So, as always, it’s been a while since my last post, but I have had some major changes in my life as many around the world have in this pandemic. I think the most important component of that is that I am making a career change to work more directly in data science so that I can actually live up to this blog’s namesake and work in an NLP related position. Naturally, there is a lot to learn, and knowing the kind of person I am, I need the framework of a class to fully ensure that I will be responsible enough to take on that task, so I enrolled in a bootcamp that will help “upskill” myself to be ready to pursue jobs once I complete it.
The first major hurdle is in the understanding of Python because it has since become the go to programming language among the data science community. I think I have had an okay time getting used to how things work for the basics since I have some experience with programming from my previous job, but I can’t be complacent, and really need to delve deeper into best practices with regards to coding. One of my requirements is that I also keep a blog updating my progress on any projects that I am working on. My first project was a group project *shudders* and that went about as well as I could have hoped in that one of my group members ended up dropping and I pretty much had to write most of the code myself, so that doesn’t particularly represent my own unique processes in how I would have tackled a project such as that, so instead I am going to start with my second project.
Being the gigantic weeb that I am and being in the midst of a bunch of other nerdy types, I felt it was a pretty safe space to do a project on anime. In this case, I was trying to predict myanimelist.com ratings for different anime series. Some of the main requirements were that I needed to utilize webscraping to obtain data, and then analyze it using regression methods. Now, without a doubt the biggest hurdle was trying to obtain the data. I learned just enough about how html is formatted in different ways to get an understanding of where the data is and how it’s formatted to be able to pull it off a webpage. I thought it was really cool when I finally was able to get the info that I needed. Definitely felt like a hacker breaking into the system (where the door was wide open the whole time). I wanted to make sure I could get enough features that would be useful, but because of how long it took me to muster the motivation to finally do it (read: the deadline was coming up and I had to get off my butt and do it or fail), I ended up just going with a lot of the content based features and making a LOT of dummy variables. Obtaining all the data was pretty interesting in its own right, but because of that I didn’t really get to delve as deeply into the analysis as maybe I was expecting my instructors to do.
The analysis itself was pretty bare bones in that this type of project is something I have done in so many other classes, so I thought I could spend more time on the data collection, but I was severely mistaken in that we had actually learned a lot more about some other methods of manipulating features and the data in order to get better results that I had not really encountered in my previous coursework. I fully intend to go back and get a better insight into those methods, but the breakneck pace of this bootcamp doesn’t really warrant the time to go back. In fact, I’m definitely falling behind, but maybe I can be overconfident enough that I can trick myself into thinking that I can handle these kinds of projects, and honestly if I can do that maybe that’s all I need in life to be successful.
Either way, I want to fully take advantage of this bootcamp to really push myself into obtaining a job in a field that I can really see myself growing into (aka not hating ALL the time). If by the end of this bootcamp, I can do one of those text generated fanfictions, I think I would know the enormous amount of money I spent to be part of this was well worth it!
P.S. In other news, I have successfully gotten back into a routine of studying Japanese. I had been doing some studies on and off the last few years, and I think I have the right mindset and motivation to really make sure I can devote myself to it. I’ve been keeping updates on my WaniKani progress on my twitter and I happened upon a random Japanese streamer on Twitch who was playing Splatoon, so I’m getting an opportunity to practice listening and writing skills which I have virtually done nothing for since I finished studying it back in undergrad. I’m doing my best to set myself up better so that I can take on 2021 with real pride as I enter the last year of my 20’s (God, typing that gave me arthritis and back pain)