All Downloads are FREE. Search and download functionalities are using the official Maven repository.

com.amazonaws.services.comprehend.model.EntityRecognizerInputDataConfig Maven / Gradle / Ivy

Go to download

The AWS Java SDK for Amazon Comprehend module holds the client classes that are used for communicating with Amazon Comprehend Service

There is a newer version: 1.12.772
Show newest version
/*
 * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 * 
 * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with
 * the License. A copy of the License is located at
 * 
 * http://aws.amazon.com/apache2.0
 * 
 * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
 * CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
 * and limitations under the License.
 */
package com.amazonaws.services.comprehend.model;

import java.io.Serializable;
import javax.annotation.Generated;
import com.amazonaws.protocol.StructuredPojo;
import com.amazonaws.protocol.ProtocolMarshaller;

/**
 * 

* Specifies the format and location of the input data. *

* * @see AWS API Documentation */ @Generated("com.amazonaws:aws-java-sdk-code-generator") public class EntityRecognizerInputDataConfig implements Serializable, Cloneable, StructuredPojo { /** *

* 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. *

*/ private String dataFormat; /** *

* 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). *

*/ private java.util.List entityTypes; /** *

* 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. *

*/ private EntityRecognizerDocuments documents; /** *

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

*/ private EntityRecognizerAnnotations annotations; /** *

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

*/ private EntityRecognizerEntityList entityList; /** *

* 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. *

*/ private java.util.List augmentedManifests; /** *

* 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. *

* * @param 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. * @see EntityRecognizerDataFormat */ public void setDataFormat(String dataFormat) { this.dataFormat = 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. *

* * @return 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. * @see EntityRecognizerDataFormat */ public String getDataFormat() { return this.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. *

* * @param 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. * @return Returns a reference to this object so that method calls can be chained together. * @see EntityRecognizerDataFormat */ public EntityRecognizerInputDataConfig withDataFormat(String dataFormat) { setDataFormat(dataFormat); return this; } /** *

* 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. *

* * @param 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. * @return Returns a reference to this object so that method calls can be chained together. * @see EntityRecognizerDataFormat */ public EntityRecognizerInputDataConfig withDataFormat(EntityRecognizerDataFormat dataFormat) { this.dataFormat = dataFormat.toString(); return this; } /** *

* 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). *

* * @return 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). */ public java.util.List getEntityTypes() { return 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). *

* * @param 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). */ public void setEntityTypes(java.util.Collection entityTypes) { if (entityTypes == null) { this.entityTypes = null; return; } this.entityTypes = new java.util.ArrayList(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). *

*

* NOTE: This method appends the values to the existing list (if any). Use * {@link #setEntityTypes(java.util.Collection)} or {@link #withEntityTypes(java.util.Collection)} if you want to * override the existing values. *

* * @param 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). * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withEntityTypes(EntityTypesListItem... entityTypes) { if (this.entityTypes == null) { setEntityTypes(new java.util.ArrayList(entityTypes.length)); } for (EntityTypesListItem ele : entityTypes) { this.entityTypes.add(ele); } return this; } /** *

* 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). *

* * @param 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). * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withEntityTypes(java.util.Collection entityTypes) { setEntityTypes(entityTypes); return this; } /** *

* 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. *

* * @param 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. */ public void setDocuments(EntityRecognizerDocuments documents) { this.documents = 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. *

* * @return 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. */ public EntityRecognizerDocuments getDocuments() { return this.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. *

* * @param 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. * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withDocuments(EntityRecognizerDocuments documents) { setDocuments(documents); return this; } /** *

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

* * @param annotations * The S3 location of the CSV file that annotates your training documents. */ public void setAnnotations(EntityRecognizerAnnotations annotations) { this.annotations = annotations; } /** *

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

* * @return The S3 location of the CSV file that annotates your training documents. */ public EntityRecognizerAnnotations getAnnotations() { return this.annotations; } /** *

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

* * @param annotations * The S3 location of the CSV file that annotates your training documents. * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withAnnotations(EntityRecognizerAnnotations annotations) { setAnnotations(annotations); return this; } /** *

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

* * @param entityList * The S3 location of the CSV file that has the entity list for your custom entity recognizer. */ public void setEntityList(EntityRecognizerEntityList entityList) { this.entityList = entityList; } /** *

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

* * @return The S3 location of the CSV file that has the entity list for your custom entity recognizer. */ public EntityRecognizerEntityList getEntityList() { return this.entityList; } /** *

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

* * @param entityList * The S3 location of the CSV file that has the entity list for your custom entity recognizer. * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withEntityList(EntityRecognizerEntityList entityList) { setEntityList(entityList); return this; } /** *

