MIS 4900/6900 - Advanced Analytics with Python (Summer 2023)

This course is a follow on to my MIS 4470/5470 - Practical Computing for Data Analytics course. In that course we learn to use both R and Python for various analytical computing tasks. Over the years, I’ve found myself wanting to address more topics and issues but the semester just refused to expand. So, I’m creating this new course and it will be entirely Python based. You should either have taken MIS 4470/5470 or have solid Python experience and have taken some data science coursework.

One of the things I want to convey through this course is that business analytics is not synonymous with just data analysis, data viz, and statistical/machine learning models. While some subset of those things are often part of analytics projects, many problems require additional modeling approaches such as simulation and optimization.

Another goal of the course is for you to develop your skills in using Python to solve the myriad of problems and tasks for which we often use spreadsheets. Using a more computational approach with tools like Python can lead to better reproducibility and reusability. Along these lines, I hope to spark a little joy by challenging you to use Python to solve some interesting and fun computational puzzles. Programming is fun and it’s a great feeling when you get a program working that solves some problem.

Finally, another focal point of the course is an introduction to topics that are more on the software engineering side of analytics. These skills are important for helping get analytics based work created, deployed and used. These topics will be infused throughout the course.

• My OU website: http://www.sba.oakland.edu/faculty/isken/

• My Github site: https://github.com/misken/

• My analytics blog: https://bitsofanalytics.org/

Course outline:

• Course logistics and technical infrastructure
  • Textbooks
  • Setting up your analytics machine
  • Resource Center
• Module 1 - Analytical and technical foundation
  • Getting started with aap
  • Intro to git and GitHub
  • Computing with Jupyter notebooks
  • Basics of using Python IDEs
• Module 2 - Statistical/ML modeling with scikit-learn
  • Review of sklearn and ensemble models
  • Using cookiecutters to structure projects
  • Data prep for Pump it Up project
  • Regularization and more classifier models
• Module 3 - Excel with Python
  • What if analysis with Python
  • Creating the whatif package
  • Using Python to wrangle Excel files
• Module 4 - Simulation modeling with Python
  • Downloads and other resources
  • Activities
• Module 5 - Web scraping and datetime analysis
  • Automated data gathering from the web
  • Interactive visualization
  • Datetime and occupancy analysis

• Search Page