Data Science from Scratch: First Principles with Python

By Joel Grus

Data science libraries, frameworks, modules, and toolkits are great for doing data science, but they’re also a good way to dive into the discipline without actually understanding data science. With this updated second edition, you’ll learn how many of the most fundamental data science tools and algorithms work by implementing them from scratch.

If you have an aptitude for mathematics and some programming skills, author Joel Grus will help you get comfortable with the math and statistics at the core of data science, and with hacking skills you need to get started as a data scientist. Today’s messy glut of data holds answers to questions no one’s even thought to ask. This book provides you with the know-how to dig those answers out.

• Language: English
• Publisher: O'Reilly Media, Inc.
• Release date: Apr 12, 2019
• ISBN: 9781492041108

Joel Grus

Joel Grus is a research engineer at the Allen Institute for Artificial Intelligence. Previously he worked as a software engineer at Google and a data scientist at several startups. He lives in Seattle, where he regularly attends data science happy hours. He blogs infrequently at joelgrus.com and tweets all day long at @joelgrus.

Reviews for Data Science from Scratch

[dcunning11235 · Rating: 3 out of 5 stars]

This is a very basic into topics in statistics and machine learning built around functioning code to perform (some of!) the tasks and algorithms discussed.

As an introduction it seemed very solid. I was looking for something a little more in depth, so this was not really the book I was looking for. What am I looking for? Something that bridges between a working knowledge of e.g. some methods in scikit learn to e.g. coding those methods, from scratch. Gradient descent and PCA are covered, but the book stops precisely at 'more interesting'/complex methods e.g. ridge regression/Lasso, and never even touches on e.g. ICA.

So, 3-ish stars for me. Maybe 4 stars if you are getting your feet wet for the first time.

[encephalical · Rating: 2 out of 5 stars]

Ambitious, but uneven, made me think of the 'how to draw an owl' meme at part. The most interesting aspect might have been the author's functional Python. The "For Further Exploration" sections have some really interesting links.