You love working with data and want to get better. You're smart and can learn on your own just fine. There's a lot of excellent and free material online. But getting started can be tough, as well as figuring out the fastest way to learn the skills you need.
We know it really helps to have experts kick-start your learning: we've been there! We will help you build solid theoretical foundations as well as practical applied data science skills. And once you're off, we'll show you how to continue learning effectively on your own.
You like data, but haven't made the step to a modern programming language. Before starting with data science, you need to learn how to code. We'll teach you the basics and help you deliver simple data products which can already make a huge difference.
You're fairly comfortable programming in Python and ready to take it to the next step. We'll teach you the tools, skills and theory you need to tackle real-world problems with Machine Learning, and how to get those solutions to production.
Our Python Booster programme will get you ready to confidently work with data and start your data science journey. You will learn common workflows while gaining a good understanding of the various data structures and programming concepts in Python. Our main teaching philosophy is that after the Booster you should be able to apply everything we have taught you.
We will provide you with a solid foundation in Python, especially it’s data science toolstack, but for a large part you will have to make your hands dirty as well! There will be many exercises, some of which are relatively straightforward (applying what you just learned) and some are harder for which you might need to find help online.
Even experienced data scientists often need help, but the key difference with less experienced data scientists is the efficiency with which they are able to find the help they need. We consider finding help as one of the most important data science skills, and in the Booster we will show you the tricks of the trade. This skill is especially important if you don’t have many experienced data science colleagues around you.
After the Python Booster you will be able to use Python for various basic data science tasks, including exploratory data analysis, data manipulation, visualization as well as a couple of simple modeling tasks. You will have the perfect basis for our Data Science Bootcamp. The Python Booster is also ideal when you are already experienced in data science but are used to another programming language such as R.
After day 1 you will be aware of the basic tools and able to write your first program
Anaconda, IDE's, Jupyter lab and notebooks
Variables, data types and structures
Logic and control flow, loops and comprehensions
On this day you will write your first function and start working with data tables!
Installing and managing with conda
Environments, hierarchies and namespacing
Introduction to pandas: reading data from excel and CSV. Summary stats, groupby operations and indexing
After this day you will be a master in Pandas!
Lots of practice
Chaining commands into a pipeline
First large assignment
After this day you will be able to do a full exploratory data analysis
Mainly using matplotlib (+ short treatment of other packages)
Reading and manipulating data from various file formats, such as Excel, CSV, HDF5, JSON, etc.
Solving typical problems you will encounter when reading and writing data
Random sampling, building a simple model
The first part of this day focuses on communicating your results with your audience, by building dashboards, reports, and interactive plots. The second part of the day focuses on debugging your code and concludes with a summary of all the things you learned during the Booster.
Dashboards, interactive plots and (automatic) report generation
Techniques to get un-stuck
Inside tips on how to keep improving
Let's celebrate our new skills with some beers!
ex Software Engineer
MSc from TU Delft
ex Project Leader for CPB