Four things sit under every working data scientist: Python they can bend data with, enough probability and statistics to tell signal from noise, the ability to query a database without asking anyone for an extract, and enough mathematics to read a model's documentation without flinching. This volume covers those four things, and deliberately little else. You will work through the subset of Python that data work actually uses, then NumPy and Pandas in depth — loading messy files, reshaping, grouping, joining, handling missing values. From there, distributions, sampling, hypothesis testing and confidence intervals, framed around the question industry actually asks: should we do this? Then SQL, joins and window functions, the chapter self-taught practitioners most often skip. Then the linear algebra and calculus that machine learning assumes you know. A Git command reference closes the book. Written for people who want the foundations solid and then want to move on.

Volume I of the "Data Science, End to End — Essentials" series by Archit Sharma.