I have just finished Supervised ML: Regression and Classification course, I have done all the assignments for it, but I still feel like I need to do a small project on it from scratch to get used to concepts in code better.
Any ideas and is what I am thinking about beneficial?
There are some datasets available on a site run by UC Irvine that are good to practice with https://archive.ics.uci.edu/
I suggest finding a dataset that’s interesting and trying what you’ve learned on them.
Hope this helps!
I’ll suggest you first do a crash course from YouTube(freecodecamp) regarding Sklearn just to get a good idea about hyperparameter tuning, pipelines etc. Then fetch some datasets from openml.com. There are 1000s of datasets available for regression and classification for you to practice on.