文档 AWS SDK 示例 GitHub 存储库中还有更多 [S AWS DK 示例](https://github.com/awsdocs/aws-doc-sdk-examples)。
本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。
# 使用 Amazon Comprehend 的代码示例 AWS SDKs
以下代码示例向您展示了如何将 Amazon Comprehend 与软件开发套件 (SDK) AWS 配合使用。
*操作*是大型程序的代码摘录，必须在上下文中运行。您可以通过操作了解如何调用单个服务函数，还可以通过函数相关场景的上下文查看操作。
*场景*是向您展示如何通过在一个服务中调用多个函数或与其他 AWS 服务服务结合来完成特定任务的代码示例。
**更多资源**
+ **[Amazon Comprehend 开发人员指南](https://docs.aws.amazon.com/comprehend/latest/dg/what-is.html)**——有关 Amazon Comprehend 的更多信息。
+ **[Amazon Comprehend API 参考](https://docs.aws.amazon.com/comprehend/latest/APIReference/welcome.html)**——有关所有可用的 Amazon Comprehend 操作的详细信息。
+ **[AWS 开发者中心](https://aws.amazon.com/developer/code-examples/?awsf.sdk-code-examples-product=product%23comprehend)** — 您可以按类别或全文搜索筛选的代码示例。
+ **[AWS SDK 示例](https://github.com/awsdocs/aws-doc-sdk-examples)** — 包含首选语言完整代码的 GitHub 存储库。包括有关设置和运行代码的说明。
**Contents**
+ [基本功能](comprehend_code_examples_basics.md)
+ [操作](comprehend_code_examples_actions.md)
+ [`CreateDocumentClassifier`](comprehend_example_comprehend_CreateDocumentClassifier_section.md)
+ [`DeleteDocumentClassifier`](comprehend_example_comprehend_DeleteDocumentClassifier_section.md)
+ [`DescribeDocumentClassificationJob`](comprehend_example_comprehend_DescribeDocumentClassificationJob_section.md)
+ [`DescribeDocumentClassifier`](comprehend_example_comprehend_DescribeDocumentClassifier_section.md)
+ [`DescribeTopicsDetectionJob`](comprehend_example_comprehend_DescribeTopicsDetectionJob_section.md)
+ [`DetectDominantLanguage`](comprehend_example_comprehend_DetectDominantLanguage_section.md)
+ [`DetectEntities`](comprehend_example_comprehend_DetectEntities_section.md)
+ [`DetectKeyPhrases`](comprehend_example_comprehend_DetectKeyPhrases_section.md)
+ [`DetectPiiEntities`](comprehend_example_comprehend_DetectPiiEntities_section.md)
+ [`DetectSentiment`](comprehend_example_comprehend_DetectSentiment_section.md)
+ [`DetectSyntax`](comprehend_example_comprehend_DetectSyntax_section.md)
+ [`ListDocumentClassificationJobs`](comprehend_example_comprehend_ListDocumentClassificationJobs_section.md)
+ [`ListDocumentClassifiers`](comprehend_example_comprehend_ListDocumentClassifiers_section.md)
+ [`ListTopicsDetectionJobs`](comprehend_example_comprehend_ListTopicsDetectionJobs_section.md)
+ [`StartDocumentClassificationJob`](comprehend_example_comprehend_StartDocumentClassificationJob_section.md)
+ [`StartTopicsDetectionJob`](comprehend_example_comprehend_StartTopicsDetectionJob_section.md)
+ [场景](comprehend_code_examples_scenarios.md)
+ [构建 Amazon Transcribe 流式传输应用程序](comprehend_example_cross_TranscriptionStreamingApp_section.md)
+ [构建 Amazon Lex 聊天机器人](comprehend_example_cross_LexChatbotLanguages_section.md)
+ [创建消息应用程序](comprehend_example_cross_SQSMessageApp_section.md)
+ [创建用于分析客户反馈的应用程序](comprehend_example_cross_FSA_section.md)
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
+ [检测从图像中提取的文本中的实体](comprehend_example_cross_TextractComprehendDetectEntities_section.md)
+ [对示例数据运行主题建模任务](comprehend_example_comprehend_Usage_TopicModeler_section.md)
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
# 使用 Amazon Comprehend 的基本示例 AWS SDKs
以下代码示例展示了如何使用 Amazon Comprehend 的基础知识。 AWS SDKs
**Contents**
+ [操作](comprehend_code_examples_actions.md)
+ [`CreateDocumentClassifier`](comprehend_example_comprehend_CreateDocumentClassifier_section.md)
+ [`DeleteDocumentClassifier`](comprehend_example_comprehend_DeleteDocumentClassifier_section.md)
+ [`DescribeDocumentClassificationJob`](comprehend_example_comprehend_DescribeDocumentClassificationJob_section.md)
+ [`DescribeDocumentClassifier`](comprehend_example_comprehend_DescribeDocumentClassifier_section.md)
+ [`DescribeTopicsDetectionJob`](comprehend_example_comprehend_DescribeTopicsDetectionJob_section.md)
+ [`DetectDominantLanguage`](comprehend_example_comprehend_DetectDominantLanguage_section.md)
+ [`DetectEntities`](comprehend_example_comprehend_DetectEntities_section.md)
+ [`DetectKeyPhrases`](comprehend_example_comprehend_DetectKeyPhrases_section.md)
+ [`DetectPiiEntities`](comprehend_example_comprehend_DetectPiiEntities_section.md)
+ [`DetectSentiment`](comprehend_example_comprehend_DetectSentiment_section.md)
+ [`DetectSyntax`](comprehend_example_comprehend_DetectSyntax_section.md)
+ [`ListDocumentClassificationJobs`](comprehend_example_comprehend_ListDocumentClassificationJobs_section.md)
+ [`ListDocumentClassifiers`](comprehend_example_comprehend_ListDocumentClassifiers_section.md)
+ [`ListTopicsDetectionJobs`](comprehend_example_comprehend_ListTopicsDetectionJobs_section.md)
+ [`StartDocumentClassificationJob`](comprehend_example_comprehend_StartDocumentClassificationJob_section.md)
+ [`StartTopicsDetectionJob`](comprehend_example_comprehend_StartTopicsDetectionJob_section.md)
# 使用 Amazon Comprehend 执行的操作 AWS SDKs
以下代码示例演示了如何使用执行单个 Amazon Comprehend 操作。 AWS SDKs每个示例都包含一个指向的链接 GitHub，您可以在其中找到有关设置和运行代码的说明。
这些代码节选调用了 Amazon Comprehend API，是必须在上下文中运行的大型程序的代码节选。您可以在[Amazon Comprehend 使用场景 AWS SDKs](comprehend_code_examples_scenarios.md)中结合上下文查看操作。
以下示例仅包括最常用的操作。有关完整列表，请参阅 [Amazon Comprehend API 参考](https://docs.aws.amazon.com/comprehend/latest/APIReference/welcome.html)。
**Topics**
+ [`CreateDocumentClassifier`](comprehend_example_comprehend_CreateDocumentClassifier_section.md)
+ [`DeleteDocumentClassifier`](comprehend_example_comprehend_DeleteDocumentClassifier_section.md)
+ [`DescribeDocumentClassificationJob`](comprehend_example_comprehend_DescribeDocumentClassificationJob_section.md)
+ [`DescribeDocumentClassifier`](comprehend_example_comprehend_DescribeDocumentClassifier_section.md)
+ [`DescribeTopicsDetectionJob`](comprehend_example_comprehend_DescribeTopicsDetectionJob_section.md)
+ [`DetectDominantLanguage`](comprehend_example_comprehend_DetectDominantLanguage_section.md)
+ [`DetectEntities`](comprehend_example_comprehend_DetectEntities_section.md)
+ [`DetectKeyPhrases`](comprehend_example_comprehend_DetectKeyPhrases_section.md)
+ [`DetectPiiEntities`](comprehend_example_comprehend_DetectPiiEntities_section.md)
+ [`DetectSentiment`](comprehend_example_comprehend_DetectSentiment_section.md)
+ [`DetectSyntax`](comprehend_example_comprehend_DetectSyntax_section.md)
+ [`ListDocumentClassificationJobs`](comprehend_example_comprehend_ListDocumentClassificationJobs_section.md)
+ [`ListDocumentClassifiers`](comprehend_example_comprehend_ListDocumentClassifiers_section.md)
+ [`ListTopicsDetectionJobs`](comprehend_example_comprehend_ListTopicsDetectionJobs_section.md)
+ [`StartDocumentClassificationJob`](comprehend_example_comprehend_StartDocumentClassificationJob_section.md)
+ [`StartTopicsDetectionJob`](comprehend_example_comprehend_StartTopicsDetectionJob_section.md)
# `CreateDocumentClassifier`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `CreateDocumentClassifier`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**创建文档分类器对文档进行分类**
以下 `create-document-classifier` 示例启动文档分类器模型的训练过程。训练数据文件 `training.csv` 位于 `--input-data-config` 标签处。`training.csv` 是一个两列文档，其中第一列提供标签或分类，第二列提供文档。
```
aws comprehend create-document-classifier \
--document-classifier-name example-classifier \
--data-access-arn arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE \
--input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
--language-code en
```
输出：
```
{
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier"
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[自定义分类](https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[CreateDocumentClassifier](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/create-document-classifier.html)*中的。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import software.amazon.awssdk.services.comprehend.model.CreateDocumentClassifierRequest;
import software.amazon.awssdk.services.comprehend.model.CreateDocumentClassifierResponse;
import software.amazon.awssdk.services.comprehend.model.DocumentClassifierInputDataConfig;
/**
* Before running this code example, you can setup the necessary resources, such
* as the CSV file and IAM Roles, by following this document:
* https://aws.amazon.com/blogs/machine-learning/building-a-custom-classifier-using-amazon-comprehend/
*
* Also, set up your development environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DocumentClassifierDemo {
public static void main(String[] args) {
final String usage = """
Usage:
Where:
dataAccessRoleArn - The ARN value of the role used for this operation.
s3Uri - The Amazon S3 bucket that contains the CSV file.
documentClassifierName - The name of the document classifier.
""";
if (args.length != 3) {
System.out.println(usage);
System.exit(1);
}
String dataAccessRoleArn = args[0];
String s3Uri = args[1];
String documentClassifierName = args[2];
Region region = Region.US_EAST_1;
ComprehendClient comClient = ComprehendClient.builder()
.region(region)
.build();
createDocumentClassifier(comClient, dataAccessRoleArn, s3Uri, documentClassifierName);
comClient.close();
}
public static void createDocumentClassifier(ComprehendClient comClient, String dataAccessRoleArn, String s3Uri,
String documentClassifierName) {
try {
DocumentClassifierInputDataConfig config = DocumentClassifierInputDataConfig.builder()
.s3Uri(s3Uri)
.build();
CreateDocumentClassifierRequest createDocumentClassifierRequest = CreateDocumentClassifierRequest.builder()
.documentClassifierName(documentClassifierName)
.dataAccessRoleArn(dataAccessRoleArn)
.languageCode("en")
.inputDataConfig(config)
.build();
CreateDocumentClassifierResponse createDocumentClassifierResult = comClient
.createDocumentClassifier(createDocumentClassifierRequest);
String documentClassifierArn = createDocumentClassifierResult.documentClassifierArn();
System.out.println("Document Classifier ARN: " + documentClassifierArn);
} catch (ComprehendException e) {
System.err.println(e.awsErrorDetails().errorMessage());
System.exit(1);
}
}
}
```
+ 有关 API 的详细信息，请参阅 *AWS SDK for Java 2.x API 参考[CreateDocumentClassifier](https://docs.aws.amazon.com/goto/SdkForJavaV2/comprehend-2017-11-27/CreateDocumentClassifier)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def create(
self,
name,
language_code,
training_bucket,
training_key,
data_access_role_arn,
mode,
):
"""
Creates a custom classifier. After the classifier is created, it immediately
starts training on the data found in the specified Amazon S3 bucket. Training
can take 30 minutes or longer. The `describe_document_classifier` function
can be used to get training status and returns a status of TRAINED when the
classifier is ready to use.
:param name: The name of the classifier.
:param language_code: The language the classifier can operate on.
:param training_bucket: The Amazon S3 bucket that contains the training data.
:param training_key: The prefix used to find training data in the training
bucket. If multiple objects have the same prefix, all
of them are used.
:param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
grants Comprehend permission to read from the
training bucket.
:return: The ARN of the newly created classifier.
"""
try:
response = self.comprehend_client.create_document_classifier(
DocumentClassifierName=name,
LanguageCode=language_code,
InputDataConfig={"S3Uri": f"s3://{training_bucket}/{training_key}"},
DataAccessRoleArn=data_access_role_arn,
Mode=mode.value,
)
self.classifier_arn = response["DocumentClassifierArn"]
logger.info("Started classifier creation. Arn is: %s.", self.classifier_arn)
except ClientError:
logger.exception("Couldn't create classifier %s.", name)
raise
else:
return self.classifier_arn
```
+ 有关 API 的详细信息，请参阅适用[CreateDocumentClassifier](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/CreateDocumentClassifier)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->createdocumentclassifier(
iv_documentclassifiername = iv_classifier_name
iv_languagecode = iv_language_code
io_inputdataconfig = NEW /aws1/cl_cpddocclifierinpdat00(
iv_s3uri = iv_training_s3_uri
)
iv_dataaccessrolearn = iv_data_access_role_arn
iv_mode = iv_mode
).
MESSAGE 'Document classifier creation started.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdresrclimitexcdex.
MESSAGE 'Resource limit exceeded.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanytagsex.
