- Dieser Titel nimmt an der folgenden Aktion teil: Prime Student Mitglieder erhalten 10% Rabatt auf ausgewählte fremdsprachige Lehrbücher. Weitere Informationen (Teilnahmebedingungen)
Andere Verkäufer auf Amazon
+ EUR 3,00 Versandkosten
Real-World Machine Learning (Englisch) Taschenbuch – 28. Juli 2016
Hinweise und Aktionen
Wird oft zusammen gekauft
Kunden, die diesen Artikel gekauft haben, kauften auch
Es wird kein Kindle Gerät benötigt. Laden Sie eine der kostenlosen Kindle Apps herunter und beginnen Sie, Kindle-Bücher auf Ihrem Smartphone, Tablet und Computer zu lesen.
Geben Sie Ihre Mobiltelefonnummer ein, um die kostenfreie App zu beziehen.
Wenn Sie dieses Produkt verkaufen, möchten Sie über Seller Support Updates vorschlagen?
Über den Autor und weitere Mitwirkende
Henrik Brink is a data scientist and software developer with extensive ML experience in industry and academia.
Joseph Richards is a senior data scientist with expertise in applied statistics and predictive analytics. Henrik and Joseph are co-founders of wise.io, a leading developer of machine learning solutions for industry.
Mark Fetherolf is founder and President of data management and predictive analytics company, Numinary Data Science. He has worked as a statistician and analytics database developer in social science research, chemical engineering, information systems performance, capacity planning, cable television, and online advertising applications.
Kunden, die diesen Artikel angesehen haben, haben auch angesehen
Dieses Produkt bewerten
1-3 von 3 Rezensionen werden angezeigt
Derzeit tritt ein Problem beim Filtern der Rezensionen auf. Bitte versuchen Sie es später noch einmal.
Page 11: I strongly believe that any ML practitioner needs a work-flow/checklist. You rarely (never?) see that with academic books.
Page 19: Loved the visual display of features to target (class). Yes, it's simple. Yes, it's non academic. But it's extremely useful for my ML mind to think visually like that.
Page 33: How much training data is required? Three cases.
Page 44: Which visualization tool do you need if your input feature is categorical and your response feature is numerical? Awesome matrix!
Page 113: Wow! Feature Engineering! How to convert a single feature (time-stamp) into a 10 datatime feature.
Page 137: Love the notes "within" the Python code. The publisher Manning seems to push that ....
Die hilfreichsten Kundenrezensionen auf Amazon.com
It is not an introductory book on this subject.
Readers interested in the mathematical foundations of machine learning are advised to refer to textbooks such as "An Introduction to Statistical Learning", by Gareth James.
The authors demonstrate their hands-on knowledge of the subject by presenting the material in a cohesive fashion with several examples and
use cases accompanied by Python, pandas and scikit-learn Notebooks. Two of the authors were amongst the co-founders of Wise.io, which was acquired by General Electric, a testament to the business value of their body of knowledge beyond this book.
In terms of content, the strengths of the book are in its coverage of feature engineering and scaling of machine learning systems.
In addition, the example Notebooks and associated data are available for download.
Its weakness is in presentation of figures in black-and-white, which makes them less than useful. Yet, Manning makes access to the PDF version of the book, containing figures in color, relatively easy.
The book is very well organized, and well presented. The authors crafted a good systematic approach for explaining and illustrating through example the various steps of the process of using ML methods to create models for classification and prediction. They book has a number of good examples.
No mathematical background is required for reading this book. Obviously it helps if the reader has some familiarity with the various types of statistical models used in ML. Even if that is not the case, the book is a good starting point for bridging between the "what" of ML and the "how" of ML. For those who want to try things in a hands-on fashion, they give a number of code examples, with sufficient brief annotations so you know what the blocks are code are being used for.
It's a very helpful guide that'll make a great addition to your library!
Trying to describe it, I would note three things that the book is not. It is not obviously more "real world" than its competitors: the "real world" reference seems to be a forgivable differentiation exercise. It is not thick: 230 pages. It is not a textbook or a catalogue of machine-learning algorithms - which you will need to get. (I would suggest "Introduction to statistical learning" by James, Witten, Hastie and Tibshirani). It is, however, a thoughtful introduction to and overview of machine-learning methods, appropriately remembering about the context and life-cycle of an ML project, and keeping things hands-on with small Python examples, but managing not to fall into the catalogue mode.
I have seen other books try this before. "Doing Data Science" by O'Neill and Schutt comes to mind first, long on enthusiasm but a little short on quality. Then there is Manning's own "Practical Data Science with R" by Zumel and Mount. Among the three, RWML looks like a clear winner.
If I had to pick on something, I would register disappointment with the book's one extended exercise, based on the NYC taxi dataset. After all the thoughtful discussion, an unimaginative take-all-variables-and-dump-them-into-an-algorithm-then-look-at-single-number exercise was a let-down. (Statisticians, taught to think hard about model specification and to prize model interpretability, often have that complaint about machine-learning hotshots. Google Norman Matloff's blog post "Statistics: Losing Ground…" for more on the differences between the two camps). This said, from editorial viewpoint, maybe not getting into the weeds actually was a good idea.
An enthusiastic endorsement for a very nicely done book.