String datasetName
The name of the dataset being created.
DatasetSchema datasetSchema
A JSON description of the data that is in each time series dataset, including names, column names, and data types.
String serverSideKmsKeyId
Provides the identifier of the KMS key used to encrypt dataset data by Amazon Lookout for Equipment.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
List<E> tags
Any tags associated with the ingested data described in the dataset.
String modelName
The name of the previously trained machine learning model being used to create the inference scheduler.
String inferenceSchedulerName
The name of the inference scheduler being created.
Long dataDelayOffsetInMinutes
The interval (in minutes) of planned delay at the start of each inference segment. For example, if inference is set to run every ten minutes, the delay is set to five minutes and the time is 09:08. The inference scheduler will wake up at the configured interval (which, without a delay configured, would be 09:10) plus the additional five minute delay time (so 09:15) to check your Amazon S3 bucket. The delay provides a buffer for you to upload data at the same frequency, so that you don't have to stop and restart the scheduler when uploading new data.
For more information, see Understanding the inference process.
String dataUploadFrequency
How often data is uploaded to the source Amazon S3 bucket for the input data. The value chosen is the length of time between data uploads. For instance, if you select 5 minutes, Amazon Lookout for Equipment will upload the real-time data to the source bucket once every 5 minutes. This frequency also determines how often Amazon Lookout for Equipment runs inference on your data.
For more information, see Understanding the inference process.
InferenceInputConfiguration dataInputConfiguration
Specifies configuration information for the input data for the inference scheduler, including delimiter, format, and dataset location.
InferenceOutputConfiguration dataOutputConfiguration
Specifies configuration information for the output results for the inference scheduler, including the S3 location for the output.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source being used for the inference.
String serverSideKmsKeyId
Provides the identifier of the KMS key used to encrypt inference scheduler data by Amazon Lookout for Equipment.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
List<E> tags
Any tags associated with the inference scheduler.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference scheduler being created.
String inferenceSchedulerName
The name of inference scheduler being created.
String status
Indicates the status of the CreateInferenceScheduler operation.
String modelQuality
Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model
quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value
is QUALITY_THRESHOLD_MET.
If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is
CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels
to the input dataset and retraining the model.
For information about using labels with your models, see Understanding labeling.
For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.
String labelGroupName
Names a group of labels.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
List<E> faultCodes
The acceptable fault codes (indicating the type of anomaly associated with the label) that can be used with this label group.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String clientToken
A unique identifier for the request to create a label group. If you do not set the client request token, Lookout for Equipment generates one.
List<E> tags
Tags that provide metadata about the label group you are creating.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String labelGroupName
The name of the label group that you have created. Data in this field will be retained for service usage. Follow best practices for the security of your data.
String labelGroupArn
The Amazon Resource Name (ARN) of the label group that you have created.
String labelGroupName
The name of a group of labels.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
Date startTime
The start time of the labeled event.
Date endTime
The end time of the labeled event.
String rating
Indicates whether a labeled event represents an anomaly.
String faultCode
Provides additional information about the label. The fault code must be defined in the FaultCodes attribute of the label group.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String notes
Metadata providing additional information about the label.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String equipment
Indicates that a label pertains to a particular piece of equipment.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String clientToken
A unique identifier for the request to create a label. If you do not set the client request token, Lookout for Equipment generates one.
String labelId
The ID of the label that you have created.
String modelName
The name for the machine learning model to be created.
String datasetName
The name of the dataset for the machine learning model being created.
DatasetSchema datasetSchema
The data schema for the machine learning model being created.
LabelsInputConfiguration labelsInputConfiguration
The input configuration for the labels being used for the machine learning model that's being created.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
Date trainingDataStartTime
Indicates the time reference in the dataset that should be used to begin the subset of training data for the machine learning model.
Date trainingDataEndTime
Indicates the time reference in the dataset that should be used to end the subset of training data for the machine learning model.
Date evaluationDataStartTime
Indicates the time reference in the dataset that should be used to begin the subset of evaluation data for the machine learning model.
Date evaluationDataEndTime
Indicates the time reference in the dataset that should be used to end the subset of evaluation data for the machine learning model.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source being used to create the machine learning model.
DataPreProcessingConfiguration 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
String serverSideKmsKeyId
Provides the identifier of the KMS key used to encrypt model data by Amazon Lookout for Equipment.
List<E> tags
Any tags associated with the machine learning model being created.
String offCondition
Indicates that the asset associated with this sensor has been shut off. As long as this condition is met, Lookout for Equipment will not use data from this asset for training, evaluation, or inference.
ModelDiagnosticsOutputConfiguration modelDiagnosticsOutputConfiguration
The Amazon S3 location where you want Amazon Lookout for Equipment to save the pointwise model diagnostics. You
must also specify the RoleArn request parameter.
String modelName
The name of the model to add the retraining scheduler to.
Date retrainingStartDate
The start date for the retraining scheduler. Lookout for Equipment truncates the time you provide to the nearest UTC day.
String retrainingFrequency
This parameter uses the ISO 8601 standard to set the frequency at which you want retraining to occur in terms of Years, Months, and/or Days (note: other parameters like Time are not currently supported). The minimum value is 30 days (P30D) and the maximum value is 1 year (P1Y). For example, the following values are valid:
P3M15D – Every 3 months and 15 days
P2M – Every 2 months
P150D – Every 150 days
String lookbackWindow
The number of past days of data that will be used for retraining.
String promoteMode
Indicates how the service will use new models. In MANAGED mode, new models will automatically be
used for inference if they have better performance than the current model. In MANUAL mode, the new
models will not be used until
they are manually activated.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
String jobId
Indicates the job ID of the data ingestion job.