MESSAGE 'Too many tags.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[CreateDocumentClassifier](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DeleteDocumentClassifier`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DeleteDocumentClassifier`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**删除自定义文档分类器**
以下 `delete-document-classifier` 示例删除了自定义文档分类器模型。
```
aws comprehend delete-document-classifier \
--document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1
```
此命令不生成任何输出。
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[管理 Amazon Comprehend 端点](https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DeleteDocumentClassifier](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/delete-document-classifier.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def delete(self):
"""
Deletes the classifier.
"""
try:
self.comprehend_client.delete_document_classifier(
DocumentClassifierArn=self.classifier_arn
)
logger.info("Deleted classifier %s.", self.classifier_arn)
self.classifier_arn = None
except ClientError:
logger.exception("Couldn't deleted classifier %s.", self.classifier_arn)
raise
```
+ 有关 API 的详细信息，请参阅适用[DeleteDocumentClassifier](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DeleteDocumentClassifier)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->deletedocumentclassifier(
iv_documentclassifierarn = iv_classifier_arn
).
MESSAGE 'Document classifier deleted.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdresourcenotfoundex.
MESSAGE 'Resource not found.' TYPE 'E'.
CATCH /aws1/cx_cpdresourceinuseex.
MESSAGE 'Resource in use.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DeleteDocumentClassifier](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DescribeDocumentClassificationJob`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DescribeDocumentClassificationJob`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**描述文档分类作业**
以下 `describe-document-classification-job` 示例将获取异步文档分类作业的属性。
```
aws comprehend describe-document-classification-job \
--job-id 123456abcdeb0e11022f22a11EXAMPLE
```
输出：
```
{
"DocumentClassificationJobProperties": {
"JobId": "123456abcdeb0e11022f22a11EXAMPLE",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:document-classification-job/123456abcdeb0e11022f22a11EXAMPLE",
"JobName": "exampleclassificationjob",
"JobStatus": "COMPLETED",
"SubmitTime": "2023-06-14T17:09:51.788000+00:00",
"EndTime": "2023-06-14T17:15:58.582000+00:00",
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/mymodel/version/1",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket/jobdata/",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-CLN-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
},
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-servicerole"
}
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[自定义分类](https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DescribeDocumentClassificationJob](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/describe-document-classification-job.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def describe_job(self, job_id):
"""
Gets metadata about a classification job.
:param job_id: The ID of the job to look up.
:return: Metadata about the job.
"""
try:
response = self.comprehend_client.describe_document_classification_job(
JobId=job_id
)
job = response["DocumentClassificationJobProperties"]
logger.info("Got classification job %s.", job["JobName"])
except ClientError:
logger.exception("Couldn't get classification job %s.", job_id)
raise
else:
return job
```
+ 有关 API 的详细信息，请参阅适用[DescribeDocumentClassificationJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DescribeDocumentClassificationJob)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->describedocclassificationjob(
iv_jobid = iv_job_id
).
MESSAGE 'Document classification job described.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdjobnotfoundex.
MESSAGE 'Job not found.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DescribeDocumentClassificationJob](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DescribeDocumentClassifier`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DescribeDocumentClassifier`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**描述文档分类器**
以下 `describe-document-classifier` 示例将获取自定义文档分类器模型的属性。
```
aws comprehend describe-document-classifier \
--document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1
```
输出：
```
{
"DocumentClassifierProperties": {
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1",
"LanguageCode": "en",
"Status": "TRAINED",
"SubmitTime": "2023-06-13T19:04:15.735000+00:00",
"EndTime": "2023-06-13T19:42:31.752000+00:00",
"TrainingStartTime": "2023-06-13T19:08:20.114000+00:00",
"TrainingEndTime": "2023-06-13T19:41:35.080000+00:00",
"InputDataConfig": {
"DataFormat": "COMPREHEND_CSV",
"S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
},
"OutputDataConfig": {},
"ClassifierMetadata": {
"NumberOfLabels": 3,
"NumberOfTrainedDocuments": 5016,
"NumberOfTestDocuments": 557,
"EvaluationMetrics": {
"Accuracy": 0.9856,
"Precision": 0.9919,
"Recall": 0.9459,
"F1Score": 0.9673,
"MicroPrecision": 0.9856,
"MicroRecall": 0.9856,
"MicroF1Score": 0.9856,
"HammingLoss": 0.0144
}
},
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
"Mode": "MULTI_CLASS"
}
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[创建和管理自定义模型](https://docs.aws.amazon.com/comprehend/latest/dg/manage-models.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DescribeDocumentClassifier](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/describe-document-classifier.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def describe(self, classifier_arn=None):
"""
Gets metadata about a custom classifier, including its current status.
:param classifier_arn: The ARN of the classifier to look up.
:return: Metadata about the classifier.
"""
if classifier_arn is not None:
self.classifier_arn = classifier_arn
try:
response = self.comprehend_client.describe_document_classifier(
DocumentClassifierArn=self.classifier_arn
)
classifier = response["DocumentClassifierProperties"]
logger.info("Got classifier %s.", self.classifier_arn)
except ClientError:
logger.exception("Couldn't get classifier %s.", self.classifier_arn)
raise
else:
return classifier
```
+ 有关 API 的详细信息，请参阅适用[DescribeDocumentClassifier](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DescribeDocumentClassifier)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->describedocumentclassifier(
iv_documentclassifierarn = iv_classifier_arn
).
MESSAGE 'Document classifier described.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdresourcenotfoundex.
MESSAGE 'Resource not found.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DescribeDocumentClassifier](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DescribeTopicsDetectionJob`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DescribeTopicsDetectionJob`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [对示例数据运行主题建模任务](comprehend_example_comprehend_Usage_TopicModeler_section.md)
------
#### [ CLI ]
**AWS CLI**
**描述主题检测作业**
以下 `describe-topics-detection-job` 示例获取异步主题检测作业的属性。
```
aws comprehend describe-topics-detection-job \
--job-id 123456abcdeb0e11022f22a11EXAMPLE
```
输出：
```
{
"TopicsDetectionJobProperties": {
"JobId": "123456abcdeb0e11022f22a11EXAMPLE",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
"JobName": "example_topics_detection",
"JobStatus": "IN_PROGRESS",
"SubmitTime": "2023-06-09T18:44:43.414000+00:00",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/testfolder/111122223333-TOPICS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
},
"NumberOfTopics": 10,
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-examplerole"
}
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的 [Amazon Comprehend 洞察的异步分析](https://docs.aws.amazon.com/comprehend/latest/dg/api-async-insights.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DescribeTopicsDetectionJob](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/describe-topics-detection-job.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendTopicModeler:
"""Encapsulates a Comprehend topic modeler."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def describe_job(self, job_id):
"""
Gets metadata about a topic modeling job.
:param job_id: The ID of the job to look up.
:return: Metadata about the job.
"""
try:
response = self.comprehend_client.describe_topics_detection_job(
JobId=job_id
)
job = response["TopicsDetectionJobProperties"]
logger.info("Got topic detection job %s.", job_id)
except ClientError:
logger.exception("Couldn't get topic detection job %s.", job_id)
raise
else:
return job
```
+ 有关 API 的详细信息，请参阅适用[DescribeTopicsDetectionJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DescribeTopicsDetectionJob)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->describetopicsdetectionjob(
iv_jobid = iv_job_id
).
MESSAGE 'Topics detection job described.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdjobnotfoundex.
MESSAGE 'Job not found.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DescribeTopicsDetectionJob](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DetectDominantLanguage`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DetectDominantLanguage`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example calls the Amazon Comprehend service to determine the
/// dominant language.
///
public static class DetectDominantLanguage
{
///
/// Calls Amazon Comprehend to determine the dominant language used in
/// the sample text.
///
public static async Task Main()
{
string text = "It is raining today in Seattle.";
var comprehendClient = new AmazonComprehendClient(Amazon.RegionEndpoint.USWest2);
Console.WriteLine("Calling DetectDominantLanguage\n");
var detectDominantLanguageRequest = new DetectDominantLanguageRequest()
{
Text = text,
};
var detectDominantLanguageResponse = await comprehendClient.DetectDominantLanguageAsync(detectDominantLanguageRequest);
foreach (var dl in detectDominantLanguageResponse.Languages)
{
Console.WriteLine($"Language Code: {dl.LanguageCode}, Score: {dl.Score}");
}
Console.WriteLine("Done");
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[DetectDominantLanguage](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/DetectDominantLanguage)*中的。
------
#### [ CLI ]
**AWS CLI**
**检测输入文本的主要语言**
以下 `detect-dominant-language` 分析输入文本并识别主要语言。预训练模型的置信度分数也是输出。
```
aws comprehend detect-dominant-language \
--text "It is a beautiful day in Seattle."
```
输出：
```
{
"Languages": [
{
"LanguageCode": "en",
"Score": 0.9877256155014038
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[主要语言](https://docs.aws.amazon.com/comprehend/latest/dg/how-languages.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DetectDominantLanguage](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/detect-dominant-language.html)*中的。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import software.amazon.awssdk.services.comprehend.model.DetectDominantLanguageRequest;
import software.amazon.awssdk.services.comprehend.model.DetectDominantLanguageResponse;
import software.amazon.awssdk.services.comprehend.model.DominantLanguage;
import java.util.List;
/**
* Before running this Java V2 code example, set up your development
* environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DetectLanguage {
public static void main(String[] args) {
// Specify French text - "It is raining today in Seattle".
String text = "Il pleut aujourd'hui à Seattle";
Region region = Region.US_EAST_1;
ComprehendClient comClient = ComprehendClient.builder()
.region(region)
.build();
System.out.println("Calling DetectDominantLanguage");
detectTheDominantLanguage(comClient, text);
comClient.close();
}
public static void detectTheDominantLanguage(ComprehendClient comClient, String text) {
try {
DetectDominantLanguageRequest request = DetectDominantLanguageRequest.builder()
.text(text)
.build();
DetectDominantLanguageResponse resp = comClient.detectDominantLanguage(request);
List allLanList = resp.languages();
for (DominantLanguage lang : allLanList) {
System.out.println("Language is " + lang.languageCode());
}
} catch (ComprehendException e) {
System.err.println(e.awsErrorDetails().errorMessage());
System.exit(1);
}
}
}
```
+ 有关 API 的详细信息，请参阅 *AWS SDK for Java 2.x API 参考[DetectDominantLanguage](https://docs.aws.amazon.com/goto/SdkForJavaV2/comprehend-2017-11-27/DetectDominantLanguage)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_languages(self, text):
"""
Detects languages used in a document.
:param text: The document to inspect.
:return: The list of languages along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_dominant_language(Text=text)
languages = response["Languages"]
logger.info("Detected %s languages.", len(languages))
except ClientError:
logger.exception("Couldn't detect languages.")
raise
else:
return languages
```
+ 有关 API 的详细信息，请参阅适用[DetectDominantLanguage](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectDominantLanguage)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->detectdominantlanguage( iv_text = iv_text ).
MESSAGE 'Languages detected.' TYPE 'I'.
CATCH /aws1/cx_cpdtextsizelmtexcdex.
MESSAGE 'Text size exceeds limit.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DetectDominantLanguage](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DetectEntities`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DetectEntities`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example shows how to use the AmazonComprehend service detect any
/// entities in submitted text.
///
public static class DetectEntities
{
///
/// The main method calls the DetectEntitiesAsync method to find any
/// entities in the sample code.
///
public static async Task Main()
{
string text = "It is raining today in Seattle";
var comprehendClient = new AmazonComprehendClient();
Console.WriteLine("Calling DetectEntities\n");
var detectEntitiesRequest = new DetectEntitiesRequest()
{
Text = text,
LanguageCode = "en",
};
var detectEntitiesResponse = await comprehendClient.DetectEntitiesAsync(detectEntitiesRequest);
foreach (var e in detectEntitiesResponse.Entities)
{
Console.WriteLine($"Text: {e.Text}, Type: {e.Type}, Score: {e.Score}, BeginOffset: {e.BeginOffset}, EndOffset: {e.EndOffset}");
}
Console.WriteLine("Done");
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[DetectEntities](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/DetectEntities)*中的。
------
#### [ CLI ]
**AWS CLI**
**检测输入文本中的命名实体**
以下 `detect-entities` 示例分析输入文本并返回命名实体。预训练模型的置信度分数也是每个预测的输出。
```
aws comprehend detect-entities \
--language-code en \
--text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."
