在範例資料上使用 AWS SDK

以下程式碼範例顯示做法：

• 針對範例資料執行 Amazon Comprehend 主題建模任務。

• 取得有關工作的資訊。

• 從 Amazon S3 擷取任務輸出資料。

Python

SDK對於 Python（肉毒桿菌 3）

注意

還有更多關於 GitHub。尋找完整範例，並瞭解如何在 AWS 代碼示例存儲庫。

建立包裝類別以呼叫 Amazon Comprehend 主題建模動作。

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

使用包裝函式類別來執行主題模型工作並取得工作資料。

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)

• 如需API詳細資訊，請參閱下列主題 AWS SDK對於 Python（肉毒桿 3）API參考。

  • DescribeTopicsDetectionJob

  • ListTopicsDetectionJobs

  • StartTopicsDetectionJob

有關的完整列表 AWS SDK開發人員指南和代碼示例，請參閱使用 Amazon Comprehend 與 SDK AWS。本主題也包含有關入門的資訊以及舊SDK版的詳細資訊。