Rachel Sholder, Data Science Intern, Analytics and Visualization
Data analysis is the process of collecting, inspecting, cleaning, transforming, and modeling data with the goal of discovering useful information, suggesting conclusions, and then communicating your results to have the biggest possible impact. According to Merriam-Webster, a process is a series of actions or steps taken in order to achieve a particular end. While the “particular end” of data analysis might be a presentation to a client, my “particular end” I have been working towards achieving is a successful end to my summer internship.
- The first step of data analysis is data collection. This involves gathering your data and getting familiar with it. Accurate data collection is of the utmost importance to maintaining the integrity of your research. Likewise, the first step of a summer internship is getting acclimated to your new environment. For me, my new environment was a data and analytics consulting firm. Each summer, it is always a challenge to get out of your “student mode”—having just finished finals and my junior year at Lehigh University—and jump into “business mode.” Like data collection, appropriate acclimation is of the utmost importance to maintaining the integrity of a summer internship.
- The second step of data analysis is data preparation (which encompasses cleansing, formatting, etc.). Ask any data analyst or data scientist and they will tell you that about 80% of the work happens here. This holds true for my internship as well. This is where all of the learning, coaching, and enrichment happened. This era marks the rise of data analytics, data science, business intelligence, and big data. One of the most exciting parts of my internship was being able to gain hands-on experience with data preparation, data cleansing, and data wrangling tools. These tools have certainly contributed to the rise and will certainly be sticking around when data analytics is no longer a “rise” but the norm. It was an incredible opportunity to see how quick-minded, smart, and predictive these tools are. In a different project I assisted with, I got to see real world applications of things I learned in the classroom. I worked with graphs of normal distributions, skewed distributions, step functions, exponential functions, asymptotic functions, sinusoidal functions and linear functions—all things that you learn about in calculus and basic statistics. To those students that always ask, “Why do I need to know this? When will I ever use math in the real world,” I can now confidently answer, “If you pick the profession of a data scientist, data analyst, or really any career in the STEM field, I can tell you one thing: your math skills are incredibly useful.”
- The final step of data analysis is the actual analysis. After working with your data for some time, you are ready to make visualizations, create a presentation, and show your clients—reaching your “particular end.” My “particular end” was not only a final presentation to show what I have spent the past few months doing, but also a feeling of satisfaction, accomplishment and gratitude. Three months ago as I finished my junior year of college, I felt like I had exhausted the math classes offered. I had learned and learned in the classroom about Brownian motion, groups and rings, and limits of sequences. Now, at the end of my internship and about to enter my senior year, I can confidently say that what I have learned outside of the classroom this summer is irreplaceable.