model_versions

Creates, updates, deletes, gets or lists a model_versions resource.

Overview

Name	model_versions
Type	Resource
Id	aws.frauddetector.model_versions

Fields

The following fields are returned by SELECT queries:

get_model_version

Name	Datatype	Description
arn	string	The model version ARN. (pattern: <code>^arn:aws[a-z-]{0,15}:frauddetector:[a-z0-9-]{3,20}:[0-9]{12}:[^\s]{2,128}$</code>)
external_events_detail	object	The details of the external events data used for training the model version. This will be populated if the trainingDataSource is EXTERNAL_EVENTS
ingested_events_detail	object	The details of the ingested events data used for training the model version. This will be populated if the trainingDataSource is INGESTED_EVENTS.
model_id	string	The model ID. (pattern: <code>^[0-9a-z_]+$</code>)
model_type	string	The model type. (ONLINE_FRAUD_INSIGHTS, TRANSACTION_FRAUD_INSIGHTS, ACCOUNT_TAKEOVER_INSIGHTS)
model_version_number	string	The model version number. (pattern: <code>^[1-9][0-9]{0,3}.[0-9]{1,2}$</code>)
status	string	The model version status. Possible values are: TRAINING_IN_PROGRESS TRAINING_COMPLETE ACTIVATE_REQUESTED ACTIVATE_IN_PROGRESS ACTIVE INACTIVATE_REQUESTED INACTIVATE_IN_PROGRESS INACTIVE ERROR
training_data_schema	object	The training data schema.
training_data_source	string	The training data source. (EXTERNAL_EVENTS, INGESTED_EVENTS)

describe_model_versions

Name	Datatype	Description
model_version_details	array	The model version details.
next_token	string	The next token.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_model_version	select	region		Gets the details of the specified model version.
describe_model_versions	select	region		Gets all of the model versions for the specified model type or for the specified model type and model ID. You can also get details for a single, specified model version.
create_model_version	insert	region, modelId, modelType, trainingDataSource, trainingDataSchema		Creates a version of the model using the specified model type and model id.
update_model_version_status	update	region, modelId, modelType, modelVersionNumber, status		Updates the status of a model version. You can perform the following status updates: Change the TRAINING_IN_PROGRESS status to TRAINING_CANCELLED. Change the TRAINING_COMPLETE status to ACTIVE. Change ACTIVE to INACTIVE.
update_model_version	update	region, modelId, modelType, majorVersionNumber		Updates a model version. Updating a model version retrains an existing model version using updated training data and produces a new minor version of the model. You can update the training data set location and data access role attributes using this action. This action creates and trains a new minor version of the model, for example version 1.01, 1.02, 1.03.
delete_model_version	delete	region		Deletes a model version. You can delete models and model versions in Amazon Fraud Detector, provided that they are not associated with a detector version. When you delete a model version, Amazon Fraud Detector permanently deletes that model version and the data is no longer stored in Amazon Fraud Detector.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
region	string	AWS region (default: us-east-1)

SELECT examples

get_model_version

Gets the details of the specified model version.

SELECT
arn,
external_events_detail,
ingested_events_detail,
model_id,
model_type,
model_version_number,
status,
training_data_schema,
training_data_source
FROM aws.frauddetector.model_versions
WHERE region = '{{ region }}' -- required
;

describe_model_versions

Gets all of the model versions for the specified model type or for the specified model type and model ID. You can also get details for a single, specified model version.

SELECT
model_version_details,
next_token
FROM aws.frauddetector.model_versions
WHERE region = '{{ region }}' -- required
;

INSERT examples

create_model_version

Creates a version of the model using the specified model type and model id.