```
输出：
```
{
"Entities": [
{
"Score": 0.9994556307792664,
"Type": "PERSON",
"Text": "Zhang Wei",
"BeginOffset": 6,
"EndOffset": 15
},
{
"Score": 0.9981022477149963,
"Type": "PERSON",
"Text": "John",
"BeginOffset": 22,
"EndOffset": 26
},
{
"Score": 0.9986887574195862,
"Type": "ORGANIZATION",
"Text": "AnyCompany Financial Services, LLC",
"BeginOffset": 33,
"EndOffset": 67
},
{
"Score": 0.9959119558334351,
"Type": "OTHER",
"Text": "1111-XXXX-1111-XXXX",
"BeginOffset": 88,
"EndOffset": 107
},
{
"Score": 0.9708039164543152,
"Type": "QUANTITY",
"Text": ".53",
"BeginOffset": 133,
"EndOffset": 136
},
{
"Score": 0.9987268447875977,
"Type": "DATE",
"Text": "July 31st",
"BeginOffset": 152,
"EndOffset": 161
},
{
"Score": 0.9858865737915039,
"Type": "OTHER",
"Text": "XXXXXX1111",
"BeginOffset": 271,
"EndOffset": 281
},
{
"Score": 0.9700471758842468,
"Type": "OTHER",
"Text": "XXXXX0000",
"BeginOffset": 306,
"EndOffset": 315
},
{
"Score": 0.9591118693351746,
"Type": "ORGANIZATION",
"Text": "Sunshine Spa",
"BeginOffset": 340,
"EndOffset": 352
},
{
"Score": 0.9797496795654297,
"Type": "LOCATION",
"Text": "123 Main St",
"BeginOffset": 354,
"EndOffset": 365
},
{
"Score": 0.994929313659668,
"Type": "PERSON",
"Text": "Alice",
"BeginOffset": 394,
"EndOffset": 399
},
{
"Score": 0.9949769377708435,
"Type": "OTHER",
"Text": "AnySpa@example.com",
"BeginOffset": 403,
"EndOffset": 418
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[实体](https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DetectEntities](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/detect-entities.html)*中的。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.DetectEntitiesRequest;
import software.amazon.awssdk.services.comprehend.model.DetectEntitiesResponse;
import software.amazon.awssdk.services.comprehend.model.Entity;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import java.util.List;
/**
* Before running this Java V2 code example, set up your development
* environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DetectEntities {
public static void main(String[] args) {
String text = "Amazon.com, Inc. is located in Seattle, WA and was founded July 5th, 1994 by Jeff Bezos, allowing customers to buy everything from books to blenders. Seattle is north of Portland and south of Vancouver, BC. Other notable Seattle - based companies are Starbucks and Boeing.";
Region region = Region.US_EAST_1;
ComprehendClient comClient = ComprehendClient.builder()
.region(region)
.build();
System.out.println("Calling DetectEntities");
detectAllEntities(comClient, text);
comClient.close();
}
public static void detectAllEntities(ComprehendClient comClient, String text) {
try {
DetectEntitiesRequest detectEntitiesRequest = DetectEntitiesRequest.builder()
.text(text)
.languageCode("en")
.build();
DetectEntitiesResponse detectEntitiesResult = comClient.detectEntities(detectEntitiesRequest);
List entList = detectEntitiesResult.entities();
for (Entity entity : entList) {
System.out.println("Entity text is " + entity.text());
}
} catch (ComprehendException e) {
System.err.println(e.awsErrorDetails().errorMessage());
System.exit(1);
}
}
}
```
+ 有关 API 的详细信息，请参阅 *AWS SDK for Java 2.x API 参考[DetectEntities](https://docs.aws.amazon.com/goto/SdkForJavaV2/comprehend-2017-11-27/DetectEntities)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_entities(self, text, language_code):
"""
Detects entities in a document. Entities can be things like people and places
or other common terms.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of entities along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_entities(
Text=text, LanguageCode=language_code
)
entities = response["Entities"]
logger.info("Detected %s entities.", len(entities))
except ClientError:
logger.exception("Couldn't detect entities.")
raise
else:
return entities
```
+ 有关 API 的详细信息，请参阅适用[DetectEntities](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectEntities)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->detectentities(
iv_text = iv_text
iv_languagecode = iv_language_code
).
MESSAGE 'Entities detected.' TYPE 'I'.
CATCH /aws1/cx_cpdtextsizelmtexcdex.
MESSAGE 'Text size exceeds limit.' TYPE 'E'.
CATCH /aws1/cx_cpdunsuppedlanguageex.
MESSAGE 'Unsupported language.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DetectEntities](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DetectKeyPhrases`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DetectKeyPhrases`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example shows how to use the Amazon Comprehend service to
/// search text for key phrases.
///
public static class DetectKeyPhrase
{
///
/// This method calls the Amazon Comprehend method DetectKeyPhrasesAsync
/// to detect any key phrases in the sample text.
///
public static async Task Main()
{
string text = "It is raining today in Seattle";
var comprehendClient = new AmazonComprehendClient(Amazon.RegionEndpoint.USWest2);
// Call DetectKeyPhrases API
Console.WriteLine("Calling DetectKeyPhrases");
var detectKeyPhrasesRequest = new DetectKeyPhrasesRequest()
{
Text = text,
LanguageCode = "en",
};
var detectKeyPhrasesResponse = await comprehendClient.DetectKeyPhrasesAsync(detectKeyPhrasesRequest);
foreach (var kp in detectKeyPhrasesResponse.KeyPhrases)
{
Console.WriteLine($"Text: {kp.Text}, Score: {kp.Score}, BeginOffset: {kp.BeginOffset}, EndOffset: {kp.EndOffset}");
}
Console.WriteLine("Done");
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[DetectKeyPhrases](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/DetectKeyPhrases)*中的。
------
#### [ CLI ]
**AWS CLI**
**检测输入文本中的关键词**
以下 `detect-key-phrases` 示例分析输入文本并识别关键名词短语。预训练模型的置信度分数也是每个预测的输出。
```
aws comprehend detect-key-phrases \
--language-code en \
--text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."
```
输出：
```
{
"KeyPhrases": [
{
"Score": 0.8996376395225525,
"Text": "Zhang Wei",
"BeginOffset": 6,
"EndOffset": 15
},
{
"Score": 0.9992469549179077,
"Text": "John",
"BeginOffset": 22,
"EndOffset": 26
},
{
"Score": 0.988385021686554,
"Text": "Your AnyCompany Financial Services",
"BeginOffset": 28,
"EndOffset": 62
},
{
"Score": 0.8740853071212769,
"Text": "LLC credit card account 1111-XXXX-1111-XXXX",
"BeginOffset": 64,
"EndOffset": 107
},
{
"Score": 0.9999437928199768,
"Text": "a minimum payment",
"BeginOffset": 112,
"EndOffset": 129
},
{
"Score": 0.9998900890350342,
"Text": ".53",
"BeginOffset": 133,
"EndOffset": 136
},
{
"Score": 0.9979453086853027,
"Text": "July 31st",
"BeginOffset": 152,
"EndOffset": 161
},
{
"Score": 0.9983011484146118,
"Text": "your autopay settings",
"BeginOffset": 172,
"EndOffset": 193
},
{
"Score": 0.9996572136878967,
"Text": "your payment",
"BeginOffset": 211,
"EndOffset": 223
},
{
"Score": 0.9995037317276001,
"Text": "the due date",
"BeginOffset": 227,
"EndOffset": 239
},
{
"Score": 0.9702621698379517,
"Text": "your bank account number XXXXXX1111",
"BeginOffset": 245,
"EndOffset": 280
},
{
"Score": 0.9179925918579102,
"Text": "the routing number XXXXX0000.Customer feedback",
"BeginOffset": 286,
"EndOffset": 332
},
{
"Score": 0.9978160858154297,
"Text": "Sunshine Spa",
"BeginOffset": 337,
"EndOffset": 349
},
{
"Score": 0.9706913232803345,
"Text": "123 Main St",
"BeginOffset": 351,
"EndOffset": 362
},
{
"Score": 0.9941995143890381,
"Text": "comments",
"BeginOffset": 379,
"EndOffset": 387
},
{
"Score": 0.9759287238121033,
"Text": "Alice",
"BeginOffset": 391,
"EndOffset": 396
},
{
"Score": 0.8376792669296265,
"Text": "AnySpa@example.com",
"BeginOffset": 400,
"EndOffset": 415
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[关键词](https://docs.aws.amazon.com/comprehend/latest/dg/how-key-phrases.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DetectKeyPhrases](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/detect-key-phrases.html)*中的。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.DetectKeyPhrasesRequest;
import software.amazon.awssdk.services.comprehend.model.DetectKeyPhrasesResponse;
import software.amazon.awssdk.services.comprehend.model.KeyPhrase;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import java.util.List;
/**
* Before running this Java V2 code example, set up your development
* environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DetectKeyPhrases {
public static void main(String[] args) {
String text = "Amazon.com, Inc. is located in Seattle, WA and was founded July 5th, 1994 by Jeff Bezos, allowing customers to buy everything from books to blenders. Seattle is north of Portland and south of Vancouver, BC. Other notable Seattle - based companies are Starbucks and Boeing.";
Region region = Region.US_EAST_1;
ComprehendClient comClient = ComprehendClient.builder()
.region(region)
.build();
System.out.println("Calling DetectKeyPhrases");
detectAllKeyPhrases(comClient, text);
comClient.close();
}
public static void detectAllKeyPhrases(ComprehendClient comClient, String text) {
try {
DetectKeyPhrasesRequest detectKeyPhrasesRequest = DetectKeyPhrasesRequest.builder()
.text(text)
.languageCode("en")
.build();
DetectKeyPhrasesResponse detectKeyPhrasesResult = comClient.detectKeyPhrases(detectKeyPhrasesRequest);
List phraseList = detectKeyPhrasesResult.keyPhrases();
for (KeyPhrase keyPhrase : phraseList) {
System.out.println("Key phrase text is " + keyPhrase.text());
}
} catch (ComprehendException e) {
System.err.println(e.awsErrorDetails().errorMessage());
System.exit(1);
}
}
}
```
+ 有关 API 的详细信息，请参阅 *AWS SDK for Java 2.x API 参考[DetectKeyPhrases](https://docs.aws.amazon.com/goto/SdkForJavaV2/comprehend-2017-11-27/DetectKeyPhrases)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_key_phrases(self, text, language_code):
"""
Detects key phrases in a document. A key phrase is typically a noun and its
modifiers.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of key phrases along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_key_phrases(
Text=text, LanguageCode=language_code
)
phrases = response["KeyPhrases"]
logger.info("Detected %s phrases.", len(phrases))
except ClientError:
logger.exception("Couldn't detect phrases.")
raise
else:
return phrases
```
+ 有关 API 的详细信息，请参阅适用[DetectKeyPhrases](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectKeyPhrases)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->detectkeyphrases(
iv_text = iv_text
iv_languagecode = iv_language_code
).
MESSAGE 'Key phrases detected.' TYPE 'I'.
CATCH /aws1/cx_cpdtextsizelmtexcdex.
MESSAGE 'Text size exceeds limit.' TYPE 'E'.
CATCH /aws1/cx_cpdunsuppedlanguageex.
MESSAGE 'Unsupported language.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DetectKeyPhrases](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DetectPiiEntities`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DetectPiiEntities`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example shows how to use the Amazon Comprehend service to find
/// personally identifiable information (PII) within text submitted to the
/// DetectPiiEntitiesAsync method.
///
public class DetectingPII
{
///
/// This method calls the DetectPiiEntitiesAsync method to locate any
/// personally dientifiable information within the supplied text.
///
public static async Task Main()
{
var comprehendClient = new AmazonComprehendClient();
var text = @"Hello Paul Santos. The latest statement for your
credit card account 1111-0000-1111-0000 was
mailed to 123 Any Street, Seattle, WA 98109.";
var request = new DetectPiiEntitiesRequest
{
Text = text,
LanguageCode = "EN",
};
var response = await comprehendClient.DetectPiiEntitiesAsync(request);
if (response.Entities.Count > 0)
{
foreach (var entity in response.Entities)
{
var entityValue = text.Substring(entity.BeginOffset, entity.EndOffset - entity.BeginOffset);
Console.WriteLine($"{entity.Type}: {entityValue}");
}
}
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[DetectPiiEntities](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/DetectPiiEntities)*中的。
------
#### [ CLI ]
**AWS CLI**
**检测输入文本中的 PII 实体**
以下 `detect-pii-entities` 示例分析输入文本，并识别包含个人身份信息（PII）的实体。预训练模型的置信度分数也是每个预测的输出。
```
aws comprehend detect-pii-entities \
--language-code en \
--text "Hello Zhang Wei, I am John. Your AnyCompany Financial Services, LLC credit card \
account 1111-XXXX-1111-XXXX has a minimum payment of $24.53 that is due by July 31st. Based on your autopay settings, \
we will withdraw your payment on the due date from your bank account number XXXXXX1111 with the routing number XXXXX0000. \
Customer feedback for Sunshine Spa, 123 Main St, Anywhere. Send comments to Alice at AnySpa@example.com."
```
输出：
```
{
"Entities": [
{
"Score": 0.9998322129249573,
"Type": "NAME",
"BeginOffset": 6,
"EndOffset": 15
},
{
"Score": 0.9998878240585327,
"Type": "NAME",
"BeginOffset": 22,
"EndOffset": 26
},
{
"Score": 0.9994089603424072,
"Type": "CREDIT_DEBIT_NUMBER",
"BeginOffset": 88,
"EndOffset": 107
},
{
"Score": 0.9999760985374451,
"Type": "DATE_TIME",
"BeginOffset": 152,
"EndOffset": 161
},
{
"Score": 0.9999449253082275,
"Type": "BANK_ACCOUNT_NUMBER",
"BeginOffset": 271,
"EndOffset": 281
},
{
"Score": 0.9999847412109375,
"Type": "BANK_ROUTING",
"BeginOffset": 306,
"EndOffset": 315
},
{
"Score": 0.999925434589386,
"Type": "ADDRESS",
"BeginOffset": 354,
"EndOffset": 365
},
{
"Score": 0.9989161491394043,
"Type": "NAME",
"BeginOffset": 394,
"EndOffset": 399
},
{
"Score": 0.9994171857833862,
"Type": "EMAIL",
"BeginOffset": 403,
"EndOffset": 418
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[个人身份信息（PII）](https://docs.aws.amazon.com/comprehend/latest/dg/pii.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DetectPiiEntities](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/detect-pii-entities.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_pii(self, text, language_code):
"""
Detects personally identifiable information (PII) in a document. PII can be
things like names, account numbers, or addresses.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of PII entities along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_pii_entities(
Text=text, LanguageCode=language_code
)
entities = response["Entities"]
logger.info("Detected %s PII entities.", len(entities))
except ClientError:
logger.exception("Couldn't detect PII entities.")
raise
else:
return entities
```
+ 有关 API 的详细信息，请参阅适用[DetectPiiEntities](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectPiiEntities)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->detectpiientities(
iv_text = iv_text
iv_languagecode = iv_language_code
).
MESSAGE 'PII entities detected.' TYPE 'I'.
CATCH /aws1/cx_cpdtextsizelmtexcdex.
MESSAGE 'Text size exceeds limit.' TYPE 'E'.
CATCH /aws1/cx_cpdunsuppedlanguageex.
