Machine Learning for OpenCV 4 - Second Edition

Understanding the task by understanding the data

What is always the first step in tackling a new machine learning problem?

You are absolutely right: getting a sense of the data. The better we understand the data, the better we understand the problem we are trying to solve. In our future endeavors, this will also help us to choose an appropriate machine learning algorithm.

The first thing to realize is that the drug column is actually not a feature value like all of the other columns. Since it is our goal to predict which drug will be prescribed based on a patient's blood values, the drug column effectively becomes the target label. In other words, the inputs to our machine learning algorithm will be the blood values, age, and gender of a ...