Data Science is definitely one of the hottest market right now. Almost every company has a data science positions opened or is thinking about one. That means it’s the best time to become a Data Scientist or hone your skills if you’re already one and want to level up to more senior positions. This text covers some of the most popular books on Data Science.
If you’re just starting your adventure with Data Science, you should definitely try:
Data Science from Scratch is what the name suggest: an introduction to Data Science for total beginners. You don’t even have to know Python to start.
If you’re a total beginner but you’d like to go more in Machine Learning direction from, Introduction to Machine Learning with Python is a book for you. It also doesn’t assume you know Python.
If you’ve already read 1 or 2 Data Science books, did 1 or 2 projects for yourself and get accustomed to working with data a little bit, here are the books which will take you further.
Python for Data Analysis is the perfect way to get to know better standard Python libraries like NumPy or pandas. It is a complete treatise starting also from reminding you how Python works.
Python Data Science Handbook is a great guide through all standard Python libraries as well: NumPy, pandas, Matplotlib, Scikit-learn.
Python Machine Learning is somewhere between intermediate and expert. It will appeal both to experts and people who are somewhere in the middle. It starts gently and then proceeds to most recent advance in machine learning and deep learning. Great read!
Python for Finance is a must read if you’re into finance and data science. It focuses on how to use data science tools to analyze financial markets and have many great examples illustrating that. It’s very practical and will also appeal to people who don’t work in finance on a daily basis.
If you’re approaching expert level, then actually reading scientific papers often makes more sense than reading books. However it is also time you study and implement deep learning in your solutions to go beyond the classical statistics. Three fantastic and now standard references are:
Deep Learning with Python was written by a creator of Keras, one of the most popular machine learning libraries in Python. The book starts gently, is very practical, gives pieces of code you can use right away and has in general many useful tips on using deep learning. An absolute must read in deep learning.
Deep Learning is an amazing reference for deep learning algorithms. It doesn’t contain much code, but has great insights about how one should approach problems with machine learning: written by pioneers of deep learning.
If you’re into mathematics, then you’ll love Machine Learning: a Probabilistic Perspective. It’s a tour-de-force through mathematics behind all machine learning methods. You probably won’t be able to read it at once, but it’s very useful as a reference in machine learning research.
This Article was first published and culled from Toward Data Science