String datasetName
The name of the dataset used for the data ingestion job.
String datasetArn
The Amazon Resource Name (ARN) of the dataset used in the data ingestion job.
IngestionInputConfiguration ingestionInputConfiguration
Specifies information for the input data for the data inference job, including data Amazon S3 location parameters.
String status
Indicates the status of the data ingestion job.
String targetSamplingRate
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
InsufficientSensorData insufficientSensorData
Parameter that gives information about insufficient data for sensors in the dataset. This includes information about those sensors that have complete data missing and those with a short date range.
MissingSensorData missingSensorData
Parameter that gives information about data that is missing over all the sensors in the input data.
InvalidSensorData invalidSensorData
Parameter that gives information about data that is invalid over all the sensors in the input data.
UnsupportedTimestamps unsupportedTimestamps
Parameter that gives information about unsupported timestamps in the input data.
DuplicateTimestamps duplicateTimestamps
Parameter that gives information about duplicate timestamps in the input data.
String inlineDataSchema
The data schema used within the given dataset.
String datasetName
The name of the dataset to be deleted.
String inferenceSchedulerName
The name of the inference scheduler to be deleted.
String labelGroupName
The name of the label group that you want to delete. Data in this field will be retained for service usage. Follow best practices for the security of your data.
String modelName
The name of the machine learning model to be deleted.
String resourceArn
The Amazon Resource Name (ARN) of the resource for which the resource policy should be deleted.
String modelName
The name of the model whose retraining scheduler you want to delete.
String jobId
The job ID of the data ingestion job.
String jobId
Indicates the job ID of the data ingestion job.
String datasetArn
The Amazon Resource Name (ARN) of the dataset being used in the data ingestion job.
IngestionInputConfiguration ingestionInputConfiguration
Specifies the S3 location configuration for the data input for the data ingestion job.
String roleArn
The Amazon Resource Name (ARN) of an IAM role with permission to access the data source being ingested.
Date createdAt
The time at which the data ingestion job was created.
String status
Indicates the status of the DataIngestionJob operation.
String failedReason
Specifies the reason for failure when a data ingestion job has failed.
DataQualitySummary dataQualitySummary
Gives statistics about a completed ingestion job. These statistics primarily relate to quantifying incorrect data such as MissingCompleteSensorData, MissingSensorData, UnsupportedDateFormats, InsufficientSensorData, and DuplicateTimeStamps.
IngestedFilesSummary ingestedFilesSummary
String statusDetail
Provides details about status of the ingestion job that is currently in progress.
Long ingestedDataSize
Indicates the size of the ingested dataset.
Date dataStartTime
Indicates the earliest timestamp corresponding to data that was successfully ingested during this specific ingestion job.
Date dataEndTime
Indicates the latest timestamp corresponding to data that was successfully ingested during this specific ingestion job.
String sourceDatasetArn
The Amazon Resource Name (ARN) of the source dataset from which the data used for the data ingestion job was imported from.
String datasetName
The name of the dataset to be described.
String datasetName
The name of the dataset being described.
String datasetArn
The Amazon Resource Name (ARN) of the dataset being described.
Date createdAt
Specifies the time the dataset was created in Lookout for Equipment.
Date lastUpdatedAt
Specifies the time the dataset was last updated, if it was.
String status
Indicates the status of the dataset.
String schema
A JSON description of the data that is in each time series dataset, including names, column names, and data types.
String serverSideKmsKeyId
Provides the identifier of the KMS key used to encrypt dataset data by Amazon Lookout for Equipment.
IngestionInputConfiguration ingestionInputConfiguration
Specifies the S3 location configuration for the data input for the data ingestion job.
DataQualitySummary dataQualitySummary
Gives statistics associated with the given dataset for the latest successful associated ingestion job id. These statistics primarily relate to quantifying incorrect data such as MissingCompleteSensorData, MissingSensorData, UnsupportedDateFormats, InsufficientSensorData, and DuplicateTimeStamps.
IngestedFilesSummary ingestedFilesSummary
IngestedFilesSummary associated with the given dataset for the latest successful associated ingestion job id.
String roleArn
The Amazon Resource Name (ARN) of the IAM role that you are using for this the data ingestion job.
Date dataStartTime
Indicates the earliest timestamp corresponding to data that was successfully ingested during the most recent ingestion of this particular dataset.
Date dataEndTime
Indicates the latest timestamp corresponding to data that was successfully ingested during the most recent ingestion of this particular dataset.
String sourceDatasetArn
The Amazon Resource Name (ARN) of the source dataset from which the current data being described was imported from.
String inferenceSchedulerName
The name of the inference scheduler being described.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model of the inference scheduler being described.
String modelName
The name of the machine learning model of the inference scheduler being described.
String inferenceSchedulerName
The name of the inference scheduler being described.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference scheduler being described.
String status
Indicates the status of the inference scheduler.
Long dataDelayOffsetInMinutes
A period of time (in minutes) by which inference on the data is delayed after the data starts. For instance, if you select an offset delay time of five minutes, inference will not begin on the data until the first data measurement after the five minute mark. For example, if five minutes is selected, the inference scheduler will wake up at the configured frequency with the additional five minute delay time to check the customer S3 bucket. The customer can upload data at the same frequency and they don't need to stop and restart the scheduler when uploading new data.
String dataUploadFrequency
Specifies how often data is uploaded to the source S3 bucket for the input data. This value is the length of time between data uploads. For instance, if you select 5 minutes, Amazon Lookout for Equipment will upload the real-time data to the source bucket once every 5 minutes. This frequency also determines how often Amazon Lookout for Equipment starts a scheduled inference on your data. In this example, it starts once every 5 minutes.
Date createdAt
Specifies the time at which the inference scheduler was created.
