AWS v6.76.0, Apr 8 25

AWS v6.76.0 published on Tuesday, Apr 8, 2025 by Pulumi

aws.sagemaker.DataQualityJobDefinition

Explore with Pulumi AI

AWS v6.76.0 published on Tuesday, Apr 8, 2025 by Pulumi

Example Usage

Basic usage:

TypeScript
Python
Go
C#
Java
YAML

import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const test = new aws.sagemaker.DataQualityJobDefinition("test", {
    name: "my-data-quality-job-definition",
    dataQualityAppSpecification: {
        imageUri: monitor.registryPath,
    },
    dataQualityJobInput: {
        endpointInput: {
            endpointName: myEndpoint.name,
        },
    },
    dataQualityJobOutputConfig: {
        monitoringOutputs: {
            s3Output: {
                s3Uri: `https://${myBucket.bucketRegionalDomainName}/output`,
            },
        },
    },
    jobResources: {
        clusterConfig: {
            instanceCount: 1,
            instanceType: "ml.t3.medium",
            volumeSizeInGb: 20,
        },
    },
    roleArn: myRole.arn,
});

import pulumi
import pulumi_aws as aws

test = aws.sagemaker.DataQualityJobDefinition("test",
    name="my-data-quality-job-definition",
    data_quality_app_specification={
        "image_uri": monitor["registryPath"],
    },
    data_quality_job_input={
        "endpoint_input": {
            "endpoint_name": my_endpoint["name"],
        },
    },
    data_quality_job_output_config={
        "monitoring_outputs": {
            "s3_output": {
                "s3_uri": f"https://{my_bucket['bucketRegionalDomainName']}/output",
            },
        },
    },
    job_resources={
        "cluster_config": {
            "instance_count": 1,
            "instance_type": "ml.t3.medium",
            "volume_size_in_gb": 20,
        },
    },
    role_arn=my_role["arn"])

package main

import (
	"fmt"

	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/sagemaker"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := sagemaker.NewDataQualityJobDefinition(ctx, "test", &sagemaker.DataQualityJobDefinitionArgs{
			Name: pulumi.String("my-data-quality-job-definition"),
			DataQualityAppSpecification: &sagemaker.DataQualityJobDefinitionDataQualityAppSpecificationArgs{
				ImageUri: pulumi.Any(monitor.RegistryPath),
			},
			DataQualityJobInput: &sagemaker.DataQualityJobDefinitionDataQualityJobInputArgs{
				EndpointInput: &sagemaker.DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs{
					EndpointName: pulumi.Any(myEndpoint.Name),
				},
			},
			DataQualityJobOutputConfig: &sagemaker.DataQualityJobDefinitionDataQualityJobOutputConfigArgs{
				MonitoringOutputs: &sagemaker.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs{
					S3Output: sagemaker.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs{
						S3Uri: pulumi.Sprintf("https://%v/output", myBucket.BucketRegionalDomainName),
					},
				},
			},
			JobResources: &sagemaker.DataQualityJobDefinitionJobResourcesArgs{
				ClusterConfig: &sagemaker.DataQualityJobDefinitionJobResourcesClusterConfigArgs{
					InstanceCount:  pulumi.Int(1),
					InstanceType:   pulumi.String("ml.t3.medium"),
					VolumeSizeInGb: pulumi.Int(20),
				},
			},
			RoleArn: pulumi.Any(myRole.Arn),
		})
		if err != nil {
			return err
		}
		return nil
	})
}

using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;

return await Deployment.RunAsync(() => 
{
    var test = new Aws.Sagemaker.DataQualityJobDefinition("test", new()
    {
        Name = "my-data-quality-job-definition",
        DataQualityAppSpecification = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityAppSpecificationArgs
        {
            ImageUri = monitor.RegistryPath,
        },
        DataQualityJobInput = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputArgs
        {
            EndpointInput = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs
            {
                EndpointName = myEndpoint.Name,
            },
        },
        DataQualityJobOutputConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobOutputConfigArgs
        {
            MonitoringOutputs = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs
            {
                S3Output = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs
                {
                    S3Uri = $"https://{myBucket.BucketRegionalDomainName}/output",
                },
            },
        },
        JobResources = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionJobResourcesArgs
        {
            ClusterConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionJobResourcesClusterConfigArgs
            {
                InstanceCount = 1,
                InstanceType = "ml.t3.medium",
                VolumeSizeInGb = 20,
            },
        },
        RoleArn = myRole.Arn,
    });

});

package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.sagemaker.DataQualityJobDefinition;
import com.pulumi.aws.sagemaker.DataQualityJobDefinitionArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionDataQualityAppSpecificationArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionDataQualityJobInputArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionDataQualityJobOutputConfigArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionJobResourcesArgs;
import com.pulumi.aws.sagemaker.inputs.DataQualityJobDefinitionJobResourcesClusterConfigArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var test = new DataQualityJobDefinition("test", DataQualityJobDefinitionArgs.builder()
            .name("my-data-quality-job-definition")
            .dataQualityAppSpecification(DataQualityJobDefinitionDataQualityAppSpecificationArgs.builder()
                .imageUri(monitor.registryPath())
                .build())
            .dataQualityJobInput(DataQualityJobDefinitionDataQualityJobInputArgs.builder()
                .endpointInput(DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs.builder()
                    .endpointName(myEndpoint.name())
                    .build())
                .build())
            .dataQualityJobOutputConfig(DataQualityJobDefinitionDataQualityJobOutputConfigArgs.builder()
                .monitoringOutputs(DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs.builder()
                    .s3Output(DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs.builder()
                        .s3Uri(String.format("https://%s/output", myBucket.bucketRegionalDomainName()))
                        .build())
                    .build())
                .build())
            .jobResources(DataQualityJobDefinitionJobResourcesArgs.builder()
                .clusterConfig(DataQualityJobDefinitionJobResourcesClusterConfigArgs.builder()
                    .instanceCount(1)
                    .instanceType("ml.t3.medium")
                    .volumeSizeInGb(20)
                    .build())
                .build())
            .roleArn(myRole.arn())
            .build());

    }
}

resources:
  test:
    type: aws:sagemaker:DataQualityJobDefinition
    properties:
      name: my-data-quality-job-definition
      dataQualityAppSpecification:
        imageUri: ${monitor.registryPath}
      dataQualityJobInput:
        endpointInput:
          endpointName: ${myEndpoint.name}
      dataQualityJobOutputConfig:
        monitoringOutputs:
          s3Output:
            s3Uri: https://${myBucket.bucketRegionalDomainName}/output
      jobResources:
        clusterConfig:
          instanceCount: 1
          instanceType: ml.t3.medium
          volumeSizeInGb: 20
      roleArn: ${myRole.arn}

Create DataQualityJobDefinition Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

new DataQualityJobDefinition(name: string, args: DataQualityJobDefinitionArgs, opts?: CustomResourceOptions);

@overload
def DataQualityJobDefinition(resource_name: str,
                             args: DataQualityJobDefinitionArgs,
                             opts: Optional[ResourceOptions] = None)

@overload
def DataQualityJobDefinition(resource_name: str,
                             opts: Optional[ResourceOptions] = None,
                             data_quality_app_specification: Optional[DataQualityJobDefinitionDataQualityAppSpecificationArgs] = None,
                             data_quality_job_input: Optional[DataQualityJobDefinitionDataQualityJobInputArgs] = None,
                             data_quality_job_output_config: Optional[DataQualityJobDefinitionDataQualityJobOutputConfigArgs] = None,
                             job_resources: Optional[DataQualityJobDefinitionJobResourcesArgs] = None,
                             role_arn: Optional[str] = None,
                             data_quality_baseline_config: Optional[DataQualityJobDefinitionDataQualityBaselineConfigArgs] = None,
                             name: Optional[str] = None,
                             network_config: Optional[DataQualityJobDefinitionNetworkConfigArgs] = None,
                             stopping_condition: Optional[DataQualityJobDefinitionStoppingConditionArgs] = None,
                             tags: Optional[Mapping[str, str]] = None)

func NewDataQualityJobDefinition(ctx *Context, name string, args DataQualityJobDefinitionArgs, opts ...ResourceOption) (*DataQualityJobDefinition, error)

public DataQualityJobDefinition(string name, DataQualityJobDefinitionArgs args, CustomResourceOptions? opts = null)

public DataQualityJobDefinition(String name, DataQualityJobDefinitionArgs args)
public DataQualityJobDefinition(String name, DataQualityJobDefinitionArgs args, CustomResourceOptions options)

type: aws:sagemaker:DataQualityJobDefinition
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name string: The unique name of the resource.
args DataQualityJobDefinitionArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

resource_name str: The unique name of the resource.
args DataQualityJobDefinitionArgs: The arguments to resource properties.
opts ResourceOptions: Bag of options to control resource's behavior.

ctx Context: Context object for the current deployment.
name string: The unique name of the resource.
args DataQualityJobDefinitionArgs: The arguments to resource properties.
opts ResourceOption: Bag of options to control resource's behavior.

name string: The unique name of the resource.
args DataQualityJobDefinitionArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

name String: The unique name of the resource.
args DataQualityJobDefinitionArgs: The arguments to resource properties.
options CustomResourceOptions: Bag of options to control resource's behavior.

