So how do you set up a project of your own? The courses that you did before will hopefully have introduced you to the new development environments, databases and so on that you will need. For project ideas, you can do it two ways: if you have an idea, you can search online for the data sets that you need to implement it. Or you can first do a bit of online scouting to see what data sets are publicly available to you. Such publicly available data sets are usually found on government sites. Perhaps looking at the kind of data available will spark off a project idea, such as finding correlations between different variables and then making predictions. Some of these data sets may be too large for data science algorithms to work on your home PC or laptop environment, and if that’s the case just take a fraction of them and continue. Even this is a part of the learning process.
As you gain in confidence, you can graduate to doing projects on sites like Kaggle. How fast and how far you want to go is really up to you. If you still haven’t found a job along the way yet, you can use any free time you have to learn about some of the linear algebra and statistics theory behind all those functions that you’ve learned to use, so that you can use them more effectively. It’s not necessary at this stage of your career, (as I said in my first post), but always nice to know. At this stage, remember that what’s most important is still that you are capable of developing data science code proficiently in at least one language.
Just keep at it, keep learning, keep being up to date on what’s developing in the data science world around you and one day you’ll get that first job break!
In my next post, I’ll talk about how graduates from the mathematics and statistics field can get on the path to becoming a data scientist.