MESSAGE 'Unsupported language.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DetectPiiEntities](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DetectSentiment`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DetectSentiment`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example shows how to detect the overall sentiment of the supplied
/// text using the Amazon Comprehend service.
///
public static class DetectSentiment
{
///
/// This method calls the DetetectSentimentAsync method to analyze the
/// supplied text and determine the overal sentiment.
///
public static async Task Main()
{
string text = "It is raining today in Seattle";
var comprehendClient = new AmazonComprehendClient(Amazon.RegionEndpoint.USWest2);
// Call DetectKeyPhrases API
Console.WriteLine("Calling DetectSentiment");
var detectSentimentRequest = new DetectSentimentRequest()
{
Text = text,
LanguageCode = "en",
};
var detectSentimentResponse = await comprehendClient.DetectSentimentAsync(detectSentimentRequest);
Console.WriteLine($"Sentiment: {detectSentimentResponse.Sentiment}");
Console.WriteLine("Done");
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[DetectSentiment](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/DetectSentiment)*中的。
------
#### [ CLI ]
**AWS CLI**
**检测输入文本的情绪**
以下 `detect-sentiment` 示例分析输入文本，并返回占主导地位的情绪（`POSITIVE`、`NEUTRAL`、`MIXED` 或`NEGATIVE`）的推断。
```
aws comprehend detect-sentiment \
--language-code en \
--text "It is a beautiful day in Seattle"
```
输出：
```
{
"Sentiment": "POSITIVE",
"SentimentScore": {
"Positive": 0.9976957440376282,
"Negative": 9.653854067437351e-05,
"Neutral": 0.002169104292988777,
"Mixed": 3.857641786453314e-05
}
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[情绪](https://docs.aws.amazon.com/comprehend/latest/dg/how-sentiment.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DetectSentiment](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/detect-sentiment.html)*中的。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import software.amazon.awssdk.services.comprehend.model.DetectSentimentRequest;
import software.amazon.awssdk.services.comprehend.model.DetectSentimentResponse;
/**
* Before running this Java V2 code example, set up your development
* environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DetectSentiment {
public static void main(String[] args) {
String text = "Amazon.com, Inc. is located in Seattle, WA and was founded July 5th, 1994 by Jeff Bezos, allowing customers to buy everything from books to blenders. Seattle is north of Portland and south of Vancouver, BC. Other notable Seattle - based companies are Starbucks and Boeing.";
Region region = Region.US_EAST_1;
ComprehendClient comClient = ComprehendClient.builder()
.region(region)
.build();
System.out.println("Calling DetectSentiment");
detectSentiments(comClient, text);
comClient.close();
}
public static void detectSentiments(ComprehendClient comClient, String text) {
try {
DetectSentimentRequest detectSentimentRequest = DetectSentimentRequest.builder()
.text(text)
.languageCode("en")
.build();
DetectSentimentResponse detectSentimentResult = comClient.detectSentiment(detectSentimentRequest);
System.out.println("The Neutral value is " + detectSentimentResult.sentimentScore().neutral());
} catch (ComprehendException e) {
System.err.println(e.awsErrorDetails().errorMessage());
System.exit(1);
}
}
}
```
+ 有关 API 的详细信息，请参阅 *AWS SDK for Java 2.x API 参考[DetectSentiment](https://docs.aws.amazon.com/goto/SdkForJavaV2/comprehend-2017-11-27/DetectSentiment)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_sentiment(self, text, language_code):
"""
Detects the overall sentiment expressed in a document. Sentiment can
be positive, negative, neutral, or a mixture.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The sentiments along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_sentiment(
Text=text, LanguageCode=language_code
)
logger.info("Detected primary sentiment %s.", response["Sentiment"])
except ClientError:
logger.exception("Couldn't detect sentiment.")
raise
else:
return response
```
+ 有关 API 的详细信息，请参阅适用[DetectSentiment](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectSentiment)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->detectsentiment(
iv_text = iv_text
iv_languagecode = iv_language_code
).
MESSAGE 'Sentiment detected.' TYPE 'I'.
CATCH /aws1/cx_cpdtextsizelmtexcdex.
MESSAGE 'Text size exceeds limit.' TYPE 'E'.
CATCH /aws1/cx_cpdunsuppedlanguageex.
MESSAGE 'Unsupported language.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DetectSentiment](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `DetectSyntax`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `DetectSyntax`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example shows how to use Amazon Comprehend to detect syntax
/// elements by calling the DetectSyntaxAsync method.
///
public class DetectingSyntax
{
///
/// This method calls DetectSynaxAsync to identify the syntax elements
/// in the sample text.
///
public static async Task Main()
{
string text = "It is raining today in Seattle";
var comprehendClient = new AmazonComprehendClient();
// Call DetectSyntax API
Console.WriteLine("Calling DetectSyntaxAsync\n");
var detectSyntaxRequest = new DetectSyntaxRequest()
{
Text = text,
LanguageCode = "en",
};
DetectSyntaxResponse detectSyntaxResponse = await comprehendClient.DetectSyntaxAsync(detectSyntaxRequest);
foreach (SyntaxToken s in detectSyntaxResponse.SyntaxTokens)
{
Console.WriteLine($"Text: {s.Text}, PartOfSpeech: {s.PartOfSpeech.Tag}, BeginOffset: {s.BeginOffset}, EndOffset: {s.EndOffset}");
}
Console.WriteLine("Done");
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[DetectSyntax](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/DetectSyntax)*中的。
------
#### [ CLI ]
**AWS CLI**
**检测输入文本中的语音部分**
以下 `detect-syntax` 示例分析输入文本的语法并返回语音的不同部分。预训练模型的置信度分数也是每个预测的输出。
```
aws comprehend detect-syntax \
--language-code en \
--text "It is a beautiful day in Seattle."
```
输出：
```
{
"SyntaxTokens": [
{
"TokenId": 1,
"Text": "It",
"BeginOffset": 0,
"EndOffset": 2,
"PartOfSpeech": {
"Tag": "PRON",
"Score": 0.9999740719795227
}
},
{
"TokenId": 2,
"Text": "is",
"BeginOffset": 3,
"EndOffset": 5,
"PartOfSpeech": {
"Tag": "VERB",
"Score": 0.999901294708252
}
},
{
"TokenId": 3,
"Text": "a",
"BeginOffset": 6,
"EndOffset": 7,
"PartOfSpeech": {
"Tag": "DET",
"Score": 0.9999938607215881
}
},
{
"TokenId": 4,
"Text": "beautiful",
"BeginOffset": 8,
"EndOffset": 17,
"PartOfSpeech": {
"Tag": "ADJ",
"Score": 0.9987351894378662
}
},
{
"TokenId": 5,
"Text": "day",
"BeginOffset": 18,
"EndOffset": 21,
"PartOfSpeech": {
"Tag": "NOUN",
"Score": 0.9999796748161316
}
},
{
"TokenId": 6,
"Text": "in",
"BeginOffset": 22,
"EndOffset": 24,
"PartOfSpeech": {
"Tag": "ADP",
"Score": 0.9998047947883606
}
},
{
"TokenId": 7,
"Text": "Seattle",
"BeginOffset": 25,
"EndOffset": 32,
"PartOfSpeech": {
"Tag": "PROPN",
"Score": 0.9940530061721802
}
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[语法分析](https://docs.aws.amazon.com/comprehend/latest/dg/how-syntax.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[DetectSyntax](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/detect-syntax.html)*中的。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import software.amazon.awssdk.services.comprehend.model.DetectSyntaxRequest;
import software.amazon.awssdk.services.comprehend.model.DetectSyntaxResponse;
import software.amazon.awssdk.services.comprehend.model.SyntaxToken;
import java.util.List;
/**
* Before running this Java V2 code example, set up your development
* environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DetectSyntax {
public static void main(String[] args) {
String text = "Amazon.com, Inc. is located in Seattle, WA and was founded July 5th, 1994 by Jeff Bezos, allowing customers to buy everything from books to blenders. Seattle is north of Portland and south of Vancouver, BC. Other notable Seattle - based companies are Starbucks and Boeing.";
Region region = Region.US_EAST_1;
ComprehendClient comClient = ComprehendClient.builder()
.region(region)
.build();
System.out.println("Calling DetectSyntax");
detectAllSyntax(comClient, text);
comClient.close();
}
public static void detectAllSyntax(ComprehendClient comClient, String text) {
try {
DetectSyntaxRequest detectSyntaxRequest = DetectSyntaxRequest.builder()
.text(text)
.languageCode("en")
.build();
DetectSyntaxResponse detectSyntaxResult = comClient.detectSyntax(detectSyntaxRequest);
List syntaxTokens = detectSyntaxResult.syntaxTokens();
for (SyntaxToken token : syntaxTokens) {
System.out.println("Language is " + token.text());
System.out.println("Part of speech is " + token.partOfSpeech().tagAsString());
}
} catch (ComprehendException e) {
System.err.println(e.awsErrorDetails().errorMessage());
System.exit(1);
}
}
}
```
+ 有关 API 的详细信息，请参阅 *AWS SDK for Java 2.x API 参考[DetectSyntax](https://docs.aws.amazon.com/goto/SdkForJavaV2/comprehend-2017-11-27/DetectSyntax)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_syntax(self, text, language_code):
"""
Detects syntactical elements of a document. Syntax tokens are portions of
text along with their use as parts of speech, such as nouns, verbs, and
interjections.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of syntax tokens along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_syntax(
Text=text, LanguageCode=language_code
)
tokens = response["SyntaxTokens"]
logger.info("Detected %s syntax tokens.", len(tokens))
except ClientError:
logger.exception("Couldn't detect syntax.")
raise
else:
return tokens
```
+ 有关 API 的详细信息，请参阅适用[DetectSyntax](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectSyntax)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->detectsyntax(
iv_text = iv_text
iv_languagecode = iv_language_code
).
MESSAGE 'Syntax tokens detected.' TYPE 'I'.
CATCH /aws1/cx_cpdtextsizelmtexcdex.
MESSAGE 'Text size exceeds limit.' TYPE 'E'.
CATCH /aws1/cx_cpdunsuppedlanguageex.
MESSAGE 'Unsupported language.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[DetectSyntax](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `ListDocumentClassificationJobs`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `ListDocumentClassificationJobs`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**列出所有文档分类作业**
以下 `list-document-classification-jobs` 示例列出所有文档分类作业。
```
aws comprehend list-document-classification-jobs
```
输出：
```
{
"DocumentClassificationJobPropertiesList": [
{
"JobId": "123456abcdeb0e11022f22a11EXAMPLE",
"JobArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classification-job/123456abcdeb0e11022f22a11EXAMPLE",
"JobName": "exampleclassificationjob",
"JobStatus": "COMPLETED",
"SubmitTime": "2023-06-14T17:09:51.788000+00:00",
"EndTime": "2023-06-14T17:15:58.582000+00:00",
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classifier/mymodel/version/12",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket/jobdata/",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/1234567890101-CLN-e758dd56b824aa717ceab551f11749fb/output/output.tar.gz"
},
"DataAccessRoleArn": "arn:aws:iam::1234567890101:role/service-role/AmazonComprehendServiceRole-example-role"
},
{
"JobId": "123456abcdeb0e11022f22a1EXAMPLE2",
"JobArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classification-job/123456abcdeb0e11022f22a1EXAMPLE2",
"JobName": "exampleclassificationjob2",
"JobStatus": "COMPLETED",
"SubmitTime": "2023-06-14T17:22:39.829000+00:00",
"EndTime": "2023-06-14T17:28:46.107000+00:00",
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:1234567890101:document-classifier/mymodel/version/12",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket/jobdata/",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/1234567890101-CLN-123456abcdeb0e11022f22a1EXAMPLE2/output/output.tar.gz"
},
"DataAccessRoleArn": "arn:aws:iam::1234567890101:role/service-role/AmazonComprehendServiceRole-example-role"
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[自定义分类](https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[ListDocumentClassificationJobs](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/list-document-classification-jobs.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def list_jobs(self):
"""
Lists the classification jobs for the current account.
:return: The list of jobs.
"""
try:
response = self.comprehend_client.list_document_classification_jobs()
jobs = response["DocumentClassificationJobPropertiesList"]
logger.info("Got %s document classification jobs.", len(jobs))
except ClientError:
logger.exception(
"Couldn't get document classification jobs.",
)
raise
else:
return jobs
```
+ 有关 API 的详细信息，请参阅适用[ListDocumentClassificationJobs](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/ListDocumentClassificationJobs)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->listdocclassificationjobs( ).
MESSAGE 'Document classification jobs listed.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidfilterex.
MESSAGE 'Invalid filter.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[ListDocumentClassificationJobs](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `ListDocumentClassifiers`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `ListDocumentClassifiers`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**列出所有文档分类器**
以下 `list-document-classifiers` 示例列出所有经过训练和正在训练的文档分类器模型。
```
aws comprehend list-document-classifiers
```
输出：
```
{
"DocumentClassifierPropertiesList": [
{
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier1",
"LanguageCode": "en",
"Status": "TRAINED",
"SubmitTime": "2023-06-13T19:04:15.735000+00:00",
"EndTime": "2023-06-13T19:42:31.752000+00:00",
"TrainingStartTime": "2023-06-13T19:08:20.114000+00:00",
"TrainingEndTime": "2023-06-13T19:41:35.080000+00:00",
"InputDataConfig": {
"DataFormat": "COMPREHEND_CSV",
"S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
},
"OutputDataConfig": {},
"ClassifierMetadata": {
"NumberOfLabels": 3,
"NumberOfTrainedDocuments": 5016,
"NumberOfTestDocuments": 557,
"EvaluationMetrics": {
"Accuracy": 0.9856,
"Precision": 0.9919,
"Recall": 0.9459,
"F1Score": 0.9673,
"MicroPrecision": 0.9856,
"MicroRecall": 0.9856,
"MicroF1Score": 0.9856,
"HammingLoss": 0.0144
}
},
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-testorle",
"Mode": "MULTI_CLASS"
},
{
"DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/exampleclassifier2",
"LanguageCode": "en",
"Status": "TRAINING",
"SubmitTime": "2023-06-13T21:20:28.690000+00:00",
"InputDataConfig": {
"DataFormat": "COMPREHEND_CSV",
"S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
},
"OutputDataConfig": {},
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-testorle",
"Mode": "MULTI_CLASS"
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[创建和管理自定义模型](https://docs.aws.amazon.com/comprehend/latest/dg/manage-models.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[ListDocumentClassifiers](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/list-document-classifiers.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def list(self):
"""
Lists custom classifiers for the current account.
