Inspiration

One of our groupmembrs was an avid baseball fan. He was impressed by recent plays of the Toronto Bluejays as they moved to the world series and was really impressed by Springer's homeruns.

What it does

Gives a formula for calculating the likelihood of a hit causing a homerun.

How we built it

We analyzed the data using R and jupyter, then composed graphs and tables using libraries. We then compiled our results into a powerpoint presentation and used some image editing software to make things presentable.

Challenges we ran into

Coming up with a good formula that actually correlated with the likelyhood of a homerun was difficult because the group overall did not know too much about baseball, so we had to try to logically deduce what makes a good hit and test our hypothesis with the data.

Accomplishments that we're proud of

Our formula r = 0.75 has a strong correlation, meaning it's quite accurate. We are proud of this because we had little knowledge of baseball coming into the project but we were able to get a satisfactory result.

What we learned

We learned the basics of using Jupyter and cleaning data, as well as summarizing what is important. We also learned more of what works for data visualization, as certain ways to present the data we trired in the beginning were not very effective. We also created some new variables based on variables that already existed, learning how to manipulate the data past its original state. Additionally, we learned what linear regression was and correlation factors.

What's next for What Makes A Homerun?

Next, we would get more data to get a more accurate read on certain points such as B3 hits as well as find more variables that could be included into our formula to make it more accurate.