public static interface CfnModelQualityJobDefinition.EndpointInputProperty
Example:
// The code below shows an example of how to instantiate this type. // The values are placeholders you should change. import software.amazon.awscdk.services.sagemaker.*; EndpointInputProperty endpointInputProperty = EndpointInputProperty.builder() .endpointName("endpointName") .localPath("localPath") // the properties below are optional .endTimeOffset("endTimeOffset") .inferenceAttribute("inferenceAttribute") .probabilityAttribute("probabilityAttribute") .probabilityThresholdAttribute(123) .s3DataDistributionType("s3DataDistributionType") .s3InputMode("s3InputMode") .startTimeOffset("startTimeOffset") .build();
Modifier and Type | Interface and Description |
---|---|
static class |
CfnModelQualityJobDefinition.EndpointInputProperty.Builder
A builder for
CfnModelQualityJobDefinition.EndpointInputProperty |
static class |
CfnModelQualityJobDefinition.EndpointInputProperty.Jsii$Proxy
An implementation for
CfnModelQualityJobDefinition.EndpointInputProperty |
Modifier and Type | Method and Description |
---|---|
static CfnModelQualityJobDefinition.EndpointInputProperty.Builder |
builder() |
java.lang.String |
getEndpointName()
An endpoint in customer's account which has enabled `DataCaptureConfig` enabled.
|
default java.lang.String |
getEndTimeOffset()
If specified, monitoring jobs substract this time from the end time.
|
default java.lang.String |
getInferenceAttribute()
The attribute of the input data that represents the ground truth label.
|
java.lang.String |
getLocalPath()
Path to the filesystem where the endpoint data is available to the container.
|
default java.lang.String |
getProbabilityAttribute()
In a classification problem, the attribute that represents the class probability.
|
default java.lang.Number |
getProbabilityThresholdAttribute()
The threshold for the class probability to be evaluated as a positive result.
|
default java.lang.String |
getS3DataDistributionType()
Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key.
|
default java.lang.String |
getS3InputMode()
Whether the `Pipe` or `File` is used as the input mode for transferring data for the monitoring job.
|
default java.lang.String |
getStartTimeOffset()
If specified, monitoring jobs substract this time from the start time.
|
java.lang.String getEndpointName()
java.lang.String getLocalPath()
default java.lang.String getEndTimeOffset()
For information about using offsets for scheduling monitoring jobs, see Schedule Model Quality Monitoring Jobs .
default java.lang.String getInferenceAttribute()
default java.lang.String getProbabilityAttribute()
default java.lang.Number getProbabilityThresholdAttribute()
default java.lang.String getS3DataDistributionType()
Defaults to FullyReplicated
default java.lang.String getS3InputMode()
Pipe
mode is recommended for large datasets. File
mode is useful for small files that fit in memory. Defaults to File
.
default java.lang.String getStartTimeOffset()
For information about using offsets for scheduling monitoring jobs, see Schedule Model Quality Monitoring Jobs .