:return: The list of classifiers.
"""
try:
response = self.comprehend_client.list_document_classifiers()
classifiers = response["DocumentClassifierPropertiesList"]
logger.info("Got %s classifiers.", len(classifiers))
except ClientError:
logger.exception(
"Couldn't get classifiers.",
)
raise
else:
return classifiers
```
+ 有关 API 的详细信息，请参阅适用[ListDocumentClassifiers](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/ListDocumentClassifiers)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->listdocumentclassifiers( ).
MESSAGE 'Document classifiers listed.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidfilterex.
MESSAGE 'Invalid filter.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[ListDocumentClassifiers](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `ListTopicsDetectionJobs`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `ListTopicsDetectionJobs`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [对示例数据运行主题建模任务](comprehend_example_comprehend_Usage_TopicModeler_section.md)
------
#### [ CLI ]
**AWS CLI**
**列出所有主题检测作业**
以下 `list-topics-detection-jobs` 示例列出所有正在进行和已完成的异步主题检测作业。
```
aws comprehend list-topics-detection-jobs
```
输出：
```
{
"TopicsDetectionJobPropertiesList": [
{
"JobId": "123456abcdeb0e11022f22a11EXAMPLE",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
"JobName" "topic-analysis-1"
"JobStatus": "IN_PROGRESS",
"SubmitTime": "2023-06-09T18:40:35.384000+00:00",
"EndTime": "2023-06-09T18:46:41.936000+00:00",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-TOPICS-123456abcdeb0e11022f22a11EXAMPLE/output/output.tar.gz"
},
"NumberOfTopics": 10,
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
},
{
"JobId": "123456abcdeb0e11022f22a1EXAMPLE2",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a1EXAMPLE2",
"JobName": "topic-analysis-2",
"JobStatus": "COMPLETED",
"SubmitTime": "2023-06-09T18:44:43.414000+00:00",
"EndTime": "2023-06-09T18:50:50.872000+00:00",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-TOPICS-123456abcdeb0e11022f22a1EXAMPLE2/output/output.tar.gz"
},
"NumberOfTopics": 10,
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
},
{
"JobId": "123456abcdeb0e11022f22a1EXAMPLE3",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/123456abcdeb0e11022f22a1EXAMPLE3",
"JobName": "topic-analysis-2",
"JobStatus": "IN_PROGRESS",
"SubmitTime": "2023-06-09T18:50:56.737000+00:00",
"InputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-bucket",
"InputFormat": "ONE_DOC_PER_LINE"
},
"OutputDataConfig": {
"S3Uri": "s3://amzn-s3-demo-destination-bucket/thefolder/111122223333-TOPICS-123456abcdeb0e11022f22a1EXAMPLE3/output/output.tar.gz"
},
"NumberOfTopics": 10,
"DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role"
}
]
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的 [Amazon Comprehend 洞察的异步分析](https://docs.aws.amazon.com/comprehend/latest/dg/api-async-insights.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[ListTopicsDetectionJobs](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/list-topics-detection-jobs.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendTopicModeler:
"""Encapsulates a Comprehend topic modeler."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def list_jobs(self):
"""
Lists topic modeling jobs for the current account.
:return: The list of jobs.
"""
try:
response = self.comprehend_client.list_topics_detection_jobs()
jobs = response["TopicsDetectionJobPropertiesList"]
logger.info("Got %s topic detection jobs.", len(jobs))
except ClientError:
logger.exception("Couldn't get topic detection jobs.")
raise
else:
return jobs
```
+ 有关 API 的详细信息，请参阅适用[ListTopicsDetectionJobs](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/ListTopicsDetectionJobs)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->listtopicsdetectionjobs( ).
MESSAGE 'Topics detection jobs listed.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdinvalidfilterex.
MESSAGE 'Invalid filter.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[ListTopicsDetectionJobs](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `StartDocumentClassificationJob`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `StartDocumentClassificationJob`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
------
#### [ CLI ]
**AWS CLI**
**列出文档分类作业**
以下 `start-document-classification-job` 示例以自定义模型启动文档分类作业，该作业对 `--input-data-config` 标签所指定地址处的所有文件都使用自定义模型。在此示例中，输入 S3 存储桶包含 `SampleSMStext1.txt`、`SampleSMStext2.txt`、和 `SampleSMStext3.txt`。该模型之前曾接受过关于垃圾邮件和非垃圾邮件，或“ham”、短信的文档分类训练。作业完成后，`output.tar.gz` 将放置在 `--output-data-config` 标签指定的位置。`output.tar.gz` 包含 `predictions.jsonl`，其中列出了每个文档的分类。Json 输出在每个文件的一行上打印，但是为了便于阅读，此处设置了格式。
```
aws comprehend start-document-classification-job \
--job-name exampleclassificationjob \
--input-data-config "S3Uri=s3://amzn-s3-demo-bucket-INPUT/jobdata/" \
--output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
--data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
--document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/mymodel/version/12
```
`SampleSMStext1.txt` 的内容：
```
"CONGRATULATIONS! TXT 2155550100 to win $5000"
```
`SampleSMStext2.txt` 的内容：
```
"Hi, when do you want me to pick you up from practice?"
```
`SampleSMStext3.txt` 的内容：
```
"Plz send bank account # to 2155550100 to claim prize!!"
```
输出：
```
{
"JobId": "e758dd56b824aa717ceab551fEXAMPLE",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:document-classification-job/e758dd56b824aa717ceab551fEXAMPLE",
"JobStatus": "SUBMITTED"
}
```
`predictions.jsonl` 的内容：
```
{"File": "SampleSMSText1.txt", "Line": "0", "Classes": [{"Name": "spam", "Score": 0.9999}, {"Name": "ham", "Score": 0.0001}]}
{"File": "SampleSMStext2.txt", "Line": "0", "Classes": [{"Name": "ham", "Score": 0.9994}, {"Name": "spam", "Score": 0.0006}]}
{"File": "SampleSMSText3.txt", "Line": "0", "Classes": [{"Name": "spam", "Score": 0.9999}, {"Name": "ham", "Score": 0.0001}]}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[自定义分类](https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[StartDocumentClassificationJob](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/start-document-classification-job.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def start_job(
self,
job_name,
input_bucket,
input_key,
input_format,
output_bucket,
output_key,
data_access_role_arn,
):
"""
Starts a classification job. The classifier must be trained or the job
will fail. Input is read from the specified Amazon S3 input bucket and
written to the specified output bucket. Output data is stored in a tar
archive compressed in gzip format. The job runs asynchronously, so you can
call `describe_document_classification_job` to get job status until it
returns a status of SUCCEEDED.
:param job_name: The name of the job.
:param input_bucket: The Amazon S3 bucket that contains input data.
:param input_key: The prefix used to find input data in the input
bucket. If multiple objects have the same prefix, all
of them are used.
:param input_format: The format of the input data, either one document per
file or one document per line.
:param output_bucket: The Amazon S3 bucket where output data is written.
:param output_key: The prefix prepended to the output data.
:param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
grants Comprehend permission to read from the
input bucket and write to the output bucket.
:return: Information about the job, including the job ID.
"""
try:
response = self.comprehend_client.start_document_classification_job(
DocumentClassifierArn=self.classifier_arn,
JobName=job_name,
InputDataConfig={
"S3Uri": f"s3://{input_bucket}/{input_key}",
"InputFormat": input_format.value,
},
OutputDataConfig={"S3Uri": f"s3://{output_bucket}/{output_key}"},
DataAccessRoleArn=data_access_role_arn,
)
logger.info(
"Document classification job %s is %s.", job_name, response["JobStatus"]
)
except ClientError:
logger.exception("Couldn't start classification job %s.", job_name)
raise
else:
return response
```
+ 有关 API 的详细信息，请参阅适用[StartDocumentClassificationJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/StartDocumentClassificationJob)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->startdocclassificationjob(
iv_jobname = iv_job_name
iv_documentclassifierarn = iv_classifier_arn
io_inputdataconfig = NEW /aws1/cl_cpdinputdataconfig(
iv_s3uri = iv_input_s3_uri
iv_inputformat = iv_input_format
)
io_outputdataconfig = NEW /aws1/cl_cpdoutputdataconfig(
iv_s3uri = iv_output_s3_uri
)
iv_dataaccessrolearn = iv_data_access_role_arn
).
MESSAGE 'Document classification job started.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdresourcenotfoundex.
MESSAGE 'Resource not found.' TYPE 'E'.
CATCH /aws1/cx_cpdresourceunavailex.
MESSAGE 'Resource unavailable.' TYPE 'E'.
CATCH /aws1/cx_cpdkmskeyvalidationex.
MESSAGE 'KMS key validation error.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanytagsex.
MESSAGE 'Too many tags.' TYPE 'E'.
CATCH /aws1/cx_cpdresrclimitexcdex.
MESSAGE 'Resource limit exceeded.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[StartDocumentClassificationJob](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# `StartTopicsDetectionJob`与 AWS SDK 或 CLI 配合使用
以下代码示例演示如何使用 `StartTopicsDetectionJob`。
操作示例是大型程序的代码摘录，必须在上下文中运行。在以下代码示例中，您可以查看此操作的上下文：
+ [对示例数据运行主题建模任务](comprehend_example_comprehend_Usage_TopicModeler_section.md)
------
#### [ .NET ]
**适用于 .NET 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Comprehend/#code-examples)中查找完整示例，了解如何进行设置和运行。
```
using System;
using System.Threading.Tasks;
using Amazon.Comprehend;
using Amazon.Comprehend.Model;
///
/// This example scans the documents in an Amazon Simple Storage Service
/// (Amazon S3) bucket and analyzes it for topics. The results are stored
/// in another bucket and then the resulting job properties are displayed
/// on the screen. This example was created using the AWS SDK for .NEt
/// version 3.7 and .NET Core version 5.0.
///
public static class TopicModeling
{
///
/// This methos calls a topic detection job by calling the Amazon
/// Comprehend StartTopicsDetectionJobRequest.
///
public static async Task Main()
{
var comprehendClient = new AmazonComprehendClient();
string inputS3Uri = "s3://input bucket/input path";
InputFormat inputDocFormat = InputFormat.ONE_DOC_PER_FILE;
string outputS3Uri = "s3://output bucket/output path";
string dataAccessRoleArn = "arn:aws:iam::account ID:role/data access role";
int numberOfTopics = 10;
var startTopicsDetectionJobRequest = new StartTopicsDetectionJobRequest()
{
InputDataConfig = new InputDataConfig()
{
S3Uri = inputS3Uri,
InputFormat = inputDocFormat,
},
OutputDataConfig = new OutputDataConfig()
{
S3Uri = outputS3Uri,
},
DataAccessRoleArn = dataAccessRoleArn,
NumberOfTopics = numberOfTopics,
};
var startTopicsDetectionJobResponse = await comprehendClient.StartTopicsDetectionJobAsync(startTopicsDetectionJobRequest);
var jobId = startTopicsDetectionJobResponse.JobId;
Console.WriteLine("JobId: " + jobId);
var describeTopicsDetectionJobRequest = new DescribeTopicsDetectionJobRequest()
{
JobId = jobId,
};
var describeTopicsDetectionJobResponse = await comprehendClient.DescribeTopicsDetectionJobAsync(describeTopicsDetectionJobRequest);
PrintJobProperties(describeTopicsDetectionJobResponse.TopicsDetectionJobProperties);
var listTopicsDetectionJobsResponse = await comprehendClient.ListTopicsDetectionJobsAsync(new ListTopicsDetectionJobsRequest());
foreach (var props in listTopicsDetectionJobsResponse.TopicsDetectionJobPropertiesList)
{
PrintJobProperties(props);
}
}
///
/// This method is a helper method that displays the job properties
/// from the call to StartTopicsDetectionJobRequest.
