From the course: Level Up: Python Data Acquisitions, Prep, and EDA

Getting started with Python for data science: Code challenges - Python Tutorial

From the course: Level Up: Python Data Acquisitions, Prep, and EDA

Start my 1-month free trial Buy for my team

Getting started with Python for data science: Code challenges

“

- [Seth] The data science world is an exciting place with state-of-the-art models coming out at an unprecedented pace. We can't forget about what makes data science so valuable, the actual data. No matter what models you end up using, acquiring and prepping your data is always going to be the first step in the data science process. No model can make up for poor data. After you have your data it's tempting to dive straight into modeling, but you always need to do some simple exploratory analyses first. Forgetting this simple step can create problems once unsavory data hits your models. In this course you'll see challenges from the beginning phases of the data science workflow, through data acquisition, data preparation, and exploratory data analysis. You'll have challenges in grabbing data from websites. You'll need to figure out ways to clean tricky text data with regular expressions, and extract specific variables that you need. Even your visualization skills will be tested. I'm Seth Berry, and I'm thrilled to give you some ideas about challenges that you'll face before you get to your models and then show you how I might solve those problems. I'm sure that you'll even figure out different ways of doing things that I present, and I'd love for you to be able to share your ideas with everyone. In the end, that's the real beauty of the data science data prep process. We can take the same ideas, tasks, and challenges, and solve them in different ways. Ultimately, we have the opportunity to share what we've learned with others.

Contents