I recently went on a Mini-Golf date with my girlfriend, which was my first time playing Mini-Golf in years. With present-day knowledge, I couldn’t help but see our score card as a dataset and suspect a trend in our performance. That called for analysis!
For this project, I decided to take a strange route to analyze an 18-row dataset. I entered in the score card into a spreadsheet and loaded the dataset into a jupyter notebook using pandas. Since I only had our stroke counts (basically the number of times we hit the ball) for each hole and the par (target number of strokes) for each hole, I needed additional calculations to derive interesting insights.
Typically, golf scores are calculated using only strokes. The strokes for each hole are compared to the par for that hole. Often, scores are reported as “x above par” or “y below par”. There are specific terms for these that I won’t get into, not only because they’re not important but because I don’t even know them!
For my analysis, I used a simple ratio to measure performance at each hole:
I also took the difference rather than the ratio, which unsurprisingly resulted in a similar looking function when graphed. All calculations were then put into new columns in the pandas dataframe.
Speaking of graphs, I took this fun project as an opportunity to learn plotly and make the scatter plot seen below. Plotly is an excellent open source visualizer made for all types of applications from traditional analysis to machine learning data, and it’s free!
This data tells a funny story, and shows the brain’s retrieval of putting skills. From the start, I was performing a little better than my girlfriend, and we both saw our performance increase through the 9th hole. On the 10th hole, however, she struggled! And it seems like I wanted to give her a chance to catch up shortly after, since my performance went down until I showed off at the end — or my hunger that afternoon went from exhausting me to motivating me.
This is a great example of a very small set of data telling a story — that’s one of the reasons I love working with data.
I hope you enjoyed the read, please feel free to reach out via email or LinkedIn with any questions or just to connect!