Portfolio

Power BI

While data analytics involves various forms of number crunching, data visualization and dashboarding are also important tasks for data analytics. What's the point of doing data analysis if there is no way to convey to a client or an executive board what the data is saying? This is why data visualization tools, such as Microsoft Power BI, are essential for data analysts. Power BI gives analyts the ability to create dynamic dashboards, which are the most efficient way to display complex or large datasets. As Power BI starts to be incorporated into all lines of businesses, LEAP has included this program into our donuts and data sessions. 

Pictured above is the dashboard on a market dataset that was created for one of our donuts and data sessions, which displays only a fraction of the features in dynamic dashboarding. This is a great program with our members to dive into because it's drag and drop capabilities makes it easy for users to use, but the Excel-based query language also allows for intricate equations and filtering. It's our hope that introducing the structure of data visualization programs, teaching the art of dashboarding, and preparing members to tell data stories will help them succeed in their careers. 

Tableau

The objective for this analysis was to highlight a trend in wealth disparity over a certain time period for countries throughout the world. The data for the Tableau analysis was sourced from the World Inequality Database (WID). Specifically, we were looking at identifying the annual trend of wealth disparity for France, China, Russia, and the USA because these were the only countries that had full data throughout years 1999-2015 in the WID. 

We displayed the trend of wealth disparity year-over-year by using a line graph conditionally formatted by a red-green color-scale benchmarked by the country's average of wealth disparity across the specific time period. As you can see, the red-green color-scale is flipped to imply that the higher the wealth disparity, the "worse" (more red). While this was used as a benchmark based on generally accepted social measures, we remain bipartisan in our discussion of data with our students. 

R

Partnered with the Sports Business Association, LEAP had a Donuts and Data session about Baseball Analytics. At the beginning of the session, we discussed the basics of baseball statistics including defining terms and benchmarks. Then, we used conditional formatting on Microsoft Excel to isolate players that had certain criteria that fit the description of an above-average baseball player. With a basic understanding of baseball statistics and how to manually use formatting to pick players, we moved to use the programming language R for looking at broader baseball trends. Above are various scatterplots that show the correlation between average runs, on-base percentage, and slugging for all MLB teams. The overall purpose of this session was to create a very basic understanding for attendees of what MLB teams use to analyze players in a sport that is now being driven by analytical insights.