Get data insights and visualizations

Description

What? Ask Copilot to look at a spreadsheet and identify interesting insights or create visualizations (e.g. pie charts, graphs).

Why? Asking Copilot for insights into data is a quick way to identify some interesting trends that might be worth exploring further, or to double check your own analysis to see if you’ve missed anything. If you ask Copilot to create visualizations, it will use the Python coding language with popular data visualization libraries (Pandas, Matplotlib) to create charts and tables which should have a high level of accuracy.

What do I need to know? This recipe works best with smaller data sets saved as .csv files. Frustratingly, Copilot seems to have a relatively small ‘token limit’ (how many words it will process) when you ask it to look at attached documents. It’s quite opaque about what the limit is – if you give it longer documents, it often ends up analysing only a section but presenting it as a full analysis. This means it’s difficult to know how much of the data Copilot’s analysis is actually based on unless you already know the data set well. Currently, other tools (like ChatGPT and Claude) work better with large data sets. If you want to try using larger data sets with Copilot, you could experiment with ‘chunking them up’ into smaller spreadsheets.

Example Video

📹 Video – Create data insights and visualizations example

Instructions

Step 1: Find a spreadsheet that you would like some insights for. This recipe works best with simple spreadsheets with a single tab/sheet. For the best results, save the spreadsheet as a .csv file on your local computer so you can upload it to Copilot.

Step 2: Go to Copilot (office.com/chat) and sign in with your Coventry account. If you’re already using Copilot, just select the ‘New chat’ button at the top right.

Step 3: Start the conversation by copying and pasting the following prompt into Copilot, then select the ‘Submit’ button (the arrow at the bottom-right):

🤖 Prompt (click to expand, then copy and paste into Copilot)

I want you to help provide insights into some data I have in a spreadsheet. First, ask me what for the data is about. Wait for my response. Then ask me to upload the spreadsheet. Wait for my response. Analyse the spreadsheet and provide some interesting insights. Ask if I’m want you to analyse anything further, or if I would like some visualisations of the data. Wait for my response.

Step 4: Copilot should ask you what the data is about. Type your messages in the box and select ‘Submit’.

Step 5: Copilot should then ask you to upload the spreadsheet. Select ‘Add a file’ (the paperclip 📎 icon) at the bottom right of the text box, and then in the file browser select the .csv file on your computer. Then select ‘Submit’.

Step 6: Copilot should give you some initial insights, which may be quite basic and general. Tell it if you want insights into anything in particular (e.g. “Give me insights into the projects I’ve spent most time on”), or if you want it to present information in a different way (e.g. “Give me times in hours rather than minutes”).

Step 7: Tell Copilot that you want some visualizations for the data. You can be specific, (e.g. “Give me a pie chart of my top 5 projects”) or let Copilot decide what type of visualisations to make.

Step 8: If you want to copy the visualizations to use them somewhere else, select the ‘Edit in Pages’ button at the bottom of the post with the chart you want. A panel will open on the right-hand side of your browser window. Right-click on the visualization and select ‘Copy’. This will copy the chart as an image to your computer clipboard. You can now past it somewhere else, e.g. a Word doc or email.

Important: Always check Copilot’s output. Generative AI tools can hallucinate (create plausible but incorrect information).

This website was created using Coventry.Domains, a service of the Coventry University Group. The information, views, opinions and discussion contained on this website are those of the author(s) and do not necessarily reflect the views and opinions of the Coventry University Group. For more information on privacy, cookies, takedown requests and more, visit our policies page.