What do you think?
Rate this book
Python Machine Learning
Link to the GitHub Repository containing the code examples and additional material: https://github.com/rasbt/python-machi...
Many of the most innovative breakthroughs and exciting new technologies can be attributed to applications of machine learning. We are living in an age where data comes in abundance, and thanks to the self-learning algorithms from the field of machine learning, we can turn this data into knowledge. Automated speech recognition on our smart phones, web search engines, e-mail spam filters, the recommendation systems of our favorite movie streaming services � machine learning makes it all possible.
Thanks to the many powerful open-source libraries that have been developed in recent years, machine learning is now right at our fingertips. Python provides the perfect environment to build machine learning systems productively.
This book will teach you the fundamentals of machine learning and how to utilize these in real-world applications using Python. Step-by-step, you will expand your skill set with the best practices for transforming raw data into useful information, developing learning algorithms efficiently, and evaluating results.
You will discover the different problem categories that machine learning can solve and explore how to classify objects, predict continuous outcomes with regression analysis, and find hidden structures in data via clustering. You will build your own machine learning system for sentiment analysis and finally, learn how to embed your model into a web app to share with the world
Many of the most innovative breakthroughs and exciting new technologies can be attributed to applications of machine learning. We are living in an age where data comes in abundance, and thanks to the self-learning algorithms from the field of machine learning, we can turn this data into knowledge. Automated speech recognition on our smart phones, web search engines, e-mail spam filters, the recommendation systems of our favorite movie streaming services � machine learning makes it all possible.
Thanks to the many powerful open-source libraries that have been developed in recent years, machine learning is now right at our fingertips. Python provides the perfect environment to build machine learning systems productively.
This book will teach you the fundamentals of machine learning and how to utilize these in real-world applications using Python. Step-by-step, you will expand your skill set with the best practices for transforming raw data into useful information, developing learning algorithms efficiently, and evaluating results.
You will discover the different problem categories that machine learning can solve and explore how to classify objects, predict continuous outcomes with regression analysis, and find hidden structures in data via clustering. You will build your own machine learning system for sentiment analysis and finally, learn how to embed your model into a web app to share with the world
454 pages, Paperback
First published September 23, 2015
783 people are currently reading
2,771 people want to read
About the author
Sebastian Raschka
24Ìýbooks141ÌýfollowersSome of my greatest passions are "Data Science" and machine learning. I enjoy everything that involves working with data: The discovery of interesting patterns and coming up with insightful conclusions using techniques from the fields of data mining and machine learning for predictive modeling.
I am a big advocate of working in teams and the concept of "open source." In my opinion, it is a positive feedback loop: Sharing ideas and tools that are useful to others and getting constructive feedback that helps us learn!
A little bit more about myself: Currently, I am sharpening my analytical skills as a PhD candidate at Michigan State University where I am currently working on a highly efficient virtual screening software for computer-aided drug-discovery and a novel approach to protein ligand docking (among other projects). Basically, it is about the screening of a database of millions of 3-dimensional structures of chemical compounds in order to identifiy the ones that could potentially bind to specific protein receptors in order to trigger a biological response.
In my free-time I am also really fond of sports: Either playing soccer or tennis in the open air or building models for predictions. I always enjoy creative discussions, and I am happy to connect with people. Please feel free to contact me by email or in one of those many other networks!
I am a big advocate of working in teams and the concept of "open source." In my opinion, it is a positive feedback loop: Sharing ideas and tools that are useful to others and getting constructive feedback that helps us learn!
A little bit more about myself: Currently, I am sharpening my analytical skills as a PhD candidate at Michigan State University where I am currently working on a highly efficient virtual screening software for computer-aided drug-discovery and a novel approach to protein ligand docking (among other projects). Basically, it is about the screening of a database of millions of 3-dimensional structures of chemical compounds in order to identifiy the ones that could potentially bind to specific protein receptors in order to trigger a biological response.
In my free-time I am also really fond of sports: Either playing soccer or tennis in the open air or building models for predictions. I always enjoy creative discussions, and I am happy to connect with people. Please feel free to contact me by email or in one of those many other networks!
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 30 of 39 reviews
December 21, 2015
This is a great book.