INSERT INTO aws.frauddetector.model_versions (
modelId,
modelType,
trainingDataSource,
trainingDataSchema,
externalEventsDetail,
ingestedEventsDetail,
tags,
region
)
SELECT 
'{{ modelId }}' /* required */,
'{{ modelType }}' /* required */,
'{{ trainingDataSource }}' /* required */,
'{{ trainingDataSchema }}' /* required */,
'{{ externalEventsDetail }}',
'{{ ingestedEventsDetail }}',
'{{ tags }}',
'{{ region }}'
RETURNING
model_id,
model_type,
model_version_number,
status
;

Manifest

# Description fields are for documentation purposes
- name: model_versions
props:
  - name: region
    value: "{{ region }}"
    description: Required parameter for the model_versions resource.
  - name: modelId
    value: "{{ modelId }}"
    description: |
      The model ID.
  - name: modelType
    value: "{{ modelType }}"
    description: |
      The model type.
    valid_values: ['ONLINE_FRAUD_INSIGHTS', 'TRANSACTION_FRAUD_INSIGHTS', 'ACCOUNT_TAKEOVER_INSIGHTS']
  - name: trainingDataSource
    value: "{{ trainingDataSource }}"
    description: |
      The training data source location in Amazon S3.
    valid_values: ['EXTERNAL_EVENTS', 'INGESTED_EVENTS']
  - name: trainingDataSchema
    description: |
      The training data schema.
    value:
      modelVariables:
        - "{{ modelVariables }}"
      labelSchema:
        labelMapper: "{{ labelMapper }}"
        unlabeledEventsTreatment: "{{ unlabeledEventsTreatment }}"
  - name: externalEventsDetail
    description: |
      Details of the external events data used for model version training. Required if trainingDataSource is EXTERNAL_EVENTS.
    value:
      dataLocation: "{{ dataLocation }}"
      dataAccessRoleArn: "{{ dataAccessRoleArn }}"
  - name: ingestedEventsDetail
    description: |
      Details of the ingested events data used for model version training. Required if trainingDataSource is INGESTED_EVENTS.
    value:
      ingestedEventsTimeWindow:
        startTime: "{{ startTime }}"
        endTime: "{{ endTime }}"
  - name: tags
    description: |
      A collection of key and value pairs.
    value:
      - key: "{{ key }}"
        value: "{{ value }}"

UPDATE examples

update_model_version_status

Updates the status of a model version. You can perform the following status updates: Change the TRAINING_IN_PROGRESS status to TRAINING_CANCELLED. Change the TRAINING_COMPLETE status to ACTIVE. Change ACTIVE to INACTIVE.

UPDATE aws.frauddetector.model_versions
SET 
modelId = '{{ modelId }}',
modelType = '{{ modelType }}',
modelVersionNumber = '{{ modelVersionNumber }}',
status = '{{ status }}'
WHERE 
region = '{{ region }}' --required
AND modelId = '{{ modelId }}' --required
AND modelType = '{{ modelType }}' --required
AND modelVersionNumber = '{{ modelVersionNumber }}' --required
AND status = '{{ status }}' --required;

update_model_version

Updates a model version. Updating a model version retrains an existing model version using updated training data and produces a new minor version of the model. You can update the training data set location and data access role attributes using this action. This action creates and trains a new minor version of the model, for example version 1.01, 1.02, 1.03.

UPDATE aws.frauddetector.model_versions
SET 
modelId = '{{ modelId }}',
modelType = '{{ modelType }}',
majorVersionNumber = '{{ majorVersionNumber }}',
externalEventsDetail = '{{ externalEventsDetail }}',
ingestedEventsDetail = '{{ ingestedEventsDetail }}',
tags = '{{ tags }}'
WHERE 
region = '{{ region }}' --required
AND modelId = '{{ modelId }}' --required
AND modelType = '{{ modelType }}' --required
AND majorVersionNumber = '{{ majorVersionNumber }}' --required
RETURNING
model_id,
model_type,
model_version_number,
status;

DELETE examples

delete_model_version

Deletes a model version. You can delete models and model versions in Amazon Fraud Detector, provided that they are not associated with a detector version. When you delete a model version, Amazon Fraud Detector permanently deletes that model version and the data is no longer stored in Amazon Fraud Detector.

DELETE FROM aws.frauddetector.model_versions
WHERE region = '{{ region }}' --required
;