Visualization / Grafiken / Report

Data Preprocessing & Feature Engineering

• Visualize Machine Learning with Yellowbrick → great for preprocessing as well

<aside> 💡 Always prioritize something useful over something pretty.

</aside>

<aside> 💡 EDA is iterative! Check the errors of your models and return to your data.

</aside>

Wie prüfe ich die Datenqualität?

The importance of EDA

Golden Rules: EDA

How to understand your data?

It's easy to fool yourself into solving the wrong problem, or trying to solve the right problem using the wrong solution. To prevent this, never start a machine learning project by building a model. Instead, start by asking questions.

Here are my 6 favorite questions to start any machine learning project:

1. What problem are we solving?
2. Why is solving this problem important?
3. What do existing solutions look like?