It gives the mathematical definitions of popular machine learning algorithms and shows you how to implement them. Then it explains how to use them with scikit-learn which has much more efficient implementations.
What is great is that this book has chapters on data cleaning, what to do with missing data, etc. Compliments greatly the Andrew Ng's ML course which lacked lectures about all of these things.
It gives the mathematical definitions of popular machine learning algorithms and shows you how to implement them. Then it explains how to use them with scikit-learn which has much more efficient implementations.
What is great is that this book has chapters on data cleaning, what to do with missing data, etc. Compliments greatly the Andrew Ng's ML course which lacked lectures about all of these things.
August 6, 2016
This is a fantastic introductory book in machine learning with python. It provides enough background about the theory of each (covered) technique followed by its python code. One nice thing about the the book is that it starts implementing Neural Networks from the scratch, providing the reader the chance of truly understanding the key underlaying techniques such as back-propagation. Even further, the book presents an efficient (and professional) way of coding in python, key to data science.
I strongly recommend it to those with a intermediate level of understanding of machine learning principals and python.
I strongly recommend it to those with a intermediate level of understanding of machine learning principals and python.
March 20, 2016
The book aims to cover a lot of topics on Machine Learning. The chapters on training Machine Learning algorithms and clustering analysis were very useful. However, embedding machine learning into web applications and training with Theano were a bit out of the scope.
January 15, 2021
** I think it is important to disclose your skill level when reviewing these types of textbooks. The complete beginner, as opposed to a statistics major with minimal programming experience will gain different essential skills from the textbook. I am an Economics major with fundamental knowledge in most of the rudimentary parts of Machine Learning (Statistics, programming, analytics). I also read PY4E, Intro to Statistical Learning, and Python for Data Analysis before this. (First 2 are available online for free by the way) **
Dr. Raschka hits a personal sweet spot as he offers a lot more mathematical theory compared to most of the other introductory Python Machine Learning textbooks I browsed through. This ultimately lead me to picking this text based on my intermediate programming level and background knowledge of machine learning.
Aside from the math, I loved his occasional coding-from-scratch approach to models like the Perceptron, Adaline and even a neural network! I think that this under-the-hood approach is tedious in isolation for every model and could easily turn to be overwhelming for a beginner, but it improves your skill to think computationally(Which I still feel like I lack) and not just take advantage of the readily available libraries. Another huge plus was that Dr. Raschka puts links to academic papers and lecture slides for supplementary information. They provides an extensive, but mainly theoretical approach to some models. If you feel a little lost with some of the brief algorithm descriptions, these can really help bring them to clarity.
That being said, I sometimes found the algorithms vaguely written, and there could have been a greater emphasis on the assumptions of each model's implementation. But there are plenty of resources out there to help demystify any misinterpretations you have.At times, I felt they could’ve touched on some other models like QDA. mixture models, and Partial Least Squares. But it is an introductory textbook and cannot give you everything, I would have found a couple more hands-on approaches of end-to-end pipelining helpful so the reader feels ready to undertake their own mini-project at the end.
I liked this book and it was a great introduction to some important models. It also gives you a basic grasp of libraries like sci-kit learn, nltk, and TensorFlow (I say fundamental because sci-kit learn user guide is over 2,700 pages long). In my opinion, I think this book is well-suited for a reader with a quantitative background (Stats, Comp Sci, Engineering etc.) as the proofs and algorithms can get a little hairy for a complete beginner. I would read this with my Jupyter notebook open, and with access to other library manuals open (Numpy, sci-kit learn, pandas etc) in the browser to get the most out of this book.
I was motivated to write a review for this textbook because I have found there is an ‘information overload�(Packt, Oreilly, and Manning are all pushing out books like the world is ending tomorrow) for data science textbooks which make it incredibly difficult to pick which one to avenue to take. I have frequently changed my mind on which activity to do next.. I’ll think about reading an NLP-based textbook, to a pure python based textbook , to doing Kaggle competitions, then to MOOCs, or to YouTube tutorials. Finding an appropriate resource isn’t easy and it’s different for everyone. The software engineer would understand the from-scratch python code very quickly while a math major would whip right through the mathematical proofs.
