StartTopicsDetectionJob搭配使用 AWS SDK或 CLI

    using System;
    using System.Threading.Tasks;
    using Amazon.Comprehend;
    using Amazon.Comprehend.Model;

    /// <summary>
    /// 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.
    /// </summary>
    public static class TopicModeling
    {
        /// <summary>
        /// This methos calls a topic detection job by calling the Amazon
        /// Comprehend StartTopicsDetectionJobRequest.
        /// </summary>
        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);
            }
        }

        /// <summary>
        /// This method is a helper method that displays the job properties
        /// from the call to StartTopicsDetectionJobRequest.
        /// </summary>
        /// <param name="props">A list of properties from the call to
        /// StartTopicsDetectionJobRequest.</param>
        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}");
        }
    }

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://DOC-EXAMPLE-BUCKET/" \
    --output-data-config "S3Uri=s3://DOC-EXAMPLE-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。

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