Автор: Sergio Rojas Galeano
Издательство: Leanpub
Год: 2019
Страниц: 95
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB
Data is nowadays ubiquitous, voluminous and puzzling. It is not surprise that scientists are so interested in analysing it, understanding it and discovering underlying complex patterns within it. And that’s the origin of what is known as Data Science. But as much as the scientific interest in this respect is growing, so it is practitioners curiosity about potential applications in real life and development of technological tools for Data Science in non-academic contexts.
This book has been designed to introduce newcomers to the essentials of Data Science using a hands-on approach rather than a theoretical perspective. For this aim, it addresses two of its most important branches: Machine Learning and Metaheuristics. The book presents many introductory examples as well as an assortment of challenges with varying levels of difficulty, for readers to solve them using the Python programming language, the current tool–of–choice adopted by the Data Science community. These challenges (nearly 90 programming exercises) will help readers to acquire skills that hopefully will foster their academic or industry interests involving data analysis for knowledge discovery.
There are two clear knowledge disciplines overlapping in this modern approach to science: in the one hand Computer Science contributing the fields of Algorithmics and Computer Programming, and on the other hand Maths and Statistics, contributing fields such as Probability, Statistical Analysis, Optimisation and Linear Algebra. In fact, the intersection of these two avenues gave birth to sub-fields of Artificial Intelligence such as Machine Learning and Metaheuristics. The big novelty is the addition of a third avenue coming from the traditional science in the form of domain expertise, experimental studies, data collection and preparation, randomisation, hypothesis testing, etc.
Скачать Models of Learning and Optimization for Data Scientists: A Python hands-on approach