Everybody has a different path to becoming a self-taught data scientist and I just wanted to share my personal experience with the textbook. If anybody has questions I can also happily answer them and I'd love to hear any experienced reader's recommendations/ advice for me as well: (As long you’re not a YouTuber pushing some junk-grade course)
I am looking for a textbook that is heavily applied which works through ML project(s) or application(s) and is also directed for the intermediate to advanced level. Specifically, Something challenging but that will mainly help give me guidance and advice on how to get a personal project off the ground.
Thanks!
9/10 ...Out of 10 scale is taken from my friend Ryan Bergen who also invoked me to write the review.
Dr. Raschka hits a personal sweet spot as he offers a lot more mathematical theory compared to most of the other introductory Python Machine Learning textbooks I browsed through. This ultimately lead me to picking this text based on my intermediate programming level and background knowledge of machine learning.
Aside from the math, I loved his occasional coding-from-scratch approach to models like the Perceptron, Adaline and even a neural network! I think that this under-the-hood approach is tedious in isolation for every model and could easily turn to be overwhelming for a beginner, but it improves your skill to think computationally(Which I still feel like I lack) and not just take advantage of the readily available libraries. Another huge plus was that Dr. Raschka puts links to academic papers and lecture slides for supplementary information. They provides an extensive, but mainly theoretical approach to some models. If you feel a little lost with some of the brief algorithm descriptions, these can really help bring them to clarity.
That being said, I sometimes found the algorithms vaguely written, and there could have been a greater emphasis on the assumptions of each model's implementation. But there are plenty of resources out there to help demystify any misinterpretations you have.At times, I felt they could’ve touched on some other models like QDA. mixture models, and Partial Least Squares. But it is an introductory textbook and cannot give you everything, I would have found a couple more hands-on approaches of end-to-end pipelining helpful so the reader feels ready to undertake their own mini-project at the end.
I liked this book and it was a great introduction to some important models. It also gives you a basic grasp of libraries like sci-kit learn, nltk, and TensorFlow (I say fundamental because sci-kit learn user guide is over 2,700 pages long). In my opinion, I think this book is well-suited for a reader with a quantitative background (Stats, Comp Sci, Engineering etc.) as the proofs and algorithms can get a little hairy for a complete beginner. I would read this with my Jupyter notebook open, and with access to other library manuals open (Numpy, sci-kit learn, pandas etc) in the browser to get the most out of this book.
I was motivated to write a review for this textbook because I have found there is an ‘information overload�(Packt, Oreilly, and Manning are all pushing out books like the world is ending tomorrow) for data science textbooks which make it incredibly difficult to pick which one to avenue to take. I have frequently changed my mind on which activity to do next.. I’ll think about reading an NLP-based textbook, to a pure python based textbook , to doing Kaggle competitions, then to MOOCs, or to YouTube tutorials. Finding an appropriate resource isn’t easy and it’s different for everyone. The software engineer would understand the from-scratch python code very quickly while a math major would whip right through the mathematical proofs.
Everybody has a different path to becoming a self-taught data scientist and I just wanted to share my personal experience with the textbook. If anybody has questions I can also happily answer them and I'd love to hear any experienced reader's recommendations/ advice for me as well: (As long you’re not a YouTuber pushing some junk-grade course)
I am looking for a textbook that is heavily applied which works through ML project(s) or application(s) and is also directed for the intermediate to advanced level. Specifically, Something challenging but that will mainly help give me guidance and advice on how to get a personal project off the ground.
Thanks!
9/10 ...Out of 10 scale is taken from my friend Ryan Bergen who also invoked me to write the review.
February 15, 2020
El original es muy buen libro para conocer el Aprendizaje Automático, pero esta traducción al español de Marcombo tiene muchos errores que habrá que resolver el próximas ediciones.
April 12, 2018
Really good book, useful. Nice concise explanations, the maths is all included, and there's even example code! I downloaded a pdf version to my computer because I think I'll be referring to it pretty often.
August 27, 2018
This a fantastic introduction to machine learning.
