Using the SageMaker Autopilot SDK

The Amazon SageMaker SDK includes a simple API for SageMaker Autopilot. You can find its documentation at https://sagemaker.readthedocs.io/en/stable/automl.html.

In this section, you'll learn how to use this API to train a model on the same dataset as in the previous section.

Launching a job

The SageMaker SDK makes it extremely easy to launch an Autopilot job – just upload your data in S3, and call a single API! Let's see how:

1. First, we import the SageMaker SDK:

   import sagemaker
   sess = sagemaker.Session()

2. Then, we download the dataset:

   %%sh
   wget -N https://sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com/autopilot/direct_marketing/bank-additional.zip unzip -o bank-additional.zip

3. Next, we upload the dataset to S3:

   bucket = sess.default_bucket()                     prefix = 'sagemaker/DEMO-automl...