Prerequisite - Data Science for Business Part 1
I expect that you are comfortable with the following concepts, which are taught in DS4B 101-R:
- Machine learning using parsnip (101 Week 6) - Part 2 of this course includes a lot of machine learning using the tidymodels system. This course is very detailed, but I assume basic knowledge of how to perform machine learning with packages like parsnip.
- Iteration using purrr (101 Week 5) - Part 2 of this course includes iteration for working with time series groups and parallelizing code. I assume you have used purrr::map() and can make a for-loop. I will cover details such as doFuture for parallelizing code using loops, but this could become unfortable if you've never made a loop.
- Data wrangling using dplyr (101 Week 2 & 3) - Most of the Feature Engineering section relies on your knowledge of basic data wrangling skills. Make sure you are comfortable working with and manipulating data. Otherwise Part 1 will be uncomfortable.
- Data visualization with ggplot2 (101 Week 4) - This course is heavy on visualization. Forturnately, much of the code has been abstracted away with functions like timetk::plot_time_series() and modeltime::plot_modeltime_forecast(). Nevertheless, there may be sections of the course that require custom visualizations.
What if I haven't taken the 101 Course?
This is OK provided you understand that some sections may be advanced. If you are on the fence, my suggestion is to try the Time Series Course. You can always go backwards. In fact, About 1/3rd of my students taking the 201 Course (pre-requisite is now 101) went backwards to take the 101 course. That's why 101 exists - to help you firm up your knowledge on basic skills so you can do advanced data science like advanced machine learning (201) and high-performance time series analysis (203).