In this chapter, I will give you a high-level overview of the process of data science. I will focus on the different stages of data science work, including common pain points, key things to get right, and where data science parts ways from other disciplines.
The process of solving a data science problem is summarized in the following figure, which I called the Data Science Road Map.
The first step is always to frame the problem: understand the business use case and craft a well-defined analytics problem (or problems) out of it. This is followed by an extensive stage of grappling with the data and the real-world things that it describes, so that we can extract meaningful features. Finally, these features are plugged into analytical tools that give us hard numerical results.
Before I go into more detail about the different stages of the roadmap, I want to point out two things.
The first is that “Model and Analyze” loops back to framing the problem. This is one of the key features of data science that differentiate it from traditional software engineering. Data scientists write code, and they use many of the same tools as software engineers. However, there is a tight feedback loop between data science work and the real world. Questions are always being reframed as new insights become available, and, as a result, data scientists must keep their ...