Angličtina
Data Science, Analytics, and Machine Learning with R explains the principles of data mining and machine learning techniques and accentuates the importance of applied and multivariate modeling. The book emphasizes the fundamentals of each technique, with step-by-step codes and real-world examples with data from areas such as medicine and health, biology, engineering, technology, and related sciences. The authors want to mitigate the readers' feeling that they may be sitting in front of a black box. Toward this end, examples use the most recent R language syntax, with recognized robust, widespread and current packages. Code scripts are exhaustively commented, making it clear to readers what happens in each command. For data collection, readers are instructed how to build their own robots from the very beginning (not only API type, but also handcrafted ones). An entire chapter focuses on the concept of spatial analysis, allowing readers to build their own maps through geo-referenced data (such as in epidemiologic research) and some basic statistical techniques. Other chapters cover ensemble and uplift modelling, and GLMM (Generalized Linear Mixed Models) estimations, both linear and nonlinear. The book will serve computer and data scientists working with researchers, clinicians, and engineers, as well as the researchers and engineers themselves who find themselves working in multidisciplinary teams and need a more in-depth understanding of machine learning, data mining and AI than is normally taught in their courses. Presents a comprehensive and practical overview of machine learning, data mining and AI techniques for a broad multidisciplinary audience Serves both readers who are interested in statistics, analytics and modeling and those who wish to deepen their knowledge in programming through the use of R Teaches readers how to apply machine learning techniques to a wide range of data and subject areas Presents data in a graphically appealing way, promoting greater information transparency and interactive learning