Textbooks in computer science in general, and machine learning in particular, have to walk a delicate line. At one level of high abstraction, everything is mathematical proofs. At a level of low-level cookbookls, it's a matter of just plugging and chugging, treating code as magical invocations without getting at the why. Raschka's book hits the sweet spot between the two exactly, explaining the underlying math, how that math is represented in Python, and then what to call in scikit-learn and tensorflow to actually do it.
Raschka assumes a little familiarity with Python (you should have Anaconda installed, know how to use functions, the basics of classes, what a list comprehension is and why it's cool, as well as the basics of manipulating pandas dataframes) and enough math to not be scared by statistics and matrix notation, but beyond that, everything is clear and elegant. I found Chapter 6, on model evaluation, hyperparameter tuning, and grid search particularly useful as a summary of what to do with simple numerical data with scikitlearn. The later chapters of the book provide the fundamentals of natural language processing and the use of multilayer neural networks and deep convolutional networks to classify images, as well as the unreasonable effectiveness of recurrent neural networks on a variety of tasks.
This is an incredible book. The only thing that prevents it from getting 6 stars is a lack of example problems, but that is what Kaggle is for.
Textbooks in computer science in general, and machine learning in particular, have to walk a delicate line. At one level of high abstraction, everything is mathematical proofs. At a level of low-level cookbookls, it's a matter of just plugging and chugging, treating code as magical invocations without getting at the why. Raschka's book hits the sweet spot between the two exactly, explaining the underlying math, how that math is represented in Python, and then what to call in scikit-learn and tensorflow to actually do it.
Raschka assumes a little familiarity with Python (you should have Anaconda installed, know how to use functions, the basics of classes, what a list comprehension is and why it's cool, as well as the basics of manipulating pandas dataframes) and enough math to not be scared by statistics and matrix notation, but beyond that, everything is clear and elegant. I found Chapter 6, on model evaluation, hyperparameter tuning, and grid search particularly useful as a summary of what to do with simple numerical data with scikitlearn. The later chapters of the book provide the fundamentals of natural language processing and the use of multilayer neural networks and deep convolutional networks to classify images, as well as the unreasonable effectiveness of recurrent neural networks on a variety of tasks.
This is an incredible book. The only thing that prevents it from getting 6 stars is a lack of example problems, but that is what Kaggle is for.
May 10, 2020
A good practical tour round your bread and butter ML techniques with scikit learn, not the most efficient library for the more complex methods such as gradient boosting or DL but good for SVM and regression techniques and the book offers solid explanations and examples .
October 9, 2024
Good info, but would I of read it if not for work? Probably not. I feel the author tried to hard to word things in a "cool" way some times which also put me off a bit. I liked the layout though of theory, then example etc and bolding when a definitions coming.
January 26, 2016
There is significant interest, across many diverse application domains, in developing applications that exploit the large and rich data sets that are acquired by computer systems in order to identify trends and correlations and to make predictions and recommendations. These kinds of applications broadly fit into the field of machine learning (ML).
This excellent book is a practical introduction to ML using the Python programming language, along with relevant components of Python’s rich open-source ecosystem of machine learning, numerical computing, graph plotting and other cognate libraries.
The author does not assume any prior ML knowledge, though a basic understanding of the Python language, linear algebra and calculus is useful. An introductory chapter introduces basic machine learning terminology, describing the various types of machine learning, and overviewing the key steps of typical machine learning processes. This introduction also discusses, in general terms, how to install and configure Python and the various libraries required by the remainder of the book.
As may be expected, a significant part of the book is given to the discussion of a variety of different learning algorithms, including the mathematical details of how they work, how they are trained and how they perform against other algorithms. Crucially, the book describes how to use library implementations of each algorithm.
While ML algorithms play a central part in any machine learning application, there are a variety of other issues involved in making these algorithms work effectively in any particular application. The book therefore contains comprehensive discussion of key topics such as data exploration, visualization and preparation, techniques for generating test and validation data sets, algorithm training and evaluation.
The author describes appropriate tools and techniques that can assist with these processes. To help put ML in context, a chapter is also devoted to describing a simple but complete online ML system embedded inside a web application.