Date updatedAt
Specifies the time at which the inference scheduler was last updated, if it was.
InferenceInputConfiguration dataInputConfiguration
Specifies configuration information for the input data for the inference scheduler, including delimiter, format, and dataset location.
InferenceOutputConfiguration dataOutputConfiguration
Specifies information for the output results for the inference scheduler, including the output S3 location.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source for the inference scheduler being described.
String serverSideKmsKeyId
Provides the identifier of the KMS key used to encrypt inference scheduler data by Amazon Lookout for Equipment.
String latestInferenceResult
Indicates whether the latest execution for the inference scheduler was Anomalous (anomalous events found) or Normal (no anomalous events found).
String labelGroupName
Returns the name of the label group.
String labelGroupName
The name of the label group.
String labelGroupArn
The Amazon Resource Name (ARN) of the label group.
List<E> faultCodes
Codes indicating the type of anomaly associated with the labels in the lagbel group.
Date createdAt
The time at which the label group was created.
Date updatedAt
The time at which the label group was updated.
String labelGroupName
The name of the requested label group.
String labelGroupArn
The Amazon Resource Name (ARN) of the requested label group.
String labelId
The ID of the requested label.
Date startTime
The start time of the requested label.
Date endTime
The end time of the requested label.
String rating
Indicates whether a labeled event represents an anomaly.
String faultCode
Indicates the type of anomaly associated with the label.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String notes
Metadata providing additional information about the label.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String equipment
Indicates that a label pertains to a particular piece of equipment.
Date createdAt
The time at which the label was created.
String modelName
The name of the machine learning model to be described.
String modelName
The name of the machine learning model being described.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model being described.
String datasetName
The name of the dataset being used by the machine learning being described.
String datasetArn
The Amazon Resouce Name (ARN) of the dataset used to create the machine learning model being described.
String schema
A JSON description of the data that is in each time series dataset, including names, column names, and data types.
LabelsInputConfiguration labelsInputConfiguration
Specifies configuration information about the labels input, including its S3 location.
Date trainingDataStartTime
Indicates the time reference in the dataset that was used to begin the subset of training data for the machine learning model.
Date trainingDataEndTime
Indicates the time reference in the dataset that was used to end the subset of training data for the machine learning model.
Date evaluationDataStartTime
Indicates the time reference in the dataset that was used to begin the subset of evaluation data for the machine learning model.
Date evaluationDataEndTime
Indicates the time reference in the dataset that was used to end the subset of evaluation data for the machine learning model.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source for the machine learning model being described.
DataPreProcessingConfiguration 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
String status
Specifies the current status of the model being described. Status describes the status of the most recent action of the model.
Date trainingExecutionStartTime
Indicates the time at which the training of the machine learning model began.
Date trainingExecutionEndTime
Indicates the time at which the training of the machine learning model was completed.
String failedReason
If the training of the machine learning model failed, this indicates the reason for that failure.
String modelMetrics
The Model Metrics show an aggregated summary of the model's performance within the evaluation time range. This is the JSON content of the metrics created when evaluating the model.
Date lastUpdatedTime
Indicates the last time the machine learning model was updated. The type of update is not specified.
Date createdAt
Indicates the time and date at which the machine learning model was created.
String serverSideKmsKeyId
Provides the identifier of the KMS key used to encrypt model data by Amazon Lookout for Equipment.
String offCondition
Indicates that the asset associated with this sensor has been shut off. As long as this condition is met, Lookout for Equipment will not use data from this asset for training, evaluation, or inference.
String sourceModelVersionArn
The Amazon Resource Name (ARN) of the source model version. This field appears if the active model version was imported.
Date importJobStartTime
The date and time when the import job was started. This field appears if the active model version was imported.
Date importJobEndTime
The date and time when the import job was completed. This field appears if the active model version was imported.
Long activeModelVersion
The name of the model version used by the inference schedular when running a scheduled inference execution.
String activeModelVersionArn
The Amazon Resource Name (ARN) of the model version used by the inference scheduler when running a scheduled inference execution.
Date modelVersionActivatedAt
The date the active model version was activated.
Long previousActiveModelVersion
The model version that was set as the active model version prior to the current active model version.
String previousActiveModelVersionArn
The ARN of the model version that was set as the active model version prior to the current active model version.
Date previousModelVersionActivatedAt
The date and time when the previous active model version was activated.
String priorModelMetrics
If the model version was retrained, this field shows a summary of the performance of the prior model on the new training range. You can use the information in this JSON-formatted object to compare the new model version and the prior model version.
String latestScheduledRetrainingFailedReason
If the model version was generated by retraining and the training failed, this indicates the reason for that failure.
String latestScheduledRetrainingStatus
Indicates the status of the most recent scheduled retraining run.
Long latestScheduledRetrainingModelVersion
Indicates the most recent model version that was generated by retraining.
Date latestScheduledRetrainingStartTime
Indicates the start time of the most recent scheduled retraining run.
Integer latestScheduledRetrainingAvailableDataInDays
Indicates the number of days of data used in the most recent scheduled retraining run.
Date nextScheduledRetrainingStartDate
Indicates the date and time that the next scheduled retraining run will start on. Lookout for Equipment truncates the time you provide to the nearest UTC day.
Date accumulatedInferenceDataStartTime
Indicates the start time of the inference data that has been accumulated.
Date accumulatedInferenceDataEndTime
Indicates the end time of the inference data that has been accumulated.
String retrainingSchedulerStatus
Indicates the status of the retraining scheduler.
ModelDiagnosticsOutputConfiguration modelDiagnosticsOutputConfiguration
Configuration information for the model's pointwise model diagnostics.
String modelQuality
Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model
quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value
is QUALITY_THRESHOLD_MET.
