Deploying models on batch transformers

Some use cases don't require a real-time endpoint. For example, you may want to predict 10 gigabytes (GB) of data once a week in one go, get the results, and feed them to a downstream application. Batch transformers are a very simple way to get this done.

In this example, we will use the scikit-learn script that we trained on the Boston Housing dataset in Chapter 7, Extending Machine Learning Services with Built-in Frameworks. Let's get started, as follows:

1. Configure the estimator as usual, by running the following code:

   from sagemaker.sklearn import SKLearn
   sk = SKLearn(entry_point='sklearn-boston-housing.py',
      role=sagemaker.get_execution_role(),
      instance_count=1,
      instance_type='ml.m5.large',
      output_path=output,
      hyperparameters=
          {'normalize': True, 'test-size': 0.1})
   sk.fit({'training...