Introduction to machine learning with python textbook free download

1. Think Stats

By Allen B. Downey

This book can be read online or downloaded as a pdf here. It covers many of the core statistical concepts for data science including data analysis, distributions and probability. It also leans heavily towards coded examples written in python rather than mathematical equations, which I think makes it easier to digest for those without advanced maths degrees.

Key topics: statistics.

Reader level: beginner.

Programming language: python

2. Bayesian Methods for Hackers: Probabilistic Programming for Bayesian Inference

By Cameron Davidson-Pilon

This book attempts to bridge the gap between theoretical Bayesian machine learning methods and their practical application in probabilistic programming.

It provides a really good introduction to Bayesian inference with a practical first approach. Similarly to think stats it leans more on python examples as opposed to heavy mathematical equations and explanations.

Key topics: bayesian methods for machine learning.

Reader level: beginner.

Programming language: python

3. Natural Language Processing with Python

By Steven Bird, Ewan Klein and Edward Loper

This is a fantastic introduction to learning natural language processing with python. The focus is on using the NLTK toolkit to process, analyse, classify and mine text data. It is a very comprehensive introduction, includes both explanations about the theory alongside lots of coded examples.

Key topics: natural language processing and text mining.

Reader level: beginner.

Programming language: python

4. R for Data Science

By Hadley Wickham and Garrett Grolemund

This book is one of the best introductions to learning R for data science. This book, rather than try to cover all aspects of R for data science, focusses on giving a solid foundation in the most commonly used tools.

It covers topics such as importing and processing data, visualisations and building models.

Key topics: importing, transforming, visualising and modelling data in R.

Reader level: beginner.

Programming language: R

5. Machine Learning Yearning

By Andrew Ng

This book draws on Andrew Ng’s work leading the Google brain team and covers practical steps and frameworks for successful machine learning projects. There are some really useful chapters on splitting data for validation, diagnosing errors and how to build machine learning models in complex settings.

Key topics: building successful machine learning systems.

Reader level: intermediate.

Programming language: None.

6. Hands-on Machine Learning with Scikit-learn and Tensorflow

By Aurelien Geron

Scikit-learn and Tensorflow are two of the most widely-used Python libraries for machine and deep learning. This book gives a very good overview of the machine learning process in general but also covers implementation with these two tools. Lots of nice diagrams and coded examples makes this very easy to digest. The pdf for this book can be accessed here.

Key topics: machine and deep learning.

Reader level: beginner.

Programming language: python.

7. Forecasting: Principles and Practice

By Rob H Hyndman and George Athanasopoulos

This book provides a very comprehensive overview of methods used for forecasting. It is extremely detailed and covers a very wide range of tools and approaches. Including techniques such as linear and nonlinear regression, ARIMA models, neural networks and some tips on practical applications.

Key topics: forecasting.

Reader level: beginner to advanced.

Programming language: R.

8. Deep learning

By Ian Goodfellow, Yoshua Bengio and Aaron Courville

This book gives an introduction to machine learning but its main focus is on deep learning. It covers modern deep learning techniques including regularization, convolutional networks and sequence modelling. It doesn’t include coded examples but instead focusses heavily on the theory. It is aimed at both students and practitioners so can be digested by the beginner.

Key topics: deep learning.

Reader level: beginner to advanced.

Programming language: none.

9. Linear Algebra

By Jim Hefferon

Linear algebra is one of the key mathematical foundations to the field of machine learning. This book is a free textbook that covers the foundational concepts that would usually be covered in a typical undergraduate course. In addition to the theory, it also includes exercises throughout.

Key topics: linear algebra.

Reader level: beginner.

Programming language: none.

10. Introduction to Machine Learning with Python

By Andreas C. Muller and Sarah Guido

This book focusses on the practical application of machine learning techniques rather than covering the maths behind the field. It includes detailed explanations of the fundamental concepts in machine learning, data processing, model evaluation and the typical machine learning workflow. It provides many coded examples using scikit-learn.

Key topics: machine learning.

Reader level: beginner.

Programming language: python.