Cleanroomsml

This page documents function available when using the Cleanroomsml module, created with @service Cleanroomsml.

Index

Documentation

Main.Cleanroomsml.create_audience_modelMethod
create_audience_model(name, training_dataset_arn)
create_audience_model(name, training_dataset_arn, params::Dict{String,<:Any})

Defines the information necessary to create an audience model. An audience model is a machine learning model that Clean Rooms ML trains to measure similarity between users. Clean Rooms ML manages training and storing the audience model. The audience model can be used in multiple calls to the StartAudienceGenerationJob API.

Arguments

  • name: The name of the audience model resource.
  • training_dataset_arn: The Amazon Resource Name (ARN) of the training dataset for this audience model.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "description": The description of the audience model.
  • "kmsKeyArn": The Amazon Resource Name (ARN) of the KMS key. This key is used to encrypt and decrypt customer-owned data in the trained ML model and the associated data.
  • "tags": The optional metadata that you apply to the resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define. The following basic restrictions apply to tags: Maximum number of tags per resource - 50. For each resource, each tag key must be unique, and each tag key can have only one value. Maximum key length - 128 Unicode characters in UTF-8. Maximum value length - 256 Unicode characters in UTF-8. If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @. Tag keys and values are case sensitive. Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Clean Rooms ML considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.
  • "trainingDataEndTime": The end date and time of the training window.
  • "trainingDataStartTime": The start date and time of the training window.
source
Main.Cleanroomsml.create_configured_audience_modelMethod
create_configured_audience_model(audience_model_arn, name, output_config, shared_audience_metrics)
create_configured_audience_model(audience_model_arn, name, output_config, shared_audience_metrics, params::Dict{String,<:Any})

Defines the information necessary to create a configured audience model.

Arguments

  • audience_model_arn: The Amazon Resource Name (ARN) of the audience model to use for the configured audience model.
  • name: The name of the configured audience model.
  • output_config: Configure the Amazon S3 location and IAM Role for audiences created using this configured audience model. Each audience will have a unique location. The IAM Role must have s3:PutObject permission on the destination Amazon S3 location. If the destination is protected with Amazon S3 KMS-SSE, then the Role must also have the required KMS permissions.
  • shared_audience_metrics: Whether audience metrics are shared.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "audienceSizeConfig": Configure the list of output sizes of audiences that can be created using this configured audience model. A request to StartAudienceGenerationJob that uses this configured audience model must have an audienceSize selected from this list. You can use the ABSOLUTE AudienceSize to configure out audience sizes using the count of identifiers in the output. You can use the Percentage AudienceSize to configure sizes in the range 1-100 percent.
  • "childResourceTagOnCreatePolicy": Configure how the service tags audience generation jobs created using this configured audience model. If you specify NONE, the tags from the StartAudienceGenerationJob request determine the tags of the audience generation job. If you specify FROMPARENTRESOURCE, the audience generation job inherits the tags from the configured audience model, by default. Tags in the StartAudienceGenerationJob will override the default. When the client is in a different account than the configured audience model, the tags from the client are never applied to a resource in the caller's account.
  • "description": The description of the configured audience model.
  • "minMatchingSeedSize": The minimum number of users from the seed audience that must match with users in the training data of the audience model. The default value is 500.
  • "tags": The optional metadata that you apply to the resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define. The following basic restrictions apply to tags: Maximum number of tags per resource - 50. For each resource, each tag key must be unique, and each tag key can have only one value. Maximum key length - 128 Unicode characters in UTF-8. Maximum value length - 256 Unicode characters in UTF-8. If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @. Tag keys and values are case sensitive. Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Clean Rooms ML considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.
source
Main.Cleanroomsml.create_training_datasetMethod
create_training_dataset(name, role_arn, training_data)
create_training_dataset(name, role_arn, training_data, params::Dict{String,<:Any})

Defines the information necessary to create a training dataset. In Clean Rooms ML, the TrainingDataset is metadata that points to a Glue table, which is read only during AudienceModel creation.

Arguments

  • name: The name of the training dataset. This name must be unique in your account and region.
  • role_arn: The ARN of the IAM role that Clean Rooms ML can assume to read the data referred to in the dataSource field of each dataset. Passing a role across AWS accounts is not allowed. If you pass a role that isn't in your account, you get an AccessDeniedException error.
  • training_data: An array of information that lists the Dataset objects, which specifies the dataset type and details on its location and schema. You must provide a role that has read access to these tables.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "description": The description of the training dataset.
  • "tags": The optional metadata that you apply to the resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define. The following basic restrictions apply to tags: Maximum number of tags per resource - 50. For each resource, each tag key must be unique, and each tag key can have only one value. Maximum key length - 128 Unicode characters in UTF-8. Maximum value length - 256 Unicode characters in UTF-8. If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @. Tag keys and values are case sensitive. Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Clean Rooms ML considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.
source
Main.Cleanroomsml.delete_audience_generation_jobMethod
delete_audience_generation_job(audience_generation_job_arn)
delete_audience_generation_job(audience_generation_job_arn, params::Dict{String,<:Any})

Deletes the specified audience generation job, and removes all data associated with the job.

