Docs Home Pulumi IaC Pulumi ESC Pulumi Cloud Packages Tutorials
  1. Packages
  2. AWS
  3. API Docs
  4. glue
  5. MLTransform
AWS v6.72.0 published on Tuesday, Mar 11, 2025 by Pulumi
pulumi/pulumi-aws

aws.glue.MLTransform

Explore with Pulumi AI

aws logo
AWS v6.72.0 published on Tuesday, Mar 11, 2025 by Pulumi
pulumi/pulumi-aws

    Provides a Glue ML Transform resource.

    Example Usage

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

const testCatalogDatabase = new aws.glue.CatalogDatabase("test", {name: "example"});
const testCatalogTable = new aws.glue.CatalogTable("test", {
    name: "example",
    databaseName: testCatalogDatabase.name,
    owner: "my_owner",
    retention: 1,
    tableType: "VIRTUAL_VIEW",
    viewExpandedText: "view_expanded_text_1",
    viewOriginalText: "view_original_text_1",
    storageDescriptor: {
        bucketColumns: ["bucket_column_1"],
        compressed: false,
        inputFormat: "SequenceFileInputFormat",
        location: "my_location",
        numberOfBuckets: 1,
        outputFormat: "SequenceFileInputFormat",
        storedAsSubDirectories: false,
        parameters: {
            param1: "param1_val",
        },
        columns: [
            {
                name: "my_column_1",
                type: "int",
                comment: "my_column1_comment",
            },
            {
                name: "my_column_2",
                type: "string",
                comment: "my_column2_comment",
            },
        ],
        serDeInfo: {
            name: "ser_de_name",
            parameters: {
                param1: "param_val_1",
            },
            serializationLibrary: "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe",
        },
        sortColumns: [{
            column: "my_column_1",
            sortOrder: 1,
        }],
        skewedInfo: {
            skewedColumnNames: ["my_column_1"],
            skewedColumnValueLocationMaps: {
                my_column_1: "my_column_1_val_loc_map",
            },
            skewedColumnValues: ["skewed_val_1"],
        },
    },
    partitionKeys: [
        {
            name: "my_column_1",
            type: "int",
            comment: "my_column_1_comment",
        },
        {
            name: "my_column_2",
            type: "string",
            comment: "my_column_2_comment",
        },
    ],
    parameters: {
        param1: "param1_val",
    },
});
const test = new aws.glue.MLTransform("test", {
    name: "example",
    roleArn: testAwsIamRole.arn,
    inputRecordTables: [{
        databaseName: testCatalogTable.databaseName,
        tableName: testCatalogTable.name,
    }],
    parameters: {
        transformType: "FIND_MATCHES",
        findMatchesParameters: {
            primaryKeyColumnName: "my_column_1",
        },
    },
}, {
    dependsOn: [testAwsIamRolePolicyAttachment],
});

    import pulumi
import pulumi_aws as aws

test_catalog_database = aws.glue.CatalogDatabase("test", name="example")
test_catalog_table = aws.glue.CatalogTable("test",
    name="example",
    database_name=test_catalog_database.name,
    owner="my_owner",
    retention=1,
    table_type="VIRTUAL_VIEW",
    view_expanded_text="view_expanded_text_1",
    view_original_text="view_original_text_1",
    storage_descriptor={
        "bucket_columns": ["bucket_column_1"],
        "compressed": False,
        "input_format": "SequenceFileInputFormat",
        "location": "my_location",
        "number_of_buckets": 1,
        "output_format": "SequenceFileInputFormat",
        "stored_as_sub_directories": False,
        "parameters": {
            "param1": "param1_val",
        },
        "columns": [
            {
                "name": "my_column_1",
                "type": "int",
                "comment": "my_column1_comment",
            },
            {
                "name": "my_column_2",
                "type": "string",
                "comment": "my_column2_comment",
            },
        ],
        "ser_de_info": {
            "name": "ser_de_name",
            "parameters": {
                "param1": "param_val_1",
            },
            "serialization_library": "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe",
        },
        "sort_columns": [{
            "column": "my_column_1",
            "sort_order": 1,
        }],
        "skewed_info": {
            "skewed_column_names": ["my_column_1"],
            "skewed_column_value_location_maps": {
                "my_column_1": "my_column_1_val_loc_map",
            },
            "skewed_column_values": ["skewed_val_1"],
        },
    },
    partition_keys=[
        {
            "name": "my_column_1",
            "type": "int",
            "comment": "my_column_1_comment",
        },
        {
            "name": "my_column_2",
            "type": "string",
            "comment": "my_column_2_comment",
        },
    ],
    parameters={
        "param1": "param1_val",
    })
test = aws.glue.MLTransform("test",
    name="example",
    role_arn=test_aws_iam_role["arn"],
    input_record_tables=[{
        "database_name": test_catalog_table.database_name,
        "table_name": test_catalog_table.name,
    }],
    parameters={
        "transform_type": "FIND_MATCHES",
        "find_matches_parameters": {
            "primary_key_column_name": "my_column_1",
        },
    },
    opts = pulumi.ResourceOptions(depends_on=[test_aws_iam_role_policy_attachment]))

