AthenaProcessingJobBoto3Example.py

response = client.create_processing_job(
    ProcessingInputs=[
        {
            'InputName': 'data',
            'DatasetDefinition': {
                'AthenaDatasetDefinition': {
                    'Catalog': 'AwsDataCatalog',
                    'Database': 'link',
                    'QueryString': 'SELECT * FROM "link"."dl_tpc_customer"',
                    'WorkGroup': 'primary',
                    'OutputS3Uri': 's3://sagemaker-studio-w16ttswarb/',
                    'OutputFormat': 'PARQUET'
                },
                'LocalPath': '/opt/ml/processing/input/dataset.parquet'
            }
        },
        {
            'InputName': 'code',
            'AppManaged': False,
            'S3Input': {
                'S3Uri': 's3://sagemaker-studio-w16ttswarb/processingCode/',
                'LocalPath': '/opt/ml/processing/input/code',
                'S3DataType': 'S3Prefix',
                'S3InputMode': 'File',
                'S3DataDistributionType': 'FullyReplicated'
            },
        },
    ],
    ProcessingOutputConfig={
        'Outputs': [
            {
                'OutputName': 'OutputProcessingJobAthenaTrain',
                'S3Output': {
                    'S3Uri': 's3://sagemaker-studio-w16ttswarb/processingJobOutput/',
                    'LocalPath': '/opt/ml/processing/output/',
                    'S3UploadMode': 'EndOfJob'
                },
            }
        ],
    },
    ProcessingJobName='processingJobAthenaBoto19',
    ProcessingResources={
        'ClusterConfig': {
            'InstanceCount': 1,
            'InstanceType': 'ml.t3.large',
            'VolumeSizeInGB': 15
        }
    },
    AppSpecification={
        'ImageUri': '683313688378.dkr.ecr.us-east-1.amazonaws.com/sagemaker-scikit-learn:0.23-1-cpu-py3',
        'ContainerEntrypoint': ['python3', '/opt/ml/processing/input/code/preprocessing.py']
    },

    RoleArn='YOUR ROLE',
)