3. Books to read
Books are grouped by purpose and level. Free means the authors or publishers offer a legal free online version (check
the official site; licences vary, often non-commercial). Paid books are often available in libraries or as second-hand
copies. Start with one book per area; finishing one good book beats starting five.
Level: ●○○ right after Grade 12 · ●●○ first/second year of university · ●●● advanced
Thinking with data (general readers — start here)
| Book |
Author(s) |
Free? |
Level |
Why read it |
| The Art of Statistics |
David Spiegelhalter |
no |
●○○ |
the best modern introduction to statistical thinking, with real stories |
| How to Lie with Statistics |
Darrell Huff |
no (short, cheap) |
●○○ |
classic, funny guide to misleading numbers and graphs |
| Factfulness |
Hans Rosling et al. |
no |
●○○ |
why we misjudge the world, and how data correct us |
| Calling Bullshit |
Carl Bergstrom, Jevin West |
course materials free online |
●○○ |
spotting misleading data and claims |
| Naked Statistics |
Charles Wheelan |
no |
●○○ |
statistics explained with humour |
| Weapons of Math Destruction |
Cathy O'Neil |
no |
●○○ |
how algorithms can harm people |
| Data Feminism |
Catherine D'Ignazio, Lauren Klein |
yes (open access) |
●○○ |
power, fairness and who counts in data |
| Invisible Women |
Caroline Criado Perez |
no |
●○○ |
the gender data gap |
| The Book of Why |
Judea Pearl, Dana Mackenzie |
no |
●●○ |
cause and effect for general readers |
Statistics and probability
| Book |
Author(s) |
Free? |
Level |
Notes |
| OpenIntro Statistics |
Diez, Çetinkaya-Rundel, Barr |
yes |
●○○ |
clear first-year textbook with exercises; the natural next step after this book |
| Introductory Statistics (OpenStax) |
Illowsky, Dean et al. |
yes |
●○○ |
another free first course |
| Think Stats (3rd ed.) |
Allen Downey |
yes |
●○○ |
statistics through Python code and notebooks |
| Introduction to Probability (2nd ed. online) |
Joseph Blitzstein, Jessica Hwang |
yes |
●●○ |
the Harvard Stat 110 book; deep and beautiful |
| Think Bayes |
Allen Downey |
yes |
●●○ |
Bayesian statistics with Python |
| Regression and Other Stories |
Gelman, Hill, Vehtari |
yes (PDF from authors) |
●●○ |
regression done thoughtfully |
| Forecasting: Principles and Practice |
Hyndman, Athanasopoulos |
yes |
●●○ |
time series and forecasting |
Programming and data handling
| Book |
Author(s) |
Free? |
Level |
Notes |
| Think Python (3rd ed.) |
Allen Downey |
yes |
●○○ |
learn Python properly from the start |
| Automate the Boring Stuff with Python |
Al Sweigart |
yes |
●○○ |
practical Python for everyday tasks |
| Python for Data Analysis (3rd ed.) |
Wes McKinney |
yes (online) |
●○○ |
pandas from its creator |
| Python Data Science Handbook |
Jake VanderPlas |
yes |
●○○ |
numpy, pandas, matplotlib, scikit-learn |
| R for Data Science (2nd ed.) |
Wickham, Çetinkaya-Rundel, Grolemund |
yes |
●○○ |
if you also learn R |
| The Turing Way |
community |
yes |
●○○ |
reproducible, collaborative research |
| Pro Git |
Scott Chacon, Ben Straub |
yes |
●○○ |
Git in depth |
Mathematics for data science
| Book |
Author(s) |
Free? |
Level |
Notes |
| Calculus (Volumes 1–3, OpenStax) |
Strang, Herman et al. |
yes |
●○○ |
a complete free calculus course |
| Linear Algebra Done Right (4th ed.) |
Sheldon Axler |
yes (open access) |
●●○ |
rigorous and elegant |
| Introduction to Linear Algebra |
Gilbert Strang |
no (MIT 18.06 videos free) |
●●○ |
the classic applied linear algebra course |
| Mathematics for Machine Learning |
Deisenroth, Faisal, Ong |
yes |
●●○ |
the maths behind ML in one book |
Machine learning and AI
| Book |
Author(s) |
Free? |
Level |
Notes |
| An Introduction to Statistical Learning (Python edition) |
James, Witten, Hastie, Tibshirani, Taylor |
yes |
●●○ |
the best first ML textbook; read after this book |
| Hands-On Machine Learning with Scikit-Learn, Keras and TensorFlow |
Aurélien Géron |
no |
●●○ |
practical, project-based |
| Data Science from Scratch |
Joel Grus |
no |
●●○ |
builds methods in plain Python to understand them |
| Interpretable Machine Learning |
Christoph Molnar |
yes |
●●○ |
explaining models and predictions |
| Fairness and Machine Learning |
Barocas, Hardt, Narayanan |
yes |
●●○ |
fairness, rigorously |
| Dive into Deep Learning |
Zhang, Lipton, Li, Smola |
yes |
●●○ |
deep learning with runnable code |
| Deep Learning |
Goodfellow, Bengio, Courville |
yes (online) |
●●● |
the standard deep-learning reference |
| The Elements of Statistical Learning |
Hastie, Tibshirani, Friedman |
yes |
●●● |
the advanced companion to ISL |
Communicating with data
| Book |
Author(s) |
Free? |
Level |
| Storytelling with Data |
Cole Nussbaumer Knaflic |
no |
●○○ |
| How Charts Lie |
Alberto Cairo |
no |
●○○ |
| Fundamentals of Data Visualization |
Claus Wilke |
yes |
●○○ |
| The Visual Display of Quantitative Information |
Edward Tufte |
no |
●●○ |
A reading order
- The Art of Statistics (or Factfulness) — for perspective.
- Think Python or Python for Data Analysis — alongside practice.
- OpenIntro Statistics — the statistics foundation.
- An Introduction to Statistical Learning — machine learning properly.
- Mathematics for Machine Learning — when you want the "why" behind the methods.
- Then follow your chosen direction.