Big Data from Scratch: Building a 4-nodes Hadoop cluster and use of the Map-Reduce Simple Skyline Algorithm (MR-SSA) based on the R Language (Big Data & MR-SSA) - Tapa blanda

Sinopsis

Big Data has been entered into our lives for real. During this book, we make an introduction and analysis on the Big Data. Thus we study the Big Data theory, giving some definitions what Big Data is. Also, we continue analyzing the types of Data and we study the goals of Big Data and see some analyzing techniques. Furthermore, we study some descriptions of previous architectures and systems of cluster computing, like Oscar, Rocks, OpenMosix, and also the root of Map-Reduce, the MPI. Finally, we make a brief reference to the use of Map-Reduce and an introduction to Hadoop framework. In the other part of this book, we study the performance of a Computer Cluster, developing a Simple Skyline Algorithm (MR-SSA). Moreover, the actual algorithm is designed to run parallel in distributed systems, with the method of Map-Reduce. Specifically, the experimental part of the book consists of a Computer Cluster with four nodes. The development of the algorithm is based on the method of Μap-Reduce and implemented within the R language. The fundamental architectural design is including three basic functions like the random range generator, the classification of the dataset in ascending order by column, and at last the calculation of the skyline points. Finally, our application has been tested locally on a computer by using Virtual Machines, which are based on the Cloudera platform.

"Sinopsis" puede pertenecer a otra edición de este libro.