String mLModelId
Constraints:
Length: 1 - 64
Pattern: [a-zA-Z0-9_.-]+
String trainingDataSourceId
Constraints:
Length: 1 - 64
Pattern: [a-zA-Z0-9_.-]+
String createdByIamUser
Constraints:
Pattern: arn:aws:iam::[0-9]+:((user/.+)|(root))
Date createdAt
Date lastUpdatedAt
String name
Constraints:
Length: 0 - 1024
String status
PENDING
- AmazonML
submitted a request to describe a MLModel.INPROGRESS
- The request is processing.FAILED
- The request did not run to completion. It is
not usable.COMPLETED
- The request completed
successufully.DELETED
- The MLModel is
marked as deleted. It is not usable.
Constraints:
Allowed Values: PENDING, INPROGRESS, FAILED, COMPLETED, DELETED
Long sizeInBytes
RealtimeEndpointInfo endpointInfo
Map<K,V> trainingParameters
The current set of training parameters follows:
sgd.l1RegularizationAmount
- Coefficient
regularization L1 norm. Controls overfitting the data by penalizing
large coefficients. Tends to drive coefficients to zero, resulting in
sparse feature set. If used, specify a small value, such as 1.0E-04 or
1.0E-08.
Implemented as a double. Range is 0 to MAX_DOUBLE. Default is not to use L1 normalization. Cannot be used when L2 is specified. Use sparingly.
sgd.l2RegularizationAmount
- Coefficient
regularization L2 norm. Controls overfitting the data by penalizing
large coefficients. Tends to drive coefficients to small, nonzero
values. If used, specify a small value, such as 1.0E-04 or 1.0E-08.
Implemented as a double. Range is 0 to MAX_DOUBLE. Default is not to use L2 normalization. Cannot be used when L1 is specified. Use sparingly.
sgd.maxPasses
- Number of
times that the training process traverses the observations to build
the MLModel. The value is an integer that ranges from 1 through
10000 for SGD. The default value is 10.
sgd.maxMLModelSizeInBytes
- Maximum allowed size
of the model.
Depending on the input data, the model size might affect the performance.
Implemented as an integer. Range is 100000 through 2147483648. Default value is 33554432.
String inputDataLocationS3
Constraints:
Length: 0 - 2048
Pattern: s3://([^/]+)(/.*)?
String mLModelType
Constraints:
Allowed Values: REGRESSION, BINARY, MULTICLASS
Float scoreThreshold
Output values greater than or equal to
the threshold receive a positive result from the MLModel, such as
true
. Output values less than the threshold receive a
negative response from the MLModel, such as false
.
Date scoreThresholdLastUpdatedAt
String logUri
String message
Constraints:
Length: 0 - 10240
String recipe
Note This parameter is provided as part of the verbose format.
Constraints:
Length: 0 - 131071
String schema
Note This parameter is provided as part of the verbose format.
Constraints:
Length: 0 - 131071
Integer code
Integer code
Integer code
Prediction prediction
Integer peakRequestsPerSecond
Date createdAt
String endpointUrl
MLModel
. The application must wait until the realtime endpoint is ready before using this URI.
Constraints:
Length: 0 - 2048
Pattern: https://[a-zA-Z0-9-.]*\.amazon(aws)?\.com[/]?
String endpointStatus
Constraints:
Allowed Values: NONE, READY, UPDATING, FAILED
Integer code
Copyright © 2015. All rights reserved.