Starting with a question

Everything in science starts with a question. For our purposes, we’ll consider two possible scenarios:

• We have a specific question in mind and we need to collect and analyze appropriate data to answer that question
• We already have data, and during exploration, a question has arisen

In our case, we’re going to recreate the data analysis phase of a potentially important breakthrough in the field of medical diagnosis. I’ll be presenting an example from Kaggle taken from a paper titled High-accuracy detection of early Parkinson’s Disease using multiple characteristics of finger movement while typing, which was conducted by Warwick Adams in 2017. You’ll find the full study paper and the dataset links in the Further reading section of this chapter.

Note

Kaggle is an online data community designed for data scientists and ML engineers. The site provides competitions, datasets, playgrounds, and other educational...