CreateModel - Amazon Lookout for Equipment

CreateModel

Creates an ML model for data inference.

A machine-learning (ML) model is a mathematical model that finds patterns in your data. In Amazon Lookout for Equipment, the model learns the patterns of normal behavior and detects abnormal behavior that could be potential equipment failure (or maintenance events). The models are made by analyzing normal data and abnormalities in machine behavior that have already occurred.

Your model is trained using a portion of the data from your dataset and uses that data to learn patterns of normal behavior and abnormal patterns that lead to equipment failure. Another portion of the data is used to evaluate the model's accuracy.

Request Syntax

{ "ClientToken": "string", "DataPreProcessingConfiguration": { "TargetSamplingRate": "string" }, "DatasetName": "string", "DatasetSchema": { "InlineDataSchema": "string" }, "EvaluationDataEndTime": number, "EvaluationDataStartTime": number, "LabelsInputConfiguration": { "S3InputConfiguration": { "Bucket": "string", "Prefix": "string" } }, "ModelName": "string", "RoleArn": "string", "ServerSideKmsKeyId": "string", "Tags": [ { "Key": "string", "Value": "string" } ], "TrainingDataEndTime": number, "TrainingDataStartTime": number }

Request Parameters

The request accepts the following data in JSON format.

ClientToken

A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 256.

Pattern: \p{ASCII}{1,256}

Required: Yes

DataPreProcessingConfiguration

The configuration is the TargetSamplingRate, which is the sampling rate of the data after post processing by Amazon Lookout for Equipment. For example, if you provide data that has been collected at a 1 second level and you want the system to resample the data at a 1 minute rate before training, the TargetSamplingRate is 1 minute.

When providing a value for the TargetSamplingRate, you must attach the prefix "PT" to the rate you want. The value for a 1 second rate is therefore PT1S, the value for a 15 minute rate is PT15M, and the value for a 1 hour rate is PT1H

Type: DataPreProcessingConfiguration object

Required: No

DatasetName

The name of the dataset for the ML model being created.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 200.

Pattern: ^[0-9a-zA-Z_-]{1,200}$

Required: Yes

DatasetSchema

The data schema for the ML model being created.

Type: DatasetSchema object

Required: No

EvaluationDataEndTime

Indicates the time reference in the dataset that should be used to end the subset of evaluation data for the ML model.

Type: Timestamp

Required: No

EvaluationDataStartTime

Indicates the time reference in the dataset that should be used to begin the subset of evaluation data for the ML model.

Type: Timestamp

Required: No

LabelsInputConfiguration

The input configuration for the labels being used for the ML model that's being created.

Type: LabelsInputConfiguration object

Required: No

ModelName

The name for the ML model to be created.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 200.

Pattern: ^[0-9a-zA-Z_-]{1,200}$

Required: Yes

RoleArn

The Amazon Resource Name (ARN) of a role with permission to access the data source being used to create the ML model.

Type: String

Length Constraints: Minimum length of 20. Maximum length of 2048.

Pattern: arn:aws(-[^:]+)?:iam::[0-9]{12}:role/.+

Required: No

ServerSideKmsKeyId

Provides the identifier of the AWS KMS customer master key (CMK) used to encrypt model data by Amazon Lookout for Equipment.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 2048.

Pattern: ^[A-Za-z0-9][A-Za-z0-9:_/+=,@.-]{0,2048}$

Required: No

Tags

Any tags associated with the ML model being created.

Type: Array of Tag objects

Array Members: Minimum number of 0 items. Maximum number of 200 items.

Required: No

TrainingDataEndTime

Indicates the time reference in the dataset that should be used to end the subset of training data for the ML model.

Type: Timestamp

Required: No

TrainingDataStartTime

Indicates the time reference in the dataset that should be used to begin the subset of training data for the ML model.

Type: Timestamp

Required: No

Response Syntax

{ "ModelArn": "string", "Status": "string" }

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

ModelArn

The Amazon Resource Name (ARN) of the model being created.

Type: String

Length Constraints: Minimum length of 20. Maximum length of 2048.

Pattern: arn:aws(-[^:]+)?:lookoutequipment:[a-zA-Z0-9\-]*:[0-9]{12}:model\/.+

Status

Indicates the status of the CreateModel operation.

Type: String

Valid Values: IN_PROGRESS | SUCCESS | FAILED

Errors

AccessDeniedException

The request could not be completed because you do not have access to the resource.

HTTP Status Code: 400

ConflictException

The request could not be completed due to a conflict with the current state of the target resource.

HTTP Status Code: 400

InternalServerException

Processing of the request has failed because of an unknown error, exception or failure.

HTTP Status Code: 500

ResourceNotFoundException

The resource requested could not be found. Verify the resource ID and retry your request.

HTTP Status Code: 400

ServiceQuotaExceededException

Resource limitations have been exceeded.

HTTP Status Code: 400

ThrottlingException

The request was denied due to request throttling.

HTTP Status Code: 400

ValidationException

The input fails to satisfy constraints specified by Amazon Lookout for Equipment or a related AWS service that's being utilized.

HTTP Status Code: 400

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: