Data is so dirty!

Click here to see the notebook on GitHub.

Click here to see the notebook on GitHub.

Here’s another data science project. It uses a dataset that mined used car sales from the internet. The data came from the German version of CraigsList and had some funny entries. Are Germans really selling Maseratis and Porsches and Bentlys online???

It looks like Germans have a strong preference for purchasing used German cars (same, lol). The most popular cars sold are all from German companies. In the top 15, 40% are German cars and 33% are from the European Union. American cars don't appear to be favored much, no surprise there!

I like making figures - but oooh dang this project got me!

Exploring data with graphs