Inference Pipeline with Scikit-learn and Linear Learner.ipynb issues

* input types
[This Inference Pipeline with Scikit-learn and Linear Learner notebook](https://github.com/awslabs/amazon-sagemaker-examples/tree/master/sagemaker-python-sdk/scikit_learn_inference_pipeline) states that csv is the only valid input type, but this is incorrect according to the [SM SKLearn docs](https://sagemaker.readthedocs.io/en/stable/frameworks/sklearn/using_sklearn.html):

"The SageMaker Scikit-learn model server provides a default implementation of input_fn. This function deserializes JSON, CSV, or NPY encoded data into a NumPy array."