Constructor example

The following reference example uses placeholder values for all input properties.

TypeScript
Python
Go
C#
Java
YAML

var dataQualityJobDefinitionResource = new Aws.Sagemaker.DataQualityJobDefinition("dataQualityJobDefinitionResource", new()
{
    DataQualityAppSpecification = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityAppSpecificationArgs
    {
        ImageUri = "string",
        Environment = 
        {
            { "string", "string" },
        },
        PostAnalyticsProcessorSourceUri = "string",
        RecordPreprocessorSourceUri = "string",
    },
    DataQualityJobInput = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputArgs
    {
        BatchTransformInput = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs
        {
            DataCapturedDestinationS3Uri = "string",
            DatasetFormat = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs
            {
                Csv = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs
                {
                    Header = false,
                },
                Json = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs
                {
                    Line = false,
                },
            },
            LocalPath = "string",
            S3DataDistributionType = "string",
            S3InputMode = "string",
        },
        EndpointInput = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs
        {
            EndpointName = "string",
            LocalPath = "string",
            S3DataDistributionType = "string",
            S3InputMode = "string",
        },
    },
    DataQualityJobOutputConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobOutputConfigArgs
    {
        MonitoringOutputs = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs
        {
            S3Output = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs
            {
                S3Uri = "string",
                LocalPath = "string",
                S3UploadMode = "string",
            },
        },
        KmsKeyId = "string",
    },
    JobResources = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionJobResourcesArgs
    {
        ClusterConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionJobResourcesClusterConfigArgs
        {
            InstanceCount = 0,
            InstanceType = "string",
            VolumeSizeInGb = 0,
            VolumeKmsKeyId = "string",
        },
    },
    RoleArn = "string",
    DataQualityBaselineConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityBaselineConfigArgs
    {
        ConstraintsResource = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs
        {
            S3Uri = "string",
        },
        StatisticsResource = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs
        {
            S3Uri = "string",
        },
    },
    Name = "string",
    NetworkConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionNetworkConfigArgs
    {
        EnableInterContainerTrafficEncryption = false,
        EnableNetworkIsolation = false,
        VpcConfig = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionNetworkConfigVpcConfigArgs
        {
            SecurityGroupIds = new[]
            {
                "string",
            },
            Subnets = new[]
            {
                "string",
            },
        },
    },
    StoppingCondition = new Aws.Sagemaker.Inputs.DataQualityJobDefinitionStoppingConditionArgs
    {
        MaxRuntimeInSeconds = 0,
    },
    Tags = 
    {
        { "string", "string" },
    },
});

example, err := sagemaker.NewDataQualityJobDefinition(ctx, "dataQualityJobDefinitionResource", &sagemaker.DataQualityJobDefinitionArgs{
	DataQualityAppSpecification: &sagemaker.DataQualityJobDefinitionDataQualityAppSpecificationArgs{
		ImageUri: pulumi.String("string"),
		Environment: pulumi.StringMap{
			"string": pulumi.String("string"),
		},
		PostAnalyticsProcessorSourceUri: pulumi.String("string"),
		RecordPreprocessorSourceUri:     pulumi.String("string"),
	},
	DataQualityJobInput: &sagemaker.DataQualityJobDefinitionDataQualityJobInputArgs{
		BatchTransformInput: &sagemaker.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs{
			DataCapturedDestinationS3Uri: pulumi.String("string"),
			DatasetFormat: &sagemaker.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs{
				Csv: &sagemaker.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs{
					Header: pulumi.Bool(false),
				},
				Json: &sagemaker.DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs{
					Line: pulumi.Bool(false),
				},
			},
			LocalPath:              pulumi.String("string"),
			S3DataDistributionType: pulumi.String("string"),
			S3InputMode:            pulumi.String("string"),
		},
		EndpointInput: &sagemaker.DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs{
			EndpointName:           pulumi.String("string"),
			LocalPath:              pulumi.String("string"),
			S3DataDistributionType: pulumi.String("string"),
			S3InputMode:            pulumi.String("string"),
		},
	},
	DataQualityJobOutputConfig: &sagemaker.DataQualityJobDefinitionDataQualityJobOutputConfigArgs{
		MonitoringOutputs: &sagemaker.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs{
			S3Output: sagemaker.DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs{
				S3Uri:        pulumi.String("string"),
				LocalPath:    pulumi.String("string"),
				S3UploadMode: pulumi.String("string"),
			},
		},
		KmsKeyId: pulumi.String("string"),
	},
	JobResources: &sagemaker.DataQualityJobDefinitionJobResourcesArgs{
		ClusterConfig: &sagemaker.DataQualityJobDefinitionJobResourcesClusterConfigArgs{
			InstanceCount:  pulumi.Int(0),
			InstanceType:   pulumi.String("string"),
			VolumeSizeInGb: pulumi.Int(0),
			VolumeKmsKeyId: pulumi.String("string"),
		},
	},
	RoleArn: pulumi.String("string"),
	DataQualityBaselineConfig: &sagemaker.DataQualityJobDefinitionDataQualityBaselineConfigArgs{
		ConstraintsResource: &sagemaker.DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs{
			S3Uri: pulumi.String("string"),
		},
		StatisticsResource: &sagemaker.DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs{
			S3Uri: pulumi.String("string"),
		},
	},
	Name: pulumi.String("string"),
	NetworkConfig: &sagemaker.DataQualityJobDefinitionNetworkConfigArgs{
		EnableInterContainerTrafficEncryption: pulumi.Bool(false),
		EnableNetworkIsolation:                pulumi.Bool(false),
		VpcConfig: &sagemaker.DataQualityJobDefinitionNetworkConfigVpcConfigArgs{
			SecurityGroupIds: pulumi.StringArray{
				pulumi.String("string"),
			},
			Subnets: pulumi.StringArray{
				pulumi.String("string"),
			},
		},
	},
	StoppingCondition: &sagemaker.DataQualityJobDefinitionStoppingConditionArgs{
		MaxRuntimeInSeconds: pulumi.Int(0),
	},
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
})