///
/// A list of properties from the call to
/// StartTopicsDetectionJobRequest.
private static void PrintJobProperties(TopicsDetectionJobProperties props)
{
Console.WriteLine($"JobId: {props.JobId}, JobName: {props.JobName}, JobStatus: {props.JobStatus}");
Console.WriteLine($"NumberOfTopics: {props.NumberOfTopics}\nInputS3Uri: {props.InputDataConfig.S3Uri}");
Console.WriteLine($"InputFormat: {props.InputDataConfig.InputFormat}, OutputS3Uri: {props.OutputDataConfig.S3Uri}");
}
}
```
+ 有关 API 的详细信息，请参阅 *适用于 .NET 的 AWS SDK API 参考[StartTopicsDetectionJob](https://docs.aws.amazon.com/goto/DotNetSDKV3/comprehend-2017-11-27/StartTopicsDetectionJob)*中的。
------
#### [ CLI ]
**AWS CLI**
**启动主题检测分析作业**
以下 `start-topics-detection-job` 示例为位于 `--input-data-config` 标签指定地址的所有文件启动异步主题检测作业。作业完成后，文件夹 `output` 将放置在 `--ouput-data-config` 标签指定的位置。`output` 包含 topic-terms.csv 和 doc-topics.csv。第一个输出文件 topic-terms.csv 是集合中的主题列表。对于每个主题，默认情况下，该列表按权重排列主题列出根据其的热门术语。第二个文件 `doc-topics.csv` 列出了与主题相关的文档以及与该主题相关的文档比例。
```
aws comprehend start-topics-detection-job \
--job-name example_topics_detection_job \
--language-code en \
--input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
--output-data-config "S3Uri=s3://amzn-s3-demo-destination-bucket/testfolder/" \
--data-access-role-arn arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role \
--language-code en
```
输出：
```
{
"JobId": "123456abcdeb0e11022f22a11EXAMPLE",
"JobArn": "arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/123456abcdeb0e11022f22a11EXAMPLE",
"JobStatus": "SUBMITTED"
}
```
有关更多信息，请参阅《Amazon Comprehend 开发人员指南》**中的[主题建模](https://docs.aws.amazon.com/comprehend/latest/dg/topic-modeling.html)。
+ 有关 API 的详细信息，请参阅*AWS CLI 命令参考[StartTopicsDetectionJob](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/comprehend/start-topics-detection-job.html)*中的。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
```
class ComprehendTopicModeler:
"""Encapsulates a Comprehend topic modeler."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def start_job(
self,
job_name,
input_bucket,
input_key,
input_format,
output_bucket,
output_key,
data_access_role_arn,
):
"""
Starts a topic modeling job. Input is read from the specified Amazon S3
input bucket and written to the specified output bucket. Output data is stored
in a tar archive compressed in gzip format. The job runs asynchronously, so you
can call `describe_topics_detection_job` to get job status until it
returns a status of SUCCEEDED.
:param job_name: The name of the job.
:param input_bucket: An Amazon S3 bucket that contains job input.
:param input_key: The prefix used to find input data in the input
bucket. If multiple objects have the same prefix, all
of them are used.
:param input_format: The format of the input data, either one document per
file or one document per line.
:param output_bucket: The Amazon S3 bucket where output data is written.
:param output_key: The prefix prepended to the output data.
:param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
grants Comprehend permission to read from the
input bucket and write to the output bucket.
:return: Information about the job, including the job ID.
"""
try:
response = self.comprehend_client.start_topics_detection_job(
JobName=job_name,
DataAccessRoleArn=data_access_role_arn,
InputDataConfig={
"S3Uri": f"s3://{input_bucket}/{input_key}",
"InputFormat": input_format.value,
},
OutputDataConfig={"S3Uri": f"s3://{output_bucket}/{output_key}"},
)
logger.info("Started topic modeling job %s.", response["JobId"])
except ClientError:
logger.exception("Couldn't start topic modeling job.")
raise
else:
return response
```
+ 有关 API 的详细信息，请参阅适用[StartTopicsDetectionJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/StartTopicsDetectionJob)于 *Python 的AWS SDK (Boto3) API 参考*。
------
#### [ SAP ABAP ]
**适用于 SAP ABAP 的 SDK**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/cpd#code-examples)中查找完整示例，了解如何进行设置和运行。
```
TRY.
oo_result = lo_cpd->starttopicsdetectionjob(
iv_jobname = iv_job_name
io_inputdataconfig = NEW /aws1/cl_cpdinputdataconfig(
iv_s3uri = iv_input_s3_uri
iv_inputformat = iv_input_format
)
io_outputdataconfig = NEW /aws1/cl_cpdoutputdataconfig(
iv_s3uri = iv_output_s3_uri
)
iv_dataaccessrolearn = iv_data_access_role_arn
).
MESSAGE 'Topics detection job started.' TYPE 'I'.
CATCH /aws1/cx_cpdinvalidrequestex.
MESSAGE 'Invalid request.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanyrequestsex.
MESSAGE 'Too many requests.' TYPE 'E'.
CATCH /aws1/cx_cpdkmskeyvalidationex.
MESSAGE 'KMS key validation error.' TYPE 'E'.
CATCH /aws1/cx_cpdtoomanytagsex.
MESSAGE 'Too many tags.' TYPE 'E'.
CATCH /aws1/cx_cpdresrclimitexcdex.
MESSAGE 'Resource limit exceeded.' TYPE 'E'.
CATCH /aws1/cx_cpdinternalserverex.
MESSAGE 'Internal server error occurred.' TYPE 'E'.
ENDTRY.
```
+ 有关 API 的详细信息，请参阅适用[StartTopicsDetectionJob](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)于 S *AP 的AWS SDK ABAP API 参考*。
------
# Amazon Comprehend 使用场景 AWS SDKs
以下代码示例向您展示了如何使用在 Amazon Comprehend 中实现常见场景。 AWS SDKs这些场景演示了如何通过调用 Amazon Comprehend 中的多个函数或与其他 AWS 服务结合来完成特定任务。每个场景都包含完整源代码的链接，您可以在其中找到有关如何设置和运行代码的说明。
场景以中等水平的经验为目标，可帮助您结合具体环境了解服务操作。
**Topics**
+ [构建 Amazon Transcribe 流式传输应用程序](comprehend_example_cross_TranscriptionStreamingApp_section.md)
+ [构建 Amazon Lex 聊天机器人](comprehend_example_cross_LexChatbotLanguages_section.md)
+ [创建消息应用程序](comprehend_example_cross_SQSMessageApp_section.md)
+ [创建用于分析客户反馈的应用程序](comprehend_example_cross_FSA_section.md)
+ [检测文档元素](comprehend_example_comprehend_Usage_DetectApis_section.md)
+ [检测从图像中提取的文本中的实体](comprehend_example_cross_TextractComprehendDetectEntities_section.md)
+ [对示例数据运行主题建模任务](comprehend_example_comprehend_Usage_TopicModeler_section.md)
+ [训练自定义分类器并对文档进行分类](comprehend_example_comprehend_Usage_ComprehendClassifier_section.md)
# 构建 Amazon Transcribe 流式传输应用程序
以下代码示例展示如何构建可实时录制、转录与翻译实时音频，并通过电子邮件发送结果的应用程序。
------
#### [ JavaScript ]
**适用于 JavaScript (v3) 的软件开发工具包**
演示了如何使用 Amazon Transcribe 构建可实时录制、转录与翻译实时音频，并通过 Amazon Simple Email Service (Amazon SES) 以电子邮件发送结果的应用程序。
有关如何设置和运行的完整源代码和说明，请参阅上的完整示例[GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/cross-services/transcribe-streaming-app)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Amazon SES
+ Amazon Transcribe
+ Amazon Translate
------
# 创建 Amazon Lex 聊天机器人来吸引您的网站访客
以下代码示例显示如何创建用于吸引网站访客的聊天机器人。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
展示如何使用 Amazon Lex API 在 Web 应用程序中创建聊天机器人，以吸引网站访客。
有关如何设置和运行的完整源代码和说明，请参阅上的完整示例[GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/usecases/creating_lex_chatbot)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Amazon Lex
+ Amazon Translate
------
#### [ JavaScript ]
**适用于 JavaScript (v3) 的软件开发工具包**
展示如何使用 Amazon Lex API 在 Web 应用程序中创建聊天机器人，以吸引网站访客。
有关如何设置和运行的完整源代码和说明，请参阅 适用于 JavaScript 的 AWS SDK 开发者指南中的[构建 Amazon Lex 聊天机器人的](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/lex-bot-example.html)完整示例。
**本示例中使用的服务**
+ Amazon Comprehend
+ Amazon Lex
+ Amazon Translate
------
# 使用 Amazon SQS 创建用于发送和检索消息的 Web 应用程序
以下代码示例显示如何使用 Amazon SQS 创建消息传输应用程序。
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
演示如何使用 Amazon SQS API 开发用于发送和检索消息的 Spring REST API。
有关如何设置和运行的完整源代码和说明，请参阅上的完整示例[GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/usecases/creating_message_application)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Amazon SQS
------
#### [ Kotlin ]
**适用于 Kotlin 的 SDK**
演示如何使用 Amazon SQS API 开发用于发送和检索消息的 Spring REST API。
有关如何设置和运行的完整源代码和说明，请参阅上的完整示例[GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/kotlin/usecases/creating_message_application)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Amazon SQS
------
# 创建用于分析客户反馈和合成音频的应用程序
以下代码示例显示如何创建应用程序来分析客户意见卡、翻译其母语、确定其情绪并根据译后的文本生成音频文件。
------
#### [ .NET ]
**适用于 .NET 的 SDK**
此示例应用程序可分析并存储客户反馈卡。具体来说，它满足了纽约市一家虚构酒店的需求。酒店以实体意见卡的形式收集来自不同语种的客人的反馈。该反馈通过 Web 客户端上传到应用程序中。意见卡图片上传后，将执行以下步骤：
+ 使用 Amazon Textract 从图片中提取文本。
+ Amazon Comprehend 确定所提取文本的情绪及其语言。
+ 使用 Amazon Translate 将所提取文本翻译为英语。
+ Amazon Polly 根据所提取文本合成音频文件。
完整的应用程序可使用 AWS CDK 进行部署。有关源代码和部署说明，请参阅中的项目[ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/cross-service/FeedbackSentimentAnalyzer)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Lambda
+ Amazon Polly
+ Amazon Textract
+ Amazon Translate
------
#### [ Java ]
**适用于 Java 的 SDK 2.x**
此示例应用程序可分析并存储客户反馈卡。具体来说，它满足了纽约市一家虚构酒店的需求。酒店以实体意见卡的形式收集来自不同语种的客人的反馈。该反馈通过 Web 客户端上传到应用程序中。意见卡图片上传后，将执行以下步骤：
+ 使用 Amazon Textract 从图片中提取文本。
+ Amazon Comprehend 确定所提取文本的情绪及其语言。
+ 使用 Amazon Translate 将所提取文本翻译为英语。
+ Amazon Polly 根据所提取文本合成音频文件。
完整的应用程序可使用 AWS CDK 进行部署。有关源代码和部署说明，请参阅中的项目[ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/usecases/creating_fsa_app)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Lambda
+ Amazon Polly
+ Amazon Textract
+ Amazon Translate
------
#### [ JavaScript ]
**适用于 JavaScript (v3) 的软件开发工具包**
此示例应用程序可分析并存储客户反馈卡。具体来说，它满足了纽约市一家虚构酒店的需求。酒店以实体意见卡的形式收集来自不同语种的客人的反馈。该反馈通过 Web 客户端上传到应用程序中。意见卡图片上传后，将执行以下步骤：
+ 使用 Amazon Textract 从图片中提取文本。
+ Amazon Comprehend 确定所提取文本的情绪及其语言。
+ 使用 Amazon Translate 将所提取文本翻译为英语。
+ Amazon Polly 根据所提取文本合成音频文件。
完整的应用程序可使用 AWS CDK 进行部署。有关源代码和部署说明，请参阅中的项目[ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/cross-services/feedback-sentiment-analyzer)。以下摘录显示了在 Lambda 函数中 适用于 JavaScript 的 AWS SDK 是如何使用的。
```
import {
ComprehendClient,
DetectDominantLanguageCommand,
DetectSentimentCommand,
} from "@aws-sdk/client-comprehend";
/**
* Determine the language and sentiment of the extracted text.
*
* @param {{ source_text: string}} extractTextOutput
*/
export const handler = async (extractTextOutput) => {
const comprehendClient = new ComprehendClient({});
const detectDominantLanguageCommand = new DetectDominantLanguageCommand({
Text: extractTextOutput.source_text,
});
// The source language is required for sentiment analysis and
// translation in the next step.
const { Languages } = await comprehendClient.send(
detectDominantLanguageCommand,
);
const languageCode = Languages[0].LanguageCode;
const detectSentimentCommand = new DetectSentimentCommand({
Text: extractTextOutput.source_text,
LanguageCode: languageCode,
});
const { Sentiment } = await comprehendClient.send(detectSentimentCommand);
return {
sentiment: Sentiment,
language_code: languageCode,
};
};
```
```
import {
DetectDocumentTextCommand,
TextractClient,
} from "@aws-sdk/client-textract";
/**
* Fetch the S3 object from the event and analyze it using Amazon Textract.
*
* @param {import("@types/aws-lambda").EventBridgeEvent<"Object Created">} eventBridgeS3Event
*/
export const handler = async (eventBridgeS3Event) => {
const textractClient = new TextractClient();
const detectDocumentTextCommand = new DetectDocumentTextCommand({
Document: {
S3Object: {
Bucket: eventBridgeS3Event.bucket,
Name: eventBridgeS3Event.object,
},
},
});
// Textract returns a list of blocks. A block can be a line, a page, word, etc.
// Each block also contains geometry of the detected text.
// For more information on the Block type, see https://docs.aws.amazon.com/textract/latest/dg/API_Block.html.
const { Blocks } = await textractClient.send(detectDocumentTextCommand);
// For the purpose of this example, we are only interested in words.
const extractedWords = Blocks.filter((b) => b.BlockType === "WORD").map(
(b) => b.Text,
);
return extractedWords.join(" ");
};
```
```
import { PollyClient, SynthesizeSpeechCommand } from "@aws-sdk/client-polly";
import { S3Client } from "@aws-sdk/client-s3";
import { Upload } from "@aws-sdk/lib-storage";
/**
* Synthesize an audio file from text.
*
* @param {{ bucket: string, translated_text: string, object: string}} sourceDestinationConfig
*/
export const handler = async (sourceDestinationConfig) => {
const pollyClient = new PollyClient({});
const synthesizeSpeechCommand = new SynthesizeSpeechCommand({
Engine: "neural",
Text: sourceDestinationConfig.translated_text,
VoiceId: "Ruth",
OutputFormat: "mp3",
});
const { AudioStream } = await pollyClient.send(synthesizeSpeechCommand);
const audioKey = `${sourceDestinationConfig.object}.mp3`;
// Store the audio file in S3.
const s3Client = new S3Client();
const upload = new Upload({
client: s3Client,
params: {
Bucket: sourceDestinationConfig.bucket,
Key: audioKey,
Body: AudioStream,
ContentType: "audio/mp3",
},
});
await upload.done();
return audioKey;
};
```
```
import {
TranslateClient,
TranslateTextCommand,
} from "@aws-sdk/client-translate";
/**
* Translate the extracted text to English.