Arguments

  • audience_generation_job_arn: The Amazon Resource Name (ARN) of the audience generation job that you want to delete.
source
Main.Cleanroomsml.delete_audience_modelMethod
delete_audience_model(audience_model_arn)
delete_audience_model(audience_model_arn, params::Dict{String,<:Any})

Specifies an audience model that you want to delete. You can't delete an audience model if there are any configured audience models that depend on the audience model.

Arguments

  • audience_model_arn: The Amazon Resource Name (ARN) of the audience model that you want to delete.
source
Main.Cleanroomsml.delete_configured_audience_modelMethod
delete_configured_audience_model(configured_audience_model_arn)
delete_configured_audience_model(configured_audience_model_arn, params::Dict{String,<:Any})

Deletes the specified configured audience model. You can't delete a configured audience model if there are any lookalike models that use the configured audience model. If you delete a configured audience model, it will be removed from any collaborations that it is associated to.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model that you want to delete.
source
Main.Cleanroomsml.delete_configured_audience_model_policyMethod
delete_configured_audience_model_policy(configured_audience_model_arn)
delete_configured_audience_model_policy(configured_audience_model_arn, params::Dict{String,<:Any})

Deletes the specified configured audience model policy.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model policy that you want to delete.
source
Main.Cleanroomsml.delete_training_datasetMethod
delete_training_dataset(training_dataset_arn)
delete_training_dataset(training_dataset_arn, params::Dict{String,<:Any})

Specifies a training dataset that you want to delete. You can't delete a training dataset if there are any audience models that depend on the training dataset. In Clean Rooms ML, the TrainingDataset is metadata that points to a Glue table, which is read only during AudienceModel creation. This action deletes the metadata.

Arguments

  • training_dataset_arn: The Amazon Resource Name (ARN) of the training dataset that you want to delete.
source
Main.Cleanroomsml.get_audience_generation_jobMethod
get_audience_generation_job(audience_generation_job_arn)
get_audience_generation_job(audience_generation_job_arn, params::Dict{String,<:Any})

Returns information about an audience generation job.

Arguments

  • audience_generation_job_arn: The Amazon Resource Name (ARN) of the audience generation job that you are interested in.
source
Main.Cleanroomsml.get_audience_modelMethod
get_audience_model(audience_model_arn)
get_audience_model(audience_model_arn, params::Dict{String,<:Any})

Returns information about an audience model

Arguments

  • audience_model_arn: The Amazon Resource Name (ARN) of the audience model that you are interested in.
source
Main.Cleanroomsml.get_configured_audience_modelMethod
get_configured_audience_model(configured_audience_model_arn)
get_configured_audience_model(configured_audience_model_arn, params::Dict{String,<:Any})

Returns information about a specified configured audience model.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model that you are interested in.
source
Main.Cleanroomsml.get_configured_audience_model_policyMethod
get_configured_audience_model_policy(configured_audience_model_arn)
get_configured_audience_model_policy(configured_audience_model_arn, params::Dict{String,<:Any})

Returns information about a configured audience model policy.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model that you are interested in.
source
Main.Cleanroomsml.get_training_datasetMethod
get_training_dataset(training_dataset_arn)
get_training_dataset(training_dataset_arn, params::Dict{String,<:Any})

Returns information about a training dataset.

Arguments

  • training_dataset_arn: The Amazon Resource Name (ARN) of the training dataset that you are interested in.
source
Main.Cleanroomsml.list_audience_export_jobsMethod
list_audience_export_jobs()
list_audience_export_jobs(params::Dict{String,<:Any})

Returns a list of the audience export jobs.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "audienceGenerationJobArn": The Amazon Resource Name (ARN) of the audience generation job that you are interested in.
  • "maxResults": The maximum size of the results that is returned per call.
  • "nextToken": The token value retrieved from a previous call to access the next page of results.
source
Main.Cleanroomsml.list_audience_generation_jobsMethod
list_audience_generation_jobs()
list_audience_generation_jobs(params::Dict{String,<:Any})

Returns a list of audience generation jobs.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "collaborationId": The identifier of the collaboration that contains the audience generation jobs that you are interested in.
  • "configuredAudienceModelArn": The Amazon Resource Name (ARN) of the configured audience model that was used for the audience generation jobs that you are interested in.
  • "maxResults": The maximum size of the results that is returned per call.
  • "nextToken": The token value retrieved from a previous call to access the next page of results.
source
Main.Cleanroomsml.list_audience_modelsMethod
list_audience_models()
list_audience_models(params::Dict{String,<:Any})

Returns a list of audience models.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "maxResults": The maximum size of the results that is returned per call.
  • "nextToken": The token value retrieved from a previous call to access the next page of results.
source
Main.Cleanroomsml.list_configured_audience_modelsMethod
list_configured_audience_models()
list_configured_audience_models(params::Dict{String,<:Any})

Returns a list of the configured audience models.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "maxResults": The maximum size of the results that is returned per call.
  • "nextToken": The token value retrieved from a previous call to access the next page of results.
source
Main.Cleanroomsml.list_tags_for_resourceMethod
list_tags_for_resource(resource_arn)
list_tags_for_resource(resource_arn, params::Dict{String,<:Any})

Returns a list of tags for a provided resource.

Arguments

  • resource_arn: The Amazon Resource Name (ARN) of the resource that you are interested in.
source
Main.Cleanroomsml.list_training_datasetsMethod
list_training_datasets()
list_training_datasets(params::Dict{String,<:Any})

Returns a list of training datasets.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "maxResults": The maximum size of the results that is returned per call.
  • "nextToken": The token value retrieved from a previous call to access the next page of results.
source
Main.Cleanroomsml.put_configured_audience_model_policyMethod
put_configured_audience_model_policy(configured_audience_model_arn, configured_audience_model_policy)
put_configured_audience_model_policy(configured_audience_model_arn, configured_audience_model_policy, params::Dict{String,<:Any})

Create or update the resource policy for a configured audience model.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model that the resource policy will govern.
  • configured_audience_model_policy: The IAM resource policy.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "policyExistenceCondition": Use this to prevent unexpected concurrent modification of the policy.
  • "previousPolicyHash": A cryptographic hash of the contents of the policy used to prevent unexpected concurrent modification of the policy.
source
Main.Cleanroomsml.start_audience_export_jobMethod
start_audience_export_job(audience_generation_job_arn, audience_size, name)
start_audience_export_job(audience_generation_job_arn, audience_size, name, params::Dict{String,<:Any})

Export an audience of a specified size after you have generated an audience.

Arguments

  • audience_generation_job_arn: The Amazon Resource Name (ARN) of the audience generation job that you want to export.
  • audience_size:
  • name: The name of the audience export job.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "description": The description of the audience export job.
source
Main.Cleanroomsml.start_audience_generation_jobMethod
start_audience_generation_job(configured_audience_model_arn, name, seed_audience)
start_audience_generation_job(configured_audience_model_arn, name, seed_audience, params::Dict{String,<:Any})

Information necessary to start the audience generation job.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model that is used for this audience generation job.
  • name: The name of the audience generation job.
  • seed_audience: The seed audience that is used to generate the audience.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "collaborationId": The identifier of the collaboration that contains the audience generation job.
  • "description": The description of the audience generation job.
  • "includeSeedInOutput": Whether the seed audience is included in the audience generation output.
  • "tags": The optional metadata that you apply to the resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define. The following basic restrictions apply to tags: Maximum number of tags per resource - 50. For each resource, each tag key must be unique, and each tag key can have only one value. Maximum key length - 128 Unicode characters in UTF-8. Maximum value length - 256 Unicode characters in UTF-8. If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @. Tag keys and values are case sensitive. Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Clean Rooms ML considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.
source
Main.Cleanroomsml.tag_resourceMethod
tag_resource(resource_arn, tags)
tag_resource(resource_arn, tags, params::Dict{String,<:Any})

Adds metadata tags to a specified resource.

Arguments

  • resource_arn: The Amazon Resource Name (ARN) of the resource that you want to assign tags.
  • tags: The optional metadata that you apply to the resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define. The following basic restrictions apply to tags: Maximum number of tags per resource - 50. For each resource, each tag key must be unique, and each tag key can have only one value. Maximum key length - 128 Unicode characters in UTF-8. Maximum value length - 256 Unicode characters in UTF-8. If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @. Tag keys and values are case sensitive. Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Clean Rooms considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.
source
Main.Cleanroomsml.untag_resourceMethod
untag_resource(resource_arn, tag_keys)
untag_resource(resource_arn, tag_keys, params::Dict{String,<:Any})

Removes metadata tags from a specified resource.

Arguments

  • resource_arn: The Amazon Resource Name (ARN) of the resource that you want to remove tags from.
  • tag_keys: The key values of tags that you want to remove.
source
Main.Cleanroomsml.update_configured_audience_modelMethod
update_configured_audience_model(configured_audience_model_arn)
update_configured_audience_model(configured_audience_model_arn, params::Dict{String,<:Any})

Provides the information necessary to update a configured audience model. Updates that impact audience generation jobs take effect when a new job starts, but do not impact currently running jobs.

Arguments

  • configured_audience_model_arn: The Amazon Resource Name (ARN) of the configured audience model that you want to update.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "audienceModelArn": The Amazon Resource Name (ARN) of the new audience model that you want to use.
  • "audienceSizeConfig": The new audience size configuration.
  • "description": The new description of the configured audience model.
  • "minMatchingSeedSize": The minimum number of users from the seed audience that must match with users in the training data of the audience model.
  • "outputConfig": The new output configuration.
  • "sharedAudienceMetrics": The new value for whether to share audience metrics.
source