If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is
CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels
to the input dataset and retraining the model.
For information about using labels with your models, see Understanding labeling.
For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.
String modelName
The name of the machine learning model that this version belongs to.
String modelArn
The Amazon Resource Name (ARN) of the parent machine learning model that this version belong to.
Long modelVersion
The version of the machine learning model.
String modelVersionArn
The Amazon Resource Name (ARN) of the model version.
String status
The current status of the model version.
String sourceType
Indicates whether this model version was created by training or by importing.
String datasetName
The name of the dataset used to train the model version.
String datasetArn
The Amazon Resource Name (ARN) of the dataset used to train the model version.
String schema
The schema of the data used to train the model version.
LabelsInputConfiguration labelsInputConfiguration
Date trainingDataStartTime
The date on which the training data began being gathered. If you imported the version, this is the date that the training data in the source version began being gathered.
Date trainingDataEndTime
The date on which the training data finished being gathered. If you imported the version, this is the date that the training data in the source version finished being gathered.
Date evaluationDataStartTime
The date on which the data in the evaluation set began being gathered. If you imported the version, this is the date that the evaluation set data in the source version began being gathered.
Date evaluationDataEndTime
The date on which the data in the evaluation set began being gathered. If you imported the version, this is the date that the evaluation set data in the source version finished being gathered.
String roleArn
The Amazon Resource Name (ARN) of the role that was used to train the model version.
DataPreProcessingConfiguration dataPreProcessingConfiguration
Date trainingExecutionStartTime
The time when the training of the version began.
Date trainingExecutionEndTime
The time when the training of the version completed.
String failedReason
The failure message if the training of the model version failed.
String modelMetrics
Shows an aggregated summary, in JSON format, of the model's performance within the evaluation time range. These metrics are created when evaluating the model.
Date lastUpdatedTime
Indicates the last time the machine learning model version was updated.
Date createdAt
Indicates the time and date at which the machine learning model version was created.
String serverSideKmsKeyId
The identifier of the KMS key key used to encrypt model version data by Amazon Lookout for Equipment.
String offCondition
Indicates that the asset associated with this sensor has been shut off. As long as this condition is met, Lookout for Equipment will not use data from this asset for training, evaluation, or inference.
String sourceModelVersionArn
If model version was imported, then this field is the arn of the source model version.
Date importJobStartTime
The date and time when the import job began. This field appears if the model version was imported.
Date importJobEndTime
The date and time when the import job completed. This field appears if the model version was imported.
Long importedDataSizeInBytes
The size in bytes of the imported data. This field appears if the model version was imported.
String priorModelMetrics
If the model version was retrained, this field shows a summary of the performance of the prior model on the new training range. You can use the information in this JSON-formatted object to compare the new model version and the prior model version.
Integer retrainingAvailableDataInDays
Indicates the number of days of data used in the most recent scheduled retraining run.
String autoPromotionResult
Indicates whether the model version was promoted to be the active version after retraining or if there was an error with or cancellation of the retraining.
String autoPromotionResultReason
Indicates the reason for the AutoPromotionResult. For example, a model might not be promoted if its
performance was worse than the active version, if there was an error during training, or if the retraining
scheduler was using MANUAL promote mode. The model will be promoted in MANAGED promote
mode if the performance is better than the previous model.
ModelDiagnosticsOutputConfiguration modelDiagnosticsOutputConfiguration
The Amazon S3 location where Amazon Lookout for Equipment saves the pointwise model diagnostics for the model version.
S3Object modelDiagnosticsResultsObject
The Amazon S3 output prefix for where Lookout for Equipment saves the pointwise model diagnostics for the model version.
String modelQuality
Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model
quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value
is QUALITY_THRESHOLD_MET.
If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is
CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels
to the input dataset and retraining the model.
For information about using labels with your models, see Understanding labeling.
For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.
String resourceArn
The Amazon Resource Name (ARN) of the resource that is associated with the resource policy.
String policyRevisionId
A unique identifier for a revision of the resource policy.
String resourcePolicy
The resource policy in a JSON-formatted string.
Date creationTime
The time when the resource policy was created.
Date lastModifiedTime
The time when the resource policy was last modified.
String modelName
The name of the model that the retraining scheduler is attached to.
String modelName
The name of the model that the retraining scheduler is attached to.
String modelArn
The ARN of the model that the retraining scheduler is attached to.
Date retrainingStartDate
The start date for the retraining scheduler. Lookout for Equipment truncates the time you provide to the nearest UTC day.
String retrainingFrequency
The frequency at which the model retraining is set. This follows the ISO 8601 guidelines.
String lookbackWindow
The number of past days of data used for retraining.
String status
The status of the retraining scheduler.
String promoteMode
Indicates how the service uses new models. In MANAGED mode, new models are used for inference if
they have better performance than the current model. In MANUAL mode, the new models are not used
until they are manually activated.
Date createdAt
Indicates the time and date at which the retraining scheduler was created.
Date updatedAt
Indicates the time and date at which the retraining scheduler was updated.
Integer totalNumberOfDuplicateTimestamps
Indicates the total number of duplicate timestamps.
String sourceDatasetArn
The Amazon Resource Name (ARN) of the dataset to import.
String datasetName
The name of the machine learning dataset to be created. If the dataset already exists, Amazon Lookout for Equipment overwrites the existing dataset. If you don't specify this field, it is filled with the name of the source dataset.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
String serverSideKmsKeyId
Provides the identifier of the KMS key key used to encrypt model data by Amazon Lookout for Equipment.
List<E> tags
Any tags associated with the dataset to be created.
String datasetName
The name of the created machine learning dataset.
String datasetArn
The Amazon Resource Name (ARN) of the dataset that was imported.
