Statistics, data mining, and machine learning in astronomy : a practical Python guide for the analysis of survey data /

In the current era of Big Data, data science has become a critical method for scientific research. Notably, CERN (the European Laboratory for Particle Physics) had collected 200 petabytes of data by 2017, where 1 petabyte of storage is equivalent to 7.5 million CD-ROM disks. This timely update of the work by Ivezić (Univ. of Washington) and colleagues (1st ed., CH, Sep'14, 52-0257) cohesively incorporates recent advances in astrophysics theory with the essential data science methods and programming tools. This edition balances theory and practice, with the goal of enabling users to handle the velocious data that is growing ever more voluminous at speed. The book covers topics from classical and Bayesian statistical inferences to supervised learning algorithms and temporal modeling. Critical summaries of pros and cons for each method provide invaluable guidance for non-statisticians and non-data-scientists to achieve veracity in statistical modeling. Every topic includes relevant astrophysics examples supported by visual illustrations. The most reader-friendly feature of this work is its presentation of relevant Python code, which will help self-directed learners with limited preparation in programming. This intelligible, broad-spectrum, and readable monograph is sure to remain a supremely useful textbook for both undergraduate and graduate students in astrophysics and astrostatistics. Summing Up: Highly recommended. Upper-division undergraduates through faculty and professionals. --Seong-Tae Kim, North Carolina A&T State University