Machine Learning Pocket Reference: Working with Structured Data in Python

Book Name: Machine Learning Pocket Reference: Working with Structured Data in Python
Author: Matt Harrison
Publisher: O’Reilly Media; 1 edition
ISBN-10: 1492047546, 978-1492047544
Year: 2019
Pages: 320 pages
Language: English
File size: 23 MB
File format: PDF

Machine Learning Pocket Reference: Working with Structured Data in Python Pdf Book Description:

Machine Learning is a big domain name and also a book covering this subject should choose carefully what to pay for. This means that he avoids talking neural network libraries like TensorFlow or Natural Language Processing programs such as spaCy or even NLTK. This conscious choice means he can concentrate on clear and comprehensive code examples of solving conventional classification or regression problems using scikit-learn (along with other python programs ). Each chapter utilizes concise code samples to wander through how to utilize a variety of python packages to perform the various steps of a normal machine learning issue. This book is most appropriate for a person which has a small bit of vulnerability to python, pandas and scikit-learn and also wants to understand how to use these resources efficiently. Additionally, it offers an excellent introduction to approximately 36 additional python libraries widely utilized in the information science discipline. . With thorough notes, tables, and illustrations, this handy reference can allow you to browse the fundamentals of machine learning. Writer Matt Harrison provides a valuable guide which you may use for extra help during training and as a suitable source once you dive into your next machine learning endeavor.

Perfect for developers, information scientists, and AI engineers, this publication contains an summary of the machine learning procedure and walks you through classification together with organized data. You will also find out strategies for clustering, forecasting a constant value (regression), and decreasing dimensionality, among other subjects. The book gives a comprehensive, example-driven remedy of each significant measure in a DS/ML undertaking, from data cleanup to model analysis. This strategy gives the book a wonderful balance of levity and market in its own delivery.