Package software.amazon.awssdk.services.comprehend.model

Interface EntityRecognizerInputDataConfig.Builder

All Superinterfaces:
Buildable, CopyableBuilder<EntityRecognizerInputDataConfig.Builder,EntityRecognizerInputDataConfig>, SdkBuilder<EntityRecognizerInputDataConfig.Builder,EntityRecognizerInputDataConfig>, SdkPojo
Enclosing class:
EntityRecognizerInputDataConfig
public static interface EntityRecognizerInputDataConfig.Builder extends SdkPojo, CopyableBuilder<EntityRecognizerInputDataConfig.Builder,EntityRecognizerInputDataConfig>

  • Method Details

    • dataFormat

      EntityRecognizerInputDataConfig.Builder dataFormat(String dataFormat)

      The format of your training data:

      • COMPREHEND_CSV: A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list.

        If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.

      • AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document.

        If you use this value, you must provide the AugmentedManifests parameter in your request.

      If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.

      Parameters:
      dataFormat - The format of your training data:

      • COMPREHEND_CSV: A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list.

        If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.

      • AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document.

        If you use this value, you must provide the AugmentedManifests parameter in your request.

      If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • dataFormat

      EntityRecognizerInputDataConfig.Builder dataFormat(EntityRecognizerDataFormat dataFormat)

      The format of your training data:

      • COMPREHEND_CSV: A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list.

        If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.

      • AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document.

        If you use this value, you must provide the AugmentedManifests parameter in your request.

      If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.

      Parameters:
      dataFormat - The format of your training data:

      • COMPREHEND_CSV: A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list.

        If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.

      • AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document.

        If you use this value, you must provide the AugmentedManifests parameter in your request.

      If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • entityTypes

      EntityRecognizerInputDataConfig.Builder entityTypes(Collection<EntityTypesListItem> entityTypes)

      The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.

      A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break), \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), space, and , (comma).

      Parameters:
      entityTypes - The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.

      A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break), \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), space, and , (comma).

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • entityTypes

      EntityRecognizerInputDataConfig.Builder entityTypes(EntityTypesListItem... entityTypes)

      The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.

      A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break), \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), space, and , (comma).

      Parameters:
      entityTypes - The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.

      A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break), \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), space, and , (comma).

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • entityTypes

      EntityRecognizerInputDataConfig.Builder entityTypes(Consumer<EntityTypesListItem.Builder>... entityTypes)

      The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.

      A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break), \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), space, and , (comma).

      This is a convenience method that creates an instance of the EntityTypesListItem.Builder avoiding the need to create one manually via EntityTypesListItem.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to entityTypes(List<EntityTypesListItem>).

      Parameters:
      entityTypes - a consumer that will call methods on EntityTypesListItem.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • documents

      EntityRecognizerInputDataConfig.Builder documents(EntityRecognizerDocuments documents)

      The S3 location of the folder that contains the training documents for your custom entity recognizer.

      This parameter is required if you set DataFormat to COMPREHEND_CSV.

      Parameters:
      documents - The S3 location of the folder that contains the training documents for your custom entity recognizer.

      This parameter is required if you set DataFormat to COMPREHEND_CSV.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • documents

      default EntityRecognizerInputDataConfig.Builder documents(Consumer<EntityRecognizerDocuments.Builder> documents)

      The S3 location of the folder that contains the training documents for your custom entity recognizer.

      This parameter is required if you set DataFormat to COMPREHEND_CSV.

      This is a convenience method that creates an instance of the EntityRecognizerDocuments.Builder avoiding the need to create one manually via EntityRecognizerDocuments.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to documents(EntityRecognizerDocuments).

      Parameters:
      documents - a consumer that will call methods on EntityRecognizerDocuments.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • annotations

      EntityRecognizerInputDataConfig.Builder annotations(EntityRecognizerAnnotations annotations)

      The S3 location of the CSV file that annotates your training documents.

      Parameters:
      annotations - The S3 location of the CSV file that annotates your training documents.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • annotations

      default EntityRecognizerInputDataConfig.Builder annotations(Consumer<EntityRecognizerAnnotations.Builder> annotations)

      The S3 location of the CSV file that annotates your training documents.

      This is a convenience method that creates an instance of the EntityRecognizerAnnotations.Builder avoiding the need to create one manually via EntityRecognizerAnnotations.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to annotations(EntityRecognizerAnnotations).

      Parameters:
      annotations - a consumer that will call methods on EntityRecognizerAnnotations.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • entityList

      EntityRecognizerInputDataConfig.Builder entityList(EntityRecognizerEntityList entityList)

      The S3 location of the CSV file that has the entity list for your custom entity recognizer.

      Parameters:
      entityList - The S3 location of the CSV file that has the entity list for your custom entity recognizer.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • entityList

      default EntityRecognizerInputDataConfig.Builder entityList(Consumer<EntityRecognizerEntityList.Builder> entityList)

      The S3 location of the CSV file that has the entity list for your custom entity recognizer.

      This is a convenience method that creates an instance of the EntityRecognizerEntityList.Builder avoiding the need to create one manually via EntityRecognizerEntityList.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to entityList(EntityRecognizerEntityList).

      Parameters:
      entityList - a consumer that will call methods on EntityRecognizerEntityList.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • augmentedManifests

      EntityRecognizerInputDataConfig.Builder augmentedManifests(Collection<AugmentedManifestsListItem> augmentedManifests)

      A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

      This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.

      Parameters:
      augmentedManifests - A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

      This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • augmentedManifests

      EntityRecognizerInputDataConfig.Builder augmentedManifests(AugmentedManifestsListItem... augmentedManifests)

      A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

      This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.

      Parameters:
      augmentedManifests - A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

      This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • augmentedManifests

      EntityRecognizerInputDataConfig.Builder augmentedManifests(Consumer<AugmentedManifestsListItem.Builder>... augmentedManifests)

      A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

      This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.

      This is a convenience method that creates an instance of the AugmentedManifestsListItem.Builder avoiding the need to create one manually via AugmentedManifestsListItem.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to augmentedManifests(List<AugmentedManifestsListItem>).

      Parameters:
      augmentedManifests - a consumer that will call methods on AugmentedManifestsListItem.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also: