ChiPy Mentorship and the Pandas Library

By Kamil Mysiak

I want to take this opportunity to introduce myself and the project I’m embarking on as I partake in the ChiPy mentorship program. I also want to share a brief overview of the Pandas library as I believe it will help others immensely when trying to analyze their data.

Introductions

It’s been just about two years since I stumbled upon a YouTube video which all but changed the trajectory of my life/career. You see, I’m an Industrial Organizational Psychologist and it is our task to study and improve the workplace. We work in the human resources (HR) department on projects around employee productivity, hiring, training, performance, motivation, etc. If you have ever taken an employee engagement survey at work, you can thank (or hunt down) an I/O psychologist. We also receive training in research design and statistical analysis which is how I ended up in my current job. I analyze heaps of HR data in order to gleam actionable insights for my clients.

With all that said, let’s get back to this YouTube video. I recall trying to forecast/predict which employees were most likely to quit in the first year of hire. I knew from grad school we could use a statistical method named log regression to predict a binary (Yes/No) outcome. As I proceeded to google “predicting employee terminations log regression” I was directed to YouTube video which walked through building a python machine learning tutorial using log regression . You have to understand, I had…