Amazon Personalize

2022/05/23 - Amazon Personalize - 1 updated api methods

Changes  Adding modelMetrics as part of DescribeRecommender API response for Personalize.

DescribeRecommender (updated) Link ΒΆ
Changes (response)
{'recommender': {'modelMetrics': {'string': 'double'}}}

Describes the given recommender, including its status.

A recommender can be in one of the following states:

  • CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED

  • STOP PENDING > STOP IN_PROGRESS > INACTIVE > START PENDING > START IN_PROGRESS > ACTIVE

  • DELETE PENDING > DELETE IN_PROGRESS

When the status is CREATE FAILED , the response includes the failureReason key, which describes why.

The modelMetrics key is null when the recommender is being created or deleted.

For more information on recommenders, see CreateRecommender.

See also: AWS API Documentation

Request Syntax

client.describe_recommender(
    recommenderArn='string'
)
type recommenderArn

string

param recommenderArn

[REQUIRED]

The Amazon Resource Name (ARN) of the recommender to describe.

rtype

dict

returns

Response Syntax

{
    'recommender': {
        'recommenderArn': 'string',
        'datasetGroupArn': 'string',
        'name': 'string',
        'recipeArn': 'string',
        'recommenderConfig': {
            'itemExplorationConfig': {
                'string': 'string'
            },
            'minRecommendationRequestsPerSecond': 123
        },
        'creationDateTime': datetime(2015, 1, 1),
        'lastUpdatedDateTime': datetime(2015, 1, 1),
        'status': 'string',
        'failureReason': 'string',
        'latestRecommenderUpdate': {
            'recommenderConfig': {
                'itemExplorationConfig': {
                    'string': 'string'
                },
                'minRecommendationRequestsPerSecond': 123
            },
            'creationDateTime': datetime(2015, 1, 1),
            'lastUpdatedDateTime': datetime(2015, 1, 1),
            'status': 'string',
            'failureReason': 'string'
        },
        'modelMetrics': {
            'string': 123.0
        }
    }
}

Response Structure

  • (dict) --

    • recommender (dict) --

      The properties of the recommender.

      • recommenderArn (string) --

        The Amazon Resource Name (ARN) of the recommender.

      • datasetGroupArn (string) --

        The Amazon Resource Name (ARN) of the Domain dataset group that contains the recommender.

      • name (string) --

        The name of the recommender.

      • recipeArn (string) --

        The Amazon Resource Name (ARN) of the recipe (Domain dataset group use case) that the recommender was created for.

      • recommenderConfig (dict) --

        The configuration details of the recommender.

        • itemExplorationConfig (dict) --

          Specifies the exploration configuration hyperparameters, including explorationWeight and explorationItemAgeCutOff , you want to use to configure the amount of item exploration Amazon Personalize uses when recommending items. Provide itemExplorationConfig data only if your recommenders generate personalized recommendations for a user (not popular items or similar items).

          • (string) --

            • (string) --

        • minRecommendationRequestsPerSecond (integer) --

          Specifies the requested minimum provisioned recommendation requests per second that Amazon Personalize will support.

      • creationDateTime (datetime) --

        The date and time (in Unix format) that the recommender was created.

      • lastUpdatedDateTime (datetime) --

        The date and time (in Unix format) that the recommender was last updated.

      • status (string) --

        The status of the recommender.

        A recommender can be in one of the following states:

        • CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED

        • STOP PENDING > STOP IN_PROGRESS > INACTIVE > START PENDING > START IN_PROGRESS > ACTIVE

        • DELETE PENDING > DELETE IN_PROGRESS

      • failureReason (string) --

        If a recommender fails, the reason behind the failure.

      • latestRecommenderUpdate (dict) --

        Provides a summary of the latest updates to the recommender.

        • recommenderConfig (dict) --

          The configuration details of the recommender update.

          • itemExplorationConfig (dict) --

            Specifies the exploration configuration hyperparameters, including explorationWeight and explorationItemAgeCutOff , you want to use to configure the amount of item exploration Amazon Personalize uses when recommending items. Provide itemExplorationConfig data only if your recommenders generate personalized recommendations for a user (not popular items or similar items).

            • (string) --

              • (string) --

          • minRecommendationRequestsPerSecond (integer) --

            Specifies the requested minimum provisioned recommendation requests per second that Amazon Personalize will support.

        • creationDateTime (datetime) --

          The date and time (in Unix format) that the recommender update was created.

        • lastUpdatedDateTime (datetime) --

          The date and time (in Unix time) that the recommender update was last updated.

        • status (string) --

          The status of the recommender update.

          A recommender can be in one of the following states:

          • CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED

          • STOP PENDING > STOP IN_PROGRESS > INACTIVE > START PENDING > START IN_PROGRESS > ACTIVE

          • DELETE PENDING > DELETE IN_PROGRESS

        • failureReason (string) --

          If a recommender update fails, the reason behind the failure.

      • modelMetrics (dict) --

        Provides evaluation metrics that help you determine the performance of a recommender. For more information, see Evaluating a recommender.

        • (string) --

          • (float) --