    package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/glue"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		testCatalogDatabase, err := glue.NewCatalogDatabase(ctx, "test", &glue.CatalogDatabaseArgs{
			Name: pulumi.String("example"),
		})
		if err != nil {
			return err
		}
		testCatalogTable, err := glue.NewCatalogTable(ctx, "test", &glue.CatalogTableArgs{
			Name:             pulumi.String("example"),
			DatabaseName:     testCatalogDatabase.Name,
			Owner:            pulumi.String("my_owner"),
			Retention:        pulumi.Int(1),
			TableType:        pulumi.String("VIRTUAL_VIEW"),
			ViewExpandedText: pulumi.String("view_expanded_text_1"),
			ViewOriginalText: pulumi.String("view_original_text_1"),
			StorageDescriptor: &glue.CatalogTableStorageDescriptorArgs{
				BucketColumns: pulumi.StringArray{
					pulumi.String("bucket_column_1"),
				},
				Compressed:             pulumi.Bool(false),
				InputFormat:            pulumi.String("SequenceFileInputFormat"),
				Location:               pulumi.String("my_location"),
				NumberOfBuckets:        pulumi.Int(1),
				OutputFormat:           pulumi.String("SequenceFileInputFormat"),
				StoredAsSubDirectories: pulumi.Bool(false),
				Parameters: pulumi.StringMap{
					"param1": pulumi.String("param1_val"),
				},
				Columns: glue.CatalogTableStorageDescriptorColumnArray{
					&glue.CatalogTableStorageDescriptorColumnArgs{
						Name:    pulumi.String("my_column_1"),
						Type:    pulumi.String("int"),
						Comment: pulumi.String("my_column1_comment"),
					},
					&glue.CatalogTableStorageDescriptorColumnArgs{
						Name:    pulumi.String("my_column_2"),
						Type:    pulumi.String("string"),
						Comment: pulumi.String("my_column2_comment"),
					},
				},
				SerDeInfo: &glue.CatalogTableStorageDescriptorSerDeInfoArgs{
					Name: pulumi.String("ser_de_name"),
					Parameters: pulumi.StringMap{
						"param1": pulumi.String("param_val_1"),
					},
					SerializationLibrary: pulumi.String("org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe"),
				},
				SortColumns: glue.CatalogTableStorageDescriptorSortColumnArray{
					&glue.CatalogTableStorageDescriptorSortColumnArgs{
						Column:    pulumi.String("my_column_1"),
						SortOrder: pulumi.Int(1),
					},
				},
				SkewedInfo: &glue.CatalogTableStorageDescriptorSkewedInfoArgs{
					SkewedColumnNames: pulumi.StringArray{
						pulumi.String("my_column_1"),
					},
					SkewedColumnValueLocationMaps: pulumi.StringMap{
						"my_column_1": pulumi.String("my_column_1_val_loc_map"),
					},
					SkewedColumnValues: pulumi.StringArray{
						pulumi.String("skewed_val_1"),
					},
				},
			},
			PartitionKeys: glue.CatalogTablePartitionKeyArray{
				&glue.CatalogTablePartitionKeyArgs{
					Name:    pulumi.String("my_column_1"),
					Type:    pulumi.String("int"),
					Comment: pulumi.String("my_column_1_comment"),
				},
				&glue.CatalogTablePartitionKeyArgs{
					Name:    pulumi.String("my_column_2"),
					Type:    pulumi.String("string"),
					Comment: pulumi.String("my_column_2_comment"),
				},
			},
			Parameters: pulumi.StringMap{
				"param1": pulumi.String("param1_val"),
			},
		})
		if err != nil {
			return err
		}
		_, err = glue.NewMLTransform(ctx, "test", &glue.MLTransformArgs{
			Name:    pulumi.String("example"),
			RoleArn: pulumi.Any(testAwsIamRole.Arn),
			InputRecordTables: glue.MLTransformInputRecordTableArray{
				&glue.MLTransformInputRecordTableArgs{
					DatabaseName: testCatalogTable.DatabaseName,
					TableName:    testCatalogTable.Name,
				},
			},
			Parameters: &glue.MLTransformParametersArgs{
				TransformType: pulumi.String("FIND_MATCHES"),
				FindMatchesParameters: &glue.MLTransformParametersFindMatchesParametersArgs{
					PrimaryKeyColumnName: pulumi.String("my_column_1"),
				},
			},
		}, pulumi.DependsOn([]pulumi.Resource{
			testAwsIamRolePolicyAttachment,
		}))
		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 testCatalogDatabase = new Aws.Glue.CatalogDatabase("test", new()
    {
        Name = "example",
    });

    var testCatalogTable = new Aws.Glue.CatalogTable("test", new()
    {
        Name = "example",
        DatabaseName = testCatalogDatabase.Name,
        Owner = "my_owner",
        Retention = 1,
        TableType = "VIRTUAL_VIEW",
        ViewExpandedText = "view_expanded_text_1",
        ViewOriginalText = "view_original_text_1",
        StorageDescriptor = new Aws.Glue.Inputs.CatalogTableStorageDescriptorArgs
        {
            BucketColumns = new[]
            {
                "bucket_column_1",
            },
            Compressed = false,
            InputFormat = "SequenceFileInputFormat",
            Location = "my_location",
            NumberOfBuckets = 1,
            OutputFormat = "SequenceFileInputFormat",
            StoredAsSubDirectories = false,
            Parameters = 
            {
                { "param1", "param1_val" },
            },
            Columns = new[]
            {
                new Aws.Glue.Inputs.CatalogTableStorageDescriptorColumnArgs
                {
                    Name = "my_column_1",
                    Type = "int",
                    Comment = "my_column1_comment",
                },
                new Aws.Glue.Inputs.CatalogTableStorageDescriptorColumnArgs
                {
                    Name = "my_column_2",
                    Type = "string",
                    Comment = "my_column2_comment",
                },
            },
            SerDeInfo = new Aws.Glue.Inputs.CatalogTableStorageDescriptorSerDeInfoArgs
            {
                Name = "ser_de_name",
                Parameters = 
                {
                    { "param1", "param_val_1" },
                },
                SerializationLibrary = "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe",
            },
            SortColumns = new[]
            {
                new Aws.Glue.Inputs.CatalogTableStorageDescriptorSortColumnArgs
                {
                    Column = "my_column_1",
                    SortOrder = 1,
                },
            },
            SkewedInfo = new Aws.Glue.Inputs.CatalogTableStorageDescriptorSkewedInfoArgs
            {
                SkewedColumnNames = new[]
                {
                    "my_column_1",
                },
                SkewedColumnValueLocationMaps = 
                {
                    { "my_column_1", "my_column_1_val_loc_map" },
                },
                SkewedColumnValues = new[]
                {
                    "skewed_val_1",
                },
            },
        },
        PartitionKeys = new[]
        {
            new Aws.Glue.Inputs.CatalogTablePartitionKeyArgs
            {
                Name = "my_column_1",
                Type = "int",
                Comment = "my_column_1_comment",
            },
            new Aws.Glue.Inputs.CatalogTablePartitionKeyArgs
            {
                Name = "my_column_2",
                Type = "string",
                Comment = "my_column_2_comment",
            },
        },
        Parameters = 
        {
            { "param1", "param1_val" },
        },
    });

    var test = new Aws.Glue.MLTransform("test", new()
    {
        Name = "example",
        RoleArn = testAwsIamRole.Arn,
        InputRecordTables = new[]
        {
            new Aws.Glue.Inputs.MLTransformInputRecordTableArgs
            {
                DatabaseName = testCatalogTable.DatabaseName,
                TableName = testCatalogTable.Name,
            },
        },
        Parameters = new Aws.Glue.Inputs.MLTransformParametersArgs
        {
            TransformType = "FIND_MATCHES",
            FindMatchesParameters = new Aws.Glue.Inputs.MLTransformParametersFindMatchesParametersArgs
            {
                PrimaryKeyColumnName = "my_column_1",
            },
        },
    }, new CustomResourceOptions
    {
        DependsOn =
        {
            testAwsIamRolePolicyAttachment,
        },
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.glue.CatalogDatabase;
import com.pulumi.aws.glue.CatalogDatabaseArgs;
import com.pulumi.aws.glue.CatalogTable;
import com.pulumi.aws.glue.CatalogTableArgs;
import com.pulumi.aws.glue.inputs.CatalogTableStorageDescriptorArgs;
import com.pulumi.aws.glue.inputs.CatalogTableStorageDescriptorSerDeInfoArgs;
import com.pulumi.aws.glue.inputs.CatalogTableStorageDescriptorSkewedInfoArgs;
import com.pulumi.aws.glue.inputs.CatalogTablePartitionKeyArgs;
import com.pulumi.aws.glue.MLTransform;
import com.pulumi.aws.glue.MLTransformArgs;
import com.pulumi.aws.glue.inputs.MLTransformInputRecordTableArgs;
import com.pulumi.aws.glue.inputs.MLTransformParametersArgs;
import com.pulumi.aws.glue.inputs.MLTransformParametersFindMatchesParametersArgs;
import com.pulumi.resources.CustomResourceOptions;
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 testCatalogDatabase = new CatalogDatabase("testCatalogDatabase", CatalogDatabaseArgs.builder()
            .name("example")
            .build());

        var testCatalogTable = new CatalogTable("testCatalogTable", CatalogTableArgs.builder()
            .name("example")
            .databaseName(testCatalogDatabase.name())
            .owner("my_owner")
            .retention(1)
            .tableType("VIRTUAL_VIEW")
            .viewExpandedText("view_expanded_text_1")
            .viewOriginalText("view_original_text_1")
            .storageDescriptor(CatalogTableStorageDescriptorArgs.builder()
                .bucketColumns("bucket_column_1")
                .compressed(false)
                .inputFormat("SequenceFileInputFormat")
                .location("my_location")
                .numberOfBuckets(1)
                .outputFormat("SequenceFileInputFormat")
                .storedAsSubDirectories(false)
                .parameters(Map.of("param1", "param1_val"))
                .columns(                
                    CatalogTableStorageDescriptorColumnArgs.builder()
                        .name("my_column_1")
                        .type("int")
                        .comment("my_column1_comment")
                        .build(),
                    CatalogTableStorageDescriptorColumnArgs.builder()
                        .name("my_column_2")
                        .type("string")
                        .comment("my_column2_comment")
                        .build())
                .serDeInfo(CatalogTableStorageDescriptorSerDeInfoArgs.builder()
                    .name("ser_de_name")
                    .parameters(Map.of("param1", "param_val_1"))
                    .serializationLibrary("org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe")
                    .build())
                .sortColumns(CatalogTableStorageDescriptorSortColumnArgs.builder()
                    .column("my_column_1")
                    .sortOrder(1)
                    .build())
                .skewedInfo(CatalogTableStorageDescriptorSkewedInfoArgs.builder()
                    .skewedColumnNames("my_column_1")
                    .skewedColumnValueLocationMaps(Map.of("my_column_1", "my_column_1_val_loc_map"))
                    .skewedColumnValues("skewed_val_1")
                    .build())
                .build())
            .partitionKeys(            
                CatalogTablePartitionKeyArgs.builder()
                    .name("my_column_1")
                    .type("int")
                    .comment("my_column_1_comment")
                    .build(),
                CatalogTablePartitionKeyArgs.builder()
                    .name("my_column_2")
                    .type("string")
                    .comment("my_column_2_comment")
                    .build())
            .parameters(Map.of("param1", "param1_val"))
            .build());

        var test = new MLTransform("test", MLTransformArgs.builder()
            .name("example")
            .roleArn(testAwsIamRole.arn())
            .inputRecordTables(MLTransformInputRecordTableArgs.builder()
                .databaseName(testCatalogTable.databaseName())
                .tableName(testCatalogTable.name())
                .build())
            .parameters(MLTransformParametersArgs.builder()
                .transformType("FIND_MATCHES")
                .findMatchesParameters(MLTransformParametersFindMatchesParametersArgs.builder()
                    .primaryKeyColumnName("my_column_1")
                    .build())
                .build())
            .build(), CustomResourceOptions.builder()
                .dependsOn(testAwsIamRolePolicyAttachment)
                .build());

    }
}

    resources:
  test:
    type: aws:glue:MLTransform
    properties:
      name: example
      roleArn: ${testAwsIamRole.arn}
      inputRecordTables:
        - databaseName: ${testCatalogTable.databaseName}
          tableName: ${testCatalogTable.name}
      parameters:
        transformType: FIND_MATCHES
        findMatchesParameters:
          primaryKeyColumnName: my_column_1
    options:
      dependsOn:
        - ${testAwsIamRolePolicyAttachment}
  testCatalogDatabase:
    type: aws:glue:CatalogDatabase
    name: test
    properties:
      name: example
  testCatalogTable:
    type: aws:glue:CatalogTable
    name: test
    properties:
      name: example
      databaseName: ${testCatalogDatabase.name}
      owner: my_owner
      retention: 1
      tableType: VIRTUAL_VIEW
      viewExpandedText: view_expanded_text_1
      viewOriginalText: view_original_text_1
      storageDescriptor:
        bucketColumns:
          - bucket_column_1
        compressed: false
        inputFormat: SequenceFileInputFormat
        location: my_location
        numberOfBuckets: 1
        outputFormat: SequenceFileInputFormat
        storedAsSubDirectories: false
        parameters:
          param1: param1_val
        columns:
          - name: my_column_1
            type: int
            comment: my_column1_comment
          - name: my_column_2
            type: string
            comment: my_column2_comment
        serDeInfo:
          name: ser_de_name
          parameters:
            param1: param_val_1
          serializationLibrary: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
        sortColumns:
          - column: my_column_1
            sortOrder: 1
        skewedInfo:
          skewedColumnNames:
            - my_column_1
          skewedColumnValueLocationMaps:
            my_column_1: my_column_1_val_loc_map
          skewedColumnValues:
            - skewed_val_1
      partitionKeys:
        - name: my_column_1
          type: int
          comment: my_column_1_comment
        - name: my_column_2
          type: string
          comment: my_column_2_comment
      parameters:
        param1: param1_val

    Create MLTransform Resource

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

    Constructor syntax

    new MLTransform(name: string, args: MLTransformArgs, opts?: CustomResourceOptions);
    @overload
def MLTransform(resource_name: str,
                args: MLTransformArgs,
                opts: Optional[ResourceOptions] = None)

@overload
def MLTransform(resource_name: str,
                opts: Optional[ResourceOptions] = None,
                input_record_tables: Optional[Sequence[MLTransformInputRecordTableArgs]] = None,
                parameters: Optional[MLTransformParametersArgs] = None,
                role_arn: Optional[str] = None,
                description: Optional[str] = None,
                glue_version: Optional[str] = None,
                max_capacity: Optional[float] = None,
                max_retries: Optional[int] = None,
                name: Optional[str] = None,
                number_of_workers: Optional[int] = None,
                tags: Optional[Mapping[str, str]] = None,
                timeout: Optional[int] = None,
                worker_type: Optional[str] = None)
    func NewMLTransform(ctx *Context, name string, args MLTransformArgs, opts ...ResourceOption) (*MLTransform, error)
    public MLTransform(string name, MLTransformArgs args, CustomResourceOptions? opts = null)
    public MLTransform(String name, MLTransformArgs args)
public MLTransform(String name, MLTransformArgs args, CustomResourceOptions options)

    type: aws:glue:MLTransform
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 MLTransformArgs
    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 MLTransformArgs
    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 MLTransformArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args MLTransformArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args MLTransformArgs
    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.

    var mltransformResource = new Aws.Glue.MLTransform("mltransformResource", new()
{
    InputRecordTables = new[]
    {
        new Aws.Glue.Inputs.MLTransformInputRecordTableArgs
        {
            DatabaseName = "string",
            TableName = "string",
            CatalogId = "string",
            ConnectionName = "string",
        },
    },
    Parameters = new Aws.Glue.Inputs.MLTransformParametersArgs
    {
        FindMatchesParameters = new Aws.Glue.Inputs.MLTransformParametersFindMatchesParametersArgs
        {
            AccuracyCostTradeOff = 0,
            EnforceProvidedLabels = false,
            PrecisionRecallTradeOff = 0,
            PrimaryKeyColumnName = "string",
        },
        TransformType = "string",
    },
    RoleArn = "string",
    Description = "string",
    GlueVersion = "string",
    MaxCapacity = 0,
    MaxRetries = 0,
    Name = "string",
    NumberOfWorkers = 0,
    Tags = 
    {
        { "string", "string" },
    },
    Timeout = 0,
    WorkerType = "string",
});

    example, err := glue.NewMLTransform(ctx, "mltransformResource", &glue.MLTransformArgs{
	InputRecordTables: glue.MLTransformInputRecordTableArray{
		&glue.MLTransformInputRecordTableArgs{
			DatabaseName:   pulumi.String("string"),
			TableName:      pulumi.String("string"),
			CatalogId:      pulumi.String("string"),
			ConnectionName: pulumi.String("string"),
		},
	},
	Parameters: &glue.MLTransformParametersArgs{
		FindMatchesParameters: &glue.MLTransformParametersFindMatchesParametersArgs{
			AccuracyCostTradeOff:    pulumi.Float64(0),
			EnforceProvidedLabels:   pulumi.Bool(false),
			PrecisionRecallTradeOff: pulumi.Float64(0),
			PrimaryKeyColumnName:    pulumi.String("string"),
		},
		TransformType: pulumi.String("string"),
	},
	RoleArn:         pulumi.String("string"),
	Description:     pulumi.String("string"),
	GlueVersion:     pulumi.String("string"),
	MaxCapacity:     pulumi.Float64(0),
	MaxRetries:      pulumi.Int(0),
	Name:            pulumi.String("string"),
	NumberOfWorkers: pulumi.Int(0),
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
	Timeout:    pulumi.Int(0),
	WorkerType: pulumi.String("string"),
})

    var mltransformResource = new MLTransform("mltransformResource", MLTransformArgs.builder()
    .inputRecordTables(MLTransformInputRecordTableArgs.builder()
        .databaseName("string")
        .tableName("string")
        .catalogId("string")
        .connectionName("string")
        .build())
    .parameters(MLTransformParametersArgs.builder()
        .findMatchesParameters(MLTransformParametersFindMatchesParametersArgs.builder()
            .accuracyCostTradeOff(0)
            .enforceProvidedLabels(false)
            .precisionRecallTradeOff(0)
            .primaryKeyColumnName("string")
            .build())
        .transformType("string")
        .build())
    .roleArn("string")
    .description("string")
    .glueVersion("string")
    .maxCapacity(0)
    .maxRetries(0)
    .name("string")
    .numberOfWorkers(0)
    .tags(Map.of("string", "string"))
    .timeout(0)
    .workerType("string")
    .build());

    mltransform_resource = aws.glue.MLTransform("mltransformResource",
    input_record_tables=[{
        "database_name": "string",
        "table_name": "string",
        "catalog_id": "string",
        "connection_name": "string",
    }],
    parameters={
        "find_matches_parameters": {
            "accuracy_cost_trade_off": 0,
            "enforce_provided_labels": False,
            "precision_recall_trade_off": 0,
            "primary_key_column_name": "string",
        },
        "transform_type": "string",
    },
    role_arn="string",
    description="string",
    glue_version="string",
    max_capacity=0,
    max_retries=0,
    name="string",
    number_of_workers=0,
    tags={
        "string": "string",
    },
    timeout=0,
    worker_type="string")

    const mltransformResource = new aws.glue.MLTransform("mltransformResource", {
    inputRecordTables: [{
        databaseName: "string",
        tableName: "string",
        catalogId: "string",
        connectionName: "string",
    }],
    parameters: {
        findMatchesParameters: {
            accuracyCostTradeOff: 0,
            enforceProvidedLabels: false,
            precisionRecallTradeOff: 0,
            primaryKeyColumnName: "string",
        },
        transformType: "string",
    },
    roleArn: "string",
    description: "string",
    glueVersion: "string",
    maxCapacity: 0,
    maxRetries: 0,
    name: "string",
    numberOfWorkers: 0,
    tags: {
        string: "string",
    },
    timeout: 0,
    workerType: "string",
});

    type: aws:glue:MLTransform
properties:
    description: string
    glueVersion: string
    inputRecordTables:
        - catalogId: string
          connectionName: string
          databaseName: string
          tableName: string
    maxCapacity: 0
    maxRetries: 0
    name: string
    numberOfWorkers: 0
    parameters:
        findMatchesParameters:
            accuracyCostTradeOff: 0
            enforceProvidedLabels: false
            precisionRecallTradeOff: 0
            primaryKeyColumnName: string
        transformType: string
    roleArn: string
    tags:
        string: string
    timeout: 0
    workerType: string

    MLTransform 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 MLTransform resource accepts the following input properties:

    InputRecordTables List<MLTransformInputRecordTable>
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    Parameters MLTransformParameters
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    RoleArn string
    The ARN of the IAM role associated with this ML Transform.
    Description string
    Description of the ML Transform.
    GlueVersion string
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    MaxCapacity double
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    MaxRetries int
    The maximum number of times to retry this ML Transform if it fails.
    Name string
    The name you assign to this ML Transform. It must be unique in your account.
    NumberOfWorkers int
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    Tags Dictionary<string, string>
    Key-value map of resource tags. .If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    Timeout int
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    WorkerType string
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    InputRecordTables []MLTransformInputRecordTableArgs
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    Parameters MLTransformParametersArgs
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    RoleArn string
    The ARN of the IAM role associated with this ML Transform.
    Description string
    Description of the ML Transform.
    GlueVersion string
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    MaxCapacity float64
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    MaxRetries int
    The maximum number of times to retry this ML Transform if it fails.
    Name string
    The name you assign to this ML Transform. It must be unique in your account.
    NumberOfWorkers int
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    Tags map[string]string
    Key-value map of resource tags. .If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    Timeout int
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    WorkerType string
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    inputRecordTables List<MLTransformInputRecordTable>
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    parameters MLTransformParameters
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    roleArn String
    The ARN of the IAM role associated with this ML Transform.
    description String
    Description of the ML Transform.
    glueVersion String
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    maxCapacity Double
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    maxRetries Integer
    The maximum number of times to retry this ML Transform if it fails.
    name String
    The name you assign to this ML Transform. It must be unique in your account.
    numberOfWorkers Integer
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    tags Map<String,String>
    Key-value map of resource tags. .If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeout Integer
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    workerType String
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    inputRecordTables MLTransformInputRecordTable[]
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    parameters MLTransformParameters
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    roleArn string
    The ARN of the IAM role associated with this ML Transform.
    description string
    Description of the ML Transform.
    glueVersion string
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    maxCapacity number
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    maxRetries number
    The maximum number of times to retry this ML Transform if it fails.
    name string
    The name you assign to this ML Transform. It must be unique in your account.
    numberOfWorkers number
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    tags {[key: string]: string}
    Key-value map of resource tags. .If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeout number
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    workerType string
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    input_record_tables Sequence[MLTransformInputRecordTableArgs]
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    parameters MLTransformParametersArgs
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    role_arn str
    The ARN of the IAM role associated with this ML Transform.
    description str
    Description of the ML Transform.
    glue_version str
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    max_capacity float
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    max_retries int
    The maximum number of times to retry this ML Transform if it fails.
    name str
    The name you assign to this ML Transform. It must be unique in your account.
    number_of_workers int
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    tags Mapping[str, str]
    Key-value map of resource tags. .If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeout int
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    worker_type str
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    inputRecordTables List<Property Map>
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    parameters Property Map
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    roleArn String
    The ARN of the IAM role associated with this ML Transform.
    description String
    Description of the ML Transform.
    glueVersion String
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    maxCapacity Number
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    maxRetries Number
    The maximum number of times to retry this ML Transform if it fails.
    name String
    The name you assign to this ML Transform. It must be unique in your account.
    numberOfWorkers Number
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    tags Map<String>
    Key-value map of resource tags. .If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeout Number
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    workerType String
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.

    Outputs

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

    Arn string
    Amazon Resource Name (ARN) of Glue ML Transform.
    Id string
    The provider-assigned unique ID for this managed resource.
    LabelCount int
    The number of labels available for this transform.
    Schemas List<MLTransformSchema>
    The object that represents the schema that this transform accepts. see Schema.
    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
    Amazon Resource Name (ARN) of Glue ML Transform.
    Id string
    The provider-assigned unique ID for this managed resource.
    LabelCount int
    The number of labels available for this transform.
    Schemas []MLTransformSchema
    The object that represents the schema that this transform accepts. see Schema.
    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
    Amazon Resource Name (ARN) of Glue ML Transform.
    id String
    The provider-assigned unique ID for this managed resource.
    labelCount Integer
    The number of labels available for this transform.
    schemas List<MLTransformSchema>
    The object that represents the schema that this transform accepts. see Schema.
    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
    Amazon Resource Name (ARN) of Glue ML Transform.
    id string
    The provider-assigned unique ID for this managed resource.
    labelCount number
    The number of labels available for this transform.
    schemas MLTransformSchema[]
    The object that represents the schema that this transform accepts. see Schema.
    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
    Amazon Resource Name (ARN) of Glue ML Transform.
    id str
    The provider-assigned unique ID for this managed resource.
    label_count int
    The number of labels available for this transform.
    schemas Sequence[MLTransformSchema]
    The object that represents the schema that this transform accepts. see Schema.
    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
    Amazon Resource Name (ARN) of Glue ML Transform.
    id String
    The provider-assigned unique ID for this managed resource.
    labelCount Number
    The number of labels available for this transform.
    schemas List<Property Map>
    The object that represents the schema that this transform accepts. see Schema.
    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 MLTransform Resource

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

    public static get(name: string, id: Input<ID>, state?: MLTransformState, opts?: CustomResourceOptions): MLTransform
    @staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        description: Optional[str] = None,
        glue_version: Optional[str] = None,
        input_record_tables: Optional[Sequence[MLTransformInputRecordTableArgs]] = None,
        label_count: Optional[int] = None,
        max_capacity: Optional[float] = None,
        max_retries: Optional[int] = None,
        name: Optional[str] = None,
        number_of_workers: Optional[int] = None,
        parameters: Optional[MLTransformParametersArgs] = None,
        role_arn: Optional[str] = None,
        schemas: Optional[Sequence[MLTransformSchemaArgs]] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None,
        timeout: Optional[int] = None,
        worker_type: Optional[str] = None) -> MLTransform
    func GetMLTransform(ctx *Context, name string, id IDInput, state *MLTransformState, opts ...ResourceOption) (*MLTransform, error)
    public static MLTransform Get(string name, Input<string> id, MLTransformState? state, CustomResourceOptions? opts = null)
    public static MLTransform get(String name, Output<String> id, MLTransformState state, CustomResourceOptions options)
    resources:  _:    type: aws:glue:MLTransform    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
    Amazon Resource Name (ARN) of Glue ML Transform.
    Description string
    Description of the ML Transform.
    GlueVersion string
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    InputRecordTables List<MLTransformInputRecordTable>
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    LabelCount int
    The number of labels available for this transform.
    MaxCapacity double
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    MaxRetries int
    The maximum number of times to retry this ML Transform if it fails.
    Name string
    The name you assign to this ML Transform. It must be unique in your account.
    NumberOfWorkers int
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    Parameters MLTransformParameters
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    RoleArn string
    The ARN of the IAM role associated with this ML Transform.
    Schemas List<MLTransformSchema>
    The object that represents the schema that this transform accepts. see Schema.
    Tags Dictionary<string, string>
    Key-value map of resource tags. .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.

    Timeout int
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    WorkerType string
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    Arn string
    Amazon Resource Name (ARN) of Glue ML Transform.
    Description string
    Description of the ML Transform.
    GlueVersion string
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    InputRecordTables []MLTransformInputRecordTableArgs
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    LabelCount int
    The number of labels available for this transform.
    MaxCapacity float64
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    MaxRetries int
    The maximum number of times to retry this ML Transform if it fails.
    Name string
    The name you assign to this ML Transform. It must be unique in your account.
    NumberOfWorkers int
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    Parameters MLTransformParametersArgs
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    RoleArn string
    The ARN of the IAM role associated with this ML Transform.
    Schemas []MLTransformSchemaArgs
    The object that represents the schema that this transform accepts. see Schema.
    Tags map[string]string
    Key-value map of resource tags. .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.

    Timeout int
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    WorkerType string
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    arn String
    Amazon Resource Name (ARN) of Glue ML Transform.
    description String
    Description of the ML Transform.
    glueVersion String
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    inputRecordTables List<MLTransformInputRecordTable>
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    labelCount Integer
    The number of labels available for this transform.
    maxCapacity Double
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    maxRetries Integer
    The maximum number of times to retry this ML Transform if it fails.
    name String
    The name you assign to this ML Transform. It must be unique in your account.
    numberOfWorkers Integer
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    parameters MLTransformParameters
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    roleArn String
    The ARN of the IAM role associated with this ML Transform.
    schemas List<MLTransformSchema>
    The object that represents the schema that this transform accepts. see Schema.
    tags Map<String,String>
    Key-value map of resource tags. .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.

    timeout Integer
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    workerType String
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    arn string
    Amazon Resource Name (ARN) of Glue ML Transform.
    description string
    Description of the ML Transform.
    glueVersion string
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    inputRecordTables MLTransformInputRecordTable[]
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    labelCount number
    The number of labels available for this transform.
    maxCapacity number
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    maxRetries number
    The maximum number of times to retry this ML Transform if it fails.
    name string
    The name you assign to this ML Transform. It must be unique in your account.
    numberOfWorkers number
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    parameters MLTransformParameters
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    roleArn string
    The ARN of the IAM role associated with this ML Transform.
    schemas MLTransformSchema[]
    The object that represents the schema that this transform accepts. see Schema.
    tags {[key: string]: string}
    Key-value map of resource tags. .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.

    timeout number
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    workerType string
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    arn str
    Amazon Resource Name (ARN) of Glue ML Transform.
    description str
    Description of the ML Transform.
    glue_version str
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    input_record_tables Sequence[MLTransformInputRecordTableArgs]
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    label_count int
    The number of labels available for this transform.
    max_capacity float
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    max_retries int
    The maximum number of times to retry this ML Transform if it fails.
    name str
    The name you assign to this ML Transform. It must be unique in your account.
    number_of_workers int
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    parameters MLTransformParametersArgs
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    role_arn str
    The ARN of the IAM role associated with this ML Transform.
    schemas Sequence[MLTransformSchemaArgs]
    The object that represents the schema that this transform accepts. see Schema.
    tags Mapping[str, str]
    Key-value map of resource tags. .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.

    timeout int
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    worker_type str
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.
    arn String
    Amazon Resource Name (ARN) of Glue ML Transform.
    description String
    Description of the ML Transform.
    glueVersion String
    The version of glue to use, for example "1.0". For information about available versions, see the AWS Glue Release Notes.
    inputRecordTables List<Property Map>
    A list of AWS Glue table definitions used by the transform. see Input Record Tables.
    labelCount Number
    The number of labels available for this transform.
    maxCapacity Number
    The number of AWS Glue data processing units (DPUs) that are allocated to task runs for this transform. You can allocate from 2 to 100 DPUs; the default is 10. max_capacity is a mutually exclusive option with number_of_workers and worker_type.
    maxRetries Number
    The maximum number of times to retry this ML Transform if it fails.
    name String
    The name you assign to this ML Transform. It must be unique in your account.
    numberOfWorkers Number
    The number of workers of a defined worker_type that are allocated when an ML Transform runs. Required with worker_type.
    parameters Property Map
    The algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. see Parameters.
    roleArn String
    The ARN of the IAM role associated with this ML Transform.
    schemas List<Property Map>
    The object that represents the schema that this transform accepts. see Schema.
    tags Map<String>
    Key-value map of resource tags. .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.

    timeout Number
    The ML Transform timeout in minutes. The default is 2880 minutes (48 hours).
    workerType String
    The type of predefined worker that is allocated when an ML Transform runs. Accepts a value of Standard, G.1X, or G.2X. Required with number_of_workers.

    Supporting Types

    MLTransformInputRecordTable, MLTransformInputRecordTableArgs

    DatabaseName string
    A database name in the AWS Glue Data Catalog.
    TableName string
    A table name in the AWS Glue Data Catalog.
    CatalogId string
    A unique identifier for the AWS Glue Data Catalog.
    ConnectionName string
    The name of the connection to the AWS Glue Data Catalog.
    DatabaseName string
    A database name in the AWS Glue Data Catalog.
    TableName string
    A table name in the AWS Glue Data Catalog.
    CatalogId string
    A unique identifier for the AWS Glue Data Catalog.
    ConnectionName string
    The name of the connection to the AWS Glue Data Catalog.
    databaseName String
    A database name in the AWS Glue Data Catalog.
    tableName String
    A table name in the AWS Glue Data Catalog.
    catalogId String
    A unique identifier for the AWS Glue Data Catalog.
    connectionName String
    The name of the connection to the AWS Glue Data Catalog.
    databaseName string
    A database name in the AWS Glue Data Catalog.
    tableName string
    A table name in the AWS Glue Data Catalog.
    catalogId string
    A unique identifier for the AWS Glue Data Catalog.
    connectionName string
    The name of the connection to the AWS Glue Data Catalog.
    database_name str
    A database name in the AWS Glue Data Catalog.
    table_name str
    A table name in the AWS Glue Data Catalog.
    catalog_id str
    A unique identifier for the AWS Glue Data Catalog.
    connection_name str
    The name of the connection to the AWS Glue Data Catalog.
    databaseName String
    A database name in the AWS Glue Data Catalog.
    tableName String
    A table name in the AWS Glue Data Catalog.
    catalogId String
    A unique identifier for the AWS Glue Data Catalog.
    connectionName String
    The name of the connection to the AWS Glue Data Catalog.

    MLTransformParameters, MLTransformParametersArgs

    FindMatchesParameters MLTransformParametersFindMatchesParameters
    The parameters for the find matches algorithm. see Find Matches Parameters.
    TransformType string
    The type of machine learning transform. For information about the types of machine learning transforms, see Creating Machine Learning Transforms.
    FindMatchesParameters MLTransformParametersFindMatchesParameters
    The parameters for the find matches algorithm. see Find Matches Parameters.
    TransformType string
    The type of machine learning transform. For information about the types of machine learning transforms, see Creating Machine Learning Transforms.
    findMatchesParameters MLTransformParametersFindMatchesParameters
    The parameters for the find matches algorithm. see Find Matches Parameters.
    transformType String
    The type of machine learning transform. For information about the types of machine learning transforms, see Creating Machine Learning Transforms.
    findMatchesParameters MLTransformParametersFindMatchesParameters
    The parameters for the find matches algorithm. see Find Matches Parameters.
    transformType string
    The type of machine learning transform. For information about the types of machine learning transforms, see Creating Machine Learning Transforms.
    find_matches_parameters MLTransformParametersFindMatchesParameters
    The parameters for the find matches algorithm. see Find Matches Parameters.
    transform_type str
    The type of machine learning transform. For information about the types of machine learning transforms, see Creating Machine Learning Transforms.
    findMatchesParameters Property Map
    The parameters for the find matches algorithm. see Find Matches Parameters.
    transformType String
    The type of machine learning transform. For information about the types of machine learning transforms, see Creating Machine Learning Transforms.

    MLTransformParametersFindMatchesParameters, MLTransformParametersFindMatchesParametersArgs

    AccuracyCostTradeOff double
    The value that is selected when tuning your transform for a balance between accuracy and cost.
    EnforceProvidedLabels bool
    The value to switch on or off to force the output to match the provided labels from users.
    PrecisionRecallTradeOff double
    The value selected when tuning your transform for a balance between precision and recall.
    PrimaryKeyColumnName string
    The name of a column that uniquely identifies rows in the source table.
    AccuracyCostTradeOff float64
    The value that is selected when tuning your transform for a balance between accuracy and cost.
    EnforceProvidedLabels bool
    The value to switch on or off to force the output to match the provided labels from users.
    PrecisionRecallTradeOff float64
    The value selected when tuning your transform for a balance between precision and recall.
    PrimaryKeyColumnName string
    The name of a column that uniquely identifies rows in the source table.
    accuracyCostTradeOff Double
    The value that is selected when tuning your transform for a balance between accuracy and cost.
    enforceProvidedLabels Boolean
    The value to switch on or off to force the output to match the provided labels from users.
    precisionRecallTradeOff Double
    The value selected when tuning your transform for a balance between precision and recall.
    primaryKeyColumnName String
    The name of a column that uniquely identifies rows in the source table.
    accuracyCostTradeOff number
    The value that is selected when tuning your transform for a balance between accuracy and cost.
    enforceProvidedLabels boolean
    The value to switch on or off to force the output to match the provided labels from users.
    precisionRecallTradeOff number
    The value selected when tuning your transform for a balance between precision and recall.
    primaryKeyColumnName string
    The name of a column that uniquely identifies rows in the source table.
    accuracy_cost_trade_off float
    The value that is selected when tuning your transform for a balance between accuracy and cost.
    enforce_provided_labels bool
    The value to switch on or off to force the output to match the provided labels from users.
    precision_recall_trade_off float
    The value selected when tuning your transform for a balance between precision and recall.
    primary_key_column_name str
    The name of a column that uniquely identifies rows in the source table.
    accuracyCostTradeOff Number
    The value that is selected when tuning your transform for a balance between accuracy and cost.
    enforceProvidedLabels Boolean
    The value to switch on or off to force the output to match the provided labels from users.
    precisionRecallTradeOff Number
    The value selected when tuning your transform for a balance between precision and recall.
    primaryKeyColumnName String
    The name of a column that uniquely identifies rows in the source table.

    MLTransformSchema, MLTransformSchemaArgs

    DataType string
    The type of data in the column.
    Name string
    The name you assign to this ML Transform. It must be unique in your account.
    DataType string
    The type of data in the column.
    Name string
    The name you assign to this ML Transform. It must be unique in your account.
    dataType String
    The type of data in the column.
    name String
    The name you assign to this ML Transform. It must be unique in your account.
    dataType string
    The type of data in the column.
    name string
    The name you assign to this ML Transform. It must be unique in your account.
    data_type str
    The type of data in the column.
    name str
    The name you assign to this ML Transform. It must be unique in your account.
    dataType String
    The type of data in the column.
    name String
    The name you assign to this ML Transform. It must be unique in your account.

    Import

    Using pulumi import, import Glue ML Transforms using id. For example:

    $ pulumi import aws:glue/mLTransform:MLTransform example tfm-c2cafbe83b1c575f49eaca9939220e2fcd58e2d5

    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 logo
    AWS v6.72.0 published on Tuesday, Mar 11, 2025 by Pulumi
    pulumi/pulumi-aws