Walkthrough and Dataset

Walkthrough

Let's take a quick look through what you’re going to see in the walkthrough ahead. We’ll start with brief introductions to gathering, then assessing, and then cleaning our data, which are our three core steps in the data wrangling process. These intros will be more conceptual in nature. Both Mat and David will guide you through these.

In between each introduction, you'll wrangle a real dataset, converting the concepts you learned in the preceding introduction to Python code. David will be your guide here. Keep in mind our end goal— to make awesome analyses and visualizations —throughout the whole process. We'll end the lesson by using our wrangled data to do just that.

Dataset

The dataset you'll be wrangling is a dataset of 19,000 online job posts from 2004 to 2015 that were posted through an Armenian human resource portal. It is hosted on Kaggle , which is an extremely popular website for exploratory data analyses and machine learning competitions. The dataset is dirty and messy enough that you'll have wrangling work to do, but also clean enough that it won't give you a headache.