# EndpointInputProperty

Input object for the endpoint.

- Source: Generated at build time
- Type last changed: v2.93.0 · 23 Aug 2023

## Example

TypeScript:

```ts
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from 'aws-cdk-lib';
const endpointInputProperty: sagemaker.CfnModelExplainabilityJobDefinition.EndpointInputProperty = {
  endpointName: 'endpointName',
  localPath: 'localPath',

  // the properties below are optional
  featuresAttribute: 'featuresAttribute',
  inferenceAttribute: 'inferenceAttribute',
  probabilityAttribute: 'probabilityAttribute',
  s3DataDistributionType: 's3DataDistributionType',
  s3InputMode: 's3InputMode',
};
```

Python:

```python
# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk import aws_sagemaker as sagemaker

endpoint_input_property = sagemaker.CfnModelExplainabilityJobDefinition.EndpointInputProperty(
    endpoint_name="endpointName",
    local_path="localPath",

    # the properties below are optional
    features_attribute="featuresAttribute",
    inference_attribute="inferenceAttribute",
    probability_attribute="probabilityAttribute",
    s3_data_distribution_type="s3DataDistributionType",
    s3_input_mode="s3InputMode"
)
```

Java:

```java
// 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
        .featuresAttribute("featuresAttribute")
        .inferenceAttribute("inferenceAttribute")
        .probabilityAttribute("probabilityAttribute")
        .s3DataDistributionType("s3DataDistributionType")
        .s3InputMode("s3InputMode")
        .build();
```

C# / .NET:

```csharp
// Install: dotnet add package Amazon.CDK.Lib
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
using Amazon.CDK.AWS.Sagemaker;

var endpointInputProperty = new EndpointInputProperty {
    EndpointName = "endpointName",
    LocalPath = "localPath",

    // the properties below are optional
    FeaturesAttribute = "featuresAttribute",
    InferenceAttribute = "inferenceAttribute",
    ProbabilityAttribute = "probabilityAttribute",
    S3DataDistributionType = "s3DataDistributionType",
    S3InputMode = "s3InputMode"
};
```

Golang:

```go
// Install: go get github.com/aws/aws-cdk-go/awscdk/v2
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import "github.com/aws/aws-cdk-go/awscdk"

endpointInputProperty := &EndpointInputProperty{
	EndpointName: jsii.String("endpointName"),
	LocalPath: jsii.String("localPath"),

	// the properties below are optional
	FeaturesAttribute: jsii.String("featuresAttribute"),
	InferenceAttribute: jsii.String("inferenceAttribute"),
	ProbabilityAttribute: jsii.String("probabilityAttribute"),
	S3DataDistributionType: jsii.String("s3DataDistributionType"),
	S3InputMode: jsii.String("s3InputMode"),
}
```

## Properties

- `endpointName`: string (required) — An endpoint in customer's account which has enabled `DataCaptureConfig` enabled.

- `featuresAttribute`: string — The attributes of the input data that are the input features.

- `inferenceAttribute`: string — The attribute of the input data that represents the ground truth label.

- `localPath`: string (required) — Path to the filesystem where the endpoint data is available to the container.

- `probabilityAttribute`: string — In a classification problem, the attribute that represents the class probability.

- `s3DataDistributionType`: string — Whether input data distributed in Amazon S3 is fully replicated or sharded by an Amazon S3 key.

  Defaults to `FullyReplicated`

- `s3InputMode`: string — Whether the `Pipe` or `File` is used as the input mode for transferring data for the monitoring job.

  `Pipe` mode is recommended for large datasets. `File` mode is useful for small files that fit in memory. Defaults to `File` .