The book covers a considerable amount of material over its four hundred pages. Rather than being a dry exposition of ML techniques, the author encourages readers to engage with the text by experimenting with the examples. Naturally, good data sets are required and the book provides links to a variety of real-world data sets that are freely available for download. In addition, the source code for the examples may be downloaded from the book’s website.
Open-source libraries are used extensively, providing efficient implementations and enabling the reader to focus on the machine learning application itself rather than getting bogged down with implementational detail. The text contains lots of practical advice as well as inline links to other sources of information. While this book is a good end-to-end read, it would also serve as a useful reference text. Recommended.
Review by Patrick Hill CEng MBCS CITP
Originally posted
This excellent book is a practical introduction to ML using the Python programming language, along with relevant components of Python’s rich open-source ecosystem of machine learning, numerical computing, graph plotting and other cognate libraries.
The author does not assume any prior ML knowledge, though a basic understanding of the Python language, linear algebra and calculus is useful. An introductory chapter introduces basic machine learning terminology, describing the various types of machine learning, and overviewing the key steps of typical machine learning processes. This introduction also discusses, in general terms, how to install and configure Python and the various libraries required by the remainder of the book.
As may be expected, a significant part of the book is given to the discussion of a variety of different learning algorithms, including the mathematical details of how they work, how they are trained and how they perform against other algorithms. Crucially, the book describes how to use library implementations of each algorithm.
While ML algorithms play a central part in any machine learning application, there are a variety of other issues involved in making these algorithms work effectively in any particular application. The book therefore contains comprehensive discussion of key topics such as data exploration, visualization and preparation, techniques for generating test and validation data sets, algorithm training and evaluation.
The author describes appropriate tools and techniques that can assist with these processes. To help put ML in context, a chapter is also devoted to describing a simple but complete online ML system embedded inside a web application.
The book covers a considerable amount of material over its four hundred pages. Rather than being a dry exposition of ML techniques, the author encourages readers to engage with the text by experimenting with the examples. Naturally, good data sets are required and the book provides links to a variety of real-world data sets that are freely available for download. In addition, the source code for the examples may be downloaded from the book’s website.
Open-source libraries are used extensively, providing efficient implementations and enabling the reader to focus on the machine learning application itself rather than getting bogged down with implementational detail. The text contains lots of practical advice as well as inline links to other sources of information. While this book is a good end-to-end read, it would also serve as a useful reference text. Recommended.
Review by Patrick Hill CEng MBCS CITP
Originally posted
October 20, 2017
This book is a tour of Machine Learning. If you are a complete beginner on the topic, you’ll get the big picture. However it is up to you to go deeper on each concept. I think there could have been a final chapter with a few exercise which incorporated all the concepts which were covered in the book.
January 3, 2017
A good book to learn scikit-learn library. Chapters on theano and embedding the code into a web application are out of scope. I would use scikit-flow instead of theano, since the former is similar to scikit-learn.
July 3, 2016
Great introduction on machine learning in Python. Good to have access to code:
February 11, 2024
Python Machine Learning gives a broad overview of ML, and has a nice balance of theoretical concepts as well as practical code samples in Python. It doesn't go too deep into the theory, which is understandable since much of it is so complicated anyway, but the book is still rather technical. There's an accompanying GitHub repo which I found to be very helpful. You can run the code samples and it's all interactive. (Although some of the code is out of date and doesn't run properly.)
My biggest quibble is that I don't necessarily feel like I understand how to do ML. Reading this book feels a bit like drinking from a fire hose. In later chapters, complicated neural network architectures are presented without much explanation for why one would choose those over the alternatives. I'm sure that'd be a long discussion on its own and this is already a huge book, but still, it'd be nice to learn more of the motivations behind this stuff.
I think this book works great as a way to get exposure to a bunch of different ML techniques, with the understanding that for any particular application, you'll likely need to learn a lot more to gain any sort of real-world proficiency.
My biggest quibble is that I don't necessarily feel like I understand how to do ML. Reading this book feels a bit like drinking from a fire hose. In later chapters, complicated neural network architectures are presented without much explanation for why one would choose those over the alternatives. I'm sure that'd be a long discussion on its own and this is already a huge book, but still, it'd be nice to learn more of the motivations behind this stuff.
