Over the past week I have struggled very hard with something. That something would be imposter syndrome both in searching for a job using the required money back job requirements and daily coding. First, I will touch on the job search. Through looking on LinkedIn and other job boards I have very quickly come to realize that the job search is going to be very difficult. I thought with my three years of consulting experience I would easily be able to land a job in either the tech or consulting world after putting Python and SQL on my resume. That would prove to be false. I realize now; the competition is very very tough. There are people with master’s and PhD’s degrees while I just have a BS degree. It has brought some light on my next steps and me realizing eventually I will probably want to go back to school. Although, first I would like to get a job in the field for at least a year or two. Nevertheless, I need to keep fighting and keep pushing. This is where the grit comes in. I have a goal and I will achieve that goal eventually. Great things take time.
Unfortunately, I realized the data I was scraping was only for the current season and the other data I had was for seasons from 2003 to 2016. I have decided to just to do two separate models and create metadata from my betting web scraped data. Then use another web scraping technique to get even more historical data from sports reference website.
As my last post touched on I decided to switch my efforts to a new sports modelling project. The first hurdle of this project was obtaining the data. I decided to google around for college basketball historical data and sure enough got lucky. I found a pretty cleaned and comprehensive data set on Kaggle. The data can be accessed using Big Query from Google.
I just recently graduated from Flatiron’s data science bootcamp program and wanted to start a project to keep my skills sharp. I decided to combine two of my favorite passions: python/modeling and sports. I have done some research to figure out what sport is the easiest to predict to start with. Then once I perfect the first sports model, I will move on to try and predict the harder sports. The sports I am choosing from are both professional and collegiate level.
Now that I have a clear path forward I started the development of the project. Step 1 is to ensure the selenium web driver is working properly, which it was. From there I navigated to each site, first PNC and Chase. PNC did not give me any problems whatsoever accessing the html and css selectors to use Selenium to click on the correct inputs(password/username) and then submit. The one road block I did face was figuring out how to ensure my passwords were safe in a secrets file. More on that to come!