Welcome back to the sixth and final installment in our Call For Code Technology mini-series, where I identify and talk about one of the six core technology areas within Call For Code. You’ll learn about that technology, how to best use it on IBM Cloud, and where to find the best resources to fuel your innovation. If you missed my other posts, make sure to check them out:
- Building Call for Code apps with IoT and Node-RED
- Building Call for Code apps with AI
- Building Call for Code apps using blockchain
- Building Call for Code apps using machine learning
- Building Call for Code apps around traffic and weather technology
If you haven’t already, accept the Call for Code challenge and join our community. In this blog post, I’ll talk about leveraging data science technologies so that you can use them to build your Call for Code solution.
Data science on IBM Cloud
You will find some overlap between this blog post and the one I wrote on machine learning, as they go hand in hand when working with big data, predictions, and insight gathering. The machine learning post also provides some information on Watson Studio, which is also applicable to this post on data science.
Prior to Watson Studio, we used to have a dedicated platform for data science called the Data Science Experience (DSX). However, we combined the best features of data science and machine learning together into a new platform called Watson Studio. Developers can work in the Watson Studio environment to work with others, train and build machine learning models, and experiment with various ways to work with data. You can take a tour of Watson Studio to see how projects come together. (It might even be a great place to collaborate with your Call for Code team members!)
Getting started with data science for Call for Code
If you don’t already have an IBM Cloud account, make sure to sign up, which takes less than two minutes. Just ensure that you use a valid email address because you must confirm your email address before you can create any services.
Given the wide impact that natural disasters can have on the world, it would be very beneficial to be ahead of the curve when it comes to making predictions that affect a large portion of the population. IBMers Vanderlei Munhoz Pereira Filho and Sanjeev Ghimire published a code pattern that utilizes data science and machine learning to predict changes in the stock market. This is an easy code pattern to follow as it introduces you to the basics of data science if you’re not already familiar. After you complete this pattern, you could take it further to visualize weather data models (don’t forget to grab your Weather APIs, mine data from hospital records of natural disaster survivors, or take past data from how natural disasters affected businesses and organizations to predict how they might be affected in the future with similar disasters.
A second useful code pattern on data science and visualization comes from IBMer Alok Singh. Learn how to take a large amount of raw data (in this case, time flight statistics) and visualize that data with Watson Studio. You could adapt this code pattern to factor in the effects of a natural disaster and its impact on travel when there is an emergency.
The final code pattern I want to showcase is one written by IBMers R K Sharath Kumar and Manjula Hosurmath, centered around text summarization and visualization using Watson Studio. This code pattern would be very useful during a natural disaster where a large amount of raw text data is generated and needs to be filtered out and understood.
This week we learned about data science and how you can utilize those resources in your Call for Code submission. I also provided you with three excellent code patterns that really show some great use cases of using data science on IBM Cloud. Hopefully, this post inspired you to incorporate data science to your solution.
I hope this mini-series over the last six weeks inspired you and gave you some ideas for your own Call for Code solutions. further develop your solution or give you some new ideas!