var dataQualityJobDefinitionResource = new DataQualityJobDefinition("dataQualityJobDefinitionResource", DataQualityJobDefinitionArgs.builder()
    .dataQualityAppSpecification(DataQualityJobDefinitionDataQualityAppSpecificationArgs.builder()
        .imageUri("string")
        .environment(Map.of("string", "string"))
        .postAnalyticsProcessorSourceUri("string")
        .recordPreprocessorSourceUri("string")
        .build())
    .dataQualityJobInput(DataQualityJobDefinitionDataQualityJobInputArgs.builder()
        .batchTransformInput(DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs.builder()
            .dataCapturedDestinationS3Uri("string")
            .datasetFormat(DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs.builder()
                .csv(DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs.builder()
                    .header(false)
                    .build())
                .json(DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs.builder()
                    .line(false)
                    .build())
                .build())
            .localPath("string")
            .s3DataDistributionType("string")
            .s3InputMode("string")
            .build())
        .endpointInput(DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs.builder()
            .endpointName("string")
            .localPath("string")
            .s3DataDistributionType("string")
            .s3InputMode("string")
            .build())
        .build())
    .dataQualityJobOutputConfig(DataQualityJobDefinitionDataQualityJobOutputConfigArgs.builder()
        .monitoringOutputs(DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs.builder()
            .s3Output(DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs.builder()
                .s3Uri("string")
                .localPath("string")
                .s3UploadMode("string")
                .build())
            .build())
        .kmsKeyId("string")
        .build())
    .jobResources(DataQualityJobDefinitionJobResourcesArgs.builder()
        .clusterConfig(DataQualityJobDefinitionJobResourcesClusterConfigArgs.builder()
            .instanceCount(0)
            .instanceType("string")
            .volumeSizeInGb(0)
            .volumeKmsKeyId("string")
            .build())
        .build())
    .roleArn("string")
    .dataQualityBaselineConfig(DataQualityJobDefinitionDataQualityBaselineConfigArgs.builder()
        .constraintsResource(DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs.builder()
            .s3Uri("string")
            .build())
        .statisticsResource(DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs.builder()
            .s3Uri("string")
            .build())
        .build())
    .name("string")
    .networkConfig(DataQualityJobDefinitionNetworkConfigArgs.builder()
        .enableInterContainerTrafficEncryption(false)
        .enableNetworkIsolation(false)
        .vpcConfig(DataQualityJobDefinitionNetworkConfigVpcConfigArgs.builder()
            .securityGroupIds("string")
            .subnets("string")
            .build())
        .build())
    .stoppingCondition(DataQualityJobDefinitionStoppingConditionArgs.builder()
        .maxRuntimeInSeconds(0)
        .build())
    .tags(Map.of("string", "string"))
    .build());

data_quality_job_definition_resource = aws.sagemaker.DataQualityJobDefinition("dataQualityJobDefinitionResource",
    data_quality_app_specification={
        "image_uri": "string",
        "environment": {
            "string": "string",
        },
        "post_analytics_processor_source_uri": "string",
        "record_preprocessor_source_uri": "string",
    },
    data_quality_job_input={
        "batch_transform_input": {
            "data_captured_destination_s3_uri": "string",
            "dataset_format": {
                "csv": {
                    "header": False,
                },
                "json": {
                    "line": False,
                },
            },
            "local_path": "string",
            "s3_data_distribution_type": "string",
            "s3_input_mode": "string",
        },
        "endpoint_input": {
            "endpoint_name": "string",
            "local_path": "string",
            "s3_data_distribution_type": "string",
            "s3_input_mode": "string",
        },
    },
    data_quality_job_output_config={
        "monitoring_outputs": {
            "s3_output": {
                "s3_uri": "string",
                "local_path": "string",
                "s3_upload_mode": "string",
            },
        },
        "kms_key_id": "string",
    },
    job_resources={
        "cluster_config": {
            "instance_count": 0,
            "instance_type": "string",
            "volume_size_in_gb": 0,
            "volume_kms_key_id": "string",
        },
    },
    role_arn="string",
    data_quality_baseline_config={
        "constraints_resource": {
            "s3_uri": "string",
        },
        "statistics_resource": {
            "s3_uri": "string",
        },
    },
    name="string",
    network_config={
        "enable_inter_container_traffic_encryption": False,
        "enable_network_isolation": False,
        "vpc_config": {
            "security_group_ids": ["string"],
            "subnets": ["string"],
        },
    },
    stopping_condition={
        "max_runtime_in_seconds": 0,
    },
    tags={
        "string": "string",
    })

const dataQualityJobDefinitionResource = new aws.sagemaker.DataQualityJobDefinition("dataQualityJobDefinitionResource", {
    dataQualityAppSpecification: {
        imageUri: "string",
        environment: {
            string: "string",
        },
        postAnalyticsProcessorSourceUri: "string",
        recordPreprocessorSourceUri: "string",
    },
    dataQualityJobInput: {
        batchTransformInput: {
            dataCapturedDestinationS3Uri: "string",
            datasetFormat: {
                csv: {
                    header: false,
                },
                json: {
                    line: false,
                },
            },
            localPath: "string",
            s3DataDistributionType: "string",
            s3InputMode: "string",
        },
        endpointInput: {
            endpointName: "string",
            localPath: "string",
            s3DataDistributionType: "string",
            s3InputMode: "string",
        },
    },
    dataQualityJobOutputConfig: {
        monitoringOutputs: {
            s3Output: {
                s3Uri: "string",
                localPath: "string",
                s3UploadMode: "string",
            },
        },
        kmsKeyId: "string",
    },
    jobResources: {
        clusterConfig: {
            instanceCount: 0,
            instanceType: "string",
            volumeSizeInGb: 0,
            volumeKmsKeyId: "string",
        },
    },
    roleArn: "string",
    dataQualityBaselineConfig: {
        constraintsResource: {
            s3Uri: "string",
        },
        statisticsResource: {
            s3Uri: "string",
        },
    },
    name: "string",
    networkConfig: {
        enableInterContainerTrafficEncryption: false,
        enableNetworkIsolation: false,
        vpcConfig: {
            securityGroupIds: ["string"],
            subnets: ["string"],
        },
    },
    stoppingCondition: {
        maxRuntimeInSeconds: 0,
    },
    tags: {
        string: "string",
    },
});

type: aws:sagemaker:DataQualityJobDefinition
properties:
    dataQualityAppSpecification:
        environment:
            string: string
        imageUri: string
        postAnalyticsProcessorSourceUri: string
        recordPreprocessorSourceUri: string
    dataQualityBaselineConfig:
        constraintsResource:
            s3Uri: string
        statisticsResource:
            s3Uri: string
    dataQualityJobInput:
        batchTransformInput:
            dataCapturedDestinationS3Uri: string
            datasetFormat:
                csv:
                    header: false
                json:
                    line: false
            localPath: string
            s3DataDistributionType: string
            s3InputMode: string
        endpointInput:
            endpointName: string
            localPath: string
            s3DataDistributionType: string
            s3InputMode: string
    dataQualityJobOutputConfig:
        kmsKeyId: string
        monitoringOutputs:
            s3Output:
                localPath: string
                s3UploadMode: string
                s3Uri: string
    jobResources:
        clusterConfig:
            instanceCount: 0
            instanceType: string
            volumeKmsKeyId: string
            volumeSizeInGb: 0
    name: string
    networkConfig:
        enableInterContainerTrafficEncryption: false
        enableNetworkIsolation: false
        vpcConfig:
            securityGroupIds:
                - string
            subnets:
                - string
    roleArn: string
    stoppingCondition:
        maxRuntimeInSeconds: 0
    tags:
        string: string

DataQualityJobDefinition Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The DataQualityJobDefinition resource accepts the following input properties:

DataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecification: Specifies the container that runs the monitoring job. Fields are documented below.
DataQualityJobInput DataQualityJobDefinitionDataQualityJobInput: A list of inputs for the monitoring job. Fields are documented below.
DataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfig: The output configuration for monitoring jobs. Fields are documented below.
JobResources DataQualityJobDefinitionJobResources: Identifies the resources to deploy for a monitoring job. Fields are documented below.
RoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
DataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfig: Configures the constraints and baselines for the monitoring job. Fields are documented below.
Name string: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
NetworkConfig DataQualityJobDefinitionNetworkConfig: Specifies networking configuration for the monitoring job. Fields are documented below.
StoppingCondition DataQualityJobDefinitionStoppingCondition: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
Tags Dictionary<string, string>: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

DataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecificationArgs: Specifies the container that runs the monitoring job. Fields are documented below.
DataQualityJobInput DataQualityJobDefinitionDataQualityJobInputArgs: A list of inputs for the monitoring job. Fields are documented below.
DataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfigArgs: The output configuration for monitoring jobs. Fields are documented below.
JobResources DataQualityJobDefinitionJobResourcesArgs: Identifies the resources to deploy for a monitoring job. Fields are documented below.
RoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
DataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfigArgs: Configures the constraints and baselines for the monitoring job. Fields are documented below.
Name string: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
NetworkConfig DataQualityJobDefinitionNetworkConfigArgs: Specifies networking configuration for the monitoring job. Fields are documented below.
StoppingCondition DataQualityJobDefinitionStoppingConditionArgs: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
Tags map[string]string: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

dataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecification: Specifies the container that runs the monitoring job. Fields are documented below.
dataQualityJobInput DataQualityJobDefinitionDataQualityJobInput: A list of inputs for the monitoring job. Fields are documented below.
dataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfig: The output configuration for monitoring jobs. Fields are documented below.
jobResources DataQualityJobDefinitionJobResources: Identifies the resources to deploy for a monitoring job. Fields are documented below.
roleArn String: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
dataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfig: Configures the constraints and baselines for the monitoring job. Fields are documented below.
name String: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
networkConfig DataQualityJobDefinitionNetworkConfig: Specifies networking configuration for the monitoring job. Fields are documented below.
stoppingCondition DataQualityJobDefinitionStoppingCondition: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags Map<String,String>: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

dataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecification: Specifies the container that runs the monitoring job. Fields are documented below.
dataQualityJobInput DataQualityJobDefinitionDataQualityJobInput: A list of inputs for the monitoring job. Fields are documented below.
dataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfig: The output configuration for monitoring jobs. Fields are documented below.
jobResources DataQualityJobDefinitionJobResources: Identifies the resources to deploy for a monitoring job. Fields are documented below.
roleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
dataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfig: Configures the constraints and baselines for the monitoring job. Fields are documented below.
name string: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
networkConfig DataQualityJobDefinitionNetworkConfig: Specifies networking configuration for the monitoring job. Fields are documented below.
stoppingCondition DataQualityJobDefinitionStoppingCondition: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags {[key: string]: string}: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

data_quality_app_specification DataQualityJobDefinitionDataQualityAppSpecificationArgs: Specifies the container that runs the monitoring job. Fields are documented below.
data_quality_job_input DataQualityJobDefinitionDataQualityJobInputArgs: A list of inputs for the monitoring job. Fields are documented below.
data_quality_job_output_config DataQualityJobDefinitionDataQualityJobOutputConfigArgs: The output configuration for monitoring jobs. Fields are documented below.
job_resources DataQualityJobDefinitionJobResourcesArgs: Identifies the resources to deploy for a monitoring job. Fields are documented below.
role_arn str: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
data_quality_baseline_config DataQualityJobDefinitionDataQualityBaselineConfigArgs: Configures the constraints and baselines for the monitoring job. Fields are documented below.
name str: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
network_config DataQualityJobDefinitionNetworkConfigArgs: Specifies networking configuration for the monitoring job. Fields are documented below.
stopping_condition DataQualityJobDefinitionStoppingConditionArgs: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags Mapping[str, str]: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

dataQualityAppSpecification Property Map: Specifies the container that runs the monitoring job. Fields are documented below.
dataQualityJobInput Property Map: A list of inputs for the monitoring job. Fields are documented below.
dataQualityJobOutputConfig Property Map: The output configuration for monitoring jobs. Fields are documented below.
jobResources Property Map: Identifies the resources to deploy for a monitoring job. Fields are documented below.
roleArn String: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
dataQualityBaselineConfig Property Map: Configures the constraints and baselines for the monitoring job. Fields are documented below.
name String: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
networkConfig Property Map: Specifies networking configuration for the monitoring job. Fields are documented below.
stoppingCondition Property Map: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags Map<String>: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

Outputs

All input properties are implicitly available as output properties. Additionally, the DataQualityJobDefinition resource produces the following output properties:

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
Id string: The provider-assigned unique ID for this managed resource.
TagsAll Dictionary<string, string>: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
Id string: The provider-assigned unique ID for this managed resource.
TagsAll map[string]string: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn String: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
id String: The provider-assigned unique ID for this managed resource.
tagsAll Map<String,String>: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn string: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
id string: The provider-assigned unique ID for this managed resource.
tagsAll {[key: string]: string}: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn str: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
id str: The provider-assigned unique ID for this managed resource.
tags_all Mapping[str, str]: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn String: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
id String: The provider-assigned unique ID for this managed resource.
tagsAll Map<String>: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

Look up Existing DataQualityJobDefinition Resource

Get an existing DataQualityJobDefinition resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

TypeScript
Python
Go
C#
Java
YAML

public static get(name: string, id: Input<ID>, state?: DataQualityJobDefinitionState, opts?: CustomResourceOptions): DataQualityJobDefinition

@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        data_quality_app_specification: Optional[DataQualityJobDefinitionDataQualityAppSpecificationArgs] = None,
        data_quality_baseline_config: Optional[DataQualityJobDefinitionDataQualityBaselineConfigArgs] = None,
        data_quality_job_input: Optional[DataQualityJobDefinitionDataQualityJobInputArgs] = None,
        data_quality_job_output_config: Optional[DataQualityJobDefinitionDataQualityJobOutputConfigArgs] = None,
        job_resources: Optional[DataQualityJobDefinitionJobResourcesArgs] = None,
        name: Optional[str] = None,
        network_config: Optional[DataQualityJobDefinitionNetworkConfigArgs] = None,
        role_arn: Optional[str] = None,
        stopping_condition: Optional[DataQualityJobDefinitionStoppingConditionArgs] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None) -> DataQualityJobDefinition

func GetDataQualityJobDefinition(ctx *Context, name string, id IDInput, state *DataQualityJobDefinitionState, opts ...ResourceOption) (*DataQualityJobDefinition, error)

public static DataQualityJobDefinition Get(string name, Input<string> id, DataQualityJobDefinitionState? state, CustomResourceOptions? opts = null)

public static DataQualityJobDefinition get(String name, Output<String> id, DataQualityJobDefinitionState state, CustomResourceOptions options)

resources:  _:    type: aws:sagemaker:DataQualityJobDefinition    get:      id: ${id}

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

resource_name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

The following state arguments are supported:

