Learning resources

Here is a non-exhaustive, most-likely-to-evolve list of my favorite books and materials. I often find my self going through these resources as a way to learn or refresh my memory, so it is a small list at best. However, I’d most likely be going over this list again in the future if I find other useful materials.

• Python Tricks - This book is for anyone wanting to “level-up” their Python skills and learn new ways to implement or think about certain topics in the Python programming language
• Numsense! - This book’s tag-line is “No Math Added”. It explains machine learning concepts in layman’s terms. In addition, the authors also have a blog called Algobeans
• Introduction to Machine Learning with Python - It covers the toolkit for machine learning in Python such as numpy, Pandas, and scikit-learn. It explains concepts in simple terms and is best for anyone starting out with machine learning. You need to know Python beforehand.
• R for Data Science - Since I don’t use R a lot but is trying to learn, I find the approach of this resource effective since it gives applications of R first (such as visualization) before going into an introduction of the language.
• An Introduction to Statistical Learning with Applications in R - This is a book for people with good foundations for mathematics and statistics. However, it does explain the machine learning / statistical learning techniques in detail (i.e. going into the mathematical formula) so it is a good reference book for appreciating the nuances of these approaches.
• Irizarry, R. A., Love, M. I. (2015). Data Analysis for the Life Sciences. Leanpub - It’s a good resource to learn about statistics in R. The approach is code + statistics and math, though less heavy in math than concepts in stats. I like it because the explanations are clear and concise with generous examples in R. It’s also a good fit for anyone wanting to apply computations in the life sciences as it includes the popular R packages used in this domain. [Updated 2019-09-02]

And these resources because they’re entertaining practice challenges:

• The Python Challenge - This is one of the first sites I used when I started learning Python. It is filled with puzzles that you can solve by writing scripts. It’s my favorite learning game since one does a little bit of sleuthing to understand the problem. Alternatively, one site I just explored recently is Checkio. It also presents Python problems in a form of a game. In addition, you can check other player’s code, so you learn other methods to solve the game as well.
• Rosalind - This is a resource for applying Python coding in bioinformatics.

Some notes:

There is an interesting piece about MOOCs and videos by Prof. Lorena A. Barbara which can be read here.

Arguably, my learning style is a little less auditory than it is tactile (I learn better by doing). So I guess knowing about one’s learning style helps with choosing the kinds of materials for learning as well.