Solve challenging and computationally intensive analytics problems by leveraging network science and graph algorithms
Key FeaturesLearn how to wrangle different types of datasets and analytics problems into networksLeverage graph theoretic algorithms to analyze data efficientlyApply the skills you gain to solve a variety of problems through case studies in PythonPurchase of the print or Kindle book includes a free PDF eBookBook DescriptionWe are living in the age of big data, and scalable solutions are a necessity. Network science leverages the power of graph theory and flexible data structures to analyze big data at scale.
This book guides you through the basics of network science, showing you how to wrangle different types of data (such as spatial and time series data) into network structures. You’ll be introduced to core tools from network science to analyze real-world case studies in Python. As you progress, you’ll find out how to predict fake news spread, track pricing patterns in local markets, forecast stock market crashes, and stop an epidemic spread. Later, you’ll learn about advanced techniques in network science, such as creating and querying graph databases, classifying datasets with graph neural networks (GNNs), and mining educational pathways for insights into student success. Case studies in the book will provide you with end-to-end examples of implementing what you learn in each chapter.
By the end of this book, you’ll be well-equipped to wrangle your own datasets into network science problems and scale solutions with Python.
What you will learnTransform different data types, such as spatial data, into network formatsExplore common network science tools in PythonDiscover how geometry impacts spreading processes on networksImplement machine learning algorithms on network data featuresBuild and query graph databasesExplore new frontiers in network science such as quantum algorithmsWho this book is forIf you’re a researcher or industry professional analyzing data and are curious about network science approaches to data, this book is for you. To get the most out of the book, basic knowledge of Python, including pandas and NumPy, as well as some experience working with datasets is required. This book is also ideal for anyone interested in network science and learning how graph algorithms are used to solve science and engineering problems. R programmers may also find this book helpful as many algorithms also have R implementations.
Table of ContentsWhat is a Network?Wrangling Data into Networks with NetworkX and igraphDemographic DataTransportation DataEcological DataStock Market DataGoods Prices/Sales DataDynamic Social NetworksMachine Learning for NetworksPathway MiningMapping Language Families – an Ontological ApproachGraph DatabasesPutting It All TogetherNew Frontiers
Colleen M. Farrelly primarily writes to explore her experiences and remember those who have passed on. Over 62 of her poems and nonfiction articles have been published in over 22 journals, and she has published 5 books, Places and Faces, Portraits of War, Phoenix Rising, The War Folder, and Juvenilia. She donates a portion (30%) of her profits to nonprofits focused on returning Veterans and providing for the homeless.
Colleen was born into a family with several generations of military service and a community that welcomed Bosnian and Hmong refugees when she was young. Her early coursework and internships focused on studying and documenting humanitarian crises with a focus on Bosnia and Sri Lanka, and she was a medical volunteer for several years (including in America’s inner cities and various cities in Sub-Saharan Africa). As an MD/PhD student, she spent several months studying in the Miami-Dade County morgue, learning forensics and documentation of medical evidence. Many of Colleen's poems and novellas (particularly The War Folder) draw from these experiences.
She is currently a data scientist, with previous projects including Ebola spread modeling to help formulate an emergency plan in Mali, developing medical risk monitoring systems for the U.S. Navy, mining failed pharmaceutical trials for subgroups of responders, and setting up analyses to help personalize education. Colleen’s scientific research includes psychometrics, topological data analysis, and ensemble learning. She plans to write a layperson's guide to machine learning and computational mathematics in 2018.