This repo includes minimal implementations of popular ML algorithms using pure python and numpy. The purpose of these notebooks is mainly for studying the basics of these algorithms rather than providing brilliant solutions (as you'll see all the problems are fairly basic).

Although the implementations are by no means optimal, they include the basic features of each algorithm plus some nice improvements (e.g. l2 regularization) to make things work better. Most implementations are based on basic numpy and scipy functions, although some utility functions from sklearn were also used (none wants to see the code for random splitting and scaling when looking at an MLP classifier).

Anyone who is studying ML algorithms and wants to get a good grasp on the technical aspects of their implementation. Aspiring data scientists who are trying to break into the field, but also seasoned professionals who might want to refresh their memory. Also, candidates preparing to ace their data science/ml interviews (since these algorithms tend to appear frequently in interviews).

If you are looking for production ready solutions, then you are probably best of using one of the existing libraries that implement these algorithms.