*
* @param {{ extracted_text: string, source_language_code: string}} textAndSourceLanguage
*/
export const handler = async (textAndSourceLanguage) => {
const translateClient = new TranslateClient({});
const translateCommand = new TranslateTextCommand({
SourceLanguageCode: textAndSourceLanguage.source_language_code,
TargetLanguageCode: "en",
Text: textAndSourceLanguage.extracted_text,
});
const { TranslatedText } = await translateClient.send(translateCommand);
return { translated_text: TranslatedText };
};
```
**本示例中使用的服务**
+ Amazon Comprehend
+ Lambda
+ Amazon Polly
+ Amazon Textract
+ Amazon Translate
------
#### [ Ruby ]
**适用于 Ruby 的 SDK**
此示例应用程序可分析并存储客户反馈卡。具体来说，它满足了纽约市一家虚构酒店的需求。酒店以实体意见卡的形式收集来自不同语种的客人的反馈。该反馈通过 Web 客户端上传到应用程序中。意见卡图片上传后，将执行以下步骤：
+ 使用 Amazon Textract 从图片中提取文本。
+ Amazon Comprehend 确定所提取文本的情绪及其语言。
+ 使用 Amazon Translate 将所提取文本翻译为英语。
+ Amazon Polly 根据所提取文本合成音频文件。
完整的应用程序可使用 AWS CDK 进行部署。有关源代码和部署说明，请参阅中的项目[ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/ruby/cross_service_examples/feedback_sentiment_analyzer)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Lambda
+ Amazon Polly
+ Amazon Textract
+ Amazon Translate
------
# 使用 Amazon Comprehend 和软件开发工具包检测文档元素 AWS
以下代码示例展示了如何：
+ 检测文档中的语言、实体和关键短语。
+ 检测文档中的个人身份信息 (PII)。
+ 检测文档的情绪。
+ 检测文档的语法元素。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
创建一个包装 Amazon Comprehend 操作的类。
```
import logging
from pprint import pprint
import boto3
from botocore.exceptions import ClientError
logger = logging.getLogger(__name__)
class ComprehendDetect:
"""Encapsulates Comprehend detection functions."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def detect_languages(self, text):
"""
Detects languages used in a document.
:param text: The document to inspect.
:return: The list of languages along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_dominant_language(Text=text)
languages = response["Languages"]
logger.info("Detected %s languages.", len(languages))
except ClientError:
logger.exception("Couldn't detect languages.")
raise
else:
return languages
def detect_entities(self, text, language_code):
"""
Detects entities in a document. Entities can be things like people and places
or other common terms.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of entities along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_entities(
Text=text, LanguageCode=language_code
)
entities = response["Entities"]
logger.info("Detected %s entities.", len(entities))
except ClientError:
logger.exception("Couldn't detect entities.")
raise
else:
return entities
def detect_key_phrases(self, text, language_code):
"""
Detects key phrases in a document. A key phrase is typically a noun and its
modifiers.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of key phrases along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_key_phrases(
Text=text, LanguageCode=language_code
)
phrases = response["KeyPhrases"]
logger.info("Detected %s phrases.", len(phrases))
except ClientError:
logger.exception("Couldn't detect phrases.")
raise
else:
return phrases
def detect_pii(self, text, language_code):
"""
Detects personally identifiable information (PII) in a document. PII can be
things like names, account numbers, or addresses.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of PII entities along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_pii_entities(
Text=text, LanguageCode=language_code
)
entities = response["Entities"]
logger.info("Detected %s PII entities.", len(entities))
except ClientError:
logger.exception("Couldn't detect PII entities.")
raise
else:
return entities
def detect_sentiment(self, text, language_code):
"""
Detects the overall sentiment expressed in a document. Sentiment can
be positive, negative, neutral, or a mixture.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The sentiments along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_sentiment(
Text=text, LanguageCode=language_code
)
logger.info("Detected primary sentiment %s.", response["Sentiment"])
except ClientError:
logger.exception("Couldn't detect sentiment.")
raise
else:
return response
def detect_syntax(self, text, language_code):
"""
Detects syntactical elements of a document. Syntax tokens are portions of
text along with their use as parts of speech, such as nouns, verbs, and
interjections.
:param text: The document to inspect.
:param language_code: The language of the document.
:return: The list of syntax tokens along with their confidence scores.
"""
try:
response = self.comprehend_client.detect_syntax(
Text=text, LanguageCode=language_code
)
tokens = response["SyntaxTokens"]
logger.info("Detected %s syntax tokens.", len(tokens))
except ClientError:
logger.exception("Couldn't detect syntax.")
raise
else:
return tokens
```
调用包装类上的函数来检测文档中的实体、短语等。
```
def usage_demo():
print("-" * 88)
print("Welcome to the Amazon Comprehend detection demo!")
print("-" * 88)
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
comp_detect = ComprehendDetect(boto3.client("comprehend"))
with open("detect_sample.txt") as sample_file:
sample_text = sample_file.read()
demo_size = 3
print("Sample text used for this demo:")
print("-" * 88)
print(sample_text)
print("-" * 88)
print("Detecting languages.")
languages = comp_detect.detect_languages(sample_text)
pprint(languages)
lang_code = languages[0]["LanguageCode"]
print("Detecting entities.")
entities = comp_detect.detect_entities(sample_text, lang_code)
print(f"The first {demo_size} are:")
pprint(entities[:demo_size])
print("Detecting key phrases.")
phrases = comp_detect.detect_key_phrases(sample_text, lang_code)
print(f"The first {demo_size} are:")
pprint(phrases[:demo_size])
print("Detecting personally identifiable information (PII).")
pii_entities = comp_detect.detect_pii(sample_text, lang_code)
print(f"The first {demo_size} are:")
pprint(pii_entities[:demo_size])
print("Detecting sentiment.")
sentiment = comp_detect.detect_sentiment(sample_text, lang_code)
print(f"Sentiment: {sentiment['Sentiment']}")
print("SentimentScore:")
pprint(sentiment["SentimentScore"])
print("Detecting syntax elements.")
syntax_tokens = comp_detect.detect_syntax(sample_text, lang_code)
print(f"The first {demo_size} are:")
pprint(syntax_tokens[:demo_size])
print("Thanks for watching!")
print("-" * 88)
```
+ 有关 API 详细信息，请参阅《AWS SDK for Python (Boto3) API Reference》**中的以下主题。
+ [DetectDominantLanguage](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectDominantLanguage)
+ [DetectEntities](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectEntities)
+ [DetectKeyPhrases](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectKeyPhrases)
+ [DetectPiiEntities](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectPiiEntities)
+ [DetectSentiment](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectSentiment)
+ [DetectSyntax](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DetectSyntax)
------
# 使用 AWS SDK 检测从图像中提取的文本中的实体
以下代码示例显示了如何使用 Amazon Comprehend 检测 Amazon Textract 从存储在 Amazon S3 内的图像中提取的文本中的实体。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
演示如何使用 Jupyter 笔记本 适用于 Python (Boto3) 的 AWS SDK 中的来检测从图像中提取的文本中的实体。此示例使用 Amazon Textract 从存储在 Amazon Simple Storage Service (Amazon S3) 内的图像中提取文本，并使用 Amazon Comprehend 检测提取文本中的实体。
此示例是 Jupyter 笔记本，必须在可以托管笔记本电脑的环境中运行。有关如何使用 Amazon A SageMaker I 运行示例的说明，请参阅 [TextractAndComprehendNotebook.ipyn](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/cross_service/textract_comprehend_notebook/TextractAndComprehendNotebook.ipynb) b 中的说明。
有关如何设置和运行的完整源代码和说明，请参阅上的完整示例[GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/cross_service/textract_comprehend_notebook#readme)。
**本示例中使用的服务**
+ Amazon Comprehend
+ Amazon S3
+ Amazon Textract
------
# 使用软件开发工具包对示例数据运行 Amazon Comprehend 主题建模作业 AWS
以下代码示例展示了如何：
+ 对示例数据运行 Amazon Comprehend 主题建模任务。
+ 获取该任务的相关信息。
+ 从 Amazon S3 提取任务输出数据。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
创建一个包装类来调用 Amazon Comprehend 主题建模操作。
```
class ComprehendTopicModeler:
"""Encapsulates a Comprehend topic modeler."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
def start_job(
self,
job_name,
input_bucket,
input_key,
input_format,
output_bucket,
output_key,
data_access_role_arn,
):
"""
Starts a topic modeling job. Input is read from the specified Amazon S3
input bucket and written to the specified output bucket. Output data is stored
in a tar archive compressed in gzip format. The job runs asynchronously, so you
can call `describe_topics_detection_job` to get job status until it
returns a status of SUCCEEDED.
:param job_name: The name of the job.
:param input_bucket: An Amazon S3 bucket that contains job input.
:param input_key: The prefix used to find input data in the input
bucket. If multiple objects have the same prefix, all
of them are used.
:param input_format: The format of the input data, either one document per
file or one document per line.
:param output_bucket: The Amazon S3 bucket where output data is written.
:param output_key: The prefix prepended to the output data.
:param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
grants Comprehend permission to read from the
input bucket and write to the output bucket.
:return: Information about the job, including the job ID.
"""
try:
response = self.comprehend_client.start_topics_detection_job(
JobName=job_name,
DataAccessRoleArn=data_access_role_arn,
InputDataConfig={
"S3Uri": f"s3://{input_bucket}/{input_key}",
"InputFormat": input_format.value,
},
OutputDataConfig={"S3Uri": f"s3://{output_bucket}/{output_key}"},
)
logger.info("Started topic modeling job %s.", response["JobId"])
except ClientError:
logger.exception("Couldn't start topic modeling job.")
raise
else:
return response
def describe_job(self, job_id):
"""
Gets metadata about a topic modeling job.
:param job_id: The ID of the job to look up.
:return: Metadata about the job.
"""
try:
response = self.comprehend_client.describe_topics_detection_job(
JobId=job_id
)
job = response["TopicsDetectionJobProperties"]
logger.info("Got topic detection job %s.", job_id)
except ClientError:
logger.exception("Couldn't get topic detection job %s.", job_id)
raise
else:
return job
def list_jobs(self):
"""
Lists topic modeling jobs for the current account.
:return: The list of jobs.
"""
try:
response = self.comprehend_client.list_topics_detection_jobs()
jobs = response["TopicsDetectionJobPropertiesList"]
logger.info("Got %s topic detection jobs.", len(jobs))
except ClientError:
logger.exception("Couldn't get topic detection jobs.")
raise
else:
return jobs
```
使用包装器类运行主题建模任务并获取任务数据。
```
def usage_demo():
print("-" * 88)
print("Welcome to the Amazon Comprehend topic modeling demo!")
print("-" * 88)
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
input_prefix = "input/"
output_prefix = "output/"
demo_resources = ComprehendDemoResources(
boto3.resource("s3"), boto3.resource("iam")
)
topic_modeler = ComprehendTopicModeler(boto3.client("comprehend"))
print("Setting up storage and security resources needed for the demo.")
demo_resources.setup("comprehend-topic-modeler-demo")
print("Copying sample data from public bucket into input bucket.")
demo_resources.bucket.copy(
{"Bucket": "public-sample-us-west-2", "Key": "TopicModeling/Sample.txt"},
f"{input_prefix}sample.txt",
)
print("Starting topic modeling job on sample data.")
job_info = topic_modeler.start_job(
"demo-topic-modeling-job",
demo_resources.bucket.name,
input_prefix,
JobInputFormat.per_line,
demo_resources.bucket.name,
output_prefix,
demo_resources.data_access_role.arn,
)
print(
f"Waiting for job {job_info['JobId']} to complete. This typically takes "
f"20 - 30 minutes."
)
job_waiter = JobCompleteWaiter(topic_modeler.comprehend_client)
job_waiter.wait(job_info["JobId"])
job = topic_modeler.describe_job(job_info["JobId"])
print(f"Job {job['JobId']} complete:")
pprint(job)
print(
f"Getting job output data from the output Amazon S3 bucket: "
f"{job['OutputDataConfig']['S3Uri']}."
)
job_output = demo_resources.extract_job_output(job)
lines = 10
print(f"First {lines} lines of document topics output:")
pprint(job_output["doc-topics.csv"]["data"][:lines])
print(f"First {lines} lines of terms output:")
pprint(job_output["topic-terms.csv"]["data"][:lines])
print("Cleaning up resources created for the demo.")
demo_resources.cleanup()
print("Thanks for watching!")
print("-" * 88)
```
+ 有关 API 详细信息，请参阅《AWS SDK for Python (Boto3) API Reference》**中的以下主题。
+ [DescribeTopicsDetectionJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DescribeTopicsDetectionJob)
+ [ListTopicsDetectionJobs](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/ListTopicsDetectionJobs)
+ [StartTopicsDetectionJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/StartTopicsDetectionJob)
------
# 训练自定义 Amazon Comprehend 分类器并使用软件开发工具包对文档进行分类 AWS
以下代码示例展示了如何：
+ 创建 Amazon Comprehend 多标签分类器。
+ 在示例数据上训练分类器。
+ 对第二组数据运行分类任务。
+ 从 Amazon S3 提取任务输出数据。
------
#### [ Python ]
**适用于 Python 的 SDK（Boto3）**
还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/comprehend#code-examples)中查找完整示例，了解如何进行设置和运行。
创建一个包装类来调用 Amazon Comprehend 文档分类器操作。
```
class ComprehendClassifier:
"""Encapsulates an Amazon Comprehend custom classifier."""
def __init__(self, comprehend_client):
"""
:param comprehend_client: A Boto3 Comprehend client.
