AI is going to change the world more than anything in the history of mankind. More than electricity. —

Dr. Kai-Fu Lee

As AI continues to grow and change data-related disciplines, I wonder if this future is already here.

In this one, we’ll explore how Claude 3.5 has changed data visualization, and how it might reshape the way we see the world.

AI-Powered Job Market Insights

Reference

In this article, we will use AI-Powered Job Market Insights from Kaggle, here is the link. Now let’s first explore this dataset by using ChatGPT 4o, and we will switch to the Claude 3.5 Sonnet in Data Visualization stage.

Data Exploration

Now do explore this dataset, use following prompt with GPT4o;

Show me the head and tail of this dataset. 
Also, display the info of the dataset and provide a description. 
Use relevant methods( head, tail, info, describe) but show me in decent way.

Here is the output.

SS of the output

Now you have an idea about the dataset.

Data Visualization

In this stage, you need to come up with ideas for the dashboard you’ll create. You can actually use ChatGPT 4.0 for this. Here’s a prompt that will generate dashboard ideas for you.

Note: I also made it generate prompts for LLMs, so we can paste them directly into Claude 3.5 Sonnet.

Here is the prompt;

Can you create 5 data visualization and dashboard ideas that spark 
curiosity and intrigue for the attached dataset? 
After outlining the curiosity element, 
write a prompt for each idea that compels an LLM to generate it using the 
attached dataset, including dashboard prompts.

Here is the output.

SS of the output

Wonderful, now we’re like Chief Data Scientists, directing LLMs to work for us. Now, I’ll use the following dashboard with Claude 3.5 Sonnet:

Create a dashboard that includes a heatmap comparing AI adoption levels 
with salary ranges across different industries. 
The dashboard should allow users to filter by industry, 
company size, and location. 
Add dynamic insights that highlight industries where lower AI adoption 
correlates with higher salaries. 
Include tooltips that provide additional information on the roles and 
companies within each cell of the heatmap.

Claude 3.5 Sonnet

Now, let’s go to your Claude account, here. Unfortunately, to use the artifact feature, which will be the core feature we use, you need to have a professional plan. But trust me, you will not regret!

Reference

Let’s paste the prompt above. Here is the initial answer of Claude 3.5 Sonnet.

Output of Claude 3.5

As you can see it generates error but it is okey, paste the error and force it to solve the error. After bunch of tries, here is the output.

Claude 3.5 Sonnet’s output

As you can see, the output of the code is displayed. You can click on the code in the top right to view it.

In case you didn’t know, Claude 3.5 Sonnet uses React to write these dashboards and display artifacts. That’s why we’ll use the following free website, where you can run your React code and share the link to the output.

codesandbox.io

Reference

Sign in to this website using your Google account, and you’re ready to go! Now, copy the code from Claude 3.5 Sonnet and paste it into App.tsx, which you can find on the left.

Reference

To run your code, use the following code to the terminal;

npm run dev

As you can see from the above of the preview, they gave you website to see your dashboard as below, here is the link they provide.

Link of This Dashboard

Final Thoughts

In this article, we explored Claude 3.5 Sonnet’s incredible feature, where you can view the output of your code and interact with it directly.

We also discovered how you can preview these results using a free website and easily share them with colleagues and friends.

If you found this one good, consider subscribing to our Substack for weekly AI news, expert tips, and exclusive tools to stay ahead in the world of AI.

Invited only notion page for our paid subscribers

Here are the free resources.

Here is the ChatGPT cheat sheet.

Here is the Prompt Techniques cheat sheet.

Here is my NumPy cheat sheet.

Here is the source code of the “How to be a Billionaire” data project.

Here is the source code of the “Classification Task with 6 Different Algorithms using Python” data project.

Here is the source code of the “Decision Tree in Energy Efficiency Analysis” data project.

Here is the source code of the “DataDrivenInvestor 2022 Articles Analysis” data project.

“Machine learning is the last invention that humanity will ever need to make.” Nick Bostrom