Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Statistics, data mining, and machine learning in astronomy : a practical Python guide for the analysis of survey data
Ivezic Z., Connolly A., VanderPlas J., Gray A., PRINCETON UNIVERSITY PRESS, Princeton, NJ, 2014. 560 pp. Type: Book (978-0-691151-68-7)
Date Reviewed: Dec 16 2014

Astronomy is universally known to be a subject of very old standing. Advances in astronomical knowledge made in recent decades, due to sophisticated space-based and terrestrial systems, are also well known. What is perhaps not as widely appreciated is that astronomy is lately one of the major application domains for statistical machine learning, data mining, and other such techniques of what is now called “data science.” While astronomy traditionally involved astronomers gathering data using whatever instruments they had and processing it by hand to reach their conclusions, contemporary data gathering in astronomy is automated to a very large degree using robotic telescopes and other sophisticated systems. There is also so much data available already (with more being added constantly) that it is practically impossible for humans to process it fast or well enough in the classical way.

This is the context of the present book, which is written to familiarize astronomers with basic concepts of statistical reasoning, data mining, and machine learning, and to get them up to speed on using Python to analyze some of the vast amounts of astronomical data, such as from the Sloan Digital Sky Survey (SDSS), that are available for download on the web. The authors and their peer community also have created an accompanying Python toolkit, available online (http://www.astroml.org). Unlike other snippets of software that are sometimes made available to accompany published books, AstroML certainly appears to be a more robust and muscular offering that may well have its own standing, with a strong developer community and user base, quite independently of this book.

The contents of the book (10 chapters, including two introductory chapters, covering basic essentials such as distributions, Bayesian inference, regression, classification, time series analyses, and so on), insofar as the theory is concerned, are entirely anticipated by several well-known books on statistics, machine learning, and related topics, as the authors themselves acknowledge. Its usefulness thus rests on its melding of astronomical problems with the theory, with many examples of how data mining can be used on SDSS data. The five appendices, covering Python, AstroML, astronomical data and queries for the same, and so on, are also useful.

The book is well written and will be most well received by astronomers, who are its target audience. Its material may also be useful in some cases to data scientists and machine learning experts who wish to understand how their tools are used in astronomy, or to instructors teaching advanced Python programming.

Reviewer:  Shrisha Rao Review #: CR143017 (1503-0213)
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Data Mining (H.2.8 ... )
 
 
Astronomy (J.2 ... )
 
 
Python (D.3.2 ... )
 
 
Statistical Computing (G.3 ... )
 
 
Learning (I.2.6 )
 
Would you recommend this review?
yes
no
Other reviews under "Data Mining": Date
Feature selection and effective classifiers
Deogun J. (ed), Choubey S., Raghavan V. (ed), Sever H. (ed) Journal of the American Society for Information Science 49(5): 423-434, 1998. Type: Article
May 1 1999
Rule induction with extension matrices
Wu X. (ed) Journal of the American Society for Information Science 49(5): 435-454, 1998. Type: Article
Jul 1 1998
Predictive data mining
Weiss S., Indurkhya N., Morgan Kaufmann Publishers Inc., San Francisco, CA, 1998. Type: Book (9781558604032)
Feb 1 1999
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy