Package com.pulumi.aws.glue

Class MLTransform

  • public class MLTransform
extends com.pulumi.resources.CustomResource
    Provides a Glue ML Transform resource. ## Example Usage 
     
 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.CatalogTableStorageDescriptorColumnArgs;
 import com.pulumi.aws.glue.inputs.CatalogTableStorageDescriptorSortColumnArgs;
 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.MLTransformParametersArgs;
 import com.pulumi.aws.glue.inputs.MLTransformParametersFindMatchesParametersArgs;
 import com.pulumi.aws.glue.inputs.MLTransformInputRecordTableArgs;
 import com.pulumi.resources.CustomResourceOptions;
 import java.util.ArrayList;
 import java.util.Arrays;
 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()
             .storageDescriptor(CatalogTableStorageDescriptorArgs.builder()
                 .serDeInfo(CatalogTableStorageDescriptorSerDeInfoArgs.builder()
                     .name("ser_de_name")
                     .parameters(Map.of("param1", "param_val_1"))
                     .serializationLibrary("org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe")
                     .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())
                 .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())
                 .sortColumns(CatalogTableStorageDescriptorSortColumnArgs.builder()
                     .column("my_column_1")
                     .sortOrder(1)
                     .build())
                 .bucketColumns("bucket_column_1")
                 .compressed(false)
                 .inputFormat("SequenceFileInputFormat")
                 .location("my_location")
                 .numberOfBuckets(1)
                 .outputFormat("SequenceFileInputFormat")
                 .storedAsSubDirectories(false)
                 .parameters(Map.of("param1", "param1_val"))
                 .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())
             .name("example")
             .databaseName(testCatalogDatabase.name())
             .owner("my_owner")
             .retention(1)
             .tableType("VIRTUAL_VIEW")
             .viewExpandedText("view_expanded_text_1")
             .viewOriginalText("view_original_text_1")
             .parameters(Map.of("param1", "param1_val"))
             .build());
 
         var test = new MLTransform("test", MLTransformArgs.builder()
             .parameters(MLTransformParametersArgs.builder()
                 .findMatchesParameters(MLTransformParametersFindMatchesParametersArgs.builder()
                     .primaryKeyColumnName("my_column_1")
                     .build())
                 .transformType("FIND_MATCHES")
                 .build())
             .inputRecordTables(MLTransformInputRecordTableArgs.builder()
                 .databaseName(testCatalogTable.databaseName())
                 .tableName(testCatalogTable.name())
                 .build())
             .name("example")
             .roleArn(testAwsIamRole.arn())
             .build(), CustomResourceOptions.builder()
                 .dependsOn(testAwsIamRolePolicyAttachment)
                 .build());
 
     }
 }
    ## Import Using `pulumi import`, import Glue ML Transforms using `id`. For example: ```sh $ pulumi import aws:glue/mLTransform:MLTransform example tfm-c2cafbe83b1c575f49eaca9939220e2fcd58e2d5 ```

    • Nested Class Summary

      • Nested classes/interfaces inherited from class com.pulumi.resources.CustomResource

        com.pulumi.resources.CustomResource.CustomResourceInternal

      • Nested classes/interfaces inherited from class com.pulumi.resources.Resource

        com.pulumi.resources.Resource.LazyField<T extends java.lang.Object>, com.pulumi.resources.Resource.LazyFields, com.pulumi.resources.Resource.ResourceInternal

    • Field Summary

      • Fields inherited from class com.pulumi.resources.Resource

        childResources, remote

    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      com.pulumi.core.Output<java.lang.String> arn()  
      com.pulumi.core.Output<java.util.Optional<java.lang.String>> description()  
      static MLTransform get​(java.lang.String name, com.pulumi.core.Output<java.lang.String> id, MLTransformState state, com.pulumi.resources.CustomResourceOptions options)
      Get an existing Host resource's state with the given name, ID, and optional extra properties used to qualify the lookup.
      com.pulumi.core.Output<java.lang.String> glueVersion()  
      com.pulumi.core.Output<java.util.List<MLTransformInputRecordTable>> inputRecordTables()  
      com.pulumi.core.Output<java.lang.Integer> labelCount()  
      com.pulumi.core.Output<java.lang.Double> maxCapacity()  
      com.pulumi.core.Output<java.util.Optional<java.lang.Integer>> maxRetries()  
      com.pulumi.core.Output<java.lang.String> name()  
      com.pulumi.core.Output<java.util.Optional<java.lang.Integer>> numberOfWorkers()  
      com.pulumi.core.Output<MLTransformParameters> parameters()  
      com.pulumi.core.Output<java.lang.String> region()  
      com.pulumi.core.Output<java.lang.String> roleArn()  
      com.pulumi.core.Output<java.util.List<MLTransformSchema>> schemas()  
      com.pulumi.core.Output<java.util.Optional<java.util.Map<java.lang.String,​java.lang.String>>> tags()  
      com.pulumi.core.Output<java.util.Map<java.lang.String,​java.lang.String>> tagsAll()  
      com.pulumi.core.Output<java.util.Optional<java.lang.Integer>> timeout()  
      com.pulumi.core.Output<java.util.Optional<java.lang.String>> workerType()  

      • Methods inherited from class com.pulumi.resources.CustomResource

        getId, id, idFuture

      • Methods inherited from class com.pulumi.resources.Resource

        getChildResources, getResourceName, getResourceType, getUrn, pulumiChildResources, pulumiResourceName, pulumiResourceType, urn

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • Constructor Detail

      • MLTransform

        public MLTransform​(java.lang.String name)
        Parameters:
        name - The _unique_ name of the resulting resource.

      • MLTransform

        public MLTransform​(java.lang.String name,
                   MLTransformArgs args)
        Parameters:
        name - The _unique_ name of the resulting resource.
        args - The arguments to use to populate this resource's properties.

      • MLTransform

        public MLTransform​(java.lang.String name,
                   MLTransformArgs args,
                   @Nullable
                   com.pulumi.resources.CustomResourceOptions options)
        Parameters:
        name - The _unique_ name of the resulting resource.
        args - The arguments to use to populate this resource's properties.
        options - A bag of options that control this resource's behavior.

    • Method Detail

      • arn

        public com.pulumi.core.Output<java.lang.String> arn()
        Returns:
        ARN of Glue ML Transform.

      • description

        public com.pulumi.core.Output<java.util.Optional<java.lang.String>> description()
        Returns:
        Description of the ML Transform.

      • glueVersion

        public com.pulumi.core.Output<java.lang.String> glueVersion()
        Returns:
        Version of glue to use, for example "1.0". For information about available versions, see the [AWS Glue Release Notes](https://docs.aws.amazon.com/glue/latest/dg/release-notes.html).

      • inputRecordTables

        public com.pulumi.core.Output<java.util.List<MLTransformInputRecordTable>> inputRecordTables()
        Returns:
        List of AWS Glue table definitions used by the transform. See `inputRecordTables`.

      • labelCount

        public com.pulumi.core.Output<java.lang.Integer> labelCount()
        Returns:
        Number of labels available for this transform.

      • maxCapacity

        public com.pulumi.core.Output<java.lang.Double> maxCapacity()
        Returns:
        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`. `maxCapacity` is a mutually exclusive option with `numberOfWorkers` and `workerType`.

      • maxRetries

        public com.pulumi.core.Output<java.util.Optional<java.lang.Integer>> maxRetries()
        Returns:
        Maximum number of times to retry this ML Transform if it fails.

      • name

        public com.pulumi.core.Output<java.lang.String> name()
        Returns:
        Name you assign to this ML Transform. It must be unique in your account.

      • numberOfWorkers

        public com.pulumi.core.Output<java.util.Optional<java.lang.Integer>> numberOfWorkers()
        Returns:
        Number of workers of a defined `workerType` that are allocated when an ML Transform runs. Required with `workerType`.

      • parameters

        public com.pulumi.core.Output<MLTransformParameters> parameters()
        Returns:
        Algorithmic parameters that are specific to the transform type used. Conditionally dependent on the transform type. See `parameters`.

      • region

        public com.pulumi.core.Output<java.lang.String> region()
        Returns:
        Region where this resource will be [managed](https://docs.aws.amazon.com/general/latest/gr/rande.html#regional-endpoints). Defaults to the Region set in the provider configuration.

      • roleArn

        public com.pulumi.core.Output<java.lang.String> roleArn()
        Returns:
        ARN of the IAM role associated with this ML Transform.

      • schemas

        public com.pulumi.core.Output<java.util.List<MLTransformSchema>> schemas()
        Returns:
        Object that represents the schema that this transform accepts. See `schema`.

      • tags

        public com.pulumi.core.Output<java.util.Optional<java.util.Map<java.lang.String,​java.lang.String>>> tags()
        Returns:
        Key-value map of resource tags. .If configured with a provider `defaultTags` configuration block present, tags with matching keys will overwrite those defined at the provider-level.

      • tagsAll

        public com.pulumi.core.Output<java.util.Map<java.lang.String,​java.lang.String>> tagsAll()
        Returns:
        Map of tags assigned to the resource, including those inherited from the provider `defaultTags` configuration block.

      • timeout

        public com.pulumi.core.Output<java.util.Optional<java.lang.Integer>> timeout()
        Returns:
        ML Transform timeout in minutes. The default is 2880 minutes (48 hours).

      • workerType

        public com.pulumi.core.Output<java.util.Optional<java.lang.String>> workerType()
        Returns:
        Type of predefined worker that is allocated when an ML Transform runs. Accepts a value of `Standard`, `G.1X`, or `G.2X`. Required with `numberOfWorkers`.

      • get

        public static MLTransform get​(java.lang.String name,
                              com.pulumi.core.Output<java.lang.String> id,
                              @Nullable
                              MLTransformState state,
                              @Nullable
                              com.pulumi.resources.CustomResourceOptions options)
        Get an existing Host resource's state with the given name, ID, and optional extra properties used to qualify the lookup.
        Parameters:
        name - The _unique_ name of the resulting resource.
        id - The _unique_ provider ID of the resource to lookup.
        state -
        options - Optional settings to control the behavior of the CustomResource.