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
DataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecification: Specifies the container that runs the monitoring job. Fields are documented below.
DataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfig: Configures the constraints and baselines for the monitoring job. Fields are documented below.
DataQualityJobInput DataQualityJobDefinitionDataQualityJobInput: A list of inputs for the monitoring job. Fields are documented below.
DataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfig: The output configuration for monitoring jobs. Fields are documented below.
JobResources DataQualityJobDefinitionJobResources: Identifies the resources to deploy for a monitoring job. Fields are documented below.
Name string: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
NetworkConfig DataQualityJobDefinitionNetworkConfig: Specifies networking configuration for the monitoring job. Fields are documented below.
RoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
StoppingCondition DataQualityJobDefinitionStoppingCondition: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
Tags Dictionary<string, string>: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
TagsAll Dictionary<string, string>: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
DataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecificationArgs: Specifies the container that runs the monitoring job. Fields are documented below.
DataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfigArgs: Configures the constraints and baselines for the monitoring job. Fields are documented below.
DataQualityJobInput DataQualityJobDefinitionDataQualityJobInputArgs: A list of inputs for the monitoring job. Fields are documented below.
DataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfigArgs: The output configuration for monitoring jobs. Fields are documented below.
JobResources DataQualityJobDefinitionJobResourcesArgs: Identifies the resources to deploy for a monitoring job. Fields are documented below.
Name string: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
NetworkConfig DataQualityJobDefinitionNetworkConfigArgs: Specifies networking configuration for the monitoring job. Fields are documented below.
RoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
StoppingCondition DataQualityJobDefinitionStoppingConditionArgs: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
Tags map[string]string: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
TagsAll map[string]string: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn String: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
dataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecification: Specifies the container that runs the monitoring job. Fields are documented below.
dataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfig: Configures the constraints and baselines for the monitoring job. Fields are documented below.
dataQualityJobInput DataQualityJobDefinitionDataQualityJobInput: A list of inputs for the monitoring job. Fields are documented below.
dataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfig: The output configuration for monitoring jobs. Fields are documented below.
jobResources DataQualityJobDefinitionJobResources: Identifies the resources to deploy for a monitoring job. Fields are documented below.
name String: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
networkConfig DataQualityJobDefinitionNetworkConfig: Specifies networking configuration for the monitoring job. Fields are documented below.
roleArn String: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
stoppingCondition DataQualityJobDefinitionStoppingCondition: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags Map<String,String>: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll Map<String,String>: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn string: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
dataQualityAppSpecification DataQualityJobDefinitionDataQualityAppSpecification: Specifies the container that runs the monitoring job. Fields are documented below.
dataQualityBaselineConfig DataQualityJobDefinitionDataQualityBaselineConfig: Configures the constraints and baselines for the monitoring job. Fields are documented below.
dataQualityJobInput DataQualityJobDefinitionDataQualityJobInput: A list of inputs for the monitoring job. Fields are documented below.
dataQualityJobOutputConfig DataQualityJobDefinitionDataQualityJobOutputConfig: The output configuration for monitoring jobs. Fields are documented below.
jobResources DataQualityJobDefinitionJobResources: Identifies the resources to deploy for a monitoring job. Fields are documented below.
name string: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
networkConfig DataQualityJobDefinitionNetworkConfig: Specifies networking configuration for the monitoring job. Fields are documented below.
roleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
stoppingCondition DataQualityJobDefinitionStoppingCondition: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags {[key: string]: string}: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll {[key: string]: string}: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn str: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
data_quality_app_specification DataQualityJobDefinitionDataQualityAppSpecificationArgs: Specifies the container that runs the monitoring job. Fields are documented below.
data_quality_baseline_config DataQualityJobDefinitionDataQualityBaselineConfigArgs: Configures the constraints and baselines for the monitoring job. Fields are documented below.
data_quality_job_input DataQualityJobDefinitionDataQualityJobInputArgs: A list of inputs for the monitoring job. Fields are documented below.
data_quality_job_output_config DataQualityJobDefinitionDataQualityJobOutputConfigArgs: The output configuration for monitoring jobs. Fields are documented below.
job_resources DataQualityJobDefinitionJobResourcesArgs: Identifies the resources to deploy for a monitoring job. Fields are documented below.
name str: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
network_config DataQualityJobDefinitionNetworkConfigArgs: Specifies networking configuration for the monitoring job. Fields are documented below.
role_arn str: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
stopping_condition DataQualityJobDefinitionStoppingConditionArgs: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags Mapping[str, str]: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tags_all Mapping[str, str]: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

arn String: The Amazon Resource Name (ARN) assigned by AWS to this data quality job definition.
dataQualityAppSpecification Property Map: Specifies the container that runs the monitoring job. Fields are documented below.
dataQualityBaselineConfig Property Map: Configures the constraints and baselines for the monitoring job. Fields are documented below.
dataQualityJobInput Property Map: A list of inputs for the monitoring job. Fields are documented below.
dataQualityJobOutputConfig Property Map: The output configuration for monitoring jobs. Fields are documented below.
jobResources Property Map: Identifies the resources to deploy for a monitoring job. Fields are documented below.
name String: The name of the data quality job definition. If omitted, the provider will assign a random, unique name.
networkConfig Property Map: Specifies networking configuration for the monitoring job. Fields are documented below.
roleArn String: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.
stoppingCondition Property Map: A time limit for how long the monitoring job is allowed to run before stopping. Fields are documented below.
tags Map<String>: A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll Map<String>: A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
Deprecated: Please use tags instead.

Supporting Types

DataQualityJobDefinitionDataQualityAppSpecification
, DataQualityJobDefinitionDataQualityAppSpecificationArgs

ImageUri string: The container image that the data quality monitoring job runs.
Environment Dictionary<string, string>: Sets the environment variables in the container that the monitoring job runs. A list of key value pairs.
PostAnalyticsProcessorSourceUri string: An Amazon S3 URI to a script that is called after analysis has been performed. Applicable only for the built-in (first party) containers.
RecordPreprocessorSourceUri string: An Amazon S3 URI to a script that is called per row prior to running analysis. It can base64 decode the payload and convert it into a flatted json so that the built-in container can use the converted data. Applicable only for the built-in (first party) containers.

ImageUri string: The container image that the data quality monitoring job runs.
Environment map[string]string: Sets the environment variables in the container that the monitoring job runs. A list of key value pairs.
PostAnalyticsProcessorSourceUri string: An Amazon S3 URI to a script that is called after analysis has been performed. Applicable only for the built-in (first party) containers.
RecordPreprocessorSourceUri string: An Amazon S3 URI to a script that is called per row prior to running analysis. It can base64 decode the payload and convert it into a flatted json so that the built-in container can use the converted data. Applicable only for the built-in (first party) containers.

imageUri String: The container image that the data quality monitoring job runs.
environment Map<String,String>: Sets the environment variables in the container that the monitoring job runs. A list of key value pairs.
postAnalyticsProcessorSourceUri String: An Amazon S3 URI to a script that is called after analysis has been performed. Applicable only for the built-in (first party) containers.
recordPreprocessorSourceUri String: An Amazon S3 URI to a script that is called per row prior to running analysis. It can base64 decode the payload and convert it into a flatted json so that the built-in container can use the converted data. Applicable only for the built-in (first party) containers.

imageUri string: The container image that the data quality monitoring job runs.
environment {[key: string]: string}: Sets the environment variables in the container that the monitoring job runs. A list of key value pairs.
postAnalyticsProcessorSourceUri string: An Amazon S3 URI to a script that is called after analysis has been performed. Applicable only for the built-in (first party) containers.
recordPreprocessorSourceUri string: An Amazon S3 URI to a script that is called per row prior to running analysis. It can base64 decode the payload and convert it into a flatted json so that the built-in container can use the converted data. Applicable only for the built-in (first party) containers.

image_uri str: The container image that the data quality monitoring job runs.
environment Mapping[str, str]: Sets the environment variables in the container that the monitoring job runs. A list of key value pairs.
post_analytics_processor_source_uri str: An Amazon S3 URI to a script that is called after analysis has been performed. Applicable only for the built-in (first party) containers.
record_preprocessor_source_uri str: An Amazon S3 URI to a script that is called per row prior to running analysis. It can base64 decode the payload and convert it into a flatted json so that the built-in container can use the converted data. Applicable only for the built-in (first party) containers.

imageUri String: The container image that the data quality monitoring job runs.
environment Map<String>: Sets the environment variables in the container that the monitoring job runs. A list of key value pairs.
postAnalyticsProcessorSourceUri String: An Amazon S3 URI to a script that is called after analysis has been performed. Applicable only for the built-in (first party) containers.
recordPreprocessorSourceUri String: An Amazon S3 URI to a script that is called per row prior to running analysis. It can base64 decode the payload and convert it into a flatted json so that the built-in container can use the converted data. Applicable only for the built-in (first party) containers.

DataQualityJobDefinitionDataQualityBaselineConfig
, DataQualityJobDefinitionDataQualityBaselineConfigArgs

ConstraintsResource DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource: The constraints resource for a monitoring job. Fields are documented below.
StatisticsResource DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource: The statistics resource for a monitoring job. Fields are documented below.

ConstraintsResource DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource: The constraints resource for a monitoring job. Fields are documented below.
StatisticsResource DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource: The statistics resource for a monitoring job. Fields are documented below.

constraintsResource DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource: The constraints resource for a monitoring job. Fields are documented below.
statisticsResource DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource: The statistics resource for a monitoring job. Fields are documented below.

constraintsResource DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource: The constraints resource for a monitoring job. Fields are documented below.
statisticsResource DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource: The statistics resource for a monitoring job. Fields are documented below.

constraints_resource DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource: The constraints resource for a monitoring job. Fields are documented below.
statistics_resource DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource: The statistics resource for a monitoring job. Fields are documented below.

constraintsResource Property Map: The constraints resource for a monitoring job. Fields are documented below.
statisticsResource Property Map: The statistics resource for a monitoring job. Fields are documented below.

DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource
, DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs

S3Uri string: The Amazon S3 URI for the constraints resource.

S3Uri string: The Amazon S3 URI for the constraints resource.

s3Uri String: The Amazon S3 URI for the constraints resource.

s3Uri string: The Amazon S3 URI for the constraints resource.

s3_uri str: The Amazon S3 URI for the constraints resource.

s3Uri String: The Amazon S3 URI for the constraints resource.

DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource
, DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs

S3Uri string: The Amazon S3 URI for the statistics resource.

S3Uri string: The Amazon S3 URI for the statistics resource.

s3Uri String: The Amazon S3 URI for the statistics resource.

s3Uri string: The Amazon S3 URI for the statistics resource.

s3_uri str: The Amazon S3 URI for the statistics resource.

s3Uri String: The Amazon S3 URI for the statistics resource.

DataQualityJobDefinitionDataQualityJobInput
, DataQualityJobDefinitionDataQualityJobInputArgs

BatchTransformInput DataQualityJobDefinitionDataQualityJobInputBatchTransformInput: Input object for the batch transform job. Fields are documented below.
EndpointInput DataQualityJobDefinitionDataQualityJobInputEndpointInput: Input object for the endpoint. Fields are documented below.

BatchTransformInput DataQualityJobDefinitionDataQualityJobInputBatchTransformInput: Input object for the batch transform job. Fields are documented below.
EndpointInput DataQualityJobDefinitionDataQualityJobInputEndpointInput: Input object for the endpoint. Fields are documented below.

batchTransformInput DataQualityJobDefinitionDataQualityJobInputBatchTransformInput: Input object for the batch transform job. Fields are documented below.
endpointInput DataQualityJobDefinitionDataQualityJobInputEndpointInput: Input object for the endpoint. Fields are documented below.

batchTransformInput DataQualityJobDefinitionDataQualityJobInputBatchTransformInput: Input object for the batch transform job. Fields are documented below.
endpointInput DataQualityJobDefinitionDataQualityJobInputEndpointInput: Input object for the endpoint. Fields are documented below.

batch_transform_input DataQualityJobDefinitionDataQualityJobInputBatchTransformInput: Input object for the batch transform job. Fields are documented below.
endpoint_input DataQualityJobDefinitionDataQualityJobInputEndpointInput: Input object for the endpoint. Fields are documented below.

batchTransformInput Property Map: Input object for the batch transform job. Fields are documented below.
endpointInput Property Map: Input object for the endpoint. Fields are documented below.

DataQualityJobDefinitionDataQualityJobInputBatchTransformInput
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs

DataCapturedDestinationS3Uri string: The Amazon S3 location being used to capture the data.
DatasetFormat DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat: The dataset format for your batch transform job. Fields are documented below.
LocalPath string: Path to the filesystem where the batch transform data is available to the container. Defaults to /opt/ml/processing/input.
S3DataDistributionType string: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

DataCapturedDestinationS3Uri string: The Amazon S3 location being used to capture the data.
DatasetFormat DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat: The dataset format for your batch transform job. Fields are documented below.
LocalPath string: Path to the filesystem where the batch transform data is available to the container. Defaults to /opt/ml/processing/input.
S3DataDistributionType string: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

dataCapturedDestinationS3Uri String: The Amazon S3 location being used to capture the data.
datasetFormat DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat: The dataset format for your batch transform job. Fields are documented below.
localPath String: Path to the filesystem where the batch transform data is available to the container. Defaults to /opt/ml/processing/input.
s3DataDistributionType String: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

dataCapturedDestinationS3Uri string: The Amazon S3 location being used to capture the data.
datasetFormat DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat: The dataset format for your batch transform job. Fields are documented below.
localPath string: Path to the filesystem where the batch transform data is available to the container. Defaults to /opt/ml/processing/input.
s3DataDistributionType string: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

data_captured_destination_s3_uri str: The Amazon S3 location being used to capture the data.
dataset_format DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat: The dataset format for your batch transform job. Fields are documented below.
local_path str: Path to the filesystem where the batch transform data is available to the container. Defaults to /opt/ml/processing/input.
s3_data_distribution_type str: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
s3_input_mode str: 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. Valid values are Pipe or File

dataCapturedDestinationS3Uri String: The Amazon S3 location being used to capture the data.
datasetFormat Property Map: The dataset format for your batch transform job. Fields are documented below.
localPath String: Path to the filesystem where the batch transform data is available to the container. Defaults to /opt/ml/processing/input.
s3DataDistributionType String: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs

Csv DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv: The CSV dataset used in the monitoring job. Fields are documented below.
Json DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson: The JSON dataset used in the monitoring job. Fields are documented below.

Csv DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv: The CSV dataset used in the monitoring job. Fields are documented below.
Json DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson: The JSON dataset used in the monitoring job. Fields are documented below.

csv DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv: The CSV dataset used in the monitoring job. Fields are documented below.
json DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson: The JSON dataset used in the monitoring job. Fields are documented below.

csv DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv: The CSV dataset used in the monitoring job. Fields are documented below.
json DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson: The JSON dataset used in the monitoring job. Fields are documented below.

csv DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv: The CSV dataset used in the monitoring job. Fields are documented below.
json DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson: The JSON dataset used in the monitoring job. Fields are documented below.

csv Property Map: The CSV dataset used in the monitoring job. Fields are documented below.
json Property Map: The JSON dataset used in the monitoring job. Fields are documented below.

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs

Header bool: Indicates if the CSV data has a header.

Header bool: Indicates if the CSV data has a header.

header Boolean: Indicates if the CSV data has a header.

header boolean: Indicates if the CSV data has a header.

header bool: Indicates if the CSV data has a header.

header Boolean: Indicates if the CSV data has a header.

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs

Line bool: Indicates if the file should be read as a json object per line.

Line bool: Indicates if the file should be read as a json object per line.

line Boolean: Indicates if the file should be read as a json object per line.

line boolean: Indicates if the file should be read as a json object per line.

line bool: Indicates if the file should be read as a json object per line.

line Boolean: Indicates if the file should be read as a json object per line.

DataQualityJobDefinitionDataQualityJobInputEndpointInput
, DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs

EndpointName string: An endpoint in customer's account which has data_capture_config enabled.
LocalPath string: Path to the filesystem where the endpoint data is available to the container. Defaults to /opt/ml/processing/input.
S3DataDistributionType string: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

EndpointName string: An endpoint in customer's account which has data_capture_config enabled.
LocalPath string: Path to the filesystem where the endpoint data is available to the container. Defaults to /opt/ml/processing/input.
S3DataDistributionType string: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

endpointName String: An endpoint in customer's account which has data_capture_config enabled.
localPath String: Path to the filesystem where the endpoint data is available to the container. Defaults to /opt/ml/processing/input.
s3DataDistributionType String: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

endpointName string: An endpoint in customer's account which has data_capture_config enabled.
localPath string: Path to the filesystem where the endpoint data is available to the container. Defaults to /opt/ml/processing/input.
s3DataDistributionType string: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

endpoint_name str: An endpoint in customer's account which has data_capture_config enabled.
local_path str: Path to the filesystem where the endpoint data is available to the container. Defaults to /opt/ml/processing/input.
s3_data_distribution_type str: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
s3_input_mode str: 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. Valid values are Pipe or File

endpointName String: An endpoint in customer's account which has data_capture_config enabled.
localPath String: Path to the filesystem where the endpoint data is available to the container. Defaults to /opt/ml/processing/input.
s3DataDistributionType String: Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defaults to FullyReplicated. Valid values are FullyReplicated or ShardedByS3Key
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. Valid values are Pipe or File

DataQualityJobDefinitionDataQualityJobOutputConfig
, DataQualityJobDefinitionDataQualityJobOutputConfigArgs

MonitoringOutputs DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs: Monitoring outputs for monitoring jobs. This is where the output of the periodic monitoring jobs is uploaded. Fields are documented below.
KmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt the model artifacts at rest using Amazon S3 server-side encryption.