String status
The status of the ImportDataset operation.
String jobId
A unique identifier for the job of importing the dataset.
String sourceModelVersionArn
The Amazon Resource Name (ARN) of the model version to import.
String modelName
The name for the machine learning model to be created. If the model already exists, Amazon Lookout for Equipment creates a new version. If you do not specify this field, it is filled with the name of the source model.
String datasetName
The name of the dataset for the machine learning model being imported.
LabelsInputConfiguration labelsInputConfiguration
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source being used to create the machine learning model.
String serverSideKmsKeyId
Provides the identifier of the KMS key key used to encrypt model data by Amazon Lookout for Equipment.
List<E> tags
The tags associated with the machine learning model to be created.
String inferenceDataImportStrategy
Indicates how to import the accumulated inference data when a model version is imported. The possible values are as follows:
NO_IMPORT – Don't import the data.
ADD_WHEN_EMPTY – Only import the data from the source model if there is no existing data in the target model.
OVERWRITE – Import the data from the source model and overwrite the existing data in the target model.
String modelName
The name for the machine learning model.
String modelArn
The Amazon Resource Name (ARN) of the model being created.
String modelVersionArn
The Amazon Resource Name (ARN) of the model version being created.
Long modelVersion
The version of the model being created.
String status
The status of the ImportModelVersion operation.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference scheduler being used for the inference event.
String inferenceSchedulerName
The name of the inference scheduler being used for the inference events.
Date eventStartTime
Indicates the starting time of an inference event.
Date eventEndTime
Indicates the ending time of an inference event.
String diagnostics
An array which specifies the names and values of all sensors contributing to an inference event.
Long eventDurationInSeconds
Indicates the size of an inference event in seconds.
String modelName
The name of the machine learning model being used for the inference execution.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model used for the inference execution.
String inferenceSchedulerName
The name of the inference scheduler being used for the inference execution.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference scheduler being used for the inference execution.
Date scheduledStartTime
Indicates the start time at which the inference scheduler began the specific inference execution.
Date dataStartTime
Indicates the time reference in the dataset at which the inference execution began.
Date dataEndTime
Indicates the time reference in the dataset at which the inference execution stopped.
InferenceInputConfiguration dataInputConfiguration
Specifies configuration information for the input data for the inference scheduler, including delimiter, format, and dataset location.
InferenceOutputConfiguration dataOutputConfiguration
Specifies configuration information for the output results from for the inference execution, including the output Amazon S3 location.
S3Object customerResultObject
The S3 object that the inference execution results were uploaded to.
String status
Indicates the status of the inference execution.
String failedReason
Specifies the reason for failure when an inference execution has failed.
Long modelVersion
The model version used for the inference execution.
String modelVersionArn
The Amazon Resource Number (ARN) of the model version used for the inference execution.
InferenceS3InputConfiguration s3InputConfiguration
Specifies configuration information for the input data for the inference, including Amazon S3 location of input data.
String inputTimeZoneOffset
Indicates the difference between your time zone and Coordinated Universal Time (UTC).
InferenceInputNameConfiguration inferenceInputNameConfiguration
Specifies configuration information for the input data for the inference, including timestamp format and delimiter.
InferenceS3OutputConfiguration s3OutputConfiguration
Specifies configuration information for the output results from for the inference, output S3 location.
String kmsKeyId
The ID number for the KMS key key used to encrypt the inference output.
String modelName
The name of the machine learning model used for the inference scheduler.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model used by the inference scheduler.
String inferenceSchedulerName
The name of the inference scheduler.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference scheduler.
String status
Indicates the status of the inference scheduler.
Long dataDelayOffsetInMinutes
A period of time (in minutes) by which inference on the data is delayed after the data starts. For instance, if an offset delay time of five minutes was selected, inference will not begin on the data until the first data measurement after the five minute mark. For example, if five minutes is selected, the inference scheduler will wake up at the configured frequency with the additional five minute delay time to check the customer S3 bucket. The customer can upload data at the same frequency and they don't need to stop and restart the scheduler when uploading new data.
String dataUploadFrequency
How often data is uploaded to the source S3 bucket for the input data. This value is the length of time between data uploads. For instance, if you select 5 minutes, Amazon Lookout for Equipment will upload the real-time data to the source bucket once every 5 minutes. This frequency also determines how often Amazon Lookout for Equipment starts a scheduled inference on your data. In this example, it starts once every 5 minutes.
String latestInferenceResult
Indicates whether the latest execution for the inference scheduler was Anomalous (anomalous events found) or Normal (no anomalous events found).
Integer totalNumberOfFiles
Indicates the total number of files that were submitted for ingestion.
Integer ingestedNumberOfFiles
Indicates the number of files that were successfully ingested.
List<E> discardedFiles
Indicates the number of files that were discarded. A file could be discarded because its format is invalid (for example, a jpg or pdf) or not readable.
IngestionS3InputConfiguration s3InputConfiguration
The location information for the S3 bucket used for input data for the data ingestion.
String bucket
The name of the S3 bucket used for the input data for the data ingestion.
String prefix
The prefix for the S3 location being used for the input data for the data ingestion.
String keyPattern
The pattern for matching the Amazon S3 files that will be used for ingestion. If the schema was created previously without any KeyPattern, then the default KeyPattern {prefix}/{component_name}/* is used to download files from Amazon S3 according to the schema. This field is required when ingestion is being done for the first time.
Valid Values: {prefix}/{component_name}_* | {prefix}/{component_name}/* | {prefix}/{component_name}[DELIMITER]* (Allowed delimiters : space, dot, underscore, hyphen)
MissingCompleteSensorData missingCompleteSensorData
Parameter that describes the total number of sensors that have data completely missing for it.