"""
self.comprehend_client = comprehend_client
self.classifier_arn = None
def create(
self,
name,
language_code,
training_bucket,
training_key,
data_access_role_arn,
mode,
):
"""
Creates a custom classifier. After the classifier is created, it immediately
starts training on the data found in the specified Amazon S3 bucket. Training
can take 30 minutes or longer. The `describe_document_classifier` function
can be used to get training status and returns a status of TRAINED when the
classifier is ready to use.
:param name: The name of the classifier.
:param language_code: The language the classifier can operate on.
:param training_bucket: The Amazon S3 bucket that contains the training data.
:param training_key: The prefix used to find training data in the training
bucket. If multiple objects have the same prefix, all
of them are used.
:param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
grants Comprehend permission to read from the
training bucket.
:return: The ARN of the newly created classifier.
"""
try:
response = self.comprehend_client.create_document_classifier(
DocumentClassifierName=name,
LanguageCode=language_code,
InputDataConfig={"S3Uri": f"s3://{training_bucket}/{training_key}"},
DataAccessRoleArn=data_access_role_arn,
Mode=mode.value,
)
self.classifier_arn = response["DocumentClassifierArn"]
logger.info("Started classifier creation. Arn is: %s.", self.classifier_arn)
except ClientError:
logger.exception("Couldn't create classifier %s.", name)
raise
else:
return self.classifier_arn
def describe(self, classifier_arn=None):
"""
Gets metadata about a custom classifier, including its current status.
:param classifier_arn: The ARN of the classifier to look up.
:return: Metadata about the classifier.
"""
if classifier_arn is not None:
self.classifier_arn = classifier_arn
try:
response = self.comprehend_client.describe_document_classifier(
DocumentClassifierArn=self.classifier_arn
)
classifier = response["DocumentClassifierProperties"]
logger.info("Got classifier %s.", self.classifier_arn)
except ClientError:
logger.exception("Couldn't get classifier %s.", self.classifier_arn)
raise
else:
return classifier
def list(self):
"""
Lists custom classifiers for the current account.
:return: The list of classifiers.
"""
try:
response = self.comprehend_client.list_document_classifiers()
classifiers = response["DocumentClassifierPropertiesList"]
logger.info("Got %s classifiers.", len(classifiers))
except ClientError:
logger.exception(
"Couldn't get classifiers.",
)
raise
else:
return classifiers
def delete(self):
"""
Deletes the classifier.
"""
try:
self.comprehend_client.delete_document_classifier(
DocumentClassifierArn=self.classifier_arn
)
logger.info("Deleted classifier %s.", self.classifier_arn)
self.classifier_arn = None
except ClientError:
logger.exception("Couldn't deleted classifier %s.", self.classifier_arn)
raise
def start_job(
self,
job_name,
input_bucket,
input_key,
input_format,
output_bucket,
output_key,
data_access_role_arn,
):
"""
Starts a classification job. The classifier must be trained or the job
will fail. Input is read from the specified Amazon S3 input bucket and
written to the specified output bucket. Output data is stored in a tar
archive compressed in gzip format. The job runs asynchronously, so you can
call `describe_document_classification_job` to get job status until it
returns a status of SUCCEEDED.
:param job_name: The name of the job.
:param input_bucket: The Amazon S3 bucket that contains input data.
:param input_key: The prefix used to find input data in the input
bucket. If multiple objects have the same prefix, all
of them are used.
:param input_format: The format of the input data, either one document per
file or one document per line.
:param output_bucket: The Amazon S3 bucket where output data is written.
:param output_key: The prefix prepended to the output data.
:param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
grants Comprehend permission to read from the
input bucket and write to the output bucket.
:return: Information about the job, including the job ID.
"""
try:
response = self.comprehend_client.start_document_classification_job(
DocumentClassifierArn=self.classifier_arn,
JobName=job_name,
InputDataConfig={
"S3Uri": f"s3://{input_bucket}/{input_key}",
"InputFormat": input_format.value,
},
OutputDataConfig={"S3Uri": f"s3://{output_bucket}/{output_key}"},
DataAccessRoleArn=data_access_role_arn,
)
logger.info(
"Document classification job %s is %s.", job_name, response["JobStatus"]
)
except ClientError:
logger.exception("Couldn't start classification job %s.", job_name)
raise
else:
return response
def describe_job(self, job_id):
"""
Gets metadata about a classification job.
:param job_id: The ID of the job to look up.
:return: Metadata about the job.
"""
try:
response = self.comprehend_client.describe_document_classification_job(
JobId=job_id
)
job = response["DocumentClassificationJobProperties"]
logger.info("Got classification job %s.", job["JobName"])
except ClientError:
logger.exception("Couldn't get classification job %s.", job_id)
raise
else:
return job
def list_jobs(self):
"""
Lists the classification jobs for the current account.
:return: The list of jobs.
"""
try:
response = self.comprehend_client.list_document_classification_jobs()
jobs = response["DocumentClassificationJobPropertiesList"]
logger.info("Got %s document classification jobs.", len(jobs))
except ClientError:
logger.exception(
"Couldn't get document classification jobs.",
)
raise
else:
return jobs
```
创建帮组运行场景的类。
```
class ClassifierDemo:
"""
Encapsulates functions used to run the demonstration.
"""
def __init__(self, demo_resources):
"""
:param demo_resources: A ComprehendDemoResources class that manages resources
for the demonstration.
"""
self.demo_resources = demo_resources
self.training_prefix = "training/"
self.input_prefix = "input/"
self.input_format = JobInputFormat.per_line
self.output_prefix = "output/"
def setup(self):
"""Creates AWS resources used by the demo."""
self.demo_resources.setup("comprehend-classifier-demo")
def cleanup(self):
"""Deletes AWS resources used by the demo."""
self.demo_resources.cleanup()
@staticmethod
def _sanitize_text(text):
"""Removes characters that cause errors for the document parser."""
return text.replace("\r", " ").replace("\n", " ").replace(",", ";")
@staticmethod
def _get_issues(query, issue_count):
"""
Gets issues from GitHub using the specified query parameters.
:param query: The query string used to request issues from the GitHub API.
:param issue_count: The number of issues to retrieve.
:return: The list of issues retrieved from GitHub.
"""
issues = []
logger.info("Requesting issues from %s?%s.", GITHUB_SEARCH_URL, query)
response = requests.get(f"{GITHUB_SEARCH_URL}?{query}&per_page={issue_count}")
if response.status_code == 200:
issue_page = response.json()["items"]
logger.info("Got %s issues.", len(issue_page))
issues = [
{
"title": ClassifierDemo._sanitize_text(issue["title"]),
"body": ClassifierDemo._sanitize_text(issue["body"]),
"labels": {label["name"] for label in issue["labels"]},
}
for issue in issue_page
]
else:
logger.error(
"GitHub returned error code %s with message %s.",
response.status_code,
response.json(),
)
logger.info("Found %s issues.", len(issues))
return issues
def get_training_issues(self, training_labels):
"""
Gets issues used for training the custom classifier. Training issues are
closed issues from the Boto3 repo that have known labels. Comprehend
requires a minimum of ten training issues per label.
:param training_labels: The issue labels to use for training.
:return: The set of issues used for training.
"""
issues = []
per_label_count = 15
for label in training_labels:
issues += self._get_issues(
f"q=type:issue+repo:boto/boto3+state:closed+label:{label}",
per_label_count,
)
for issue in issues:
issue["labels"] = issue["labels"].intersection(training_labels)
return issues
def get_input_issues(self, training_labels):
"""
Gets input issues from GitHub. For demonstration purposes, input issues
are open issues from the Boto3 repo with known labels, though in practice
any issue could be submitted to the classifier for labeling.
:param training_labels: The set of labels to query for.
:return: The set of issues used for input.
"""
issues = []
per_label_count = 5
for label in training_labels:
issues += self._get_issues(
f"q=type:issue+repo:boto/boto3+state:open+label:{label}",
per_label_count,
)
return issues
def upload_issue_data(self, issues, training=False):
"""
Uploads issue data to an Amazon S3 bucket, either for training or for input.
The data is first put into the format expected by Comprehend. For training,
the set of pipe-delimited labels is prepended to each document. For
input, labels are not sent.
:param issues: The set of issues to upload to Amazon S3.
:param training: Indicates whether the issue data is used for training or
input.
"""
try:
obj_key = (
self.training_prefix if training else self.input_prefix
) + "issues.txt"
if training:
issue_strings = [
f"{'|'.join(issue['labels'])},{issue['title']} {issue['body']}"
for issue in issues
]
else:
issue_strings = [
f"{issue['title']} {issue['body']}" for issue in issues
]
issue_bytes = BytesIO("\n".join(issue_strings).encode("utf-8"))
self.demo_resources.bucket.upload_fileobj(issue_bytes, obj_key)
logger.info(
"Uploaded data as %s to bucket %s.",
obj_key,
self.demo_resources.bucket.name,
)
except ClientError:
logger.exception(
"Couldn't upload data to bucket %s.", self.demo_resources.bucket.name
)
raise
def extract_job_output(self, job):
"""Extracts job output from Amazon S3."""
return self.demo_resources.extract_job_output(job)
@staticmethod
def reconcile_job_output(input_issues, output_dict):
"""
Reconciles job output with the list of input issues. Because the input issues
have known labels, these can be compared with the labels added by the
classifier to judge the accuracy of the output.
:param input_issues: The list of issues used as input.
:param output_dict: The dictionary of data that is output by the classifier.
:return: The list of reconciled input and output data.
"""
reconciled = []
for archive in output_dict.values():
for line in archive["data"]:
in_line = int(line["Line"])
in_labels = input_issues[in_line]["labels"]
out_labels = {
label["Name"]
for label in line["Labels"]
if float(label["Score"]) > 0.3
}
reconciled.append(
f"{line['File']}, line {in_line} has labels {in_labels}.\n"
f"\tClassifier assigned {out_labels}."
)
logger.info("Reconciled input and output labels.")
return reconciled
```
使用已知标签对分类器进行一系列 GitHub 问题训练，然后将第二组 GitHub 问题发送给分类器以便对其进行标记。
```
def usage_demo():
print("-" * 88)
print("Welcome to the Amazon Comprehend custom document classifier demo!")
print("-" * 88)
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
comp_demo = ClassifierDemo(
ComprehendDemoResources(boto3.resource("s3"), boto3.resource("iam"))
)
comp_classifier = ComprehendClassifier(boto3.client("comprehend"))
classifier_trained_waiter = ClassifierTrainedWaiter(
comp_classifier.comprehend_client
)
training_labels = {"bug", "feature-request", "dynamodb", "s3"}
print("Setting up storage and security resources needed for the demo.")
comp_demo.setup()
print("Getting training data from GitHub and uploading it to Amazon S3.")
training_issues = comp_demo.get_training_issues(training_labels)
comp_demo.upload_issue_data(training_issues, True)
classifier_name = "doc-example-classifier"
print(f"Creating document classifier {classifier_name}.")
comp_classifier.create(
classifier_name,
"en",
comp_demo.demo_resources.bucket.name,
comp_demo.training_prefix,
comp_demo.demo_resources.data_access_role.arn,
ClassifierMode.multi_label,
)
print(
f"Waiting until {classifier_name} is trained. This typically takes "
f"30–40 minutes."
)
classifier_trained_waiter.wait(comp_classifier.classifier_arn)
print(f"Classifier {classifier_name} is trained:")
pprint(comp_classifier.describe())
print("Getting input data from GitHub and uploading it to Amazon S3.")
input_issues = comp_demo.get_input_issues(training_labels)
comp_demo.upload_issue_data(input_issues)
print("Starting classification job on input data.")
job_info = comp_classifier.start_job(
"issue_classification_job",
comp_demo.demo_resources.bucket.name,
comp_demo.input_prefix,
comp_demo.input_format,
comp_demo.demo_resources.bucket.name,
comp_demo.output_prefix,
comp_demo.demo_resources.data_access_role.arn,
)
print(f"Waiting for job {job_info['JobId']} to complete.")
job_waiter = JobCompleteWaiter(comp_classifier.comprehend_client)
job_waiter.wait(job_info["JobId"])
job = comp_classifier.describe_job(job_info["JobId"])
print(f"Job {job['JobId']} complete:")
pprint(job)
print(
f"Getting job output data from Amazon S3: "
f"{job['OutputDataConfig']['S3Uri']}."
)
job_output = comp_demo.extract_job_output(job)
print("Job output:")
pprint(job_output)
print("Reconciling job output with labels from GitHub:")
reconciled_output = comp_demo.reconcile_job_output(input_issues, job_output)
print(*reconciled_output, sep="\n")
answer = input(f"Do you want to delete the classifier {classifier_name} (y/n)? ")
if answer.lower() == "y":
print(f"Deleting {classifier_name}.")
comp_classifier.delete()
print("Cleaning up resources created for the demo.")
comp_demo.cleanup()
print("Thanks for watching!")
print("-" * 88)
```
+ 有关 API 详细信息，请参阅《AWS SDK for Python (Boto3) API Reference》**中的以下主题。
+ [CreateDocumentClassifier](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/CreateDocumentClassifier)
+ [DeleteDocumentClassifier](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DeleteDocumentClassifier)
+ [DescribeDocumentClassificationJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DescribeDocumentClassificationJob)
+ [DescribeDocumentClassifier](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/DescribeDocumentClassifier)
+ [ListDocumentClassificationJobs](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/ListDocumentClassificationJobs)
+ [ListDocumentClassifiers](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/ListDocumentClassifiers)
+ [StartDocumentClassificationJob](https://docs.aws.amazon.com/goto/boto3/comprehend-2017-11-27/StartDocumentClassificationJob)
------