Network Science with Python: Explore the networks around us using network science, social network analysis, and machine learning

The authors enthusiasm for the topic shows through in the writing. It’s one of those rare books that’s makes a deeply technical topic approachable by those with little preexisting knowledge but high ability to learn quickly. It doesn’t over-simplify, it just makes you enthusiastic enough to invest the effort required to learn.

As a data scientist, NLP is an area I've had limited experience in. It was never as striking to me as other areas of data science. But I've followed David Knickerbocker for a while now and was happy to purchase this the moment I saw his announcement on LinkedIn. It is hard for me to imagine a better introduction to this topic and it was, I think, precisely what I needed. The linear progression and friendly tone makes it highly bingeable. It is written with contagious enthusiasm and seasoned wisdom. It quite plainly communicates the profundity and power of a good network analysis - and this is what I never understood, why I should ever care, what all can really be done with a graph? David answers by providing quickly digestible examples and inspires a curiosity to explore. This is a hit-the-ground-running book, a why-should-I-care-answer book, and a I-didn't-know-I'd-find-this-so-interesting book. Needless to say, I look forward to exploring these concepts with my own projects. David's enthusiasm is indeed contagious.

I really like this book. Laid out in good progression - give you an expanding range of the concepts use cases and the code works well and documented well enough I could think my way through enhancing the code examples for my particular use cases.

I learned all about graphs and networks in College a few decades ago. It has proven fairly useless knowledge to me. This book, on the other hand, is incredible. I can now see how these tools and approaches are relevant to my work in data. It's really reshaped how I think of data problems through brilliant examples and with appropriate context. David has taken the Academic and made it Useful. And it's wicked cool!

This is the book that convinced me that I wanted to and could be an engineer. Randomly one day I happened across David Knickerbocker on LinkedIn. I don't remember how or why but I started following his Network Science blog and I ate it up. Then I started reading his book and the lid of this field was blown right off. Now I have suffered through other technical books and wondered if anyone ***really*** read the whole things. But not this one. You'll read this one. David clearly loves his reader and subject. He communicates technical concepts in such an approachable way that you are up and building in no time. This material is **important.** It allows us to blend the technical with the practical. It shows us how to use these skills in fun and easy ways that help us to nail down the fundamentals which empowers us to transfer them to more complex subject matter. Subject matter that underlies the cause and effect, the powerful influences of our world. Which during this current climate is critical in order not to be driven by invisible forces. David is a skilled teacher. He pulls back the veil to show you how things work under the hood and he stands next to you saying, "you can do this." This book is the most readable technical book I've encountered. I had so much fun making projects based on what I learned from David. This book, quite literally, changed my life and I am grateful. I can't recommend it enough.

🚀 Network Science with Python by David Knickerbocker 🚀 First, the preface in the book was a very humble thank-you note, Love it! Made me think to learn and write more! 🪄 Influence of network on us every day. I love how RLHF (Reinforcement Learning with Human Feedback) was put as “Human guided Science” in one of the articles I came across, similarly, the impact of networking in Language (Network Science in NLP) is something I was very interested in. Network analysis has a great scope in Social Media Data Mining - which in turn might need some granular insights while uncovering large search volume indices. ✍🏻 Making the less obvious friends meet - NLP and networks: Uncovering the underlying relationship in texts. While it may not be very evident in the generative AI phase, to perform analysis in every sentence generated from the language models, there is a good scope of uncovering the relationship that might enhance the “missing knowledge”. Very nicely put - If there are sequences in data and it's down to words or not - get an NLP technique to process it! Figuring out relationships: Though the language domain space is possibly seeming “infinite”, there are still some “templates” surrounding it. Similar to how David mentioned questions of “Who, what, When, Where, Why, How” can be used to draw relationships. ✍🏻 The scope of “insights” to “actionable insights is the sweet spot of the conversational AI domain to understand the customers and take actions based on what they want and not based on what's easy to deliver. I loved the history of NLP rooted in “sequence analysis” and his use cases with NLP solutions for the problems experienced. While there are many NLP tasks available, it is important to select the task that best addresses the problem at hand and avoid becoming overwhelmed by attempting to apply every available technique. I am planning to read one chapter a day to consume the impact of Network Science in the NLP domain. It was an insightful start of reminding the important aspects of NLP and text analysis while I was moving into the generative AI landscape of "controlling the text generation that I can't really control" - prompts. I have been reading about memory-assisted agents too in conversational AI, thinking memory as a distributed network that could be pieced out and ensembled together is something I want to experiment! 🚀 Thank you Packt Vinishka Kalra for sending the book! Appreciate it! I would love to study the exploration of conversations, and relationships and how they can serve as a better context memory for referencing conversations, how the links and relationships would help to decipher an initial look towards the "Missing text phenomenon" that language models in some cases struggle to decode. #networkscience #nlp

It is really easy to follow along with the book,both entertaining and enlightening,gives me a lot of ideas for implementation!

As the author says in the book, this book is great in that, despite many other books dealing with math only, this book treats practical implementation. In particular, there is the chapter in which you manually build graphs from scratch. Before reading this book, constructing graph datasets seemed too heavy but I now know it is feasible.

Written in a very approachable way, fun and practical, fantastic read! It will launch a whole generation of exploration