SensorsWithShortDateRange sensorsWithShortDateRange
Parameter that describes the total number of sensors that have a short date range of less than 14 days of data overall.
LabelsS3InputConfiguration s3InputConfiguration
Contains location information for the S3 location being used for label data.
String labelGroupName
The name of the label group to be used for label data.
String labelGroupName
The name of the label group.
String labelId
The ID of the label.
String labelGroupArn
The Amazon Resource Name (ARN) of the label group.
Date startTime
The timestamp indicating the start of the label.
Date endTime
The timestamp indicating the end of the label.
String rating
Indicates whether a labeled event represents an anomaly.
String faultCode
Indicates the type of anomaly associated with the label.
Data in this field will be retained for service usage. Follow best practices for the security of your data.
String equipment
Indicates that a label pertains to a particular piece of equipment.
Date createdAt
The time at which the label was created.
String status
Indicates whether there is a potential data issue related to large gaps in timestamps.
Integer numberOfLargeTimestampGaps
Indicates the number of large timestamp gaps, if there are any.
Integer maxTimestampGapInDays
Indicates the size of the largest timestamp gap, in days.
String datasetName
The name of the dataset being used for the data ingestion job.
String nextToken
An opaque pagination token indicating where to continue the listing of data ingestion jobs.
Integer maxResults
Specifies the maximum number of data ingestion jobs to list.
String status
Indicates the status of the data ingestion job.
String nextToken
An opaque pagination token indicating where to continue the listing of inference events.
Integer maxResults
Specifies the maximum number of inference events to list.
String inferenceSchedulerName
The name of the inference scheduler for the inference events listed.
Date intervalStartTime
Lookout for Equipment will return all the inference events with an end time equal to or greater than the start time given.
Date intervalEndTime
Returns all the inference events with an end start time equal to or greater than less than the end time given.
String nextToken
An opaque pagination token indicating where to continue the listing of inference executions.
List<E> inferenceEventSummaries
Provides an array of information about the individual inference events returned from the
ListInferenceEvents operation, including scheduler used, event start time, event end time,
diagnostics, and so on.
String nextToken
An opaque pagination token indicating where to continue the listing of inference executions.
Integer maxResults
Specifies the maximum number of inference executions to list.
String inferenceSchedulerName
The name of the inference scheduler for the inference execution listed.
Date dataStartTimeAfter
The time reference in the inferenced dataset after which Amazon Lookout for Equipment started the inference execution.
Date dataEndTimeBefore
The time reference in the inferenced dataset before which Amazon Lookout for Equipment stopped the inference execution.
String status
The status of the inference execution.
String nextToken
An opaque pagination token indicating where to continue the listing of inference executions.
List<E> inferenceExecutionSummaries
Provides an array of information about the individual inference executions returned from the
ListInferenceExecutions operation, including model used, inference scheduler, data configuration,
and so on.
If you don't supply the InferenceSchedulerName request parameter, or if you supply the name of an
inference scheduler that doesn't exist, ListInferenceExecutions returns an empty array in
InferenceExecutionSummaries.
String nextToken
An opaque pagination token indicating where to continue the listing of inference schedulers.
Integer maxResults
Specifies the maximum number of inference schedulers to list.
String inferenceSchedulerNameBeginsWith
The beginning of the name of the inference schedulers to be listed.
String modelName
The name of the machine learning model used by the inference scheduler to be listed.
String status
Specifies the current status of the inference schedulers.
String nextToken
An opaque pagination token indicating where to continue the listing of inference schedulers.
List<E> inferenceSchedulerSummaries
Provides information about the specified inference scheduler, including data upload frequency, model name and ARN, and status.
String labelGroupNameBeginsWith
The beginning of the name of the label groups to be listed.
String nextToken
An opaque pagination token indicating where to continue the listing of label groups.
Integer maxResults
Specifies the maximum number of label groups to list.
String labelGroupName
Returns the name of the label group.
Date intervalStartTime
Returns all the labels with a end time equal to or later than the start time given.
Date intervalEndTime
Returns all labels with a start time earlier than the end time given.
String faultCode
Returns labels with a particular fault code.
String equipment
Lists the labels that pertain to a particular piece of equipment.
String nextToken
An opaque pagination token indicating where to continue the listing of label groups.
Integer maxResults
Specifies the maximum number of labels to list.
String nextToken
An opaque pagination token indicating where to continue the listing of datasets.
List<E> labelSummaries
A summary of the items in the label group.
If you don't supply the LabelGroupName request parameter, or if you supply the name of a label group
that doesn't exist, ListLabels returns an empty array in LabelSummaries.
String nextToken
An opaque pagination token indicating where to continue the listing of machine learning models.
Integer maxResults
Specifies the maximum number of machine learning models to list.
String status
The status of the machine learning model.
String modelNameBeginsWith
The beginning of the name of the machine learning models being listed.
String datasetNameBeginsWith
The beginning of the name of the dataset of the machine learning models to be listed.
String modelName
Then name of the machine learning model for which the model versions are to be listed.
String nextToken
If the total number of results exceeds the limit that the response can display, the response returns an opaque
pagination token indicating where to continue the listing of machine learning model versions. Use this token in
the NextToken field in the request to list the next page of results.
Integer maxResults
Specifies the maximum number of machine learning model versions to list.
String status
Filter the results based on the current status of the model version.
String sourceType
Filter the results based on the way the model version was generated.
Date createdAtEndTime
Filter results to return all the model versions created before this time.
Date createdAtStartTime
Filter results to return all the model versions created after this time.
Long maxModelVersion
Specifies the highest version of the model to return in the list.
Long minModelVersion
Specifies the lowest version of the model to return in the list.