MonitoringOutputs DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs: Monitoring outputs for monitoring jobs. This is where the output of the periodic monitoring jobs is uploaded. Fields are documented below.
KmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt the model artifacts at rest using Amazon S3 server-side encryption.

monitoringOutputs DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs: Monitoring outputs for monitoring jobs. This is where the output of the periodic monitoring jobs is uploaded. Fields are documented below.
kmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt the model artifacts at rest using Amazon S3 server-side encryption.

monitoringOutputs DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs: Monitoring outputs for monitoring jobs. This is where the output of the periodic monitoring jobs is uploaded. Fields are documented below.
kmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt the model artifacts at rest using Amazon S3 server-side encryption.

monitoring_outputs DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs: Monitoring outputs for monitoring jobs. This is where the output of the periodic monitoring jobs is uploaded. Fields are documented below.
kms_key_id str: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt the model artifacts at rest using Amazon S3 server-side encryption.

monitoringOutputs Property Map: Monitoring outputs for monitoring jobs. This is where the output of the periodic monitoring jobs is uploaded. Fields are documented below.
kmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt the model artifacts at rest using Amazon S3 server-side encryption.

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs
, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs

S3Output DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output: The Amazon S3 storage location where the results of a monitoring job are saved. Fields are documented below.

S3Output DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output: The Amazon S3 storage location where the results of a monitoring job are saved. Fields are documented below.

s3Output DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output: The Amazon S3 storage location where the results of a monitoring job are saved. Fields are documented below.

s3Output DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output: The Amazon S3 storage location where the results of a monitoring job are saved. Fields are documented below.

s3_output DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output: The Amazon S3 storage location where the results of a monitoring job are saved. Fields are documented below.

s3Output Property Map: The Amazon S3 storage location where the results of a monitoring job are saved. Fields are documented below.

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output
, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs

S3Uri string: A URI that identifies the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job.
LocalPath string: The local path to the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job. LocalPath is an absolute path for the output data. Defaults to /opt/ml/processing/output.
S3UploadMode string: Whether to upload the results of the monitoring job continuously or after the job completes. Valid values are Continuous or EndOfJob

S3Uri string: A URI that identifies the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job.
LocalPath string: The local path to the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job. LocalPath is an absolute path for the output data. Defaults to /opt/ml/processing/output.
S3UploadMode string: Whether to upload the results of the monitoring job continuously or after the job completes. Valid values are Continuous or EndOfJob

s3Uri String: A URI that identifies the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job.
localPath String: The local path to the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job. LocalPath is an absolute path for the output data. Defaults to /opt/ml/processing/output.
s3UploadMode String: Whether to upload the results of the monitoring job continuously or after the job completes. Valid values are Continuous or EndOfJob

s3Uri string: A URI that identifies the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job.
localPath string: The local path to the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job. LocalPath is an absolute path for the output data. Defaults to /opt/ml/processing/output.
s3UploadMode string: Whether to upload the results of the monitoring job continuously or after the job completes. Valid values are Continuous or EndOfJob

s3_uri str: A URI that identifies the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job.
local_path str: The local path to the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job. LocalPath is an absolute path for the output data. Defaults to /opt/ml/processing/output.
s3_upload_mode str: Whether to upload the results of the monitoring job continuously or after the job completes. Valid values are Continuous or EndOfJob

s3Uri String: A URI that identifies the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job.
localPath String: The local path to the Amazon S3 storage location where Amazon SageMaker AI saves the results of a monitoring job. LocalPath is an absolute path for the output data. Defaults to /opt/ml/processing/output.
s3UploadMode String: Whether to upload the results of the monitoring job continuously or after the job completes. Valid values are Continuous or EndOfJob

DataQualityJobDefinitionJobResources
, DataQualityJobDefinitionJobResourcesArgs

ClusterConfig DataQualityJobDefinitionJobResourcesClusterConfig: The configuration for the cluster resources used to run the processing job. Fields are documented below.

ClusterConfig DataQualityJobDefinitionJobResourcesClusterConfig: The configuration for the cluster resources used to run the processing job. Fields are documented below.

clusterConfig DataQualityJobDefinitionJobResourcesClusterConfig: The configuration for the cluster resources used to run the processing job. Fields are documented below.

clusterConfig DataQualityJobDefinitionJobResourcesClusterConfig: The configuration for the cluster resources used to run the processing job. Fields are documented below.

cluster_config DataQualityJobDefinitionJobResourcesClusterConfig: The configuration for the cluster resources used to run the processing job. Fields are documented below.

clusterConfig Property Map: The configuration for the cluster resources used to run the processing job. Fields are documented below.

DataQualityJobDefinitionJobResourcesClusterConfig
, DataQualityJobDefinitionJobResourcesClusterConfigArgs

InstanceCount int: The number of ML compute instances to use in the model monitoring job. For distributed processing jobs, specify a value greater than 1.
InstanceType string: The ML compute instance type for the processing job.
VolumeSizeInGb int: The size of the ML storage volume, in gigabytes, that you want to provision. You must specify sufficient ML storage for your scenario.
VolumeKmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt data on the storage volume attached to the ML compute instance(s) that run the model monitoring job.

InstanceCount int: The number of ML compute instances to use in the model monitoring job. For distributed processing jobs, specify a value greater than 1.
InstanceType string: The ML compute instance type for the processing job.
VolumeSizeInGb int: The size of the ML storage volume, in gigabytes, that you want to provision. You must specify sufficient ML storage for your scenario.
VolumeKmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt data on the storage volume attached to the ML compute instance(s) that run the model monitoring job.

instanceCount Integer: The number of ML compute instances to use in the model monitoring job. For distributed processing jobs, specify a value greater than 1.
instanceType String: The ML compute instance type for the processing job.
volumeSizeInGb Integer: The size of the ML storage volume, in gigabytes, that you want to provision. You must specify sufficient ML storage for your scenario.
volumeKmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt data on the storage volume attached to the ML compute instance(s) that run the model monitoring job.

instanceCount number: The number of ML compute instances to use in the model monitoring job. For distributed processing jobs, specify a value greater than 1.
instanceType string: The ML compute instance type for the processing job.
volumeSizeInGb number: The size of the ML storage volume, in gigabytes, that you want to provision. You must specify sufficient ML storage for your scenario.
volumeKmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt data on the storage volume attached to the ML compute instance(s) that run the model monitoring job.

instance_count int: The number of ML compute instances to use in the model monitoring job. For distributed processing jobs, specify a value greater than 1.
instance_type str: The ML compute instance type for the processing job.
volume_size_in_gb int: The size of the ML storage volume, in gigabytes, that you want to provision. You must specify sufficient ML storage for your scenario.
volume_kms_key_id str: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt data on the storage volume attached to the ML compute instance(s) that run the model monitoring job.

instanceCount Number: The number of ML compute instances to use in the model monitoring job. For distributed processing jobs, specify a value greater than 1.
instanceType String: The ML compute instance type for the processing job.
volumeSizeInGb Number: The size of the ML storage volume, in gigabytes, that you want to provision. You must specify sufficient ML storage for your scenario.
volumeKmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker AI uses to encrypt data on the storage volume attached to the ML compute instance(s) that run the model monitoring job.

DataQualityJobDefinitionNetworkConfig
, DataQualityJobDefinitionNetworkConfigArgs

EnableInterContainerTrafficEncryption bool: Whether to encrypt all communications between the instances used for the monitoring jobs. Choose true to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.
EnableNetworkIsolation bool: Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.
VpcConfig DataQualityJobDefinitionNetworkConfigVpcConfig: Specifies a VPC that your training jobs and hosted models have access to. Control access to and from your training and model containers by configuring the VPC. Fields are documented below.