* 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. *

* * @return 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. */ public java.util.List getAugmentedManifests() { return 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. *

* * @param 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. */ public void setAugmentedManifests(java.util.Collection augmentedManifests) { if (augmentedManifests == null) { this.augmentedManifests = null; return; } this.augmentedManifests = new java.util.ArrayList(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. *

*

* NOTE: This method appends the values to the existing list (if any). Use * {@link #setAugmentedManifests(java.util.Collection)} or {@link #withAugmentedManifests(java.util.Collection)} if * you want to override the existing values. *

* * @param 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. * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withAugmentedManifests(AugmentedManifestsListItem... augmentedManifests) { if (this.augmentedManifests == null) { setAugmentedManifests(new java.util.ArrayList(augmentedManifests.length)); } for (AugmentedManifestsListItem ele : augmentedManifests) { this.augmentedManifests.add(ele); } return this; } /** *

* 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. *

* * @param 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. * @return Returns a reference to this object so that method calls can be chained together. */ public EntityRecognizerInputDataConfig withAugmentedManifests(java.util.Collection augmentedManifests) { setAugmentedManifests(augmentedManifests); return this; } /** * Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be * redacted from this string using a placeholder value. * * @return A string representation of this object. * * @see java.lang.Object#toString() */ @Override public String toString() { StringBuilder sb = new StringBuilder(); sb.append("{"); if (getDataFormat() != null) sb.append("DataFormat: ").append(getDataFormat()).append(","); if (getEntityTypes() != null) sb.append("EntityTypes: ").append(getEntityTypes()).append(","); if (getDocuments() != null) sb.append("Documents: ").append(getDocuments()).append(","); if (getAnnotations() != null) sb.append("Annotations: ").append(getAnnotations()).append(","); if (getEntityList() != null) sb.append("EntityList: ").append(getEntityList()).append(","); if (getAugmentedManifests() != null) sb.append("AugmentedManifests: ").append(getAugmentedManifests()); sb.append("}"); return sb.toString(); } @Override public boolean equals(Object obj) { if (this == obj) return true; if (obj == null) return false; if (obj instanceof EntityRecognizerInputDataConfig == false) return false; EntityRecognizerInputDataConfig other = (EntityRecognizerInputDataConfig) obj; if (other.getDataFormat() == null ^ this.getDataFormat() == null) return false; if (other.getDataFormat() != null && other.getDataFormat().equals(this.getDataFormat()) == false) return false; if (other.getEntityTypes() == null ^ this.getEntityTypes() == null) return false; if (other.getEntityTypes() != null && other.getEntityTypes().equals(this.getEntityTypes()) == false) return false; if (other.getDocuments() == null ^ this.getDocuments() == null) return false; if (other.getDocuments() != null && other.getDocuments().equals(this.getDocuments()) == false) return false; if (other.getAnnotations() == null ^ this.getAnnotations() == null) return false; if (other.getAnnotations() != null && other.getAnnotations().equals(this.getAnnotations()) == false) return false; if (other.getEntityList() == null ^ this.getEntityList() == null) return false; if (other.getEntityList() != null && other.getEntityList().equals(this.getEntityList()) == false) return false; if (other.getAugmentedManifests() == null ^ this.getAugmentedManifests() == null) return false; if (other.getAugmentedManifests() != null && other.getAugmentedManifests().equals(this.getAugmentedManifests()) == false) return false; return true; } @Override public int hashCode() { final int prime = 31; int hashCode = 1; hashCode = prime * hashCode + ((getDataFormat() == null) ? 0 : getDataFormat().hashCode()); hashCode = prime * hashCode + ((getEntityTypes() == null) ? 0 : getEntityTypes().hashCode()); hashCode = prime * hashCode + ((getDocuments() == null) ? 0 : getDocuments().hashCode()); hashCode = prime * hashCode + ((getAnnotations() == null) ? 0 : getAnnotations().hashCode()); hashCode = prime * hashCode + ((getEntityList() == null) ? 0 : getEntityList().hashCode()); hashCode = prime * hashCode + ((getAugmentedManifests() == null) ? 0 : getAugmentedManifests().hashCode()); return hashCode; } @Override public EntityRecognizerInputDataConfig clone() { try { return (EntityRecognizerInputDataConfig) super.clone(); } catch (CloneNotSupportedException e) { throw new IllegalStateException("Got a CloneNotSupportedException from Object.clone() " + "even though we're Cloneable!", e); } } @com.amazonaws.annotation.SdkInternalApi @Override public void marshall(ProtocolMarshaller protocolMarshaller) { com.amazonaws.services.comprehend.model.transform.EntityRecognizerInputDataConfigMarshaller.getInstance().marshall(this, protocolMarshaller); } }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy