-

Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

Topik

import sagemaker
from sagemaker.serializers import CSVSerializer
xgb_predictor=xgb_model.deploy(
    initial_instance_count=1,
    instance_type='ml.t2.medium',
    serializer=CSVSerializer()
)

xgb_predictor.endpoint_name

Tip

import sagemaker
xgb_predictor_reuse=sagemaker.predictor.Predictor(
    endpoint_name="sagemaker-xgboost-YYYY-MM-DD-HH-MM-SS-SSS",
    sagemaker_session=sagemaker.Session(),
    serializer=sagemaker.serializers.CSVSerializer()
)

  1. X_test.to_csv('test.csv', index=False, header=False)

boto3.Session().resource('s3').Bucket(bucket).Object(
os.path.join(prefix, 'test/test.csv')).upload_file('test.csv')

  2. # The location of the test dataset
batch_input = 's3://{}/{}/test'.format(bucket, prefix)

# The location to store the results of the batch transform job
batch_output = 's3://{}/{}/batch-prediction'.format(bucket, prefix)

  3. transformer = xgb_model.transformer(
    instance_count=1, 
    instance_type='ml.m4.xlarge', 
    output_path=batch_output
)

  4. transformer.transform(
    data=batch_input, 
    data_type='S3Prefix',
    content_type='text/csv', 
    split_type='Line'
)
transformer.wait()

  5. ! aws s3 cp {batch_output} ./ --recursive