EnableInterContainerTrafficEncryption bool: Whether to encrypt all communications between the instances used for the monitoring jobs. Choose true to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.
EnableNetworkIsolation bool: Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.
VpcConfig DataQualityJobDefinitionNetworkConfigVpcConfig: Specifies a VPC that your training jobs and hosted models have access to. Control access to and from your training and model containers by configuring the VPC. Fields are documented below.

enableInterContainerTrafficEncryption Boolean: Whether to encrypt all communications between the instances used for the monitoring jobs. Choose true to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.
enableNetworkIsolation Boolean: Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.
vpcConfig DataQualityJobDefinitionNetworkConfigVpcConfig: Specifies a VPC that your training jobs and hosted models have access to. Control access to and from your training and model containers by configuring the VPC. Fields are documented below.

enableInterContainerTrafficEncryption boolean: Whether to encrypt all communications between the instances used for the monitoring jobs. Choose true to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.
enableNetworkIsolation boolean: Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.
vpcConfig DataQualityJobDefinitionNetworkConfigVpcConfig: Specifies a VPC that your training jobs and hosted models have access to. Control access to and from your training and model containers by configuring the VPC. Fields are documented below.

enable_inter_container_traffic_encryption bool: Whether to encrypt all communications between the instances used for the monitoring jobs. Choose true to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.
enable_network_isolation bool: Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.
vpc_config DataQualityJobDefinitionNetworkConfigVpcConfig: Specifies a VPC that your training jobs and hosted models have access to. Control access to and from your training and model containers by configuring the VPC. Fields are documented below.

enableInterContainerTrafficEncryption Boolean: Whether to encrypt all communications between the instances used for the monitoring jobs. Choose true to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.
enableNetworkIsolation Boolean: Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.
vpcConfig Property Map: Specifies a VPC that your training jobs and hosted models have access to. Control access to and from your training and model containers by configuring the VPC. Fields are documented below.

DataQualityJobDefinitionNetworkConfigVpcConfig
, DataQualityJobDefinitionNetworkConfigVpcConfigArgs

SecurityGroupIds List<string>: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the subnets field.
Subnets List<string>: The ID of the subnets in the VPC to which you want to connect your training job or model.

SecurityGroupIds []string: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the subnets field.
Subnets []string: The ID of the subnets in the VPC to which you want to connect your training job or model.

securityGroupIds List<String>: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the subnets field.
subnets List<String>: The ID of the subnets in the VPC to which you want to connect your training job or model.

securityGroupIds string[]: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the subnets field.
subnets string[]: The ID of the subnets in the VPC to which you want to connect your training job or model.

security_group_ids Sequence[str]: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the subnets field.
subnets Sequence[str]: The ID of the subnets in the VPC to which you want to connect your training job or model.

securityGroupIds List<String>: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the subnets field.
subnets List<String>: The ID of the subnets in the VPC to which you want to connect your training job or model.

DataQualityJobDefinitionStoppingCondition
, DataQualityJobDefinitionStoppingConditionArgs

MaxRuntimeInSeconds int: The maximum runtime allowed in seconds.

MaxRuntimeInSeconds int: The maximum runtime allowed in seconds.

maxRuntimeInSeconds Integer: The maximum runtime allowed in seconds.

maxRuntimeInSeconds number: The maximum runtime allowed in seconds.

max_runtime_in_seconds int: The maximum runtime allowed in seconds.

maxRuntimeInSeconds Number: The maximum runtime allowed in seconds.

Import

Using pulumi import, import data quality job definitions using the name. For example:

$ pulumi import aws:sagemaker/dataQualityJobDefinition:DataQualityJobDefinition test_data_quality_job_definition data-quality-job-definition-foo

To learn more about importing existing cloud resources, see Importing resources.

Package Details

Repository: AWS Classic pulumi/pulumi-aws
License: Apache-2.0
Notes: This Pulumi package is based on the aws Terraform Provider.

AWS v6.76.0 published on Tuesday, Apr 8, 2025 by Pulumi

pulumi/pulumi-aws

aws.sagemaker.DataQualityJobDefinition

On this page

On this page

Example Usage

Create DataQualityJobDefinition Resource

Constructor syntax

Parameters

Constructor example

DataQualityJobDefinition Resource Properties

Inputs

Outputs

Look up Existing DataQualityJobDefinition Resource

Supporting Types

DataQualityJobDefinitionDataQualityAppSpecification
, DataQualityJobDefinitionDataQualityAppSpecificationArgs

DataQualityJobDefinitionDataQualityBaselineConfig
, DataQualityJobDefinitionDataQualityBaselineConfigArgs

DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource
, DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs

DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource
, DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs

DataQualityJobDefinitionDataQualityJobInput
, DataQualityJobDefinitionDataQualityJobInputArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInput
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs

DataQualityJobDefinitionDataQualityJobInputEndpointInput
, DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs

DataQualityJobDefinitionDataQualityJobOutputConfig
, DataQualityJobDefinitionDataQualityJobOutputConfigArgs

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs
, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output
, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs

DataQualityJobDefinitionJobResources
, DataQualityJobDefinitionJobResourcesArgs

DataQualityJobDefinitionJobResourcesClusterConfig
, DataQualityJobDefinitionJobResourcesClusterConfigArgs

DataQualityJobDefinitionNetworkConfig
, DataQualityJobDefinitionNetworkConfigArgs

DataQualityJobDefinitionNetworkConfigVpcConfig
, DataQualityJobDefinitionNetworkConfigVpcConfigArgs

DataQualityJobDefinitionStoppingCondition
, DataQualityJobDefinitionStoppingConditionArgs

Import

Package Details

On this page

On this page

aws.sagemaker.DataQualityJobDefinition

On this page

On this page

Example Usage

Create DataQualityJobDefinition Resource

Constructor syntax

Parameters

Constructor example

DataQualityJobDefinition Resource Properties

Inputs

Outputs

Look up Existing DataQualityJobDefinition Resource

Supporting Types

DataQualityJobDefinitionDataQualityAppSpecification, DataQualityJobDefinitionDataQualityAppSpecificationArgs

DataQualityJobDefinitionDataQualityBaselineConfig, DataQualityJobDefinitionDataQualityBaselineConfigArgs

DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource, DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs

DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource, DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs

DataQualityJobDefinitionDataQualityJobInput, DataQualityJobDefinitionDataQualityJobInputArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInput, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs

DataQualityJobDefinitionDataQualityJobInputEndpointInput, DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs

DataQualityJobDefinitionDataQualityJobOutputConfig, DataQualityJobDefinitionDataQualityJobOutputConfigArgs

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs

DataQualityJobDefinitionJobResources, DataQualityJobDefinitionJobResourcesArgs

DataQualityJobDefinitionJobResourcesClusterConfig, DataQualityJobDefinitionJobResourcesClusterConfigArgs

DataQualityJobDefinitionNetworkConfig, DataQualityJobDefinitionNetworkConfigArgs

DataQualityJobDefinitionNetworkConfigVpcConfig, DataQualityJobDefinitionNetworkConfigVpcConfigArgs

DataQualityJobDefinitionStoppingCondition, DataQualityJobDefinitionStoppingConditionArgs

Import

Package Details

On this page

On this page

DataQualityJobDefinitionDataQualityAppSpecification
, DataQualityJobDefinitionDataQualityAppSpecificationArgs

DataQualityJobDefinitionDataQualityBaselineConfig
, DataQualityJobDefinitionDataQualityBaselineConfigArgs

DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResource
, DataQualityJobDefinitionDataQualityBaselineConfigConstraintsResourceArgs

DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResource
, DataQualityJobDefinitionDataQualityBaselineConfigStatisticsResourceArgs

DataQualityJobDefinitionDataQualityJobInput
, DataQualityJobDefinitionDataQualityJobInputArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInput
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormat
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsv
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatCsvArgs

DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJson
, DataQualityJobDefinitionDataQualityJobInputBatchTransformInputDatasetFormatJsonArgs

DataQualityJobDefinitionDataQualityJobInputEndpointInput
, DataQualityJobDefinitionDataQualityJobInputEndpointInputArgs

DataQualityJobDefinitionDataQualityJobOutputConfig
, DataQualityJobDefinitionDataQualityJobOutputConfigArgs

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputs
, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsArgs

DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3Output
, DataQualityJobDefinitionDataQualityJobOutputConfigMonitoringOutputsS3OutputArgs

DataQualityJobDefinitionJobResources
, DataQualityJobDefinitionJobResourcesArgs

DataQualityJobDefinitionJobResourcesClusterConfig
, DataQualityJobDefinitionJobResourcesClusterConfigArgs

DataQualityJobDefinitionNetworkConfig
, DataQualityJobDefinitionNetworkConfigArgs

DataQualityJobDefinitionNetworkConfigVpcConfig
, DataQualityJobDefinitionNetworkConfigVpcConfigArgs

DataQualityJobDefinitionStoppingCondition
, DataQualityJobDefinitionStoppingConditionArgs