Applying our learning

In this chapter, we have learned how to create baseline models using AutoML, tracking our MLOps with MLflow, and even using more advanced language models in order to extract more information and ultimately business value from our data. Now, let’s take what we have learned and apply it to our datasets that we cleaned in Chapter 4 and featurized in Chapter 5.

We will start with creating and training a classification model for our Parkinson’s data so that, ultimately, we can classify hesitation using the patients’ tracking data.

Parkinson’s FOG

As mentioned in the Technical requirements section, we are using PyTorch. To use this, either install the packages in your notebook using pip or add it to your cluster configuration under libraries:

Figure 6.12 – Installing the PyTorch library

Once you have your libraries loaded, we import all the libraries we use:

Figure 6...