String nextToken
If the total number of results exceeds the limit that the response can display, the response returns an opaque
pagination token indicating where to continue the listing of machine learning model versions. Use this token in
the NextToken field in the request to list the next page of results.
List<E> modelVersionSummaries
Provides information on the specified model version, including the created time, model and dataset ARNs, and status.
If you don't supply the ModelName request parameter, or if you supply the name of a model that
doesn't exist, ListModelVersions returns an empty array in ModelVersionSummaries.
String modelNameBeginsWith
Specify this field to only list retraining schedulers whose machine learning models begin with the value you specify.
String status
Specify this field to only list retraining schedulers whose status matches the value you specify.
String nextToken
If the number of results exceeds the maximum, a pagination token is returned. Use the token in the request to show the next page of retraining schedulers.
Integer maxResults
Specifies the maximum number of retraining schedulers to list.
List<E> retrainingSchedulerSummaries
Provides information on the specified retraining scheduler, including the model name, model ARN, status, and start date.
String nextToken
If the number of results exceeds the maximum, this pagination token is returned. Use this token in the request to show the next page of retraining schedulers.
String datasetName
The name of the dataset associated with the list of Sensor Statistics.
String ingestionJobId
The ingestion job id associated with the list of Sensor Statistics. To get sensor statistics for a particular ingestion job id, both dataset name and ingestion job id must be submitted as inputs.
Integer maxResults
Specifies the maximum number of sensors for which to retrieve statistics.
String nextToken
An opaque pagination token indicating where to continue the listing of sensor statistics.
List<E> sensorStatisticsSummaries
Provides ingestion-based statistics regarding the specified sensor with respect to various validation types, such as whether data exists, the number and percentage of missing values, and the number and percentage of duplicate timestamps.
String nextToken
An opaque pagination token indicating where to continue the listing of sensor statistics.
String resourceArn
The Amazon Resource Name (ARN) of the resource (such as the dataset or model) that is the focus of the
ListTagsForResource operation.
Integer affectedSensorCount
Indicates the number of sensors that have data missing completely.
ModelDiagnosticsS3OutputConfiguration s3OutputConfiguration
The Amazon S3 location for the pointwise model diagnostics.
String kmsKeyId
The Amazon Web Services Key Management Service (KMS) key identifier to encrypt the pointwise model diagnostics files.
String bucket
The name of the Amazon S3 bucket where the pointwise model diagnostics are located. You must be the owner of the Amazon S3 bucket.
String prefix
The Amazon S3 prefix for the location of the pointwise model diagnostics. The prefix specifies the folder and
evaluation result file name. (bucket).
When you call CreateModel or UpdateModel, specify the path within the bucket that you
want Lookout for Equipment to save the model to. During training, Lookout for Equipment creates the model
evaluation model as a compressed JSON file with the name model_diagnostics_results.json.gz.
When you call DescribeModel or DescribeModelVersion, prefix contains the
file path and filename of the model evaluation file.
String modelName
The name of the machine learning model.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model.
String datasetName
The name of the dataset being used for the machine learning model.
String datasetArn
The Amazon Resource Name (ARN) of the dataset used to create the model.
String status
Indicates the status of the machine learning model.
Date createdAt
The time at which the specific model was created.
Long activeModelVersion
The model version that the inference scheduler uses to run an inference execution.
String activeModelVersionArn
The Amazon Resource Name (ARN) of the model version that is set as active. The active model version is the model version that the inference scheduler uses to run an inference execution.
String latestScheduledRetrainingStatus
Indicates the status of the most recent scheduled retraining run.
Long latestScheduledRetrainingModelVersion
Indicates the most recent model version that was generated by retraining.
Date latestScheduledRetrainingStartTime
Indicates the start time of the most recent scheduled retraining run.
Date nextScheduledRetrainingStartDate
Indicates the date that the next scheduled retraining run will start on. Lookout for Equipment truncates the time you provide to the nearest UTC day.
String retrainingSchedulerStatus
Indicates the status of the retraining scheduler.
ModelDiagnosticsOutputConfiguration modelDiagnosticsOutputConfiguration
String modelQuality
Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model
quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value
is QUALITY_THRESHOLD_MET.
If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is
CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels
to the input dataset and retraining the model.
For information about using labels with your models, see Understanding labeling.
For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.
String modelName
The name of the model that this model version is a version of.
String modelArn
The Amazon Resource Name (ARN) of the model that this model version is a version of.
Long modelVersion
The version of the model.
String modelVersionArn
The Amazon Resource Name (ARN) of the model version.
Date createdAt
The time when this model version was created.
String status
The current status of the model version.
String sourceType
Indicates how this model version was generated.
String modelQuality
Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model
quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value
is QUALITY_THRESHOLD_MET.
If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is
CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels
to the input dataset and retraining the model.
For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.
String status
Indicates whether there is a potential data issue related to having multiple operating modes.
String resourceArn
The Amazon Resource Name (ARN) of the resource for which the policy is being created.
String resourcePolicy
The JSON-formatted resource policy to create.
String policyRevisionId
A unique identifier for a revision of the resource policy.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
String modelName
The name of the model that the retraining scheduler is attached to.
String modelArn
The ARN of the model that the retraining scheduler is attached to.
String status
The status of the retraining scheduler.
Date retrainingStartDate
The start date for the retraining scheduler. Lookout for Equipment truncates the time you provide to the nearest UTC day.
String retrainingFrequency
The frequency at which the model retraining is set. This follows the ISO 8601 guidelines.
String lookbackWindow
The number of past days of data used for retraining.
String componentName
Name of the component to which the particular sensor belongs for which the statistics belong to.
String sensorName
Name of the sensor that the statistics belong to.
