Firstly, I really want to thank the pedagogical team behind this MOOC. I have done several ML/DL/DS MOOCs in the past which lingered around the theory shying away from the practical aspects. This one was certainly different and had lots of new information concerning the implementation. The most interesting part about this course for me was the preprocessing/transformations and hyperparameter tuning sections. Midway through the course, I went back to Kaggle and joined a tabular-data competition that gave me a 0.70 ROC model on the holdout set. After a few more lessons (on tuning) I was able to take my model up to 0.76 ROC. The highest-ranked model for this competition was at 0.78 ROC! This really means something to me. And again, I really want to thank the entire team for enabling us learners to achieve such/their small successes.
The image above is a sort of mind-map that I made while taking this course, listing all the sklearn modules/functions that we used. It helped me create a mental picture of the sklearn “toolkit” and devise a strategy to approach a new problem. I hope you find this useful 
. You can find here the full resolution image.
Cheers!