On a book Algorithms for data science by Brian Steele, John Chandler and Swarn Reddy

Krzysztof J. Szajowski

Mathematica Applicanda, Tome 45 (2017) no. 2, pp. 179 - 184.

Résumé

The book under review gives a comprehensive presentation of data science algorithms, which means on practical data analytics unites fundamental principles, algorithms, and data. Algorithms are the keystone of data analytics and the focal point of this textbook. The data science, as the authors claim, is the discipline since 2001. However, informally it worked before that date (cf. Cleveland(2001)). The crucial role had the graphic presentation of the data as the visualization of the knowledge hidden in the data. It is the discipline which covers the data mining as the tool or important topic. The escalating demand for insights into big data requires a fundamentally new approach to architecture, tools, and practices. It is why the term data science is useful. It underscores the centrality of data in the investigation because they store of potential value in the field of action. The label science invokes certain very real concepts within it, like the notion of public knowledge and peer review. This point of view makes that the data science is not a new idea. It is part of a continuum of serious thinking dates back hundreds of years. The good example of results of data science is the Benford law (see Arno Berger and Theodore P. Hill(2015, 2017). In an effort to identifying some of the best-known algorithms that have been widely used in the data mining community, the IEEE International Conference on Data Mining (ICDM) has identified the top 10 algorithms in data mining for presentation at ICDM '06 in Hong Kong. This panel will announce the top 10 algorithms and discuss the impact and further research of each of these 10 algorithms in 2006. In the present book, there are clear and intuitive explanations of the mathematical and statistical foundations make the algorithms transparent. Most of the algorithms announced by IEEE in 2006 are included. But practical data analytics requires more than just the foundations. Problems and data are enormously variable and only the most elementary of algorithms can be used without modification. Programming fluency and experience with real and challenging data are indispensable and so the reader is immersed in Python and R and real data analysis. By the end of the book, the reader will have gained the ability to adapt algorithms to new problems and carry out innovative analysis.

Détail

DOI : 10.14708/ma.v45i2.4369

Classification : 62-02, 62-07, 62Pxx, 68-XX
Mots-clés : Algorithms, Associative Statistics, Computation, Computing Similarity, Cluster Analysis, Correlation, Data Reduction, Data Mapping, Data Dictionary, Data Visualization, Forecasting, Hadoop, Histogram, k-Means Algorithm, k-Nearest Neighbor Prediction