Boolean dataExists
Parameter that indicates whether data exists for the sensor that the statistics belong to.
CountPercent missingValues
Parameter that describes the total number of, and percentage of, values that are missing for the sensor that the statistics belong to.
CountPercent invalidValues
Parameter that describes the total number of, and percentage of, values that are invalid for the sensor that the statistics belong to.
CountPercent invalidDateEntries
Parameter that describes the total number of invalid date entries associated with the sensor that the statistics belong to.
CountPercent duplicateTimestamps
Parameter that describes the total number of duplicate timestamp records associated with the sensor that the statistics belong to.
CategoricalValues categoricalValues
Parameter that describes potential risk about whether data associated with the sensor is categorical.
MultipleOperatingModes multipleOperatingModes
Parameter that describes potential risk about whether data associated with the sensor has more than one operating mode.
LargeTimestampGaps largeTimestampGaps
Parameter that describes potential risk about whether data associated with the sensor contains one or more large gaps between consecutive timestamps.
MonotonicValues monotonicValues
Parameter that describes potential risk about whether data associated with the sensor is mostly monotonic.
Date dataStartTime
Indicates the time reference to indicate the beginning of valid data associated with the sensor that the statistics belong to.
Date dataEndTime
Indicates the time reference to indicate the end of valid data associated with the sensor that the statistics belong to.
Integer affectedSensorCount
Indicates the number of sensors that have less than 14 days of data.
String datasetName
The name of the dataset being used by the data ingestion job.
IngestionInputConfiguration ingestionInputConfiguration
Specifies information for the input data for the data ingestion job, including dataset S3 location.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source for the data ingestion job.
String clientToken
A unique identifier for the request. If you do not set the client request token, Amazon Lookout for Equipment generates one.
String inferenceSchedulerName
The name of the inference scheduler to be started.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model being used by the inference scheduler.
String modelName
The name of the machine learning model being used by the inference scheduler.
String inferenceSchedulerName
The name of the inference scheduler being started.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference scheduler being started.
String status
Indicates the status of the inference scheduler.
String modelName
The name of the model whose retraining scheduler you want to start.
String inferenceSchedulerName
The name of the inference scheduler to be stopped.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model used by the inference scheduler being stopped.
String modelName
The name of the machine learning model used by the inference scheduler being stopped.
String inferenceSchedulerName
The name of the inference scheduler being stopped.
String inferenceSchedulerArn
The Amazon Resource Name (ARN) of the inference schedule being stopped.
String status
Indicates the status of the inference scheduler.
String modelName
The name of the model whose retraining scheduler you want to stop.
Integer totalNumberOfUnsupportedTimestamps
Indicates the total number of unsupported timestamps across the ingested data.
String modelName
The name of the machine learning model for which the active model version was set.
String modelArn
The Amazon Resource Name (ARN) of the machine learning model for which the active model version was set.
Long currentActiveVersion
The version that is currently active of the machine learning model for which the active model version was set.
Long previousActiveVersion
The previous version that was active of the machine learning model for which the active model version was set.
String currentActiveVersionArn
The Amazon Resource Name (ARN) of the machine learning model version that is the current active model version.
String previousActiveVersionArn
The Amazon Resource Name (ARN) of the machine learning model version that was the previous active model version.
String inferenceSchedulerName
The name of the inference scheduler to be updated.
Long dataDelayOffsetInMinutes
A period of time (in minutes) by which inference on the data is delayed after the data starts. For instance, if you select an offset delay time of five minutes, inference will not begin on the data until the first data measurement after the five minute mark. For example, if five minutes is selected, the inference scheduler will wake up at the configured frequency with the additional five minute delay time to check the customer S3 bucket. The customer can upload data at the same frequency and they don't need to stop and restart the scheduler when uploading new data.
String dataUploadFrequency
How often data is uploaded to the source S3 bucket for the input data. The value chosen is the length of time between data uploads. For instance, if you select 5 minutes, Amazon Lookout for Equipment will upload the real-time data to the source bucket once every 5 minutes. This frequency also determines how often Amazon Lookout for Equipment starts a scheduled inference on your data. In this example, it starts once every 5 minutes.
InferenceInputConfiguration dataInputConfiguration
Specifies information for the input data for the inference scheduler, including delimiter, format, and dataset location.
InferenceOutputConfiguration dataOutputConfiguration
Specifies information for the output results from the inference scheduler, including the output S3 location.
String roleArn
The Amazon Resource Name (ARN) of a role with permission to access the data source for the inference scheduler.
String modelName
The name of the model to update.
LabelsInputConfiguration labelsInputConfiguration
String roleArn
The ARN of the model to update.
ModelDiagnosticsOutputConfiguration modelDiagnosticsOutputConfiguration
The Amazon S3 location where you want Amazon Lookout for Equipment to save the pointwise model diagnostics for
the model. You must also specify the RoleArn request parameter.
String modelName
The name of the model whose retraining scheduler you want to update.
Date retrainingStartDate
The start date for the retraining scheduler. Lookout for Equipment truncates the time you provide to the nearest UTC day.
String retrainingFrequency
This parameter uses the ISO 8601 standard to set the frequency at which you want retraining to occur in terms of Years, Months, and/or Days (note: other parameters like Time are not currently supported). The minimum value is 30 days (P30D) and the maximum value is 1 year (P1Y). For example, the following values are valid:
P3M15D – Every 3 months and 15 days
P2M – Every 2 months
P150D – Every 150 days
String lookbackWindow
The number of past days of data that will be used for retraining.
String promoteMode
Indicates how the service will use new models. In MANAGED mode, new models will automatically be
used for inference if they have better performance than the current model. In MANUAL mode, the new
models will not be used until
they are manually activated.
Copyright © 2025. All rights reserved.