Handling a data set

The first thing you should do when faced with a spreadsheet full of lines of data is to understand it, that is to know its shape and size, the rows and columns, the types of data it contains, (and what it doesn’t contain!) In this activity, we’re going to start handling our data.

Understanding data

Now we have a data set open and in front of us, we can start looking at the types of data it contains and how it’s organised.

We’re going to be working from the spreadsheet of data from the course exercise, it’s linked again below. Start thinking about the quality and accuracy of the data. Here’s a list of questions to ask yourself about your data set:

• How big is it? How many rows and columns does it contain?
• What characteristics does it describe? What real-world information does it relate to? + What are the column headings? What categories can you see?
• How does it describe them? What is the formatting and how does the real-world information map to what’s in your data?
• What’s its scope (eg, does it cover time, geography, products)?
• How accurate is it? Are there typos or formatting errors?
• Is there any missing data: blank cells, rows or columns where you would expect to see data?

Unless you can answer these questions, it’s tricky to plan how to analyse data confidently, and it’s easy to make mistakes or at least wrong assumptions about the data.

In the comments below share what you’re seeing in the data set, how big is it, what categories and types of data can you see? And, start thinking about how the data may help us answer our business question: What can the data set tell us about the sales team’s performance?

Don’t worry if you can’t answer them all perfectly, we’ll move onto specific techniques to help you handle your data in the next steps. The most important thing at this stage is to think like a data analyst.