StartDocumentClassificationJob 搭配 AWS SDK或 使用 CLI

啟動文件分類任務

下列start-document-classification-job範例會啟動文件分類任務，在--input-data-config標籤指定的地址的所有檔案上具有自訂模型。在此範例中，輸入 S3 儲存貯體包含 SampleSMStext1.txt、 SampleSMStext2.txt和 SampleSMStext3.txt。此模型先前已針對垃圾郵件和非垃圾郵件的文件分類，或「ham」SMS訊息進行訓練。當任務完成時， output.tar.gz 會放在--output-data-config標籤指定的位置。 output.tar.gz包含 predictions.jsonl，其中列出每個文件的分類。Json 輸出會列印在每個檔案的一行上，但此處的格式為可讀性。

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 的內容：

"CONGRATULATIONS! TXT 2155550100 to win $5000"

SampleSMStext2.txt 的內容：

"Hi, when do you want me to pick you up from practice?"

SampleSMStext3.txt 的內容：

"Plz send bank account # to 2155550100 to claim prize!!"

輸出：

{
    "JobId": "e758dd56b824aa717ceab551fEXAMPLE",
    "JobArn": "arn:aws:comprehend:us-west-2:111122223333:document-classification-job/e758dd56b824aa717ceab551fEXAMPLE",
    "JobStatus": "SUBMITTED"
}

predictions.jsonl 的內容：

{"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}]}

如需詳細資訊，請參閱《Amazon Comprehend 開發人員指南》中的自訂分類。

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