Use StartDocumentClassificationJob with an AWS SDK or CLI

To start document classification job

The following start-document-classification-job example starts a document classification job with a custom model on all of the files at the address specified by the --input-data-config tag. In this example, the input S3 bucket contains SampleSMStext1.txt, SampleSMStext2.txt, and SampleSMStext3.txt. The model was previously trained on document classifications of spam and non-spam, or, "ham", SMS messages. When the job is complete, output.tar.gz is put at the location specified by the --output-data-config tag. output.tar.gz contains predictions.jsonl which lists the classification of each document. The Json output is printed on one line per file, but is formatted here for readability.

aws comprehend start-document-classification-job \
    --job-name exampleclassificationjob \
    --input-data-config "S3Uri=s3://DOC-EXAMPLE-BUCKET-INPUT/jobdata/" \
    --output-data-config "S3Uri=s3://DOC-EXAMPLE-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

Contents of SampleSMStext1.txt:

"CONGRATULATIONS! TXT 2155550100 to win $5000"

Contents of SampleSMStext2.txt:

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

Contents of SampleSMStext3.txt:

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

Output:

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

Contents of predictions.jsonl:

{"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}]}

For more information, see Custom Classification in the Amazon Comprehend Developer Guide.

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