I think this book works great as a way to get exposure to a bunch of different ML techniques, with the understanding that for any particular application, you'll likely need to learn a lot more to gain any sort of real-world proficiency.
August 4, 2021
Great introduction to scikit-learn, scipy, tensorflow and keras, provided code is good. The math behind the concepts being talked about though is very poorly delivered, so this is not a book to learn about mathematical aspect of any of the described approaches, better to look elsewhere for those. It has, though, a lot of references to other books and articles, which is nice, and allows the reader to dig deeper into any of the topics being discussed. Another really good thing, is that the author is very responsive on associated github repo. So, great book if you want to get some hands-on experience with python ML stack, but not the best to learn about fundamentals and inner workings of ML methods.
December 23, 2021
It's my first book to learn machine learning modeling using python. This book covers a lot of topics, from logistic regression to neural networks and provides step-by-step implementation code so that you can replicate and test on your own machine. The author's explanation is splendid and suitable for any reader with some background in probability and linear algebra. Though I feel like the content of this book is bit of outdated, it's still a good starting point for anyone who is interested in machine learning and wishing to realize these algorithms using Python.
January 31, 2019
Highly recommend. Several years ago I was a scientist looking to learn machine learning. This book hit the perfect sweet spot between technical accuracy and accessibility and gave me a great foundation. Highly recommend for an accessible, but not watered down introduction. Early in the book you will write your own neural network and keep going from there. I give this to other scientists who want to learn machine learning.
September 10, 2021
Took me a quite bit of time to complete the book.
But I will say the time spent on the book is worth it.
This book provided me the all necessary guidance while I began my journey in ML/DL.
Topics started from the basics and ended at Reinforcement Learning while covering boosting , NN, CNNs, RNNs, and GAN in an elaborative manner.
PS : The book is not that much mathematical demanding and in my opinion covers the right amount to get you started.
But I will say the time spent on the book is worth it.
This book provided me the all necessary guidance while I began my journey in ML/DL.
Topics started from the basics and ended at Reinforcement Learning while covering boosting , NN, CNNs, RNNs, and GAN in an elaborative manner.
PS : The book is not that much mathematical demanding and in my opinion covers the right amount to get you started.
June 11, 2017
Okay, not 5 stars, 4.75 really. The book finds a sweet balance between mathematics and python, although throughout reading the book I found the balance was shifting a but (in the bad sense of shifting). One of the better books I've read on this subject.
February 18, 2018
I really appreciate the well documented code repository on github. Book was easy to follow despite being relatively math heavy. Explanations on common ML algorithms and clustering analysis were on point and easy to follow. This book is a good reference point for learners.
September 19, 2018
A solid and practical intro to machine learning
The combination of reasonably explained math and excellent code examples are what make this book excellent. It also always gives a good reference for going deeper.
The combination of reasonably explained math and excellent code examples are what make this book excellent. It also always gives a good reference for going deeper.
October 1, 2018
This is a good book that combines mathematical explanation, intuition, python implementation, and off-the-shelf model usage. For my background, this is a very logical way of approaching machine learning.
August 12, 2017
Challenging, yet so rewarding for the Microsoft Imagine Cup Competition
March 9, 2018
The best intro Python ML book, becuase it actually tries to teach you. Read the Author's reponse to 'why this book' on the goodreads page, it's accurate.
May 2, 2018
My baseline in Machine Learning research
January 20, 2019
Excelente livro.
April 25, 2019
Lots of examples (every idea has an example), but...
...aaaaa, Polish translation is awful!!!!! I hope that original English version doesn’t have this huge disadvantage.
...aaaaa, Polish translation is awful!!!!! I hope that original English version doesn’t have this huge disadvantage.
April 12, 2020
Perfect book for introduction on machine learning to intermediate level. Very comprehensive for graduate or undergraduate students.
February 6, 2021
It is amazing book with best collection of lectures, codes and insights in Machine Learning.
Read
November 26, 2021Did not finish. I gave it a year and a half and just couldn’t make the time. Got about halfway through. I’ll keep it as a reference for the next project I have that requires tools like this.
Displaying 1 - 30 of 39 reviews
Can't find what you're looking for?
Get help and learn more about the design.