapper maps the Amazon Fraud Detector supported model classification labels (FRAUD, LEGIT) to the appropriate event type labels. For example, if "FRAUD" and "LEGIT" are Amazon Fraud Detector supported labels, this mapper could be: {"FRAUD" => ["0"], "LEGIT" => ["1"]} or {"FRAUD" => ["false"], "LEGIT" => ["true"]} or {"FRAUD" => ["fraud", "abuse"], "LEGIT" => ["legit", "safe"]}. The value part of the mapper is a list, because you may have multiple label variants from your event type for a single Amazon Fraud Detector label.

unlabeled_events_treatment instance-attribute 

unlabeled_events_treatment: NotRequired[UnlabeledEventsTreatment]

The action to take for unlabeled events.

  • Use IGNORE if you want the unlabeled events to be ignored. This is recommended when the majority of the events in the dataset are labeled.

  • Use FRAUD if you want to categorize all unlabeled events as “Fraud”. This is recommended when most of the events in your dataset are fraudulent.

  • Use LEGIT if you want to categorize all unlabeled events as “Legit”. This is recommended when most of the events in your dataset are legitimate.

  • Use AUTO if you want Amazon Fraud Detector to decide how to use the unlabeled data. This is recommended when there is significant unlabeled events in the dataset.

By default, Amazon Fraud Detector ignores the unlabeled data.