Product guide

Python Machine Learning, 3rd Edition

Python Machine Learning, Third Edition is a practical guide to machine learning and deep learning for readers who know some Python. It combines conceptual explanations with code examples using scikit-learn and TensorFlow 2, covering topics from model evaluation and regression to neural networks, GANs, and reinforcement learning.

At a glance

Uses Python examples to explain machine learning concepts alongside practical implementation.
Covers scikit-learn and TensorFlow 2, including Keras API features.
Topics include data preprocessing, classification, regression, clustering, model evaluation, and hyperparameter tuning.
Deep-learning coverage includes neural networks, image classification, recurrent networks, GANs, and reinforcement learning.
Also discusses sentiment analysis and embedding a machine-learning model in a web application.

Price

$40.59Save 26%

Reference price: ~~$54.99~~

Price checked: Nov 14, 2026

View offer Ahead of Black FridayExplore the selection

Often bought together

Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python

$32.78

Mathematics of Machine Learning: Master linear algebra, calculus, and probability for machine learning

$39.97

Pros and cons

Pros

Connects theory and hands-on code across a broad range of machine-learning topics.
Includes practical coverage of both scikit-learn workflows and TensorFlow-based deep learning.
The stated topic range extends from foundational techniques to GANs and reinforcement learning.

Technical specifications

9 specifications

Book details
Edition	3rd ed.
Publisher	Packt Publishing
Publication date	December 12, 2019
Language	English
Print length	770 pages
ISBN-10	1789955750
ISBN-13	978-1789955750

Dimensions and installation
Weight listed	2.87 pounds
Dimensions	7.5 x 1.74 x 9.25 inches

What to know before buying

This third edition was published in 2019 and describes updates for TensorFlow 2 and then-current versions of NumPy, SciPy, and scikit-learn. Readers needing guidance for newer software releases should confirm that the examples match their current environment. Customer feedback includes a concern about print legibility.

Who is it for?

A good fit for

Python developers beginning machine learning who want explanations as well as coding examples.
Data scientists, developers, students, or researchers looking for a wide-ranging reference to traditional machine learning and deep learning.

Less suited to

Readers seeking a book that starts with teaching Python from scratch.
Buyers who need coverage explicitly updated for software releases newer than those described in this edition.

Customer reviews on Amazon

4.5 / 5 · 497 ratings

5 stars72%72%
4 stars19%19%
3 stars5%5%
2 stars2%2%
1 star2%2%

Customer feedback describes the explanations and coding illustrations as understandable and says the book can be practically useful, with a reported balance between intuition and mathematical rigor. Some feedback criticizes legibility. For readers working through its code examples, the content praise supports its practical appeal, while the legibility concern matters for sustained reading. These reports are opinions and do not establish that every copy has the same print quality.

Positive themes

Readers report clear explanations and coding illustrations.
Feedback describes a useful balance of intuition and mathematical rigor, and practical relevance.

Negative themes

A customer reports that the text is very difficult to read.

Frequently asked questions

Does the book cover both machine learning and deep learning?

Yes. The listed content spans conventional machine-learning methods and deep-learning topics such as neural networks, image classification, recurrent networks, GANs, and reinforcement learning.

Which Python frameworks are covered?

The title and listing specify scikit-learn for machine learning and TensorFlow 2 for deep learning, including TensorFlow's Keras API.

Is this a beginner Python programming book?

No. The listing is aimed at readers who already know some Python and want to learn machine learning or deepen existing knowledge.

How current are the software examples?

The listing describes updates for TensorFlow 2 and current-at-publication versions of NumPy, SciPy, and scikit-learn. Because the edition was published in 2019, check whether its examples fit the versions you use.