How to use Kaggle for Climate Change studies

In this post we'll talk a bit about Data Science and how we can make a difference by alerting people to Weather Events.

- What is Kaggle?

What's up, devs! Have you heard of the Kaggle platform? If not, I'll tell you... Kaggle is the place where people who enjoy data science, machine learning and data analysis meet. There, you can explore data sets of all kinds, from cute kittens to crazy market forecasts.

But it doesn't stop there! The cool thing is that there's also a competition. It's like a championship of who can create the most accurate models and share them with the community. And you don't have to be an expert, see? There are lots of great people sharing their knowledge there.

- Briefly: Global Warming

Here's the thing: the Earth is getting warmer, and it's not because of the summer. It's because of human actions, from the most diverse of what we've heard lately about burning fossil fuels and dumping pollution into the air. The result? Insane climate change, like more brutal hurricanes and longer droughts.

We know it's serious, and we're late, but we can act in time.... Saving energy, using sustainable transport and supporting conservation projects all make a difference. Let's face it and save our planet, because there's no backup, right?

- The Power of Study in Global Impact

And that's what I want to demonstrate here, the superpower we all have: the power of study! You know that line of code that you can't get your head around? Well, it's like that, but applied to the whole world.

When we study, we understand what really happens. And when you understand it, you can make it happen. Imagine the impact if everyone studied global issues such as sustainability, equality and innovation?

Developers play a crucial role in this. We can create apps, systems and solutions that positively impact the planet and society. We not only solve problems, we inspire others to do the same...

- Example of how weather events affect our daily lives

A while ago, as a study in a data science specialization, I did a nice study, which is this one: 911 Calls - Case Study.

In it, I was able to apply my knowledge from college using a data set that is well known in the community.

In this our exploratory analysis in all occurrences: EMS, FIRE, TRAFFIC, during the period of 2016.

Then exploratory data analysis was used to discover some interesting aspects, a fact that caught my attention were the occurrences of January 23, 2016, due to the high accident rate on the present date.

This led me to analyze, because of so many occurrences. So I looked up information on Google regarding the weather that day, and we identified that there was a blizzard, and for that reason caused several traffic problems. We noticed that on the other days that there was no snowfall, the occurrence frequency was much lower.

Another relevant analysis is the issue of time, with most occurrences starting at 07:00, where it is the time that people go to work / school, and 18:00, Rush hour, end of office hours .

When accessing the site: January 2016 Weather in Philadelphia — Graph, you see that on January 23, 2016 a Nevada in Philadelphia occurred.

For this reason, the chart presented an outlier value in the TRAFFIC dataset, precisely on January 23, 2016.

Thanks for reading!
This is a simple one, but I hope it can help!
If you have any questions, just send me a message

Did you like this text?
Recommend it so that more people read it☻

Take the opportunity to follow me on social media:

Follow me on LinkedIn| GitHub| Kaggle

Thanks for Nail Gilfanov from Unsplash for cover image

See you soon!